湖北汽车工业学院学报2025，Vol.39Issue(4)：31-34,39,5.DOI:10.3969/j.issn.1008-5483.2025.04.006
基于GWO-BP神经网络的摩擦片磨损量预测
Wear Amount Prediction of Friction Plates Based on GWO-BP Neural Network
摘要
Abstract
In order to solve the problems of high complexity,many parameters,and insufficient accura-cy of traditional prediction models,a wear amount prediction model of the friction plate based on a back-propagation neural network optimized by the grey wolf optimizer(GWO-BP)was proposed.The predic-tion accuracy of the model was improved through the optimization of initial parameters,and the conver-gence speed was accelerated to effectively avoid falling into a local optimum.The experiments on the public dataset show that the determination coefficient of the model is 0.9940;the average absolute error is 0.0030,and the mean bias error is 0.0011,demonstrating excellent predictive performance.关键词
摩擦片/磨损量预测/灰狼优化算法/BP神经网络Key words
friction plate/wear amount prediction/gray wolf optimization algorithm/BP neural network分类
交通工程引用本文复制引用
Wang Guiqian,Hou Jun..基于GWO-BP神经网络的摩擦片磨损量预测[J].湖北汽车工业学院学报,2025,39(4):31-34,39,5.基金项目
汽车动力传动与电子控制湖北省重点实验室开放基金(ZDK12023B10) （ZDK12023B10）
湖北汽车工业学院博士科研启动基金(BK202223) （BK202223）
