V. Plevris, "Blockchain applications in the construction industry", in Digital Twin and Blockchain for Sensor Networks in Smart Cities, T.A. Nguyen (Ed.), Elsevier, pp. 265-290, 2025.

Abstract:

This chapter delves into the transformative potential of blockchain technology in the construction industry, a sector pivotal to the global economy yet plagued by inefficiencies, lack of transparency, and slow adoption of digital innovations. It presents a comprehensive analysis, starting from the fundamental concepts of blockchain technology, including its decentralized nature, security features, and the role of consensus mechanisms like Proof of Work and Proof of Stake. The exploration extends to the practical applications of blockchain across various aspects of construction management, such as supply chain management, contract management, project management and documentation, and real estate transactions. Highlighting the sector’s critical challenges, including fragmented communication, inefficient supply chain management, and the perennial issues of delays and budget overruns, the chapter positions blockchain as a potent solution capable of enhancing transparency, efficiency, and accountability within the industry. It provides detailed insights into how blockchain can streamline operations, from automating procurement and improving inventory management to securing land registry processes and facilitating real-time tracking of materials. Moreover, the study reviews significant scholarly contributions to the field, offering a bibliometric analysis that underscores the burgeoning interest and research activity surrounding blockchain in construction and engineering. It also discusses the technical hurdles, legal and regulatory considerations, and the financial implications of blockchain adoption, laying out a balanced view of the opportunities and obstacles ahead. Concluding with a forward-looking perspective, the chapter envisions a future where blockchain technology not only addresses the current limitations of the construction industry but also fosters a new era of innovation, sustainability, and collaboration. Through this comprehensive examination, the chapter contributes valuable knowledge to academics, industry professionals, and policymakers interested in the intersection of blockchain technology and construction, encouraging further exploration and adoption of this groundbreaking technology in shaping the future of the built environment.

V. Plevris, “A Glimpse into the Future of Civil Engineering Education: The New Era of Artificial Intelligence, Machine Learning, and Large Language Models”, Journal of Civil Engineering Education, 151(2) (10.1061/JCEECD.EIENG-2193), 2025.

Introduction:
In recent years, the integration of machine learning (ML) and artificial intelligence (AI) into education has revolutionized the field, creating opportunities for enhancing teaching and learning. This transformation is significant in the domain of civil engineering, where students must grasp complex theoretical concepts and acquire extensive practical knowledge to succeed in their careers. This demand necessitates innovative approaches that can provide personalized, efficient, and effective learning experiences. AI, with its ability to process vast amounts of data and learn from patterns, is uniquely positioned to meet these demands. Large language models (LLMs), such as ChatGPT, have shown potential in providing personalized learning experiences, offering real-time assistance, and automating tasks. These capabilities can address some persistent challenges in civil engineering education, such as the need for individualized attention, timely feedback, and catering to different learning needs. In this paper we explore the application of AI, ML, and LLMs, in civil engineering education and highlight five key areas where AI can make a significant impact. We show that the integration of AI technologies in civil engineering education offers benefits, including improved learning outcomes (LOs), efficiency in teaching, and enhanced engagement. However, it also presents challenges. Through a comprehensive exploration of these topics, we aim to provide valuable insights into how AI techniques can be leveraged to enhance the education of civil engineers, contributing to the ongoing dialogue about the future of civil engineering education in the age of AI.

V. Plevris, A.T. Al-Sayegh, J. Mir and A. Ahmad, “Nondestructive Evaluation of Hybrid Concrete Properties Using Image Processing and Machine Learning”, Structures, 79, Article ID 109423 (DOI: 10.1016/j.istruc.2025.109423), 2025.

Abstract:
Advancements in informatics, such as image processing (IP) and machine learning (ML), are increasingly being utilized to evaluate the mechanical properties of reinforced concrete structures. This study focuses on hybrid concrete (HC), which incorporates cement replacement materials (CRM) like fly ash and silica fume to enhance its mechanical performance while promoting sustainability. A novel methodology combining IP with supervised ML models—Support vector machine (SVM), boosted ensemble regression (BRE), and Gaussian process regression (GPR)—was developed to predict the compressive and tensile strengths of HC. A comprehensive dataset was created using 162 cylindrical specimens prepared with various mix ratios, CRM replacement levels, and curing durations. High-resolution images of both horizontal and vertical cuts of the specimens were analyzed, and statistical features were extracted to train the ML models. The results demonstrated the models’ high accuracy in predicting mechanical properties, with GPR emerging as the most reliable method. The findings confirm the effectiveness of integrating IP with ML as a nondestructive testing approach for concrete evaluation, offering a fast, cost-effective, and environmentally friendly alternative to traditional methods. This study underscores the potential of combining advanced computational techniques with sustainable materials to innovate in concrete technology.

V. Plevris and H. Hosamo, “Responsible AI in Structural Engineering: A Framework for Ethical Use”, Frontiers in Built Environment, 11:1612575 (DOI: 10.3389/fbuil.2025.1612575), 2025.

Abstract:
The integration of Artificial Intelligence (AI) into structural engineering holds great promise for advancing analysis, design, and maintenance. However, it also raises critical ethical and governance challenges—including bias, lack of transparency, accountability gaps, and equity concerns—which are particularly significant in a discipline where public safety is paramount. This study addresses these issues through eight fictional but realistic case studies that illustrate plausible ethical dilemmas, such as algorithmic bias in predictive models and tensions between AI-generated recommendations and human engineering judgment. In response, the study proposes a structured framework for responsible AI implementation, organized into three key domains: (i) Technical Foundations (focusing on bias mitigation, robust validation, and explainability); (ii) Operational and Governance Considerations (emphasizing industry standards and human-in-the-loop oversight); and (iii) Professional and Societal Responsibilities (advocating for equity, accessibility, and ethical awareness among engineers). The framework offers actionable guidance for engineers, policymakers, and researchers seeking to align AI adoption with ethical principles and regulatory standards. Beyond offering practical tools, the study explores broader theoretical and institutional implications of AI, including risks associated with model drift, the need for lifecycle oversight, and the importance of cultural and geographic adaptability. It also outlines future challenges and opportunities, such as incorporating AI ethics into engineering education and considering the ethical impact of emerging technologies like quantum computing and digital twins. Rather than offering prescriptive answers, the study aims to initiate an essential dialogue on the evolving role of AI in structural engineering, equipping stakeholders to manage its benefits and risks while upholding trust, fairness, and public safety.

H. Hosamo, V. Plevris, D. Kraniotis and C.N. Rolfsen, “Can Quantum Computing Surpass Classical Algorithms in Optimizing Building Performance? A Benchmark Study with 15000 Simulations”, Energy & Buildings, 346(1), Article ID 116156 (DOI: 10.1016/j.enbuild.2025.116156), 2025.

Abstract:
Optimizing building performance is essential for enhancing energy efficiency and occupant comfort. This study evaluates the applicability of quantum computing–based optimization methods in the Architecture, Engineering, and Construction (AEC) industry by comparing the Quantum Approximate Optimization Algorithm (QAOA) and Quantum Annealing (QA) with classical multi-objective optimization algorithms, namely Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Multi-Objective Particle Swarm Optimization (MOPSO). A dataset of 15,000 building simulations was used to train an Extreme Gradient Boosting (XGBoost) model for predicting total energy consumption (kWh/m²/year) and Predicted Percentage of Dissatisfied (PPD) occupants. These predictions were then used in the optimization phase. NSGA-II produced the best trade-offs, achieving energy consumption between 17.84 and 19.84 kWh/m²/year and PPD below 5.2 %, with strong diversity and convergence. QAOA executed faster (0.54 min) than NSGA-II (18.9 min) but resulted in higher energy values (31.85–55.62 kWh/m²/year) and weaker solution quality. Quantum Annealing completed in 0.37 min but returned clustered solutions near 45.88 kWh/m²/year. While the current limitations of quantum methods constrain their effectiveness, the findings indicate their potential as fast solvers in future building performance optimization workflows, particularly as hardware and algorithmic capabilities mature.

V. Plevris, L. Hadji and H. Ait Atmane, “An n-order refined plate theory for Bending and Buckling of Functionally Graded Polymer Composite Plates Reinforced with Graphene Nanoplatelets”, Advances in Nano Research, 19(1), pp, 41-51 (DOI: 10.12989/anr.2025.19.1.041), 2025.

Abstract:
This study investigates the bending and buckling behavior of functionally graded multilayer graphene nanoplatelet (GPL)/polymer composite plates using an n-order refined plate theory. The theory introduces a higher-order polynomial displacement field that ensures variational consistency and eliminates the need for shear correction factors. In this formulation, shear stresses vary parabolically through the plate thickness, and stress-free conditions are satisfied at both the top and bottom surfaces, resulting in improved accuracy compared to conventional plate theories. A key innovation of this work lies in the layer-wise variation of GPL weight fractions, enabling the design of functionally graded nanocomposites with both uniform and non-uniform reinforcement patterns-specifically, UD, FG-O, FG-X, and FG-A. While most existing studies are limited to uniformly distributed GPLs or rely on lower-order theories, this study addresses these limitations by proposing an analytically tractable higher-order model that can accurately capture shear deformation effects and by systematically analyzing the mechanical influence of different GPL distribution patterns. This dual advancement fills an important gap in the literature, particularly in understanding the performance of non-uniformly graded nanocomposites under bending and buckling. The effective Young's modulus is predicted using the Halpin-Tsai micromechanics model, and the rule of mixtures is used to determine the effective Poisson's ratio and mass density. Analytical solutions for static deflection and buckling are derived for simply supported plates using the Navier solution technique. The results show that non-uniform GPL distributions, particularly FG-X and FG-O, significantly enhance bending stiffness and buckling resistance by concentrating reinforcement near high-stress regions. Additionally, increasing the GPL weight fraction and optimizing GPL geometry further improve structural performance. This study offers new insights into the tailored design of functionally graded nanocomposite plates and provides practical guidance for lightweight, high-performance structural components in aerospace, automotive, and civil engineering applications.

