A Topological Neural-Based Scheme for Classification of Faults in Induction Machines

This article presents a data-driven approach for the classification of faults in induction machines. The designed scheme involves newly engineered features extracted from the line current signals, which provides an improved fault discrimination. For this purpose, a topological-based fast projection technique (curvilinear component analysis) is used as a tool to reduce the dimensionality of the data and interpret the feature behavior. Consequently, a shallow convolutional neural network has been designed to classify the three-phase stator current signals. Experimental tests at different operating conditions have assessed the procedure, confirming its effectiveness and suitability for online and real-time diagnostics.

I. Introduction

In recent years, research in the area of electrical machines and drives maintenance and diagnosis has experienced a breathtaking dynamism. This has been due to their incorporation into an endless number of industrial processes and applications. Indeed, the extensive use of electrical motors and generators, whose possible failures may lead to serious repercussions in monetary terms (repair costs and shutdowns), as well as other less tangible factors have drawn the attention of industry to this topic. A perfect analytic system should be able to extract the minimum amount of measurements from a machine and, by an investigation, provide a correct diagnosis so that its operating condition can be quickly determined to give a clear indication of the incipient fault.