Aviation bearing fault diagnosis method based on CHSMM

Aiming at realizing the effective fault diagnosis for aviation bearing, a method based on coupled hidden semi Markov model is proposed. Firstly, according to the aviation dynamic components of transmission structure, the monitoring network is designed for monitoring radial and axial vibration data of bearings; Secondly, the nonlinear feature extraction method is applied for obtaining a few key features which provides a prerequisite for improving the efficiency and accuracy of fault diagnosis; Finally, the left and right type homogenous hidden Markov chain, extending coupled hidden semi Markov model to multi-channel data fusion fault diagnosis, is utilized for building the reasonable model of the state of residence time distribution in the practical problems, moreover, the initial state model selection and parameter estimation algorithm of coupled hidden semi Markov model with two chains is researched by probability reasoning algorithm. The validation and effectivity of the proposed CHSMM(Coupled Hidden semi Markov Model) model is verified by the result of fault diagnosis on rolling bearing.