Investigation Study of Structure Real Load Spectra Acquisition and Fatigue Life Prediction Based on the Optimized E cient Hinging Hyperplane Neural Network Model  

作　　者：Lin Zhu Benao Xing Xingbao Li Min Chen Minping Jia 

机构地区：[1]School of Mechanical Engineering,Yangzhou University,Yangzhou 225001,China [2]Jiangsu Yawei Machine Tool Co.,Ltd,Yangzhou 225200,China [3]School of Advanced Technology,Xi’an Jiaotong-Liverpool University,Suzhou 215123,China [4]School of Mechanical Engineering,Southeast University,Nanjing 211189,China

出　　处：《Chinese Journal of Mechanical Engineering》2024年第6期628-648,共21页中国机械工程学报(英文版)

基　　金：Supported by National Natural Science Foundation of China(Grant No.51805447);Natural Science Foundation of Jiangsu Higher Education of China(Grant No.22KJB460010);Jiangsu Provincial Innovation and Promotion Project of Forestry Science and Technology of China(Grant No.LYKJ[2023]06);Yangzhou Science and Technology Plan(City School Cooperation Project)of China(Grant No.YZ2022193);Cyan Blue Project of Yangzhou University of China。

摘　　要：In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predicting the fatigue life of structures becomes notably arduous.This paper proposed an approach to predict the fatigue life of structure based on the optimized load spectra,which is accurately estimated by an efficient hinging hyperplane neural network(EHH-NN)model.The construction of the EHH-NN model includes initial network generation and parameter optimization.Through the combination of working conditions design,multi-body dynamics analysis and structural static mechanics analysis,the simulated load spectra of the structure are obtained.The simulated load spectra are taken as the input variables for the optimized EHH-NN model,while the measurement load spectra are used as the output variables.The prediction results of case structure indicate that the optimized EHH-NN model can achieve the high-accuracy load spectra,in comparison with support vector machine(SVM),random forest(RF)model and back propagation(BP)neural network.The error rate between the prediction values and the measurement values of the optimized EHH-NN model is 4.61%.In the Cauchy-Lorentz distribution,the absolute error data of 92%with EHH-NN model appear in the intermediate range of±1.65%.Also,the fatigue life analysis is performed for the case structure,based on the accurately predicted load spectra.The fatigue life of the case structure is calculated based on the comparison between the measured and predicted load spectra,with an accuracy of 93.56%.This research proposes the optimized EHH-NN model can more accurately reflect the measurement load spectra,enabling precise calculation of fatigue life.Additionally,the optimized EHH-NN model provides reliability assessment for industrial engineering equipment.

关 键 词：Efficient hinging hyperplane neural network model ANOVA decomposition Load spectra optimization Optimal parameter Fatigue life prediction 

分 类 号：TG1[金属学及工艺—金属学]