利用神经网络对齿轮箱进行故障诊断的实例分析

Analysis of Gearbox Fault Diagnosis Based on Neural Networks

以JZQ250型号齿轮箱为实验对象,根据实际状况下齿轮箱的故障机理和振动特点,设计了状态监测与故障诊断实验方案,采集了齿轮箱振动信号,应用MATLAB软件中自带的神经网络工具箱,编程实现了神经网络预测模型。仿真和实验证明,此模型能够有效地检测出齿轮箱的典型故障,可以用于齿轮箱的故障诊断。

Taking gearbox JZQ250 as test objects,based on the fault mechanism and vibration trait of the gearbox in the practical state of work ,the experiment project on condition monitoring and fault diagnosis of the gearbox is designed ,the vibration signals of the gearbox are tested. Then with modularized programming thought the neural network predicting model is realized by using the neural network toolbox in MATLAB. The model can effectively predict the typical fault of gearbox and can be applied to the fault diagnosis of gearbox.