Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science · 2011 · 23 citations · 40 references
ComputingData ScienceFeature EngineeringMachine LearningStatistical LearningDiagnosisDiagnosticsFault DetectionHidden Markov ModelsVibration DiagnosticsVibration MonitoringBearing Fault DiagnosisBearing FaultsCoupled Hidden Markov ModelsMachine Fault DiagnosisMultiple State ModelsSystem Fault DiagnosisVibration-based DiagnosticsWavelet Packet Transform
This paper presents a novel multichannel fusion approach based on coupled hidden Markov models (CHMMs) for rolling element bearing fault diagnosis. Different from a hidden Markov model (HMM), a CHMM contains multiple state sequences and observation sequences, and hence has powerful potential for multichannel fusion. In this study, a two-chain CHMM is employed to integrate the two-channel vibration signals collected from bearings, i.e. the horizontal and vertical vibration signals. Efficient probabilistic inference and parameter estimation algorithms are developed for the model. An experiment was carried out to validate the proposed approach. Normalized wavelet packet energy and wavelet packet energy entropy are extracted as features for classification respectively. Then, the results of the proposed approach are compared with those of the currently used approach based on HMMs and one-channel signals. The results show that the proposed approach is feasible and effective to improve the classification rate.
40
Mixture Densities, Maximum Likelihood and the EM Algorithm
Richard A. Redner, Homer F. Walker · SIAM Review · 1984 · 2.7K citations
Coupled hidden Markov models for complex action recognition
Matthew Brand, Nuria Oliver, Alex Pentland · 2002 · 1.1K citations