V. Plevris and A. Ahmad, “Deriving analytical solutions using symbolic matrix structural analysis for continuous beams”, Scientific Reports, 15, Article ID 15897 (DOI: 10.1038/s41598-025-98023-x), 2025.

Abstract:
This study investigates the use of symbolic computation in Matrix Structural Analysis (MatSA) for continuous beams, using the MATLAB Symbolic Math Toolbox. By employing symbolic MatSA, analytical expressions for displacements, support reactions, and internal forces are derived, offering deeper insights into structural behavior. This approach facilitates efficient and scalable sensitivity analysis, where partial derivatives of outputs concerning input parameters can be directly computed, enhancing design exploration. The development includes an open-source MATLAB program, hosted on GitHub, enabling symbolic analysis of continuous beams subjected to point and uniform loads. This approach is valuable for both engineering practice and pedagogy, enriching the understanding of structural mechanics and aiding in education by illustrating clear parameter relationships. The program supports deriving influence lines and identifying maximum response values.

V. Plevris, “From Integrity to Inflation: Ethical and Unethical Citation Practices in Academic Publishing”, Journal of Academic Ethics (DOI: 10.1007/s10805-025-09631-1), 2025.

Abstract:
Citation counts are a key metric in academic success, influencing career advancement and funding. However, the pressure to increase these counts has led to unethical practices such as citation inflation through manipulation. This paper examines strategies such as excessive self-citation, coercive citation demands by reviewers, and overuse of unpublished works, which distort the academic record and undermine scholarly integrity. The paper also explores ethical approaches to increasing citation counts, emphasizing high-quality research, appropriate journal selection, and active dissemination through reputable channels. A quantitative analysis of self-citation practices across different countries and fields revealed significant disparities, with some nations exhibiting high levels of self-citation among top scientists, while others showed more restrained behaviors. These findings suggest that citation practices may be influenced by various factors, including national research policies, cultural norms and others. The study highlights the potential long-term consequences of these behaviors for academic careers and the scientific community. Practical solutions to curb citation manipulation, such as stricter editorial oversight and improved journal collaboration, are proposed. The study aims to raise awareness of ethical challenges in academic publishing and offers strategies to maintain integrity in citation practices, ensuring that metrics reliably measure scholarly impact.

A. Jiménez Rios, V. Plevris and M. Nogal, “Towards Industry 5.0: A Stakeholder Analysis to Understand the Human Role in the Adoption of a Heritage Bridge Human-Centric Digital Twin Framework”, Structure and Infrastructure Engineering, Article ID 2490126 (DOI: 10.1080/15732479.2025.2490126), 2025.

Abstract:
The adoption of a novel industry paradigm is an untamed problem that requires strong social consensus and involves a high degree of technological uncertainty. To solve this problem a multi-actor engagement and agreement are needed. In this article, the methodology and the findings obtained after conducting a stakeholder analysis to understand how different actors could work together towards the adoption of Industry 5.0 principles and enabling technologies are presented. The analysis has been framed within a case study dealing with the conservation of historical bridges in the city of Oslo, Norway. The education institutions of the city were assumed as the problem owners. This research indicates that the Ministry of Transport and the Ministry of Climate and Environment, along with their subordinate agencies (Statens Vegvesen and Riksantikvaren, respectively) together with Oslo Kommune and its Cultural Heritage Office, possess the critical financial and regulatory resources necessary for adopting this paradigm. Their leadership and capacity to mobilise resources are pivotal in incentivising other stakeholders. Such resources should be driven towards a suitable business model, the adoption of human-centric digital twins as enabling technology, the establishment of interdisciplinary collaborations between the identified stakeholders, and the up-skilling/re-skilling of the industry workforce.

A. Jiménez Rios, V. Plevris, M. Nogal and W. Admiraal, “Scholarship of Teaching and Learning in Civil and Structural Engineering. A Systematic Literature Review”, Journal of Civil Engineering Education, 151(3) (DOI: 10.1061/JCEECD.EIENG-2103), 2025.

Abstract:
The Scholarship of Teaching and Learning (SoTL) pertains to scholarly endeavors centered on the pedagogical aspects of teaching and learning, and its principal objective is the enhancement of students’ educational experiences. This systematic literature review addresses the following questions: (1) In what capacity do educators within the field of civil and structural engineering (CaSE) engage with SoTL?, and (2) What are the benefits of implementing a SoTL for CaSE educators? The scope of the review encompasses SoTL studies specifically developed by CaSE educators and implemented within CaSE teaching and learning environments. Findings are synthesized and disseminated via a bibliometric analysis and a narrative synthesis. The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. It was found that CaSE educators participate in SoTL endeavors through diverse approaches; however, such involvement remains more of an exception than a common practice. The insufficiency of existing benefits and incentives, if any, serves as a barrier hindering broader engagement and participation in SoTL activities.

V. Plevris and A. Ahmad, "Deriving Analytical Solutions Using Symbolic Matrix Structural Analysis: Part 2 – Plane Trusses", Heliyon, 11(4), Article ID e42372, 19 pages (DOI: 10.1016/j.heliyon.2025.e42372), 2025.

Abstract:
This study extends the use of symbolic computation in matrix structural analysis to plane trusses, expanding on previous work that focused on continuous beams. We present a fully open-source MATLAB program, available on GitHub, that performs symbolic analysis of 2D trusses subjected to point loads, applicable to any truss configuration. Using the Symbolic Math Toolbox, the program derives closed-form analytical expressions for displacements, support reactions, and axial forces, providing deeper insight into structural behavior. A key advantage of the symbolic approach is its ability to perform sensitivity analysis efficiently by computing partial derivatives of structural responses with respect to input parameters. This feature enhances design exploration and optimization by allowing direct evaluation of parameter influences. Moreover, the framework is highly scalable, capable of generating symbolic solutions even for large-scale truss structures, something previously unattainable using traditional methods due to computational limitations. The tool serves both engineering practice and education, offering clear insights into parameter relationships and strengthening conceptual understanding in structural mechanics. To ensure accuracy, the symbolic results were rigorously validated against two commercial finite element software programs and results from the literature, with complete agreement. These validations confirm the reliability, scalability, and general applicability of the proposed methodology.

V. Plevris, "Assessing Uncertainty in Image-Based Monitoring: Addressing False Positives, False Negatives, and Base Rate Bias in Structural Health Evaluation", Stochastic Environmental Research and Risk Assessment (DOI: 10.1007/s00477-024-02898-7), 2025.

Abstract:
This study explores the limitations of image-based structural health monitoring (SHM) techniques in detecting structural damage. Leveraging machine learning and computer vision, image-based SHM offers a scalable and efficient alternative to manual inspections. However, its reliability is impacted by challenges such as false positives, false negatives, and environmental variability, particularly in low base rate damage scenarios. The Base Rate Bias plays a significant role, as low probabilities of actual damage often lead to misinterpretation of positive results. This study uses both Bayesian analysis and a frequentist approach to evaluate the precision of damage detection systems, revealing that even highly accurate models can yield misleading results when the occurrence of damage is rare. Strategies for mitigating these limitations are discussed, including hybrid systems that combine multiple data sources, human-in-the-loop approaches for critical assessments, and improving the quality of training data. These findings provide essential insights into the practical applicability of image-based SHM techniques, highlighting both their potential and their limitations for real-world infrastructure monitoring.

V. Plevris and G. Papazafeiropoulos, "AI in Structural Health Monitoring for Infrastructure Maintenance and Safety", Infrastructures, 9(12), 25 pages (DOI: 10.3390/infrastructures9120225), 2024.

Abstract:
This study explores the growing influence of artificial intelligence (AI) on structural health monitoring (SHM), a critical aspect of infrastructure maintenance and safety. This study begins with a bibliometric analysis to identify current research trends, key contributing countries, and emerging topics in AI-integrated SHM. We examine seven core areas where AI significantly advances SHM capabilities: (1) data acquisition and sensor networks, highlighting improvements in sensor technology and data collection; (2) data processing and signal analysis, where AI techniques enhance feature extraction and noise reduction; (3) anomaly detection and damage identification using machine learning (ML) and deep learning (DL) for precise diagnostics; (4) predictive maintenance, using AI to optimize maintenance scheduling and prevent failures; (5) reliability and risk assessment, integrating diverse datasets for real-time risk analysis; (6) visual inspection and remote monitoring, showcasing the role of AI-powered drones and imaging systems; and (7) resilient and adaptive infrastructure, where AI enables systems to respond dynamically to changing conditions. This review also addresses the ethical considerations and societal impacts of AI in SHM, such as data privacy, equity, and transparency. We conclude by discussing future research directions and challenges, emphasizing the potential of AI to enhance the efficiency, safety, and sustainability of infrastructure systems.

