A new approach for rolling bearing fault diagnosis based on EEMD hierarchical entropy and improved CS-SVM

• Published in: 2019 Prognostics and System Health Management Conference (PHM-Qingdao) pp. 1 - 6
• Main Authors: Wang, Rui, Zhang, Zhisheng, Xia, Zhijie, Miao, Jindan, Guo, Yiming
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2019
• Subjects: Cuckoo Search; EEMD; Entropy; Fault diagnosis; hierarchical entropy; Machine tools; Rolling bearings; Support vector machines; SVM; Time series analysis; Vibrations
• DOI: 10.1109/PHM-Qingdao46334.2019.8942988

The fault diagnosis of CNC machine tools has become an important area of Prognostic and Health Management (PHM). The failure of rolling bearings on spindle is main cause of machine tool faults. Therefore, the significant focus of health management of CNC machine tools and other rotating machines is fault diagnosis of rolling bearings. In terms of the fault diagnosis, it is the most critical task to extracting bearing fault characteristics from vibration signals of rolling bearings. As a result, a new fault diagnosis method for bearing fault classification is proposed in this paper, which is built on the hierarchical entropy and improved Cuckoo Search-Support Vector Machine(CS-SVM). Firstly, ensemble empirical mode decomposition(EEMD) is adopted to decompose time domain vibration signals, aiming at eliminating modal confusion in empirical mode decomposition(EMD) method. Afterwards, the hierarchical entropy is chosen as fault feature parameters compared with sample entropy to construct feature vectors. In addition, the classification algorithm of multiple SVM optimized by the improved CS algorithm is utilized to identify rolling bearing fault modes. Finally, the proposed method is verified through the data taken from the Case Western Reserve University (CWRU) Bearing Data Center. The result demonstrates that the proposed method has promising performance and achieves accurate fault classification accuracy in rolling bearing fault diagnosis in comparison with other methods.