现代电子技术2025，Vol.48Issue(20)：69-73,5.DOI:10.16652/j.issn.1004-373x.2025.20.012
改进BP神经网络的车载称重测量方法
Method of on-board weighing measurement based onimproved BP neural network
摘要
Abstract
In allusion to the low measurement accuracy of on-board weighing systema dynamic weighing model based on BP neural network optimized by Parrot optimization(PO)algorithm is proposed to cope with the overloading of trucks and realize the dynamic and accurate measurement of truck's load capacity.The on-board weighing system is introduced briefly,and the signal collected by the sensor is preprocessed by means of the composite filtering method.The weights and thresholds of the neural network are optimized iteratively by means of the PO-BP algorithm to construct a weighing model with the preprocessed signals of tire pressure,wheel rotational acceleration and temperature as inputs,so as to estimate the loadcapacity of the truck.The experimental results show that the PO optimization based BP neural network weighing algorithm can decrease the root-mean-square error to 2.3%and the average absolute error to 1.9%within a smaller number of iterations.In comparison with the traditional BP neural network,the algorithm has higher measurement accuracy,the measured value of truck load capacity is closer to the real value,and the relative error is within 5%,which can meet the accuracyrequirement of on-board weighing.关键词
车载称重系统/鹦鹉优化算法/BP神经网络/胎压传感器/货车载重/测量精度Key words
on-board weighing system/Parrot optimization algorithm/BP neural network/tire pressure sensor/truck load/measurement accuracy分类
信息技术与安全科学引用本文复制引用
王浩齐,尹继辉,郑旭光,陈东东,张鹏雷..改进BP神经网络的车载称重测量方法[J].现代电子技术,2025,48(20):69-73,5.基金项目
国家重点实验室开发基金项目(413228001) （413228001）