Keywords:
artificial intelligence (AI); structural health monitoring (SHM); predictive maintenance; sensor networks; anomaly detection; infrastructure resilience; machine learning (ML).

A. Jiménez Rios, M. Nogal, V. Plevris, R. Ramirez and M.L. Petrou, "Towards Enhanced Built Cultural Heritage Conservation Practices: Perceptions on Industry 5.0 Principles and Enabling Technologies", The Historic Environment: Policy & Practice, pp. 1-27 (DOI: 10.1080/17567505.2024.2429167), 2024.

Abstract:
Despite its recent adoption, Industry 5.0 has attracted significant attention from researchers across various fields. However, the Architecture, Engineering, Construction, Management, Operation, and Conservation (AECMO&C) industry, particularly in the context of built cultural heritage conservation, has lagged in this regard. This study aims to gain a deeper understanding of conservation professionals’ perceptions regarding the adoption of Industry 5.0 principles and enabling technologies, as well as the perceived barriers and the skills needed to address them. A survey questionnaire was designed, tested, and implemented to collect relevant data. Analysis of the collected data reveals that, although there is a clear recognition of the significance of Industry 5.0 principles and enabling technologies, their application in built cultural heritage conservation remains limited. Future initiatives should prioritise bridging knowledge gaps, enhancing training programmes, and securing necessary resources to overcome these existing barriers.

Keywords:
Industry 5.0; human-centrism; resilience; sustainability; built cultural heritage environment; conservation.

V. Plevris, "AI-Driven Innovations in Earthquake Risk Mitigation: A Future-Focused Perspective", Geosciences, 14(9), 29 pages (DOI: 10.3390/geosciences14090244), 2024.

Abstract:
This study explores the transformative potential of artificial intelligence (AI) in revolutionizing earthquake risk mitigation across six key areas. Unlike traditional approaches, this paper examines how AI-driven innovations can uniquely enhance early warning systems, enabling real-time structural health monitoring, and providing dynamic, multi-hazard risk assessments that seamlessly integrate seismic data with other natural hazards such as tsunamis and landslides. It introduces groundbreaking applications of AI in earthquake-resilient design, where generative design algorithms and predictive analytics create structures that optimally balance safety, cost, and sustainability. The study also presents a novel discussion on the ethical implications of AI in this domain, stressing the critical need for transparency, accountability, and bias mitigation. Looking forward, the manuscript envisions the development of advanced AI platforms capable of delivering real-time, personalized risk assessments, immersive public training programs, and collaborative design tools that adapt to evolving seismic data. These innovations promise not only to significantly enhance current earthquake preparedness but also to pave the way toward a future where the societal impact of earthquakes is drastically reduced. This work underscores the potential of AI’s role in shaping a safer, more resilient future, emphasizing the importance of continued innovation, ethical governance, and collaborative efforts.

Keywords:
artificial intelligence (AI); earthquake risk mitigation; seismic hazard mapping; structural health monitoring; multi-hazard risk assessment; earthquake-resilient design; real-time data integration.

A. Jiménez Rios, M.L. Petrou, R. Ramirez, V. Plevris, M. Nogal, "Industry 5.0, Towards an Enhanced Built Cultural Heritage Conservation Practice", Journal of Building Engineering, 96, 20 pages (DOI: 10.1016/j.jobe.2024.110542), 2024.

Abstract:
The rise of Industry 4.0 has led to a rapid increase in digitalization and industrial operations. However, it has recently been deemed insufficient in fulfilling European objectives for 2030. In response, and to counteract the unintended negative consequences triggered by Industry 4.0, Industry 5.0 has been introduced. The purpose of this article is to shed light on how the architecture, engineering, construction, management, operation, and conservation industry can adapt and better prepare to embrace novel Industry 5.0 principles and enabling technologies, ultimately resulting in enhanced conservation practices for the built cultural heritage environment. To achieve this, a systematic literature review was conducted following the PRISMA methodology. The principal results of this article highlight the work of different conservation professionals and our views on the potential of Industry 5.0 for enhancing conservation practices. Major conclusions indicate that artificial intelligence and digital twins are the two most studied technologies in the field. Sustainability is broadly discussed throughout the analyzed literature, whereas resilience and human centrism require further research and implementation efforts to achieve a holistic Industry 5.0 adoption. The significant scientific novelty of this work lies in the comprehensive scope of the review in terms of principles and enabling technologies, with a particular emphasis on heritage buildings. Thus, it is valuable for conservation practitioners seeking best practices, for policymakers as it suggests ways to encourage the adoption of novel technologies and principles in conservation, and for researchers as it highlights gaps and stimulates further paths of research and innovation.

Keywords:
Industry 5.0; Human-centrism; Resilience; Sustainability; Built cultural heritage environment; Conservation; Systematic literature review

A. Jiménez Rios, M.E.A. Ben Seghier, V. Plevris and J. Dai, "Explainable Ensemble Learning Framework for Estimating Corrosion Rate in Suspension Bridge Main Cables", Results in Engineering, 23, Article ID 102723, 15 pages (DOI: 10.1016/j.rineng.2024.102723), 2024.

Abstract:
Ensuring the safe operation of suspension bridges is paramount to prevent unwanted events that can cause failures. Therefore, it is crucial to continuously monitor their operational status to uphold safety and reliability levels. However, natural deterioration caused by the surrounding environment, primarily due to corrosion, inevitably impacts these structures over time, particularly the main cables made of steel. In this study, a robust framework is proposed to predict the annual corrosion rate in main cables of suspension bridges, while investigating the impact of the surrounding environmental factors on this process. To do so, the implementation of four regression models and four machine learning techniques are used in the first phase for modeling the annual corrosion rate based on a comprehensive database containing various environmental factors. The modeling performance is evaluated through a range of statistical and graphical metrics. After that, Shapley Additive Explanations (SHAP) is utilized to explain the model and to extract the impact of each variable on the final modeling results. Overall, the findings demonstrate the effectiveness of the proposed framework for addressing this issue. The Extreme Gradient Boosting (XGB) emerged as the top-performing model, achieving an overall R2 of 0.982. Moreover, the SHAP findings highlight the impact of CL− on the annual corrosion rate as the factor with the highest influence during the modeling process. The high performance of the proposed model suggests its potential utility in further research concerning the reliability of suspension bridge main cables.

Keywords:
Suspension bridges; Main cables; Annual corrosion rate; Ensemble learning models; Regression techniques; Shapley additive explanations.

G. 63 Papazafeiropoulos and V. Plevris, "OpenSeismoMatlab: New Features, Verification and Charting Future Endeavors", Buildings, 14(1), Article ID 304, 31 pages (DOI: 10.3390/buildings14010304), 2024.

Abstract:
To facilitate the precise design of earthquake-resistant structures, it is imperative to accurately evaluate the impact of seismic events on these constructions and predict their responses. OpenSeismoMatlab, a robust, free ground motion data processing software, plays a pivotal role in this endeavor. It empowers users to compute a wide array of outcomes using input acceleration time histories, encompassing time histories themselves, as well as linear and nonlinear spectra. These capabilities are instrumental in supporting structural design initiatives. This study provides a comprehensive exposition of the latest version (v 5.05) of OpenSeismoMatlab. It delves into intricate facets of the software, encompassing a detailed exploration of the input and output variables integral to each operational category. Comprehensive calculation flowcharts are presented to elucidate the software’s organizational structure and operational sequences. Furthermore, a meticulous verification assessment is conducted to validate OpenSeismoMatlab’s performance. This verification entails a rigorous examination of specific cases drawn from existing literature, wherein the software’s outcomes are rigorously compared against corresponding results from prior studies. The examination not only underscores the reliability of OpenSeismoMatlab but also emphasizes its ability to generate outcomes that closely align with findings documented in the established body of literature. Concluding the study, the paper outlines potential directions for future research, shedding light on avenues where further development and exploration can enhance the utility and scope of OpenSeismoMatlab in advancing seismic engineering and structural design practices.

Keywords:
OpenSeismoMatlab; earthquake; seismic design; nonlinear spectra; pulse; resampling.

V. Plevris, L. Hadji and R. Madan, "Exploring porosity impact on the free vibration of FG plates using trigonometric shear deformation theory", Structural Engineering and Mechanics, 92(3), pp. 267-275 (DOI: 10.12989/sem.2024.92.3.267), 2024.

Abstract:
This study investigates the free vibration behavior of functionally graded (FG) plates using trigonometric shear deformation plate theory. The novelty of this work lies in the incorporation of porosities, which are inherent in FG materials due to manufacturing processes, and their detailed impact on the vibrational performance of these plates. Unlike existing studies, this research comprehensively examines multiple porosity distribution patterns, including homogeneous, "O", "X", and "V" configurations, which are seldom analyzed together. The governing equations of motion are derived using Hamilton's principle and solved analytically with the Navier method for simply supported boundary conditions. A key contribution of this study is the exploration of how porosity levels, distribution types, and geometry parameters collectively influence the natural frequencies of FG plates. The results highlight the significant effect of different porosity patterns, with "X"-shaped porosity yielding the highest natural frequency and homogeneous distribution leading to the lowest. Furthermore, the findings reveal that increased porosity levels can either enhance or diminish the vibrational characteristics depending on the distribution pattern. These insights provide valuable guidance for optimizing the design of FG plates for various engineering applications, such as aerospace and biomedical industries.

