Optimal design of step-stress accelerated degradation tests based on genetic algorithm and neural network

AbstractIn this study, the optimal design of step-stress accelerated degradation tests is focused. An optimization model is proposed where an improved accelerated degradation model is involved to comprehensively consider the influence of accelerated stress and the measurement error. Then, a novel optimal design method is constructed, where multiple decision variables can be simultaneously optimized based on neural network and genetic algorithm. An effective sensitivity analysis method is further established to quantitively illustrate the influence of the predetermined model parameters on the optimal results. Finally, a case study is implemented, and a series of comparisons are implemented to demonstrate the effectiveness and rationality of the proposed method.Keywords: genetic algorithmmultiple decision variablesproxy modeloptimal designstep-stress accelerated degradation test AcknowledgmentThe authors are grateful to the editor and the anonymous reviewers for their critical and constructive review of the manuscript.Additional informationFundingThis study was supported by the National Natural Science Foundation of China (Grant No. 11872085).Notes on contributorsGen LiuGen Liu is currently a PhD candidate at School of Aeronautics Sciences and Engineering, Beihang University (Beijing, China). His research interests are optimal design of accelerated degradation tests and reliability evaluation of small sample life test.Zhihua WangZhihua Wang received the B.S. degree in mechanical engineering from the Dalian University of Technology, Dalian, China, and the Ph.D. degree in mechanical engineering from Beihang University, Beijing, China. She is currently an Associate Professor with the School of Aeronautics Sciences and Engineering, Beihang University. Her research interests include degradation modeling, life test optimal design, and small sample reliability assessment via multi-source information fusion.Rui BaoRui Bao is currently a Full Professor in structural integrity and durability in Solid Mechanics. Her teaching duties include under-graduate and graduate courses in material mechanics, fatigue reliability and structural fatigue life evaluation methods, and providing supervision to MSc and Ph.D students.Zelong MaoZelong Mao received the master degree from the Beijing University of Aeronautics and Astronautics, Beijing, China, in 2021. He is currently an Engineer with the Tianjin Navigation Instrument Research Institute, Tianjin, China. His research interests include electric component quality control and reliability design of ship equipment.Kunpeng RenKunpeng Ren received the master degree from the Beijing University of Aeronautics and Astronautics, Beijing, China, in 2013. He is currently a Senior Engineer with the Tianjin Navigation Instrument Research Institute, Tianjin, China. His research interests include electric component failure analysis, electric component quality control and accelerated life test design of ship equipment.