航空科学技术2025，Vol.36Issue(5)：44-50,7.DOI:10.19452/j.issn1007-5453.2025.05.005
基于数据驱动的复合材料层合板疲劳分层扩展研究
Fatigue Delamination Prediction of Composite Laminates Based on Data-Driven
摘要
Abstract
Fatigue delamination growth(FDG)is one of the most important reasons for the failure of composite structures.Fiber bridging,as a shielding mechanism,can have significant retardation effects on FDG behavior,contributing to loading-history dependence on FDG.How to analyze and predict FDG effectively in composites with fiber bridging has become a key problem to be solved in the current composite fatigue field.In this study,a machine learning model,based on the long short-term memory(LSTM)network,is proposed for fiber-bridged fatigue delamination determination under FDG testing with different fiber bridging.The results clearly demonstrate that fatigue delamination behavior can be well represented via this machine learning model,as all predictions almost fall within the 2 times error band,which provides an accurate and fast method for characterization and prediction of FDG behavior in composites.关键词
数据驱动/疲劳分层扩展/纤维桥联/复合材料Key words
data driven/FDG/fiber bridging/composites引用本文复制引用
王杰雄,李兴福,裴兆东,姚辽军,果立成..基于数据驱动的复合材料层合板疲劳分层扩展研究[J].航空科学技术,2025,36(5):44-50,7.基金项目
航空科学基金(2022Z055077004) （2022Z055077004）
强度与结构完整性全国重点实验室开放基金(ASSIKFJJ202302003) Aeronautical Science Foundation of China(2022Z055077004) （ASSIKFJJ202302003）
National Key Laboratory of Strength and Structural Integrity Science Foundation(ASSIKFJJ202302003) （ASSIKFJJ202302003）
