A Deep Learning Based on Sparse Auto-Encoder with MCSA for Broken Rotor Bar Fault Detection and Diagnosis

摘要

The understanding of the Broken Rotor Bar (BRB) features frequencies and amplitudes has a great importance for all diagnostic methods. These characteristics frequencies shows a drawbacks under varying load condition. The discrete Fourier transform (DFT) has been widely used to achieve these requirements, because of its efficiency. However, this paper present an enhancing of the fault detection based on a Machine Current Signature Analysis (MCSA) method. Indeed, the use of Sparse Autoencoder (AE) with the combination of Multi-Layer Perceptron (MLP) shown a good accuracy. Furthermore, the extraction of the new features to use in multi-class classification for the healthy and faulty Induction Motor (IM) is presented.