Pattern recognition of rolling bearing fault based on wavelet and radial basis function neural networks

State monitoring and fault diagnosing of rolling bearing by analyzing vibration signal is one of the major problems which need to be solved in engineering. The traditional analyzing method based on stable signal is not applicable for the fault bearing whose signal is unstable. Extracting the fault features of fault bearing efficiently and classifying these features correctly are the two linchpins for solving the problem. Wavelet analysis possesses excellent characteristic of time-frequency localization and is suitable for analyzing the time-varying or transient signals. Neural network is successful in recognizing non-linear system and classifying pattern. According to the vibration signal features of frequency-domain, energy eigenvector was established by means of wavelet packet, then recognition of fault pattern of rolling bearing was presented using radial basis function neural network. The experimental result shows that the system can not only detect the fault of bearing but also can recognize inner or outer rings fault pattern correctly. The results are of great significance for engineering application.