SI17 · Special Issue
Open for Submissions
AI-Driven and Surrogate-Assisted Optimization in Computational Engineering
- Publisher
- Tech Science Press
- Guest Editors
- V. Plevris and G. Papazafeiropoulos
- Editorial Period
- Oct 2026 – Present
- Submission Deadline
- 31 Oct 2027
- artificial intelligence
- machine learning
- engineering optimization
- computational modeling
- surrogate-assisted optimization
- surrogate modeling
- evolutionary algorithms
- physics-informed machine learning
- multiobjective optimization
- simulation-based optimization
View Editor Certificate (PDF, opens in a new tab) View Special Issue (opens in a new tab)
Artificial intelligence (AI) and machine learning (ML) are increasingly integrated into computational engineering optimization, enabling more efficient exploration of complex design spaces and improved solutions to computationally demanding problems. In particular, surrogate-assisted and AI-driven optimization frameworks offer promising approaches for reducing computational costs, handling nonlinear behavior, addressing multiple objectives, and accounting for uncertainties in engineering systems.
This Special Issue focuses on advances in AI-driven and surrogate-assisted optimization, emphasizing the integration of machine learning, intelligent optimization algorithms, surrogate models, and physics-based numerical simulations. Contributions presenting novel computational methodologies, hybrid optimization frameworks, and well-validated engineering applications are encouraged across structural, mechanical, aerospace, materials, energy, and related engineering disciplines.
Topics of interest include, but are not limited to:
- AI- and ML-driven engineering optimization.
- Surrogate-assisted, Bayesian, and multi-fidelity optimization.
- Machine learning-based surrogate models and metamodeling techniques.
- Evolutionary, swarm-based, and hybrid intelligent optimization algorithms.
- Physics-informed learning and simulation-based optimization.
- Structural, topology, and multidisciplinary design optimization.
- Multiobjective, robust, and reliability-based optimization.
- Deep learning and reinforcement learning for engineering optimization.
- Optimization under uncertainty and computationally expensive simulations.
- Data-driven computational modeling and reduced-order models for optimization.
Contributions demonstrating methodological advances, computational efficiency, and rigorous validation against established numerical or engineering benchmarks are particularly welcome.