湖南大学学报（自然科学版）2025，Vol.52Issue(10)：23-30,8.DOI:10.16339/j.cnki.hdxbzkb.2025202
基于SAGRU神经网络的车架载荷谱高效提取方法研究
Research on an Efficient Extraction Method for Chassis Load Spectra Based on SAGRU Neural Network
摘要
Abstract
To address the issue of long periods in extracting load spectra based on virtual iteration(VI),this paper presents a method for extracting chassis load spectra based on a spatial attention gated recurrent unit(SAGRU)neural network.Firstly,load spectra such as the six-axis wheel force,the acceleration and the displacement on multiple monitoring locations were acquired through reinforced proving ground testing.Then,a full vehicle multi-body dynamics(MBD)model is established,and the vertical displacement excitation at the wheel center under road test conditions is inversely solved based on SAGRU.Finally,the response of monitoring locations and chassis loads under road test conditions are calculated through MBD simulation analysis using the vertical displacement excitation and the five-component force in other directions as input.By comparing with the virtual iteration method for obtaining load spectra,it is shown that the proposed method achieves a 22.5%efficiency improvement while ensuring accuracy.关键词
载荷谱/疲劳寿命/虚拟迭代/六分力/注意力机制/神经网络/有限元分析Key words
load spectra/fatigue life/virtual iteration/six-component force/attention mechanism/neural net-works/finite element analysis分类
交通工程引用本文复制引用
陈为欢,赵军辉,余显忠,曾建邦..基于SAGRU神经网络的车架载荷谱高效提取方法研究[J].湖南大学学报（自然科学版）,2025,52(10):23-30,8.基金项目
国家重点研发计划资助项目(2020YFB1807204),National Key Research and Development Program of China(2020YFB1807204) （2020YFB1807204）
国家自然科学基金资助项目(U2001213),National Natural Science Foundation of China(U2001213) （U2001213）
江西省人工智能交通信息传输与处理重点实验室资助项目(20202BCD42010),Jiangxi Key Laboratory of Artificial Intelligence Transportation Information Transmission and Processing(20202BCD42010) （20202BCD42010）
