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.

Three-phase induction motors are widely employed in industrial production processes, due to their low acquisition cost and maintenance as well as their adaptation in front of different conditions of mechanical loads and robustness for use in harsh environments. Diagnosing an incipient fault when these motors are in operation, even before significant faults may occur, has received special attention from the industry. Thus, a proper diagnosis can lead to a reduction of losses in the processes, service time out, and equipment replacement, also ensure consistent and reliable operation of industrial systems. Based on that, this paper presents a comprehensive study concerning the use of intelligent tools in the classification of bearing faults in induction motors. We even considered when they are subject to various operating conditions such as variations in coupled load torque, regardless of power supply: direct-line or inverter fed. This work proposes the extraction of fault characteristics in the time domain, based on mutual information measurements between two phase current signals. In order to evaluate the classification accuracy under various fault severity levels, the performance of three different pattern recognition techniques were compared: artificial neural networks, specifically multilayer perceptron, k-nearest neighbors, and support vector machines. The experimental results presented in this study validate the robustness and effectiveness of the proposed methodology.

Induction motors are very robust, with low operating and maintenance costs, and are therefore widely used in industry. They are, however, not fault-free, with bearings and rotor bars accounting for about 50% of the total failures. This work presents a two-stage approach for three-phase induction motors diagnosis based on mutual information measures of the current signals, principal component analysis, and intelligent systems. In a first stage, the fault is identified, and, in a second stage, the severity of the defect is diagnosed. A case study is presented where different severities of bearing wear and bar breakage are analyzed. To test the robustness of the proposed method, voltage imbalances and load torque variations are considered. The results reveal the promising performance of the proposal with overall accuracies above 90% in all cases, and in many scenarios 100% of the cases are correctly classified. This work also evaluates different strategies for extracting the signals, showing the possibility of reducing the amount of information needed. Results show a satisfactory relation between efficiency and computational cost, with decreases in accuracy of less than 4% but reducing the amount of data by more than 90%, facilitating the efficient use of this method in embedded systems.

Production processes in industrial facilities are essentially a dynamic activity, but traditional time domain analysis (TDA) and frequency domain analysis (FDA) assume stationary conditions for induction machine fault diagnosis. The time-frequency domain analysis (TFDA) is an alternative to overcome the inadequacy of TDA and FDA techniques in transitory situations. In this context, the quadratic time-frequency distributions (QTFD) have demonstrated the potential to reveal time-variant features and information about the energy distribution of non-stationary signals. Therefore, several methodologies have been proposed lately based on these methods to perform electric machine health accompaniment. This paper presents a comprehensive survey of recent advancements in the application of QTFD for fault diagnosis in industrial time-varying systems. The concepts of the conventional joint time-frequency decomposition methods and the theoretical framework of the quadratic tools are briefly presented. This compilation promotes insights into the current state-of-the-art of TFDA-based condition monitoring techniques and highlights the progress, limitations, and future prospects in this field. The paper aims to provide valuable information for researchers and professionals seeking to optimize the health monitoring of electric machines in the industrial environment.