LAUSR

Induction machines are omnipresent in industry because of their sturdiness and their ease of implementation. Nevertheless, these electrical motors still concede failures [e.g., interturn short circuit (ITSC) and broken rotor bar], which may lead to unplanned shutdowns. Consequently, manufacturing industries invest significant resources to avoid them with maintenance. Some studies have been achieved in this area of research, but any of the optimal solution (detecting, localizing, and estimating the degree of severity of failures) has been developed. Thus, in this paper, we propose to perform a comparison of performance and robustness between different classification algorithms, which can detect, approximate (severity of the failure), and localize (which phase) the ITSC in the stator phase(s) of the three-phase induction machine. To the best of our knowledge, it is the first time that such an evaluation has been suggested by using automated classification into predefined categories for ITSC in the stator phase(s) detection (recognition). This paper aims at providing an understanding vision of the recognition of failures that may occur, in order to develop future optimal solutions, which will be deployed in industry environment.