Discrimination of Electrical Motor Faults in Thermal Images by using First-order Statistics and Classifiers

Fault detection and classification of an electrical equipment is a significant subject concerning the continuity of efficient working and necessary tasks. The heat concept creates a stimulating effect in case of failure among the electrical equipment. For this reason, thermal camera images can be functional and are used to detect the malfunctions. In this paper, thermal camera images are utilized to detect 11 different conditions of induction motors that are 8 different short-circuit faults of stator windings, rotor failure, cooling fan failure, and no-load. First-order statistics (FOS) are considered to obtain the discriminative information among the thermal images. The classification unit of model is specified examining five efficient algorithms that are neural networks (NN), k-nearest neighbors (k-NN), random forest (RF), logistic regression (LR), and support vector machines (SVM). In the experiments, 10-fold cross validation is chosen as the test method, and four metrics (accuracy, specificity, sensitivity, AUC) are considered to evaluate the performance. Consequently, the best accuracy of 97.29% is observed by k-NN and RF techniques. In a detailed examination, it is revealed that the most qualified technique rises as RF for the proposed model by considering the accuracy and AUC rates.