Fault Diagnosis of High-Speed Brushless Permanent-Magnet DC Motor Based on Support Vector Machine Optimized by Modified Grey Wolf Optimization Algorithm

With the development of reliability theory, people realized that “absolutely reliable” machines could not be made. its incomparable advantages, high-speed permanent-magnet brushless DC motor is usually used in symmetrical structure operation working systems, which at present are widely aerospace and other fields. The manufacturing process involves a strict processing, but work failure still occur. No matter what field permanent magnet applied to, it very important to identify states run fault diagnosis, great significance maintain system. In this study, diagnosis method studied, combination model modified gray wolf optimization algorithm (MGWO) support vector machine (SVM) have been proposed for research. Based on traditional (GWO) algorithm, performance improved by initializing population through tent map introducing sine wave dynamic adaptive factor. Then optimize internal parameters SVM improve diagnostic accuracy model. Through signal acquisition test, current signals under different faultless were collected, data set required experiment obtained. experimental result showed that, compared with GWO or sailfish (SFO) optimized models, Extreme learning Back Propagation neural network classical classification highest, proving excellent good robustness MGWO-SVM