Abstract
As a powerful tool for measuring complexity and randomness, multivariate multi-scale permutation entropy (MMPE) has been widely applied to the feature representation and extraction of multi-channel signals. However, MMPE still has some intrinsic shortcomings that exist in the coarse-grained procedure, and it lacks the precise estimation of entropy value. To address these issues, in this paper a novel non-linear dynamic method named composite multivariate multi-scale permutation entropy (CMMPE) is proposed, for optimizing insufficient coarse-grained process in MMPE, and thus to avoid the loss of information. The simulated signals are used to verify the validity of CMMPE by comparing it with the often-used MMPE method. An intelligent fault diagnosis method is then put forward on the basis of CMMPE, Laplacian score (LS), and bat optimization algorithm-based support vector machine (BA-SVM). Finally, the proposed fault diagnosis method is utilized to analyze the test data of rolling bearings and is then compared with the MMPE, multivariate multi-scale multiscale entropy (MMFE), and multi-scale permutation entropy (MPE) based fault diagnosis methods. The results indicate that the proposed fault diagnosis method of rolling bearing can achieve effective identification of fault categories and is superior to comparative methods.
Highlights
Rolling bearings has an indispensable role in many large rotating machines; once it works with a local failure, the normal operation of mechanical equipment will be disturbed, and serious economic losses and safety incidents will be caused if the fault cannot be detected in time [1,2]
composite multivariate multi-scale permutation entropy (CMMPE), multivariate multi-scale permutation entropy (MMPE), and multivariate multi-scale fuzzy entropy (MMFE) based methods, it can be seen that the relatively stable recognition rate obtained by the proposed fault diagnosis method is greater than 99%, while there is a large fluctuation in the outputs of MMPE, Laplacian score (LS), and based support vector machine (BA-SVM)
An improved nonlinear dynamic method named CMMPE is proposed in this paper to measure the complexity and dynamic mutation of multi-channel time series, which can effectively address the insufficient coarse-grained process in MMPE
Summary
Rolling bearings has an indispensable role in many large rotating machines; once it works with a local failure, the normal operation of mechanical equipment will be disturbed, and serious economic losses and safety incidents will be caused if the fault cannot be detected in time [1,2]. [10], an approach based on local characteristic-scale decomposition (LCD) and the PE method was put forward for the diagnosis of faulty rolling bearings. The above entropy-based methods have acquired a good performance on the early fault intelligent diagnosis for rolling bearings. They are limited by the single-scale analysis of these entropy methods and tend to ignore the information of time series when processing multi-scale signals. To overcome the shortcoming of MMPE, an improved method, composite multivariate multi-scale permutation entropy (CMMPE), is proposed in this paper. According to the reliable and stable results of CMMPE, an intelligent fault diagnosis method for rolling bearing is put forward based on the CMMPE, LS, and BA-SVM, where the following three steps are contained.
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
