Diagnóstico de Falhas de Rolamento em Motores de Indução Trifásicos a partir de um Modelo Matemático

Abstract

The wide use of three-phase induction motors (TIM) in various industry sectors encourages the search for techniques for monitoring and diagnosing defects in these machines to avoid production stops and unforeseen maintenance. Bearing fault detection is performed by analyzing the behavior of some motor variables, such as vibration and stator current, and their classification using artificial intelligence and machine learning. However, few studies on the modeling and simulation of these faults present a viable resource to cover several engines and specific operating conditions, such as different loads and speeds. Therefore, this work aims to implement a model for TIM’s bearing failure simulations in dq0 reference that provides current data of a stator phase to analyze this frequency spectrum. From information extracted from this spectrum, 200 samples representing different TIM situations with bearing failures are submitted to two pattern classifiers, Multilayer Perceptron network and Kohonen network, to validate the proposed diagnostic method.