Broken bar condition monitoring of an induction motor under different supplies using a Linear Discriminant Analysis

This paper presents a procedure for broken rotor bar diagnosis in induction motors based in data extracted from stator current, which is calculated in the time and frequency domains. Data comes from a tested motor fed by different types of supply: direct line and two different Voltage Source Inverters. Diagnosis is always difficult in Voltage Source Inverter fed motors due to inherent noise level and the presence of additional non-related fault harmonics in the stator current spectrum. Moreover, the motor was tested under different load conditions, from no-load to full-load. Diagnosis is also more difficult at lower load levels. Previous to fault classification, a variable reduction was carried out using Principal Component Analysis. Fault classification was performed using Linear Discriminant Analysis. The motor was tested with different fault severities, what allowed us to perform an analysis oriented to different maintenance approaches, considering the criticality of the motor.