中文摘要：

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。

英文摘要：

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.