Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model

摘要: Ball bearings are integral elements in most rotating manufacturing machineries. While detecting defective bearing is relatively straightforward, discovering the source of defect requires advanced signal processing techniques. This paper proposes an automatic diagnosis method based on Swarm Rapid Centroid Estimation (SRCE) and Hidden Markov Model (HMM). Using frequency signatures extracted with Wavelet Kurtogram Cepstral Liftering, SRCE+HMM achieved average sensitivity, specificity, error rate 98.02%, 96.03%, 2.65%, respectively, fault vibration data provided by Case School Engineering Western Reserve University (CSE) which warrants further investigation. Graphical abstractDisplay Omitted HighlightsThis algorithm for rolling defects.The classification was optimized swarm clustering.The features were harmonics using wavelet kurtogram cepstral liftering.The obtained from University.Sensitivity specificity 98.02% 96.03% test data.