A Hybrid Modeling-Based Reliability Optimization Method for Complex Engineering Structures
Abstract
Reliability-based optimization design plays a crucial role in enhancing the safety, economic efficiency, and sustainability of equipment incorporating complex engineering structures. To improve the accuracy and efficiency of optimization design, surrogate models are often employed to replace time-consuming and computationally expensive limit state evaluations of complex engineering structures. However, current surrogate model-based reliability optimization design methods still suffer from limited generalization capability, insufficient fitting accuracy, and low efficiency in sample construction. To address these challenges, this paper proposes a reliability-based optimization design method based on a multi-model adaptive ensemble surrogate strategy. The proposed method consists of three stages, aiming to improve the accuracy and efficiency of surrogate modeling while ensuring the reliability of optimization results. In the first stage, an adaptive ensemble surrogate model is constructed, incorporating both local variance and stability metrics to enhance model robustness. In the second stage, an optimization design framework is established, considering multiple damage modes in complex engineering structures. In the third stage, a decoupling strategy is applied to solve the optimization framework, yielding the optimal design solution. Finally, the proposed optimization framework is validated through a case study on an offshore wind turbine support structure, with results demonstrating the effectiveness and superiority of the proposed method.
Shun-Peng Zhu
Professor
Ph.D, Professor, Doctoral Supervisor, PIF Fellow of Politecnico di Milano, Italy since April 2016 and research associate at University of Maryland, United States from 2010 to 2011. His research which has been published in scholarly journals and edited volumes, over 100 peer-reviewed book chapters, journals and proceedings papers, explores the aspects: Fatigue assessment; Probabilistic Physics of Failure modeling; reliability and risk analysis; Multi-physics damage modeling and life prediction under uncertainty; Multi-scale uncertainty quantification and propagation; Bayesian inference and Fuzzy sets; Probability-based life prediction/design for engineering components/materials. Dr. Zhu also studies advanced numerical methods for uncertainty quantification in engineering. He received the Award of Merit of European Structural Integrity Society (ESIS)-TC12 in 2019, Most Cited Chinese Researchers (Elsevier) in the field of Safety, Risk, Reliability and Quality since 2018, 2nd prize of the National Defense Science and Technology Progress Award of Ministry of Industry and Information Technology of China in 2014, Polimi International Fellowship in 2015, Hiwin Doctoral Dissertation Award in 2012, Best Paper Awards of several international conferences and Elsevier Outstanding Reviewer Status. He serves as guest editor, editorial board member of several international journals and Springer book series, Organizing Committee Co-Chair of the International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE 2013), TPC Member of ICMR 2015, ICMFM XIX 2018-2020 and IRAS 2019.