Abstract
This paper proposes a new method named composite multiscale fluctuation dispersion entropy (CMFDE), which measures the complexity of time series under different scale factors and synthesizes the information of multiple coarse-grained sequences. A simulation validates that CMFDE could improve the stability of entropy estimation. Meanwhile, a fault recognition method for rolling bearings based on CMFDE, the minimum redundancy maximum relevancy (mRMR) method, and the k nearest neighbor (kNN) classifier (CMFDE-mRMR-kNN) is developed. For the CMFDE-mRMR-kNN method, the CMFDE method is introduced to extract the fault characteristics of the rolling bearings. Then, the sensitive features are obtained by utilizing the mRMR method. Finally, the kNN classifier is used to recognize the different conditions of the rolling bearings. The effectiveness of the proposed CMFDE-mRMR-kNN method is verified by analyzing the standard experimental dataset. The experimental results show that the proposed fault diagnosis method can effectively classify the conditions of rolling bearings.
Highlights
The working performance of rolling bearings directly affects the safety, reliability, and stability of rotating machinery
The effectiveness of the proposed composite multiscale fluctuation dispersion entropy (CMFDE)-minimum redundancy maximum relevancy (mRMR)-k nearest neighbor (kNN) method is verified by analyzing the standard experimental dataset
The results show that approximate entropy (APE) can effectively
Summary
The working performance of rolling bearings directly affects the safety, reliability, and stability of rotating machinery. The nonlinear dynamics theory can be directly applied to extract the fault features of rolling bearings without signal decomposition or transformation. In consideration of the deficiency of single scale, multiscale sample entropy (MSE) [21] and multiscale permutation entropy (MPE) [22,23,24] were proposed, which were used to extract the fault features for rolling bearings [25] and reflect the characteristics of milling force signals [26], respectively. In 2016, to overcome the problems of APE, SE, and PE, Hamed Azami et al [27] proposed a nonlinear time complexity evaluation method based on dispersion entropy (DE), which would not create unreliable entropy values as well as was insensitive to noise interference, had high computational efficiency, and could solve the equivalence problem. As the core of this method, the function of CMFDE is to extract the nonlinear fault features of rolling bearings.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
