Development and experimental evaluation of a vision system for detecting defects of stator windings in induction motor assembly lines

Abstract

There are many sources of faults during the assembly process of induction motors and most of them are related to the stator. In industry, electrical tests are typically performed, but some defects cannot be detected by such tests and the motors still need to be inspected by human operators. This is a potential point for improvement, since the limitations of human operators are widely discussed in literature. Vision systems are an interesting option to surpass those limitations. This paper presents the development of a vision system to inspect defects related to the windings of stators in a motor assembly line, after the rotor is assembled to the motor. In a previous work, the viability of inspecting this type of defect before the rotor insertion has already been shown. In the present work, some modifications in the test rig have been performed to adapt it to the new condition of inspection and a new algorithm has been developed. The tests achieved a success rate of 96.7%. Based on the results, improvements are discussed to enhance its reliability, allowing its implementation in manufacturing lines.