基于扭振分析方法的齿轮传动系统故障辨识

通过分析齿轮啮合过程的数学模型及典型故障,论证了扭振分析方法在齿轮系统故障诊断上的优越性,并提出一种测量齿轮轴上扭振信息的新方法。在此基础上搭建了齿轮传动系统,通过采用永磁旋转(角)加速度传感器检测齿轮系统各个运行状态下不同轴上的扭振信号;然后,分别对齿轮传动系统轴上的扭振信号和平台的振动信号采用小波包分解,提取各个节点的能量作为特征向量;最后,结合以径向基函数(RBF)为核函数的支持向量机(SVM)分别进行故障的辨识。实验结果表明:轴上的扭振信号在齿轮系统故障诊断上的效果要优于平台振动信号的诊断效果。

Gear Fault Identification Based on Torsional Vibration Analysis Method

A new method to measure the torsional vibration of gear shaft is proposed, though analyzing and studying the mathematical model and typical faults of gear, the superiority of torsional vibration analysis in fault diagnosis of gear system is theoretically demonstrated. To verify the correctness of theoretical analysis, a gear transmission system is set up to detect the torsional vibration signals of different axes under various operating states of the gear system by the permanent magnet rotary (angular) acceleration sensor. Then, the torsional vibration signals of the gear transmission system shaft and the vibration signal of the platform is decomposed by wavelet packet, and the energy of each node is extracted as the eigenvector. Finally, the fault identification is carried out with support vector machine (SVM) with radial basis function (RBF) as kernel function. The experimental result shows that the torsional vibration signal on the shaft is superior to the diagnostic results of the platform vibration signal in fault diagnosis of gear system.