Segmentation in thermography images for bearing defect analysis in induction motors

Abstract

This paper proposes a methodology to be used in the segmentation of infrared thermography images for the detection of bearing faults in induction motors. The proposed methodology can be a helpful tool for preventive and predictive maintenance of the induction motor. This methodology is based on manual threshold image processing to obtain a segmentation of an infrared thermal image, which is used for the detection of critical points known as hot spots on the system under test. From these hot spots, the parameters of interest that describe the thermal behavior of the induction motor were obtained. With the segmented image, it is possible to compare and analyze the thermal conditions of the system.