Bearing Fault Diagnosis Based on Multi-Sensor Information Fusion with SVM
This paper proposed a fault diagnosis based on multi-sensor information fusion for rolling bearing. This method used the energy value of multiple sensors is used as feature vector and a binary tree support vector machine (Binary Tree Support Vector Machine, BT-SVM) is used for pattern recognition and fault diagnosis. By analyzing the training samples, penalty factor and the kernel function parameters have effects on the recognition rate of bearing fault, then a approximate method to determine optimum value are proposed, Compared with the traditional single sensor by using the components energy of EMD as feature, the results show that the proposed method in this paper significantly reduce feature extraction time, and improve diagnostic accuracy, which is up to99.82%. This method is simple, effective and fast in feature extraction and meets the bearing diagnosis requirement of real-time fault diagnosis.
Shengyi Li, Yingchun Liu, Rongbo Zhu, Hongguang Li, Wensi Ding
X. J. Li et al., "Bearing Fault Diagnosis Based on Multi-Sensor Information Fusion with SVM", Applied Mechanics and Materials, Vols. 34-35, pp. 995-999, 2010