A Kalman Filter Based Deep Learning Autoencoder for Induction Motor Broken Rotor Bar Diagnosis

The present study tries to propose a new method which is using central difference Kalman filter (CDKF) as input index of deep learning (DL), for simulating state estimation and broken rotor bars (BRBs) diagnosis in induction motors (IMs). In addition, an advanced selective ensemble algorithm to diagnose the BRBs in IMs is proposed in the following study. In this study, at the initial step, in order to take sufficient data within the usual efficiency, it is needed to train the DL network. The outcomes indicate that the offered scheme can be more accurately and powerfully to detect diverse forms of BRBs with an accuracy of more than 98%. And also, Filter precision is enhanced via changing the sigma points of the filter, however, the stability of the filter enhances more because of its utilization, and the CDKF is further stable and precise in comparison to the extended Kalman filter (EKF). The CDKF performance is assessed to estimate the speed and is used as an input index of DL to diagnose the broken rotor bars in IMs. The obtained outcomes prove the performance of this combined scheme to be effective.