Abstract
Multiscale fuzzy entropy (MFE), as an enhanced multiscale sample entropy (MSE) method, is an effective nonlinear method for measuring the complexity of time series. In this paper, an improved MFE algorithm termed composite interpolation-based multiscale fuzzy entropy (CIMFE) is proposed by using cubic spline interpolation of the time series over different scales to overcome the drawbacks of the coarse-grained MFE process. The proposed CIMFE method is compared with MSE and MFE by analyzing simulation signals and the result indicates that CIMFE is more robust than MSE and MFE in analyzing short time series. Taking this into account, a new fault diagnosis method for rolling bearing is presented by combining CIMFE for feature extraction with Laplacian support vector machine for fault feature classification. Finally, the proposed fault diagnosis method is applied to the experiment data of rolling bearing by comparing with the MSE, MFE and other existing methods, and the recognition rate of the proposed method is 98.71%, 98.71%, 98.71%, 98.71% and 100% under different training samples (5, 10, 15, 20 and 25), which is higher than that of the existing methods.
Highlights
Rolling bearings are some of the most common mechanical parts in rotating machinery and their running state often affects the performance of the whole machine [1,2]
Han and Pan proposed a fault diagnosis method combined with local mean decomposition (LMD), sample entropy and energy ratio for rolling bearing [8]
The above analysis of simulation signals indicates that composite interpolation-based multiscale fuzzy entropy (CIMFE) as a new complexity measure method for time series that can get much better performance than the existing methods, i.e., multiscale entropy (MSE), method for time series that can get much better performance than the existing methods, i.e., MSE, Multiscale fuzzy entropy (MFE) and Composite multiscale entropy (CMSE)
Summary
Rolling bearings are some of the most common mechanical parts in rotating machinery and their running state often affects the performance of the whole machine [1,2]. Yang et al [4] proposed an intelligent fault diagnosis of rolling element bearings based on support vector machines (SVMs) and fractal dimensions. Zhang et al [12] proposed a bearing fault diagnosis method by using multiscale entropy (MSE) and adaptive neuro-fuzzy inference. (ii) The process of coarse-grained MSE is regarded as a result of linear interpolation, which has some limitations when analyzing non-stationary and nonlinear data. The composite interpolation-based fuzzy entropy (CIMFE) is proposed to overcome the drawbacks of MSE. CIMFE is applied to extract the nonlinear mechanical fault features from vibration signals of rolling bearings. A fault diagnosis method for rolling bearings is put forward based on CIMFE and LapSVM.
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
