Thermographic fault diagnosis of electrical faults of commutator and induction motors

In this paper, the author proposes a fault diagnosis technique for the analysis of thermal images of commutator motors (CMs) and single-phase induction motors (SIMs). The aim of scientific research is to confirm the effectiveness of the proposed technique for the analysis of thermal images of electric motors. Original feature extraction methods: DAMOM (Differences of Arithmetic Mean with Otsu's Method), DAM20HP (Differences of Arithmetic Mean with 20 Highest Peaks), DAMMH (Differences of Arithmetic Mean with Mean of the histogram), IB (Ignore Binarization). The Nearest Neighbor classifier and Long short-term memory (LSTM) classified feature vectors. The thermal imaging camera was moved 0-1 [m/s2] vertically, during the measurements. Thermal imaging measurements with shivering and analysis are a novelty for fault diagnosis methods. The following conditions of motors were analyzed: healthy commutator motor (HCM), broken rotor coil of the commutator motor (BRCoCM), shorted stator coils of the commutator motor (SSCoCM), healthy single-phase induction motor (HSIM), single-phase induction motor with shorted coils of auxiliary winding (SIMwSCoAW), single-phase induction motor with shorted coils of auxiliary winding, and main winding (SIMwSCoAWaMW). The proposed analysis was successful. The value of AMECM (Arithmetic mean of the efficiency of recognition) was equal to 100% for the analyzed states of the CM. The value of AMESIM was in the range of 95.33%-100% for the analyzed states of the SIM. The original perspective of the presented study is to develop techniques of thermal imaging diagnostics. Readers can learn about the subject of thermographic diagnostics of electrical motors. Readers also gain knowledge about the processing of thermal images. A literature review on the diagnostics of electric motors was also presented.