Submission Deadline: 31 August 2026 View: 142 Submit to Special Issue
Dr. Ahmed G. Gad
Email: ahmed.gad@fci.kfs.edu.eg
Affiliation: Faculty of Computers and Information, Kafrelsheikh University, Kafrelsheikh, 33516, Egypt
Research Interests: swarm intelligence, evolutionary computation, machine learning
Prof. Gai-Ge Wang
Email: wgg@ouc.edu.cn
Affiliation: School of Computer Science and Technology, Ocean University of China, Qingdao, 266100, China
Research Interests: evolutionary computation, swarm intelligence, constrained optimization
Prof. Panagiotis G. Asteris
Email: asteris@aspete.gr
Affiliation: School of Pedagogical and Technological Education, Athens, GR15122, Greece
Research Interests: computational mechanics, computational intelligence, artificial intelligence in civil engineering, structural health monitoring
Engineering systems—particularly in materials science, continuum mechanics, and structural health monitoring—are becoming increasingly complex. While Swarm Intelligence (SI) and Particle Swarm Optimization (PSO) have been cornerstones of optimization, traditional variants face critical limitations when applied to "expensive" problems where a single fitness evaluation (e.g., Finite Element Analysis or CFD) takes minutes or hours.
This Special Issue moves beyond standard algorithmic variants to focus on Data-Driven and Surrogate-Assisted Evolutionary Computation (SAEA). We aim to explore how Machine Learning (Gaussian Processes, Radial Basis Functions, Neural Networks) can be hybridized with evolutionary algorithms to act as surrogates, predicting performance and drastically reducing computational costs.
We specifically invite research on solving Inverse Problems in material parameter identification, Many-Objective Optimization in manufacturing, and Digital Twin calibration using next-generation intelligence.
Suggested Themes:
· Surrogate-Assisted Evolutionary Computation: Data-driven optimization for computationally expensive engineering problems.
· Inverse Analysis in Materials: Parameter identification for constitutive models using meta-heuristics.
· Many-Objective Optimization: Algorithms handling 4+ conflicting objectives in structural design (beyond standard Multi-Objective).
· Hybrid Intelligence: Integration of Evolutionary Algorithms with Deep Learning (CNNs, RNNs) for topology optimization.
· Digital Twins & Industry 4.0: Evolutionary scheduling and control in smart manufacturing.
· Large-Scale Global Optimization: Techniques for high-dimensional variables in continuum mechanics.
Login
Register
Submit a Paper
Propose a Special lssue