Application of wavelet-neural network in rolling bearings fault diagnosis

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 assumption of stable signal is not applicable for the non-stable fault bearing signal. According to the frequency changing feature of rolling bearings vibration signals, the signal is decomposed by wavelet packet transform and frequency domain energy eigenvector is established. Recognition of fault pattern of rolling bearing was presented using radial basis function (RBF) neural network. Results show that wavelet-neural network can check the existence of rolling bearings malfunction and recognize inner or outer rings fault pattern accurately. The results are of great significance for engineering application.