A Multi-scale Fuzzy Measure Entropy and Infinite Feature Selection Based Approach for Rolling Bearing Fault Diagnosis
- 5 Downloads
Fuzzy measure entropy (FuzzyMEn) is a recently improved non-linear dynamic parameter for evaluating the signals’ complexity. In comparison with fuzzy entropy (FuzzyEn), which only emphasizes the local characteristics of the signal but neglects its global trend, FuzzyMEn can reflect not only the local but also the global characteristics of the signal. Therefore, by calculating the FuzzyMEn values in different scales, the multi-scale fuzzy measure entropy (MFME) method is put forward in this paper and used for extracting the fault features from vibration signals of rolling bearing. After the feature extraction, the newly developed infinite feature selection (Inf-FS) method is employed to choose the most representative features from the original ones of high dimension. Finally, a new rolling bearing fault diagnosis approach is presented based on MFME, Inf-FS and support vector machine (SVM). The experimental analysis indicates that the presented approach can realize the rolling bearing fault diagnosis effectively.
KeywordsMulti-scale fuzzy measure entropy Infinite feature selection Bearing fault diagnosis
- 10.Yan, R., Gao, R.X.: Approximate entropy as a diagnostic tool for machine health monitoring. Mech. Syst. Signal. Process. 21, 241–250 (2007)Google Scholar
- 20.Zhang, L., Xiong, G.L., Liu, H.S.: Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference. Expert Syst. Appl. 37, 6017–6085 (2010)Google Scholar
- 24.Giorgio, R., Melzi, S., Cristani, M.: Infinite feature selection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4202–4210 (2015)Google Scholar
- 30.He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. Adv. Neural. Inf. Process. Syst. 18, 507–514 (2005)Google Scholar