Application of ICEEMDAN Energy Entropy and AFSA-SVM for Fault Diagnosis of Hoist Sheave Bearing

• Published in: Entropy (Basel, Switzerland) Vol. 22; no. 12; p. 1347
• Main Authors: Kou, Ziming, Yang, Fen, Wu, Juan, Li, Tengyu
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 28.11.2020; MDPI
• Subjects: Accuracy; Algorithms; artificial fish swarm algorithm; Bearings; Classification; Coal mining; Decomposition; Derricks; Diagnostic systems; Energy; energy entropy; Entropy; Fault diagnosis; Model accuracy; Optimization; sheave bearing; Signal processing; support vector machine; Support vector machines; energy entropy; support vector machine; sheave bearing; artificial fish swarm algorithm
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e22121347

The mine hoist sheave bearing is a large heavy-duty bearing, located in a derrick of tens of meters. Aiming at the difficulty of sheave bearing fault diagnosis, a combined fault-diagnosis method based on the improved complete ensemble EMD (ICEEMDAN) energy entropy and support vector machine (SVM) optimized by artificial fish swarm algorithm (AFSA) was proposed. Different location of the bearing defect will result in different frequency components and different amplitude energy of the frequency. According to this feature, the position of the bearing defect can be determined by calculating the ICEEMDAN energy entropy of different vibration signals. In view of the difficulty in selecting the penalty factor and radial basis kernel parameter in the SVM model, the AFSA was used to optimize them. The experimental results show that the accuracy rate of the optimized fault-diagnosis model is improved by 10% and the diagnostic accuracy rate is 97.5%.