ANN based fault diagnosis of permanent magnet synchronous motor under stator winding shorted turn

• Inter turn short circuit fault diagnosis was studied by the help of MLP ANN.
• We implement fault feature extraction under various speeds, loads, and severity of faults.
• A vector controlled PMSM was employed for healthy and faulty operation.
• Analytical, FE and experimental tests were employed to validate the results.
• We justify the usage of ANN and prove non-linearity of identified features in 3D plots.

The fault detection and diagnosis in electrical motors is a topic of increasing interest in the field of highly reliable and fault-tolerant measurement and control systems. This paper focuses on inter-turn short circuit fault diagnosis in stator windings of a Permanent magnet synchronous motor (PMSM). A multilayer artificial neural network (MANN) has been used for diagnosis and classification of different levels of short circuit. The analytical and finite element method (FEM) based results have been validated by experimental results. Experimental data have been employed to train ANN.