基于PSO-BP神经网络的轮胎负荷测量方法  

Tire Load Measurement Method Based on PSO-BP Neural Network

作　　者：曹旭 张舜 许彦峰[1] 王青春[1] CAO Xu;ZHANG Shun;XU Yanfeng;WANG Qingchun(Beijing Forestry University,Beijing 100083,China;Anhui Lupital Iot Co.,Ltd,Hefei 230031,China)

机构地区：[1]北京林业大学工学院,北京100083 [2]安徽路必达智能科技有限公司,安徽合肥230031

出　　处：《轮胎工业》2024年第5期312-315,共4页Tire Industry

摘　　要：研究基于粒子群优化(PSO)算法-BP神经网络的轮胎负荷测量方法。将采集的轮胎状态信息与提取到的加速度特征输入到BP神经网络,对轮胎负荷进行回归预测,使用PSO算法优化BP神经网络的权值与阈值,得到轮胎状态信息与轮胎负荷的关系。结果表明,采用PSO-BP神经网络预测轮胎负荷误差为1.8656%,PSO-BP神经网络预测精度较高,在转变工况条件下,预测误差为2.496%。The tire load measurement method based on particle swarm optimization(PSO)algorithm-BP neural network was studied.The collected tire condition information and extracted acceleration features were input into the BP neural network to regressively predict the tire load.The weight and threshold of BP neural network were optimized by PSO algorithm,and the relationship between tire state information and tire load was obtained.The results showed that the prediction error for tire load using the PSO-BP neural network was 1.8656%and the prediction accuracy of PSO-BP neural network was higher.Under changing working conditions,the prediction error was 2.496%.

关 键 词：轮胎负荷 轮胎状态信息 加速度特征 粒子群优化算法 BP神经网络 

分 类 号：TQ336.1[化学工程—橡胶工业]