测控技术2025，Vol.44Issue(10)：61-66,6.DOI:10.19708/j.ckjs.2025.10.003
基于优化CNN模型的新能源汽车制动系统机械故障诊断
Mechanical Fault Diagnosis of New Energy Vehicle Braking System Based on Optimized CNN Model
摘要
Abstract
As a key safety component,the fault diagnosis of new energy vehicle braking system is of great sig-nificance for improving driving safety and system reliability.Traditional mechanical diagnosis methods are limit-ed by low precision and high time consumption,and it is difficult to meet the needs of complex fault scenarios in new energy vehicles.Therefore,a fault diagnosis model based on optimized convolutional neural network(CNN)is designed.The spatial and temporal features of the input signal are extracted by incorporating CNN and bidirectional gated recurrent units,and inter-channel attention mechanisms is used to optimize feature weight assignment.The experimental results show that the model performs well in the classification tasks of 6 typical brake faults,with accuracy of 98.7％,mean squared error of 0.02,and diagnosis time controlled within 1.2s.The results show that the proposed model effectively improves the diagnostic performance and efficiency,and is suitable for complex fault scenarios.关键词
新能源汽车/制动系统/故障诊断/卷积神经网络/门控循环单元Key words
new energy vehicle/braking system/fault diagnosis/CNN/GRU分类
交通工程引用本文复制引用
温志力,张忠其..基于优化CNN模型的新能源汽车制动系统机械故障诊断[J].测控技术,2025,44(10):61-66,6.基金项目
广西教育科学"十四五"规划2024年度专项课题(2024ZJY394) （2024ZJY394）
