Health monitoring of induction motor with impedance analysis and artificial intelligence

Abstract

The induction motor is utilized in almost all technological applications, and it is known as one of the industry’s workhorses. In every system, it is critical to ensure that the induction motor operates safely and reliably to prevent any personnel from dangerous hazards.

The stator winding faults of the induction motor are one of the most common faults that can happen. As a result, implementing and utilizing new technology like Artificial Intelligence to monitor for any early stage of defects within the induction motor will be beneficial in providing timely maintenance and condition monitoring.

The proposed technique for detecting stator winding faults in induction motors discussed in this study is a non-intrusive Machine Learning method. The early stages of any stator winding faults can be detected by using frequency and impedance magnitude data as my main parameters. As a result, possible dangers will be eliminated, motor downtime will be reduced, and maintenance costs are reduced as well.

The reliability and accuracy of the proposed method will be proven by the experimental results of my Neural Network Model.