Bearing Fault Diagnosis Method Based on Singular Value Decomposition and Hidden Markov Model

The fault signal feature extraction and fault identification of the bearing has important scientific research significance in the mechanized production. Aiming at this, this paper puts forward bearing fault diagnosis method based on singular value decomposition (SVD) and Hidden Markov Model (HMM). To gain required fault feature information, firstly, it builds Hankel matrix, and conducts decomposition through SVD. SVD method is helpful for gaining effective fault feature information from the complex bearing fault signals, and then apply the achieved characteristic value to build the training model of Markov. The test result proves that the method of this paper has good practicability in the bearing fault identification.