Condition Monitoring Accuracy in Inverter-Driven Permanent Magnet Synchronous Machines Based on Motor Voltage Signature Analysis

Condition monitoring and preventative maintenance are essential for reliable efficient operation of permanent magnet synchronous machines driven by inverters. There two types industrial inverter drives available: field oriented control direct torque control. Their compensation nature structure distinct and, therefore, the condition approach designed former may not be applicable to latter one. In this paper, we investigate Motor Voltage Signature Analysis both under healthy faulty conditions. Four typical fault conditions addressed: turn-to-turn short circuit, high resistance contact, static eccentricity, local demagnetization. High fidelity cosimulation is developed coupling finite element machine model with drives. The spectral elements commanded stator voltage utilized as indicators supervised classification identify, categorize, estimate severity faults. Linear discriminate analysis, k-nearest neighbor, support vector techniques used. Results indicate that based on performs adequately in Nevertheless, scheme does exhibit satisfactory performance owing nonlinear characteristics tolerance drive.