Identification of bearing faults using linear discriminate analysis and continuous hidden Markov model

Abstract

It is important to diagnose the bearing fault to prevent the serious accident of equipment. This paper introduces a bearing fault identification scheme based on envelope power spectrum analysis, linear discriminate analysis and continuous hidden Markov model. First the envelope power spectrum features are extracted from amplitude demodulated vibration signals from fault bearings. Then, linear discriminate analysis is employed to reduce the feature dimensions, which are helpful for improving the computing speed and diagnosing accuracy. At last, the new linear discriminate analysis features are input into continuous hidden Markov model to train the models under different conditions, respectively. In bearing fault identification, test data are input into the pretrained continuous hidden Markov models, and the bearing state can be detected by the output of continuous hidden Markov model. To validate the effectiveness of the proposed method, experimental samples of four bearing conditions at different fault sizes and loads are utilized to test the continuous hidden Markov model and back-propagation neural network. The result shows that continuous hidden Markov model and linear discriminate analysis-based method have higher accuracy and efficiency than back-propagation neural network.

Weak thruster fault detection for AUV based on Bayesian network and Hidden Markov model

“…Hence, it has attracted extensive interests in fault diagnosis for rotational machinery. 25 For example, a fault classification model was developed based on the coupled hidden Markov model with a minimum intra-class distance for Gyro motors in Dong et al 26 In addition, to obtain better identification performance for bearing faults, a continuous hidden Markov model was established by combining with linear discriminate analysis in Liu et al 27 In AUV field, a state transition method was presented based on a Markov chain to analysis the safety of the vehicle during the complete mission in Brito and Griffiths. 28 However, to the best of our knowledge, hidden Markov model has not been applied to fault diagnosis in the AUV with thruster fault.…”