Keywords:
FG plate; free vibration; functionally graded (FG) materials; porosity; trigonometric shear deformation theory.

L. Hadji, V. Plevris, R. Madan and H. Ait Atmane, "Multi-Directional Functionally Graded Sandwich Plates: Buckling and Free Vibration Analysis with Refined Plate Models under Various Boundary Conditions", Computation, 12(4), Article ID 65, 22 pages (DOI: 10.3390/computation12040065), 2024.

Abstract:
This study conducts buckling and free vibration analyses of multi-directional functionally graded sandwich plates subjected to various boundary conditions. Two scenarios are considered: a functionally graded (FG) skin with a homogeneous hard core, and an FG skin with a homogeneous soft core. Utilizing refined plate models, which incorporate a parabolic distribution of transverse shear stresses while ensuring zero shear stresses on both the upper and lower surfaces, equations of motion are derived using Hamilton’s principle. Analytical solutions for the buckling and free vibration analyses of multi-directional FG sandwich plates under diverse boundary conditions are developed and presented. The obtained results are validated against the existing literature for both the buckling and free vibration analyses. The composition of metal–ceramic-based FG materials varies longitudinally and transversely, following a power law. Various types of sandwich plates are considered, accounting for plate symmetry and layer thicknesses. This investigation explores the influence of several parameters on buckling and free vibration behaviors.

Keywords:
buckling; free vibration; hard core; soft core; multi-directional FGM.

G. Papazafeiropoulos and V. Plevris, "OpenSeismoMatlab: New Features, Verification and Charting Future Endeavors", Buildings, 14(1), Article ID 304, 31 pages (DOI: 10.3390/buildings14010304), 2024.

Abstract:
To facilitate the precise design of earthquake-resistant structures, it is imperative to accurately evaluate the impact of seismic events on these constructions and predict their responses. OpenSeismoMatlab, a robust, free ground motion data processing software, plays a pivotal role in this endeavor. It empowers users to compute a wide array of outcomes using input acceleration time histories, encompassing time histories themselves, as well as linear and nonlinear spectra. These capabilities are instrumental in supporting structural design initiatives. This study provides a comprehensive exposition of the latest version (v 5.05) of OpenSeismoMatlab. It delves into intricate facets of the software, encompassing a detailed exploration of the input and output variables integral to each operational category. Comprehensive calculation flowcharts are presented to elucidate the software’s organizational structure and operational sequences. Furthermore, a meticulous verification assessment is conducted to validate OpenSeismoMatlab’s performance. This verification entails a rigorous examination of specific cases drawn from existing literature, wherein the software’s outcomes are rigorously compared against corresponding results from prior studies. The examination not only underscores the reliability of OpenSeismoMatlab but also emphasizes its ability to generate outcomes that closely align with findings documented in the established body of literature. Concluding the study, the paper outlines potential directions for future research, shedding light on avenues where further development and exploration can enhance the utility and scope of OpenSeismoMatlab in advancing seismic engineering and structural design practices.

Keywords:
OpenSeismoMatlab; earthquake; seismic design; nonlinear spectra; pulse; resampling.

I. Chamatidis, M. Stoumpos, G. Kazakis, N.A. Kallioras, S. Triantafyllou, V. Plevris and N.D. Lagaros, "Overview on Machine Learning Assisted Topology Optimization Methodologies", in Machine Learning in Modeling and Simulation (Part of the book series: Computational Methods in Engineering & the Sciences (CMES)), T. Rabczuk and K-J. Bathe (Eds.), Springer, pp. 373-394, 2023.

Abstract:

The past two decades saw tremendous developments in artificial intelligence (AI). Advancements in software, algorithms, and hardware led to the development of significantly more accurate and versatile artificial intelligence models. This rendered artificial intelligence a powerful tool that is used in diverse scientific areas, e.g. medicine and drug design, economics, and self-driving cars, among many others. These methods, having been successfully implemented in the simulation and modeling of structures, found their way to topology optimization problems, where artificial intelligence appears to have great potential for successful implementation. In conventional topology optimization, the optimal design of a specific domain must be calculated subject to specific constraints and the objective is to minimize the total compliance of the structure and use a specific amount of material. This is typically an iterative process that involves large matrices and can be very timeconsuming. By means of artificial intelligence models, referred to also as surrogate models (or surrogates), the computing time can be reduced significantly. The surrogate model is apriori trained offline. Following, during the optimization process the model is inferred based on input data, which is a lot faster due to limited matrix multiplications that the surrogate performs. The usual process involves either an artificial intelligence surrogate that complements the conventional procedure to reduce computational costs or a standalone surrogate which calculates the whole optimized structures by itself. The AI surrogates that are used belong to two main categories, i.e. Surrogates that use density and surrogates that use images. The surrogates that use density have similar inputs as the conventional method since the optimization process uses the density of the structure and is updated in each iteration of the AImodel. The surrogates that perform optimization on images are a bit different because they use techniques like image segmentation and filtering to output the optimized image (structure) which then is mapped into density. Most surrogates can be used for 2D and 3D structures and they are transferable, meaning that once trained they can be used in another topology optimization problem (thermodynamics or different material). The Background section contains an introduction to artificial intelligence, the surrogate models that will be used and an introduction to conventional topology optimization. The Literature Survey section provides areview ofrecent advancements of topology optimization using artificial intelligence models. This section is divided into two parts, the first describing the models that use density and the second the models that use image-based approaches.

K.G.M. Kandethanthri, M. Nikoo, G. Hafeez, A. Bagchi and V. Plevris, "Estimating the In-Plane Lateral Resistance of Reinforced Log Wall Employing Soft Modelling Techniques", in Advanced Optimization Applications in Engineering, A. Ahmad and C.V. Camp (Eds.), IGI Global, pp. 1-21, 2024.

Abstract:

The popularity of log houses has been on the rise in numerous regions worldwide. In the context of log construction, the stability of log walls is notably influenced by the friction existing between the layers of logs and the openings designated for windows and doors. This study endeavors to comprehensively evaluate the lateral resistance of log walls through an extensive parametric analysis utilizing finite element (FE) methods. To construct a robust dataset, a total of 71 distinct samples were generated employing FE analysis, where the shuffled frog-leaping algorithm (SFLA) was incorporated in conjunction with a feed-forward (FF) neural network. Within this framework, the accuracy of the SFLA-based informational model was juxtaposed against that of an artificial neural network (ANN) coupled with particle swarm optimization (PSO), genetic algorithm (GA), and statistical models including multiple linear regression (MLR).

Book: "Insights: Frontiers in Built Environment", Eds: Z. Chen, A. Matsumoto, J.R. Casas, V. Plevris, G. Tsiatas, H. Guo, Y. Li and S. Kaewunruen, Frontiers Media SA, Lausanne, 2024.

Description

We are now entering the third decade of the 21st Century, and, especially in recent years, the achievements made by researchers and professionals have been exceptional, leading to major advancements in the fast-growing field of the Built Environment.Frontiers has organised a series of Research Topics to highlight the latest advancements in research across the field of Built Environment with articles from the members of our accomplished Editorial Boards. This editorial initiative in question, led by Dr. Zhen Chen, Specialty Chief Editor of Frontiers Construction Management is focused on new insights, novel developments, current challenges, latest discoveries, recent advances, and future perspectives in the field of Built Environment. The Research Topic solicits brief, forward-looking articles from the Editorial Board Members that describe the state of the art, outlining recent developments and major accomplishments that have been achieved and that need to occur to move the field forward. Authors are encouraged to identify the greatest challenges in the sub-disciplines, and how to address those challenges.The goal of this special edition Research Topic is to shed light on the progress made in the past decade in the Built Environment field, and on its future challenges to provide a thorough overview of the field. This article collection will inspire, inform, and provide direction and guidance to researchers and practitioners in the field. We welcome original research, reviews, perspective, outstanding achievements in the Built Environment field and thought-provoking opinion pieces to this Research Topic.

Book: "Advanced Concrete and Construction Materials", Eds: M. Kioumarsi and V. Plevris, ISBN-13: 978-3-7258-0446-7 (hardcover), E-ISBN-13: 978-3-7258-0445-0 (ebook), DOI: 10.3390/books978-3-7258-0445-0, MDPI, Basel, Switzerland, 182 pages, 2024.

Description

The reprint Advanced Concrete and Construction Materials offers a comprehensive exploration of cutting-edge research and critical insights into the dynamic field of construction materials and structural engineering. This meticulously curated volume delves beyond the traditional perceptions of concrete, examining transformative microstructures and alternative binders, which hold immense potential for revolutionizing construction practices and reducing the carbon footprint of concrete. Comprising ten diverse studies, the reprint tackles pivotal sustainability, durability, and innovation issues within the construction industry. From enhancing the strength and durability of fly ash aggregate concrete with nanosilica to exploring the utilization of waste tires for reinforcing concrete columns, each contribution offers valuable insights and showcases innovative approaches. Additionally, the reprint delves into numerical modeling techniques for specialized cementitious composites and evaluates the viability of utilizing water-treatment sludge as a sustainable alternative to clay in fired clay bricks. A valuable resource for academic professionals and researchers, this collection underscores the significance of advancing construction materials. By providing a platform for groundbreaking research and critical reviews, it encourages scholars to contribute to the ongoing discourse, thereby shaping the future of construction.

