Feature Index Extraction And Performance Degradation Evaluation Of Rolling Bearing Performance Degradation Based On S-Transformation

Reliable and comprehensive performance degradation assessment of important components of rotating machinery has become a research hotspot in the field of equipment condition monitoring.Model 6307 single row deep groove ball bearing is used as the research object of this paper.Based on the S-transformation spectrum,the exploration extracted new and more effective feature indices and applied them to the performance degradation assessment of rolling bearings.The spectrum of the S transform is measured by the complexity,and the complexity of the spectrum is measured for the S transform,and the S-time-frequency entropy is proposed.The S-time entropy is proposed for the S-transformation spectrum along the time series expansion.The S-time entropy is proposed.The S-frequency entropy is proposed for the S-transformation spectrum.Through the mathematical model simulation analysis of three entropy index and the comparison of the life cycle accelerated fatigue test data,it is shown that the three entropy indexes have different advantages for the failure stages of rolling bearings.The feature group under the performance degradation assessment framework is enriched.The S-GLCM entropy rolling bearing performance degradation characteristic index was proposed.The S-time spectrum is obtained by S-transformation of the rolling bearing signal,and the GLCM entropy feature extraction is performed on the S-time spectrum matrix as the final characteristic index.The mathematical model simulation analysis of the S-GLCM entropy index and the comparison of the life-cycle accelerated fatigue test data are carried out.Analysis,the validity of this indicator was verified.The S-SVD entropy rolling bearing performance degradation characteristic index was proposed.The S-time spectrum is obtained by S-transformation of the rolling bearing signal,and the SVD entropy feature extraction is performed on the S-time spectrum matrix as the final characteristic index.The mathematical model simulation analysis of the S-GLCM entropy index and the comparison of the life-cycle accelerated fatigue test data are carried out.The analysis found that the index has a large difference in the different bearing data under the same working condition,and can not be applied as a characteristic index to evaluate the performance degradation of the rolling bearing.The effective feature index(S-time-frequency entropy,S-time entropy,S-frequency entropy,S-GLCM entropy)and the effective value and STFT entropy and CWT entropy proposed in the paper constitute a new feature group,and the CHMM performance degradation evaluation of the rolling bearing is carried out.The results show that the above method can sensitively monitor the operating state of the equipment and accurately determine the important stage of equipment performance degradation.