A rolling bearing fault diagnosis strategy based on improved multiscale permutation entropy and least squares SVM

A novel rolling bearing fault diagnosis strategy is proposed based on Improved multiscale permutation entropy (IMPE), Laplacian score (LS) and Least squares support vector machine-Quantum behaved particle swarm optimization (QPSO-LSSVM). Entropy-based concepts have attracted attention recently within the domain of physiological signals and vibration data collected from human body or rotating machines. IMPE, which was developed to reduce the variability of entropy estimation in time series, was used to obtain more precise and reliable values in rolling element bearing vibration signals. The extracted features were then refined by LS approach to form a new feature vector containing main unique information. By constructing the fault feature, the effective characteristic vector was input to QPSO-LSSVM classifier to distinguish the health status of rolling bearings. The comparative test results indicate that the proposed methodology led to significant improvements in bearing defect identification.