G. Papazafeiropoulos and V. Plevris, "OpenSeismoMatlab: New Features, Verification and Charting Future Endeavors", Buildings, 14(1), Article ID 304, 31 pages (DOI: 10.3390/buildings14010304), 2024.

Abstract:
To facilitate the precise design of earthquake-resistant structures, it is imperative to accurately evaluate the impact of seismic events on these constructions and predict their responses. OpenSeismoMatlab, a robust, free ground motion data processing software, plays a pivotal role in this endeavor. It empowers users to compute a wide array of outcomes using input acceleration time histories, encompassing time histories themselves, as well as linear and nonlinear spectra. These capabilities are instrumental in supporting structural design initiatives. This study provides a comprehensive exposition of the latest version (v 5.05) of OpenSeismoMatlab. It delves into intricate facets of the software, encompassing a detailed exploration of the input and output variables integral to each operational category. Comprehensive calculation flowcharts are presented to elucidate the software’s organizational structure and operational sequences. Furthermore, a meticulous verification assessment is conducted to validate OpenSeismoMatlab’s performance. This verification entails a rigorous examination of specific cases drawn from existing literature, wherein the software’s outcomes are rigorously compared against corresponding results from prior studies. The examination not only underscores the reliability of OpenSeismoMatlab but also emphasizes its ability to generate outcomes that closely align with findings documented in the established body of literature. Concluding the study, the paper outlines potential directions for future research, shedding light on avenues where further development and exploration can enhance the utility and scope of OpenSeismoMatlab in advancing seismic engineering and structural design practices.

Keywords:
OpenSeismoMatlab; earthquake; seismic design; nonlinear spectra; pulse; resampling.

T.G. Wakjira, A. Abushanab, M. Shahria Alam, W. Alnahhal* and V. Plevris, "Explainable Machine Learning-Aided Efficient Prediction Model and Software Tool for Bond Strength of Concrete with Corroded Reinforcement", Structures, 59, Article ID 105693 (DOI: 10.1016/j.istruc.2023.105693), 2024.

Abstract:

The bond strength between concrete and reinforcement is crucial for the composite action and serviceability of reinforced concrete (RC) structures. However, it is vulnerable to deterioration from the corrosion of reinforcement bars, especially in marine structures. Thus, a precise and reliable model for the bond strength in corrosive environments is necessary to evaluate the serviceability and structural performance of corroded RC members. This study employs explainable machine learning (ML) techniques to assess the bond strength between concrete and corroded bars. Eight ML models are developed to establish the best predictive model for bond behavior, considering seven input parameters: corrosion level (CL), steel yield strength, compressive strength of concrete, concrete cover-to-bar diameter ratio, bar diameter-to-bonded length ratio, reinforcement type, and test type. The super learner (SL) model, integrating three ML models, outperforms other models and analytical methods with a large R² value (98% on the test set) and minimal statistical errors. The SHapley Additive exPlanation (SHAP) technique identifies CL as the most influential parameter on bond strength, while the reinforcement and test types have the least effect. Finally, a user-friendly graphical user interface (GUI) tool is established to facilitate the practical implementation of the developed model and support accurate bond strength prediction in concrete with steel reinforcement under corrosive environments.

Keywords:
Machine learning; Bond strength; Concrete; Corrosion; SHAP; Graphical user interface.

R. Ehtisham, W. Qayyum, C.V. Camp, V. Plevris*, J. Mir, Q.Z. Khan and A. Ahmad, "Computing the Characteristics of Defects in Wooden Structures using Image Processing and CNN", Automation in Construction, 158, Article ID 105211 (DOI: 10.1016/j.autcon.2023.105211), 2023.

Abstract:

Wood, a time-honored construction material prized for its exceptional properties, has been in use for millennia. Its enduring popularity is attributed to its remarkable strength, aesthetic appeal, and favorable environmental footprint. However, wooden structures are susceptible to various defects and imperfections that pose threats to their structural integrity, durability, and safety. These issues encompass knots, cracks, warping, twisting, decay, insect infestations, and more, all of which, if left unaddressed, can culminate in structural failures. Thus, a comprehensive strategy involving inspection, maintenance, and remediation is indispensable for safeguarding wooden structures. Traditional manual inspections, while effective, are characterized by their resource-intensive nature, entailing significant time and cost investments. This study presents a pioneering approach that leverages Convolutional Neural Networks (CNNs) and Image Processing techniques to revolutionize the assessment of damage in wooden structures using digital imagery. Initially, CNNs are employed to categorize images into three fundamental classes: cracks, knots, and undamaged sections. Subsequently, Image Processing techniques are harnessed to compute precise characteristics of these defects, including parameters such as crack length, width, angle, and the extent of the defective area within knots. The Inception-ResNet-V2 pre-trained model is utilized, fine-tuned and validated with a robust dataset comprising 9000 wooden defect images, evenly distributed across the three aforementioned categories. A prudent division allocates 70% of the dataset for model training, with the remaining 30% reserved for validation. Following successful training, the model demonstrates an impressive overall accuracy of 92% when classifying an independent test set comprising 100 new images. To illustrate the model's performance, two images from each damage category are selected and tested to compute the characteristics of the defects. The quantification error for crack angle is only 0.15%, while it is 0.99% for crack length, and 2% for crack width, demonstrating the high performance of the model. The practical implications of this work are profound. By automating defect assessment in wooden structures, our approach offers significant advantages to industry professionals. It expedites inspections, reduces labor costs, and enhances the accuracy of defect quantification.

Keywords:
Wooden structures; Characteristics of defects; CNN; Image processing.

V. Plevris, A. Jimenéz Rios* and G. Papazafeiropoulos, "Chatbots put to the test in math and logic problems: A comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard", AI, 4(4), Article ID 4040048 (DOI: 10.3390/ai4040048), 2023.

Abstract:
In an age where artificial intelligence is reshaping the landscape of education and problem solving, our study unveils the secrets behind three digital wizards, ChatGPT-3.5, ChatGPT-4, and Google Bard, as they engage in a thrilling showdown of mathematical and logical prowess. We assess the ability of the chatbots to understand the given problem, employ appropriate algorithms or methods to solve it, and generate coherent responses with correct answers. We conducted our study using a set of 30 questions. These questions were carefully crafted to be clear, unambiguous, and fully described using plain text only. Each question has a unique and well-defined correct answer. The questions were divided into two sets of 15: Set A consists of “Original” problems that cannot be found online, while Set B includes “Published” problems that are readily available online, often with their solutions. Each question was presented to each chatbot three times in May 2023. We recorded and analyzed their responses, highlighting their strengths and weaknesses. Our findings indicate that chatbots can provide accurate solutions for straightforward arithmetic, algebraic expressions, and basic logic puzzles, although they may not be consistently accurate in every attempt. However, for more complex mathematical problems or advanced logic tasks, the chatbots’ answers, although they appear convincing, may not be reliable. Furthermore, consistency is a concern as chatbots often provide conflicting answers when presented with the same question multiple times. To evaluate and compare the performance of the three chatbots, we conducted a quantitative analysis by scoring their final answers based on correctness. Our results show that ChatGPT-4 performs better than ChatGPT-3.5 in both sets of questions. Bard ranks third in the original questions of Set A, trailing behind the other two chatbots. However, Bard achieves the best performance, taking first place in the published questions of Set B. This is likely due to Bard’s direct access to the internet, unlike the ChatGPT chatbots, which, due to their designs, do not have external communication capabilities.

Keywords:
Chatbot; AI; logic; mathematics; ChatGPT; GPT-3.5; GPT-4; Google Bard.

R. Ehtisham, W. Qayyum, C.V. Camp, V. Plevris*, J. Mir, Q.Z. Khan and A. Ahmad, "Classification of defects in wooden structures using pre-trained models of convolutional neural network", Case Studies in Construction Materials, 19, Article ID e02530 (DOI: 10.1016/j.cscm.2023.e02530), 2023.

Abstract:
Wooden structures, over time, are challenged by different types of defects. Due to mechanical and weathering effects, these defects can occur in the form of cracks, live and dead knots, dampness, and others. Because of the risk of damage or complete failure, treatment of these defects is necessary, but doing so necessitates their proper identification and classification (categorization). Crack identification and categorization must be part of the inspection procedure for engineering structures in the built environment. Convolutional neural networks (CNNs), a sub-type of Deep Learning (DL), can automatically classify the images of wooden structures to identify such defects. In this study, ten pre-trained models of CNN, namely ResNet18, ResNet50, ResNet101, ShuffleNet, GoogLeNet, Inception-V3, MobileNet-V2, Xception, Inception-ResNet-V2, and NASNet-Mobile are evaluated for the tasks of classification and prediction of defects in wooden structures. Each pre-trained CNN model is additionally trained and validated on an image dataset of 9000 images, equally divided into three classes: cracks, knots, and intact (undamaged). A smaller dataset of 300 images is separately used for testing purposes. Statistical parameters such as accuracy, precision, recall, and F1-score are computed for each CNN model. The Inception-V3 model proved to be the best CNN model for classifying defects in wooden structures based on the model’s accuracy, processing time and overall performance.

