| The probability of machinery failure is very big for rolling bearing damaged in mechanical equipment failure. The working conditions of the bearing will directly influence the operation of the whole machinery and equipment. Methods on rolling bearing fault diagnosis are different. With the development of science and technology, it puts forward new requirements to the real-time detection of rolling bearing and the accuracy of diagnosis results and maintenance plan, which has important significance to the research of rolling bearing fault diagnosis.In order to be able to diagnosis Rolling Bearing Failure better, this paper analyzes the current main methods applied in rolling bearing fault diagnosis, adopts the theory of wavelet analysis which widely used at present to de-noise the rolling bearing vibration signal, then comes up with a more reasonable new threshold function, which is analyzed in theory. The experimental result shows that the noise reduction effect of new threshold function is more superior than the traditional threshold function. At the same time, the wavelet packet method is adopted to extract bearing fault feature information. The intelligent diagnosis of BP neural network is introduced to the diagnosis system. Using the characteristic information extracted by wavelet packet as the training samples and the prediction samples of BP neural network. For the reasons that BP neural network can easily fall into the local minimum value and the convergence speed is slow and all so defects, this paper adopts genetic algorithm to optimize the initial weights and threshold value of BP neural network. The optimized BP neural network can overcome the defects of BP network better. It can find the global optimal value when train and diagnose the rolling bearing fault. This paper adopts the development function of Lab VIEW friendly interface and powerful numerical analysis and data processing functions of MATLAB to research and develop the rolling bearing fault diagnosis system, making full use of LabVIEW's own MATLAB script node to combine the strengths of the two software together and realizing the intelligent diagnosis of rolling bearing. It also makes diagnosis speed and accuracy of the system get bigger increase. |
