This paper proposes a novel approach for detection of stator short circuit faults in three-phase induction motors. The method is based on two stages: feature extraction and classification by intelligent systems. First, mutual information is estimated from delayed stator current signals, which are used as inputs of C4.5 decision trees and multilayer perceptron neural networks in the second step. Several offline and online experimental tests are presented considering voltage unbalance, load torque variations, and 1% to 10% short circuit levels. The obtained results corroborate the effectiveness of this new diagnostic approach.

A comprehensive study of intelligent tools used to classify broken rotor bars in induction motors, which operate with three different types of frequency inverters, is presented. The diagnosis of defective rotor bars is a critical issue for the predictive maintenance of induction motors. A proper classification of these defects in their early stages of evolution is necessary for preventing major machine failures and production downtime. The proposed approach is performed by analysing the amplitude of the stator current signal in the time domain, using a dynamic acquisition rate based on machine frequency supply. To assess classification accuracy under the various severity levels of the faults, the performance of four different learning machine techniques is investigated: (i) fuzzy ARTMAP network; (ii) support vector machine (sequential minimal optimisation); (iii) k ‐nearest neighbour; and (iv) multilayer perceptron network. Results obtained from 1274 experimental tests are presented in order to validate the study, which considers a wide range of load conditions and operating frequencies. Experimental results presented in this study validate the robustness and efficacy of the proposed approach.

Three-phase induction motors are the primary means of transformation of electrical energy into mechanical energy in industry, since they are robust and present low cost. However, despite being robust, these machines are subject to electrical or mechanical faults. Thus, identifying a defect in a running motor may decrease the risk of possible damage. This paper proposes an alternative approach to identify defects in the stator of these motors, by analyzing current signals in the time domain. In addition, it presents the determination of the consequent fault severity by means of two proposals: 1) a multiagent system with a classifier behavior; and 2) a neural estimator. The faults observed are related to short circuits between turns in the stator coil of 1% to 10%. Experimental results are observed with motors of different powers, under various adverse situations of electrical feed and a wide range of load conditions on the machine shaft.