Keywords:
Wooden defects; Defects Classification; Pre-trained Models; CNN.

A. de Macêdo Wahrhaftig, V. Plevris, B.A. Mohamad and D.L. Pereira, "Minimum design bending moment for systems of equivalent stiffness", Structures, 57, Article ID 105224 (DOI: 10.1016/j.istruc.2023.105224), 2023.

Abstract:
In this article, the minimum design bending moment of concrete slender columns is studied by assuming a system of equivalent stiffness. For concrete structural parts such as slender columns, their stiffness is dependent on the loading, originated from lumped and distributed masses, and the rheological behavior of the material. The latter alters the concrete’s modulus of elasticity, introducing changes over time. Basically, the desired transformation is from a one-dimensional non-prismatic system to another prismatic one which exhibits an equivalent bending stiffness. As the bending stiffness changes due to the change of the problem’s independent variables, the geometric characteristics of the transformed system reflect the same dependence as the original system. This implies changes in the minimum design moment since it is linked to the dimensions of the equivalent section. To assess the hypothesis proposed, a numerical simulation is conducted over a real structural system using a vertical loading ranging from zero up to the critical buckling force, taking into account the change in the modulus of deformation of concrete and assuming a certain level of cracking of the material. The results obtained showed that the strategy of using a system of equivalent stiffness simplifies the analysis of non-prismatic elements because the problem is reduced to a prismatic element of equivalent properties. Besides that, due to the incorporation of the concrete creep in the problem, the maximum moment obtained in the equivalent system needs to be multiplied by a factor of 2.94 in order to equal the maximum moment occurring in the original system.

Keywords:
Minimum design moment; Equivalent stiffness; Buckling; Rheological behavior; Reinforced concrete column; Rayleigh method.

L. Hadji*, V. Plevris and G. Papazafeiropoulos, “Investigation of the Static Bending Response of FGM Sandwich Plates”, Journal of Applied and Computational Mechanics, 10(1), pp. 26-37, 2024. DOI: 10.22055/jacm.2023.44278.4194

Abstract:
In the present work, a displacement-based high-order shear deformation theory is introduced for the static response of functionally graded plates. The present theory is variationally consistent and strongly similar to the classical plate theory in many aspects. It does not require the shear correction factor, and gives rise to the transverse shear stress variation so that the transverse shear stresses vary parabolically across the thickness to satisfy free surface conditions for the shear stress. By dividing the transverse displacement into the bending and shear parts and making further assumptions, the number of unknowns and equations of motion of the present theory is reduced a and hence makes them simple to use. The material properties of the plate are assumed to be graded in the thickness direction according to a simple power-law distribution in terms of volume fractions of material constituents. The equilibrium equations of a functionally graded plate are given based on the higher order shear deformation theory. The numerical results presented in the paper are demonstrated by comparing the results with solutions derived from other higher-order models found in the literature and the present numerical results of Finite Element Analysis (FEA). In the numerical results, the effects of the grading materials, lay-up scheme and aspect ratio on the normal stress, shear stress and static deflections of the functionally graded sandwich plates are presented and discussed. It can be concluded that the proposed theory is accurate, elegant and simple in solving the problem of the bending behavior of functionally graded plates.

Keywords:
Sandwich Plates, Functionally Graded Materials, Higher-Order Plate Theory, Stress, FEA.

G. Solorzano and V. Plevris, “An Open-Source Framework for Modeling RC Shear Walls Using Deep Neural Networks”, Advances in Civil Engineering, vol. 2023, Article ID 7953869, 17 pages (DOI: 10.1155/2023/7953869), 2023.

Abstract:
Reinforced concrete (RC) shear walls macroscopic models are simplified strategies able to simulate the complex nonlinear behavior of RC shear walls to some extent, but their efficacy and robustness are limited. In contrast, microscopic models are sophisticated finite element method (FEM) models that are far more accurate and reliable. However, their elevated computational cost turns them unfeasible for most practical applications. In this study, a data-driven surrogate model for analyzing RC shear walls is developed using deep neural networks (DNNs). The surrogate model is trained with thousands of FEM simulations to predict the characteristic curve obtained when a static nonlinear pushover analysis is performed. The surrogate model is extensively tested and found to exhibit a high degree of accuracy in its predictions while being extremely faster than the detailed FEM analysis. The complete framework that made this study possible is provided as an open-source project. The project is developed in Python and includes a parametric FEM model of an RC shear wall in OpenSeesPy, the training and validation of the DNN model in TensorFlow, and an application with an interactive graphical user interface to test the methodology and visualize the results.

Keywords:
Shear Wall, Surrogate Model, Deep Neural Network, Pushover Analysis, OpenSees, Open-Source.

M. Shabani, M. Kioumarsi and V. Plevris, “Performance-based seismic assessment of a historical masonry arch bridge: Effect of pulse-like excitations”, Frontiers of Structural and Civil Engineering (DOI: 10.1007/s11709-023-0972-z), 2023.

Abstract:
Seismic analysis of historical masonry bridges is important for authorities in all countries hosting such cultural heritage assets. The masonry arch bridge investigated in this study was built during the Roman period and is on the island of Rhodes, in Greece. Fifteen seismic records were considered and categorized as far-field, pulse-like near-field, and non-pulse-like near-field. The earthquake excitations were scaled to a target spectrum, and nonlinear time-history analyses were performed in the transverse direction. The performance levels were introduced based on the pushover curve, and the post-earthquake damage state of the bridge was examined. According to the results, pulse-like near-field events are more damaging than non-pulse-like near-field ground motions. Additionally the bridge is more vulnerable to far-field excitations than near-field events. Furthermore, the structure will suffer extensive post-earthquake damage and must be retrofitted.

Keywords:
Masonry arch bridges, seismic behavior, modal properties, pulse-like records, nonlinear time history analysis.

M. Georgioudakis* and V. Plevris, "Response Spectrum Analysis of Multi-Story Shear Buildings Using Machine Learning Techniques", Computation, 11(7), Article ID 11070126, 22 pages (DOI: 10.3390/computation11070126), 2023.

Abstract:
The dynamic analysis of structures is a computationally intensive procedure that must be considered, in order to make accurate seismic performance assessments in civil and structural engineering applications. To avoid these computationally demanding tasks, simplified methods are often used by engineers in practice, to estimate the behavior of complex structures under dynamic loading. This paper presents an assessment of several machine learning (ML) algorithms, with different characteristics, that aim to predict the dynamic analysis response of multi-story buildings. Large datasets of dynamic response analyses results were generated through standard sampling methods and conventional response spectrum modal analysis procedures. In an effort to obtain the best algorithm performance, an extensive hyper-parameter search was elaborated, followed by the corresponding feature importance. The ML model which exhibited the best performance was deployed in a web application, with the aim of providing predictions of the dynamic responses of multi-story buildings, according to their characteristics.

Keywords:
Response spectrum analysis, ensemble algorithms, machine learning, shear building, SHAP explainability.

A. Jiménez Rios, S. Ruiz-Capel, V. Plevris and M. Nogal, “Computational Methods Applied to Earthen Historical Structures”, Frontiers in Built Environment, 9:1219108 (DOI: 10.3389/fbuil.2023.1219108), 2023.

Abstract:
Earthen structures have an important representation among the UNESCO World Heritage List sites as well as among the built environment in general. Unfortunately, earthen heritage structures are also numerous within the UNESCO List of World Heritage in Danger whereas other existing common earthen structures are extremely vulnerable to seismic and climate change events. Within the field of heritage conservation, structural analysis contributes to the safety evaluation of the structure, the diagnosis of the causes of damage and decay, and to the validation of interventions. Thus, the need to develop effective and accurate computational methods suitable for the study of both monumental and vernacular earthen structures becomes evident. This paper compiles, summarizes, and highlights the latest developments and implementations of computational methods for the study of such structure typologies. The literature has been explored following the PRISMA-S checklist methodology and a narrative synthesis was used for the presentation of results. Finally, future trends, opportunities, and challenges are discussed.

Keywords:
Adobe, rammed earth, cob, finite element method, discrete element method, limit analysis.

M. Nikoo, G. Hafeez, G. Doudak and V. Plevris, "Predicting the Fundamental Period of Light-Frame Wooden Buildings by Employing Bat Algorithm-Based Artificial Neural Network", in Artificial Intelligence and Machine Learning Techniques for Civil Engineering, V. Plevris, A. Ahmad and N.D. Lagaros (Eds.), IGI Global, pp. 139-162, 2023.

