Rotor Faults diagnosis in PMSMs Based on Branch Current Analysis and Machine Learning

To solve the problem that it is difficult to accurately identify the rotor eccentric fault, demagnetization fault and mixed fault of permanent magnet synchronous motor (PMSM) with slot pole ratio of 3/2 and several times of it, this paper proposes a method to identify the rotor fault based on the combination of branch current analysis and machine learning algorithm. First, in this paper, we select the stator branch current fluctuation in time domain without mutual cancellation as the feature of fault classification. Secondly, after signal preprocessing, feature factors are extracted and several fault feature factors with large differences are selected to construct feature vectors. Finally, genetic algorithm is used to optimize the parameters of support vector machine (SVM), and GA-SVM model is constructed as a classifier for multi fault classification of permanent magnet synchronous motor to classify these three types of faults. The fault classification results show that the proposed method using branch current signal combined with GA-SVM can be effectively diagnose faulty PMSM.