Algorithm And Software For Fault Diagnosis Of Rolling Bearing

Because rolling 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. According to statistical, about 30% fault in rotating machinery is resulted from rolling bearing fault. The method of rolling bearing fault diagnosis is almost implemented when rotating machinery is diagnosed, so that the rolling bearing diagnosis is very important.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 rolling bearing fault diagnosis because of its advantages. The way of fault diagnosis is turned to artificial from traditional method.In this thesis, a new BP network-based fault diagnosis method of rolling bearing is presented. By established BP network model, analyse rolling bearing vibration data, acquire characteristics, then input neural network ,and then train the network with BP algorithm. The pattern of rolling bearing failure can be identified with the intellectual ability of BP neural network. The simulation result shows that the method presented in this paper is practical and effective.The specialists who grasp the computer programming language can establish BP network model ,which does not favor the promotion of the nerve network technology in a way. The MATLAB software has provided an available nerve network toolbox (NNT). The dissertation designs the rolling bearing fault diagnosis system with VC++ 6.0 develop software and MATLAB nerve network toolbox (NNT), and implements two modules, neural network learning and neural networkdiagnosis. The design and implementation of this system makes the fault diagnosis of rolling bearing effective, and this system is very convenient in practical use. The paper verifies the conclusion by simulation using actual data. The results show that the diagnosis method which is based on ANN is accurate and practical has a good applicative expectation.