Abstract:

The study utilizes an artificial neural network model for determining the fundamental period of Light-Frame Wooden Buildings, employing the Bat algorithm on a data set of 71 measured periods of wooden buildings. The number of stories, floor area, storey height, maximum length, and maximum width are selected as input parameters to estimate the fundamental period of light-frame wooden buildings. The accuracy and the competitiveness of the developed model were evaluated by comparing it with a similar particle swarm optimization (PSO)- ANN scheme, the formulas provided in the National Building Code of Canada, an equation obtained from the Eureqa software, and a non-linear regression (NLR) model. The results of the research show that the bat-ANN model exhibited the best overall performance with the lowest RMSE and MAE error values and the highest values of the Coefficient of determination, R², in comparison to the other examined models. Therefore, the proposed Bat-ANN model can be considered as a reliable, robust, and accurate tool for predicting the fundamental period of wooden buildings.

Book: "Artificial Intelligence and Machine Learning Techniques for Civil Engineering", Eds: V. Plevris, A. Ahmad, N.D. Lagaros, IGI Global, 2023. DOI: 10.4018/978-1-6684-5643-9

Description

In recent years, artificial intelligence (AI) has drawn significant attention with respect to its applications in several scientific fields, varying from big data handling to medical diagnosis. A tremendous transformation has taken place with the emerging application of AI. AI can provide a wide range of solutions to address many challenges in civil engineering.

Artificial Intelligence and Machine Learning Techniques for Civil Engineering highlights the latest technologies and applications of AI in structural engineering, transportation engineering, geotechnical engineering, and more. It features a collection of innovative research on the methods and implementation of AI and machine learning in multiple facets of civil engineering. Covering topics such as damage inspection, safety risk management, and information modeling, this premier reference source is an essential resource for engineers, government officials, business leaders and executives, construction managers, students and faculty of higher education, librarians, researchers, and academicians.

G. Nekouei, A. Vatani Oskouei, S. Gharehbaghi and V. Plevris*, "Seismic response modification, over-strength, and displacement amplification factors of steel special truss moment frames", Asian Journal of Civil Engineering (DOI: 10.1007/s42107-023-00661-x), 2023.

Abstract:
In this paper, the seismic design parameters of steel special truss moment frames (STMFs), including the response modification factor (R), over-strength factor (Ω) and displacement modification factor (C_d) are evaluated for two performance levels, namely life safety (LS) and collapse prevention (CP). The effects of geometrical dimensions of the special segment located at the middle part of truss girder and the number of stories are investigated. Twelve steel STMFs with 3, 5, 7, and 9 stories with three bays are considered to evaluate the parameters. In addition, three special segment lengths are considered for each STMF. The truss-girder members are made of hollow structural sections (HSSs) and W-sections are used for columns, which are designed based on ASCE7-16 recommendations. The results show that the number of stories and the different special segment lengths affect the seismic parameters significantly. Moreover, the values obtained for R, Ω and C_d show some differences compared to the ones recommended by ASCE7-16.

Keywords:
Special truss moment frames, Behavior factor, Over-strength factor, Displacement modification factor, Hollow steel section

G. Solorzano* and V. Plevris, "DNN-MLVEM: A Data-Driven Macromodel for RC Shear Walls Based on Deep Neural Networks", Mathematics, 11(10), Article ID 2347, 19 pages (DOI: 10.3390/math11102347), 2023.

Abstract:
This study proposes the DNN-MVLEM, a novel macromodel for the non-linear analysis of RC shear walls based on deep neural networks (DNN); while most RC shear wall macromodeling techniques follow a deterministic approach to find the right configuration and properties of the system, in this study, an alternative data-driven strategy is proposed instead. The proposed DNNMVLEM is composed of four vertical beam-column elements and one horizontal shear spring. The beam-column elements implement the fiber section formulation with standard non-linear uniaxial material models for concrete and steel, while the horizontal shear spring uses a multi-linear force–displacement relationship. Additionally, three calibration factors are introduced to improve the performance of the macromodel. The data-driven component of the proposed strategy consists of a large DNN that is trained to predict the force–displacement curve of the shear spring and the three calibration factors. The training data is created using a parametric microscopic FEM model based on the multi-layer shell element formulation and a genetic algorithm (GA) that optimizes the response of the macromodel to match the behavior of the microscopic FEM model. The DNN-MVLEM is tested in two types of examples, first as a stand-alone model and then as part of a two-bay multi-story frame structure. The results show that the DNN-MVLEM is capable of reproducing the results obtained with the microscopic FEM model up to 100 times faster and with an estimated error lower than 5%.

Keywords:
shear wall, macromodel, deep neural network, genetic algorithm, OpenSees.

G. Papazafeiropoulos and V. Plevris, "Kahramanmaraş—Gaziantep, Türkiye Mw 7.8 Earthquake on 6 February 2023: Strong Ground Motion and Building Response Estimations", Buildings, 13(5), Article ID 1194, 30 pages (DOI: 10.3390/buildings13051194), 2023.

Abstract:
The effects on structures of the earthquake with the magnitude of 7.8 on the Richter scale (moment magnitude scale) that took place in Pazarcık, Kahramanmaraş, Türkiye at 04:17 a.m. local time (01:17 UTC) on 6 February 2023, are investigated by processing suitable seismic records using the open-source software OpenSeismoMatlab. The earthquake had a maximum Mercalli intensity of XI (Extreme) and it was followed by a Mw 7.5 earthquake nine hours later, centered 95 km to the north–northeast from the first. Peak and cumulative seismic measures as well as elastic response spectra, constant ductility (or isoductile) response spectra, and incremental dynamic analysis curves were calculated for two representative earthquake records of the main event. Furthermore, the acceleration response spectra of a large set of records were compared to the acceleration design spectrum of the Turkish seismic code. Based on the study, it is concluded that the structures were overloaded far beyond their normal design levels. This, in combination with considerable vertical seismic components, was a contributing factor towards the collapse of many buildings in the region. Modifications of the Turkish seismic code are required so that higher spectral acceleration values can be prescribed, especially in earthquake-prone regions.

Keywords:
earthquake; Türkiye; design; collapse; ductility; reinforcement; concrete.

A. Jimenez Rios, V. Plevris and M. Nogal, “Bridge management through digital twin-based anomaly detection systems: A systematic review”, Frontiers in Built Environment, 9:1176621 (DOI: 10.3389/fbuil.2023.1176621), 2023.

Abstract:
Bridge infrastructure has great economic, social, and cultural value. Nevertheless, many of the infrastructural assets are in poor conservation condition as has been recently evidenced by the collapse of several bridges worldwide. The objective of this systematic review is to collect and synthesize state-of-the-art knowledge and information about how bridge information modeling, finite element modeling, and bridge health monitoring are combined and used in the creation of digital twins (DT) of bridges, and how these models could generate damage scenarios to be used by anomaly detection algorithms for damage detection on bridges, especially in bridges with cultural heritage value. A total of 76 relevant studies from 2017 up to 2022 have been taken into account in this review. The synthesis results show a consensus toward the future adoption of DT for bridge design, management, and operation among the scientific community and bridge practitioners. The main gaps identified are related to the lack of software interoperability, the required improvement of the performance of anomaly-detection algorithms, and the approach definition to be adopted for the integration of DT at the macro scale. Other potential developments are related to the implementation of Industry 5.0 concepts and ideas within DT frameworks.

Keywords:
Bridges, digital twins, anomaly detection algorithms, finite element method, cultural heritage conservation, bridge information modeling, bridge health monitoring.

M.E.A. Ben Seghier, V. Plevris and Α. Malekjafarian, “Development of Hybrid Adaptive Neural Fuzzy Inference System-Based Evolutionary Algorithms for Flexural Capacity Prediction in Corroded Steel Reinforced Concrete Beam”, Arabian Journal for Science and Engineering (DOI: 10.1007/s13369-023-07708-w), 2023.

Abstract:
The damages in reinforced concrete (RC) beams due to reinforcement corrosion is a major problem in the RC industry. Accurate prediction of the residual bearing capacity of RC beams can effectively prevent structural failures or unwanted over-costs of inspections and rehabilitations. This paper proposes a novel machine learning-based prediction framework that combines the adaptive neural fuzzy inference system (ANFIS) with several metaheuristic algorithms for the effective estimation of the flexural strength capacity. Five optimization algorithms are employed for auto-selection of the optimum ANFIS parameters, including differential evolution (DE), genetic algorithm, particle swarm optimization, artificial bee colony, and firefly algorithm (FFA). A comprehensive experimental database of the flexural capacity of corroded steel reinforced concrete beams obtained from the literature, consisting of 177 tests, is used as a case study to evaluate the prediction performance of the proposed hybrid models. The results demonstrate that the proposed hybrid models transcend the previously developed models, while the optimized ANFIS using FFA represents the highest accuracy and strong stability among the proposed models. It is concluded that the proposed framework using ANFIS-FFA can be effectively employed as a useful tool for the accurate estimation of the flexural strength capacity of corroded reinforced concrete beams.

Keywords:
Flexural strength capacity; Prediction; Machine learning; Adaptive neural fuzzy inference system; Nature-inspired algorithms; Firefly algorithm.

S.V.R. Tosee, I. Faridmehr, M.L. Nehdi, V. Plevris and K.A. Valerievich, "Predicting Crack Width in CFRP Strengthened RC One-Way Slabs Using Hybrid Grey Wolves Optimizer Neural Network Model", Buildings, 12(11), Article ID 1870, 26 pages (DOI: 10.3390/buildings12111870), 2022.

