A Reinforcement Learning Hyper-Heuristic in Multi-Objective Optimization with Application to Structural Damage Identification

• Published in: Structural and multidisciplinary optimization Vol. 66; no. 1; p. 16
• Main Authors: Cao, Pei, Zhang, Yang, Tang, Jiong
• Format: Journal Article
• Language: English
• Published: 2230 Support Springer Nature (United States) 01.01.2023; Springer Berlin Heidelberg; Springer Nature B.V
• Subjects: Advanced Optimization Enabling Digital Twin Technology; Completeness; Computational Mathematics and Numerical Analysis; Damage detection; Engineering; Engineering Design; Heuristic; Interrogation; Machine learning; Mechanical Engineering; Multiple objective analysis; Optimization; Research Paper; Search algorithms; Simulated annealing; Structural damage; Theoretical and Applied Mechanics; Structural damage identification; Multi-objective optimization; Reinforcement learning; Simulated annealing; Hyper-heuristic

Multi-objective optimization allows satisfying multiple decision criteria concurrently, and generally yields multiple solutions. It has the potential to be applied to structural damage identification applications which are oftentimes under-determined. How to achieve high-quality solutions in terms o...