Application of Hidden Semi-Markov Models based on wavelet correlation feature scale entropy in equipment degradation state recognition

In order to correctly recognize the current state of equipment for preventing equipment farther degradation and occurrence of failure, a new method of equipment degradation state recognition based on wavelet correlation feature scale entropy(WCFSE) and hidden semi-Markov models (HSMM ) was proposed. Firstly, the gathered vibration signal of equipment was processed by the way of the wavelet transform correlation filter (WTCF), in order to get the high Signal-to-Noise scales wavelet coefficients, the conception of W_CFSE was presented based on integration of information entropy theory and WTCF, and then constructed W_CFSE eigenvectors of signal. Those W_CFSE eigenvectors were inputted to the HSMM for training, running states classified model of equipment based on HSMM was constructed to recognize the equipment degradation states. A roller bearing was taken as an example and several states of roller with normal state and different fault severity states were recognized by the proposed method, Experiment results show that this proposed method is very effective.