Abstract:
This study deploys a hybrid Grey Wolf Optimizer Neural Network Model for predicting the crack width in reinforced concrete slabs strengthened with carbon fiber-reinforced polymers (CFRP). Reinforced concrete (RC) one-way slabs (1800 × 400 × 120 mm in size) were strengthened with CFRP with various lengths (1800, 1100, and 700 mm) and subjected to four-point bending. The experimental results were compared to corresponding values for conventional RC slabs. The observed crack width results were recorded, and subsequently examined against the expression recommended by Eurocode 2. To estimate the crack width of CFRP-reinforced slabs, ANN combined with the Grey Wolf Optimizer algorithm was employed whereby the applied load, CFRP width/length, X/Y crack positions, and stress in steel reinforcement and concrete were defined as the input parameters. Experimental results showed that the larger the length and width of the carbon fiber, the smaller the maximum crack width in the tensile area of the slab at the final load step. On average, the crack width in slabs retrofitted with CFRP laminates increased by around 80% compared to a slab without CFRP. The results confirm that the equation provided by Eurocode 2 provides an unconservative estimation of crack widths for RC slabs strengthened with CFRP laminates. On the other hand, the results also confirm that the proposed informational model could be used as a reliable tool for estimating the crack width in RC slabs. The findings provide valuable insight into the design approaches for RC slabs and rehabilitation strategies for existing deficient RC slabs using CFRP.

Keywords:
crack width; CFRP; artificial intelligence; neural networks; concrete slab.

G. Solorzano* and V. Plevris, “Computational intelligence methods in simulation and modeling of structures: A state-of-the-art review using bibliometric maps”, Frontiers in Built Environment, 8:1049616, 2022. DOI: 10.3389/fbuil.2022.1049616

Abstract:
The modeling and simulation of structural systems is a task that requires high precision and reliable results to ensure the stability and safety of construction projects of all kinds. For many years now, structural engineers have relied on hard computing strategies for solving engineering problems, such as the application of the Finite Element Method (FEM) for structural analysis. However, despite the great success of FEM, as the complexity and difficulty of modern constructions increases, the numerical procedures required for their appropriated design become much harder to process using traditional methods. Therefore, other alternatives such as Computational Intelligence (CI) techniques are gaining substantial popularity among professionals and researchers in the field. In this study, a data-driven bibliometric analysis is presented with the aim to investigate the current research directions and the applications of CI-based methodologies for the simulation and modeling of structures. The presented study is centered on a self-mined database of nearly 8000 publications from 1990 to 2022 with topics related to the aforementioned field. The database is processed to create various two-dimensional bibliometric maps and analyze the relevant research metrics. From the maps, some of the trending topics and research gaps are identified based on an analysis of the keywords. Similarly, the most contributing authors and their collaborations are assessed through an analysis of the corresponding citations. Finally, based on the discovered research directions, various recent publications are selected from the literature and discussed in detail to set examples of innovative CI-based applications for the modeling and simulation of structures. The full methodology that is used to obtain the data and generate the bibliometric maps is presented in detail as a means to provide a clearer interpretation of the bibliometric analysis results.

Keywords:
computational intelligence, structural analysis, soft computing, finite element method, structural engineering, bibliometric analysis, bibliometric maps.

D. Koutsantonis, K. Koutsantonis, N.P. Bakas*, V. Plevris, A. Langousis and S.A. Chatzichristofis, "Bibliometric Literature Review of Adaptive Learning Systems", Sustainability, 14(19) (DOI: 10.3390/su141912684), 2022.

Abstract:
In this review paper, we computationally analyze a vast volume of published articles in the field of Adaptive Learning, as obtained by the Scopus Database. Particularly, we use a query with search terms targeting the area of Adaptive Learning Systems by utilizing a combination of specific keywords. Accordingly, we apply a multidimensional scaling algorithm to construct bibliometric maps for keywords, authors, and references. Subsequently, we present the computational results for the studied dataset, reveal significant patterns appearing in the field of adaptive learning and the inter-item associations, and interpret the findings based on the current state-of-the-art literature in the area. Furthermore, we demonstrate the time-series of the evolution of the research terms, their trends over time, as well as their prevalent statistical associations.

Keywords:
Adaptive learning, intelligent tutoring systems, personalized learning, machine learning, bibliometrics.

Book: "Artificial Intelligence (AI) Applied in Civil Engineering", Eds: N.D. Lagaros and V. Plevris, MDPI, Basel, Switzerland, 698 pages, 2022.

Description

In recent years, the application of artificial intelligence (AI) in several scientific fields, varying from big data handling to medical diagnosis, has drawn significant attention. The use of AI is already present in our daily lives, as exemplified by personalized ads, virtual assistants, autonomous driving, etc. Not surprisingly, AI methodologies have demonstrated impressive results through a wide range of uses and applications in engineering fields, including civil and structural engineering. The increase in AI studies shows that the use of AI in civil engineering is gaining momentum and will keep increasing in the coming years, bringing new innovations and applications. This book collection contains applications and recent advances of AI with regard to civil engineering problems, promoting cross-fertilization between these scientific fields. In particular, the focus is on hybrid studies and applications related to structural engineering, transportation engineering, geotechnical engineering, hydraulic engineering, environmental engineering, coastal and ocean engineering, structural health monitoring, and construction management. The book contains 35 contributions in total from 19 different countries around the world, covering a broad range of topics related to the applications of AI in civil engineering.

M.E.A. Ben Seghier, V. Plevris* and G. Solorzano, "Random forest-based algorithms for accurate evaluation of ultimate bending capacity of steel tubes", Structures, 44, pp. 261-273 (DOI: 10.1016/j.istruc.2022.08.007), 2022.

Abstract:
Despite the existence of methods for estimating the behavior of steel circular tubes subjected to pure bending, analytical models are still restricted due to the problem’s complexity and significant nonlinearity. Using the random forest (RF) as the basic model, novel intelligent models are constructed to estimate the ultimate pure bending capacity of circular steel tubes in this study. The RF model’s parameters are optimized using three nature inspired optimization algorithms, namely, the particle swarm optimization (PSO), ant colony optimization (ACO) and whale optimization algorithm (WOA). In the experimental part, a database of 104 tests that comprise 49 and 55 pure bending tests conducted on fabricated and cold-formed steel circular tubes, respectively, are evaluated and utilized to investigate the applicability of the hybrid RF-models. A single RF model is also built for comparative reasons in order to estimate the ultimate pending capacity. Various statistical and graphical measures are used to evaluate the performance of the developed models. The results show that the proposed RF-based nature-inspired algorithms can outperform the original RF predictive model. When the hybrid-RF models were assessed, it was discovered that the RF-WOA performed best. In addition, the influence of each parameter on the prediction findings based on the best RF-model is investigated via sensitivity analysis. Taking into account the overall findings, the hybrid RF-models may be used as powerful tools to predict the ultimate bending capacity of circular steel tubes and may be viable to aid technicians in making proper judgments.

Keywords:
Ultimate bending capacity, Circular steel tubes, Prediction, Random forest, Whale optimization algorithm, Performance index.

N.D. Lagaros and V. Plevris*, "Artificial Intelligence (AI) Applied in Civil Engineering", Applied Sciences, 12(15), pp 1-7 (DOI: 10.3390/app12157595), 2022.

Abstract:
In recent years, artificial intelligence (AI) has drawn significant attention with respect to its applications in several scientific fields, varying from big data handling to medical diagnosis. The use of AI is already present in our daily lives with several uses, such as personalized ads, virtual assistants, autonomous driving, etc. Not surprisingly, AI methodologies have found a wide range of uses and applications in engineering fields, including civil and structural engineering, with impressive results. The increase in AI studies with great acceleration shows that the use of AI in civil engineering is gaining momentum and will keep increasing in the coming years, bringing new innovations and applications. This research topic contains applications and recent advances of AI in civil engineering problems, promoting cross-fertilization between these scientific fields. In particular, the focus is on hybrid studies and applications related to structural engineering, transportation engineering, geotechnical engineering, hydraulic engineering, environmental engineering, coastal and ocean engineering, structural health monitoring, as well as construction management.

N.D. Lagaros, V. Plevris and N.A. Kallioras, "The mosaic of metaheuristic algorithms in structural optimization", Archives of Computational Methods in Engineering (State of the art reviews), 2022.

Abstract:
Metaheuristic optimization algorithms (MOAs) represent powerful tools for dealing with multi-modal nonlinear optimization problems. The considerable attention that MOAs have received over the last decade and especially when adopted for dealing with several types of structural optimization problems can be mainly credited to the advances achieved in computer science and computer technology rendering possible, among others, the solution of real-world structural design optimization cases in reasonable computational time. The primal scope of the study is to present a state-of-the-art review of past and current developments achieved so far in structural optimization problems dealt with MOAs, accompanied by a set of tests aiming to examine the efficiency of various MOAs in several benchmark structural optimization problems. For this purpose, 24 population-based state-of-the-art MOAs belonging in four classes, (i) swarm-based; (ii) physics-based; (iii) evolutionary-based; and (iv) human-based, are used for solving 11 single objective benchmark structural optimization test problems of different levels of complexity. The size of the problems employed varies, with the number of unknowns ranging from 3 to 328 and the number of constraint functions ranging from 2 to 264, related to the structural performance of the design with reference to deformation and stress limits.