基于自适应AR谱与神经网络的汽车变速器轴承故障诊断  

Fault Diagnosis for Bearings in Automotive Transmission Based on Adaptive AR Spectrum and Neural Network

作　　者：蔡源春[1] 周云山[1] 张飞铁[1] 刘金刚[1] 邹乃威[2] 

机构地区：[1]湖南大学,汽车车身先进设计制造国家重点实验室,长沙410082 [2]吉林大学汽车工程学院,长春130025

出　　处：《汽车工程》2008年第4期372-375,共4页Automotive Engineering

基　　金：国家自然科学基金项目(50275050);高等学校博士点专项科研基金项目(20020532024)资助

摘　　要：提出了基于自适应AR谱和神经网络的汽车变速器轴承故障诊断方法。该方法采用自适应滤波将轴承振动信号进行滤波,建立AR模型,从而提取出故障轴承的特征,再利用BP神经网络进行故障分类。试验证明该方法适用于汽车变速器轴承的故障诊断。Based on the theories of adaptive AR spectrum and neural network, a fault diagnosis method for bearings in automotive transmission is presented. The method uses adaptive filtering technique to filter the vibration signals of beatings, sets up an AR model to extract the features of faulty beatings, and utilizes neural network to classify the faults. The test results show that the proposed approach can effectively identify the fault patterns of transmission bearings.

关 键 词：变速器 轴承 故障诊断 自适应滤波 AR谱 神经网络 

分 类 号：U463.212[机械工程—车辆工程]