Induction Motor Failure Analysis: An Automatic Methodology Based on Infrared Imaging

The main techniques used for failure analysis in induction motors are limited because they are not capable of detecting all the faults present in an induction motor. However, a complementary technique that aids in fault diagnosis in induction motors is infrared imaging. This paper proposes an automatic methodology based on infrared imaging for thermal condition monitoring and failure analysis in induction motors and the kinematic chain; it can be considered an alternative tool for classical infrared imaging inspection procedures and for monitoring and failure analysis techniques in an induction motor in particular. The proposed methodology detects the region of interest using automatic image segmentation by means of the Otsu thresholding method, where it performs the feature extraction of temperatures for the thermal analysis of induction motors. The methodology is based on the standard ASTM E1934-99a for fault diagnosis in induction motors. To demonstrate the efficiency of the proposed methodology, this paper presents the failure analysis of three fault conditions in an induction motor: a broken rotor bar, bearing damage, and misalignment.