Method Research And Application Of Roller Bearing Fault Diagnosis Based On Neural Network

Because roller bearing is the common component in rotating machinery and its special using condition, its using expiration is various and hard to estimate exactly. Its running state can influence the performance of the whole machine directly, and related to the manufacturing process and product quality. The roller bearing diagnosis is very important so that roller bearing is almost diagnosed when rotating machinery is diagnosed. Vibration reflects the running state of roller bearing which is arose by rotating. Vibration signal testing is easy to collect and observe. Analysing vibration signal to analyse roller bearing state then to diagnose is convenient and reliable.Artificial neural network (ANN) is widely applied because of its advantages recent years. ANN has been appeared in fault diagnosis field. There are three most remarkable excellences in ANN: Firstly it is nonlinear, secondly it is constructed paralleled, Thirdly is its ability of studying and generalization. In the same time, ANN is easy to be realized because ANN is consist of a lot of simple neural cells and can solve those problems which are hard to be solved by analytics directly. It is suitable to introduce ANN to roller bearing fault diagnosis because of its advantages. The way of fault diagnosis is turned to artificial from traditional method. Following microcomputer techniques fast developing, the microcomputer system composed with microcomputer adding required software and hardware is more flexible and easy to patulous. ANN can be realized by software or hardware, so the roller fault diagnosis system performs works by utilizing software and hardware, reducing consumption.In machinery state diagnosis based on vibration signals, not only is there fault...