This paper investigates diagnostic techniques for electrical machines with special reference to induction machines and to papers published in the last ten years. A comprehensive list of references is reported and examined, and research activities classified into four main topics: 1) electrical faults; 2) mechanical faults; 3) signal processing for analysis and monitoring; and 4) artificial intelligence and decision-making techniques.

Advances in Diagnostic Techniques for Induction Machines

1D convolutional neural networks and applications: A survey

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application-specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and motor-fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publically shared in a dedicated website.

1D Convolutional Neural Networks and Applications: A Survey

Medium-voltage (MV) induction motors are widely used in the industry and are essential to industrial processes. The breakdown of these MV motors not only leads to high repair expenses but also causes extraordinary financial losses due to unexpected downtime. To provide reliable condition monitoring and protection for MV motors, this paper presents a comprehensive survey of the existing condition monitoring and protection methods in the following five areas: thermal protection and temperature estimation, stator insulation monitoring and fault detection, bearing fault detection, broken rotor bar/end-ring detection, and air gap eccentricity detection. For each category, the related features of MV motors are discussed; the effectiveness of the existing methods are discussed in terms of their robustness, accuracy, and implementation complexity. Recommendations for the future research in these areas are also presented.

A Survey of Condition Monitoring and Protection Methods for Medium-Voltage Induction Motors

Motor-current-signature analysis has been successfully used in induction machines for fault diagnosis. The method, however, does not always achieve good results when the speed or the load torque is not constant, because this causes variations on the motor-slip and fast Fourier transform problems appear due to a nonstationary signal. This paper proposes a new method for motor fault detection, which analyzes the spectrogram based on a short-time Fourier transform and a further combination of wavelet and power-spectral-density (PSD) techniques, which consume a smaller amount of processing power. The proposed algorithms have been applied to detect broken rotor bars as well as shorted turns. Besides, a merit factor based on PSD is introduced as a novel approach for condition monitoring, and a further implementation of the algorithm is proposed. Theoretical development and experimental results are provided to support the research.

Fault Detection in Induction Machines Using Power Spectral Density in Wavelet Decomposition

This paper describes a new analytical model for the influence of rolling-element bearing faults on induction motor stator current. Bearing problems are one major cause for drive failures. Their detection is possible by vibration monitoring of characteristic bearing frequencies. As it is possible to detect other machine faults by monitoring the stator current, a great interest exists in applying the same method for bearing fault detection. After a presentation of the existing fault model, a new detailed approach is proposed. It is based on the following two effects of a bearing fault: 1. the introduction of a particular radial rotor movement and 2. load torque variations caused by the bearing fault. The theoretical study results in new expressions for the stator current frequency content. Experimental tests with artificial and realistic bearing damage were conducted by measuring vibration, torque, and stator current. The obtained results by spectral analysis of the measured quantities validate the proposed theoretical approach.

/pdf/models-for-bearing-damage-detection-in-induction-motors-zq7k8exor2.pdf

Models for Bearing Damage Detection in Induction Motors Using Stator Current Monitoring

This paper describes new models for the influence of rolling-element bearing faults on induction motor stator current. Bearing problems are one major cause for drive failures. Their detection is possible by vibration monitoring of characteristic bearing frequencies. As it is possible to detect other machine faults by monitoring the stator current, a great interest exists in applying the same method for bearing fault detection. After a presentation of the existing fault model, a new detailed approach is proposed. It is based on two effects of a bearing fault: the introduction of a particular radial rotor movement and load torque variations caused by the bearing fault. The theoretical study results in new expressions for the stator current frequency content. Experimental tests with artificial and realistic bearing damage were conducted by measuring vibration, torque and stator current. The obtained results by spectral analysis of the measured quantities validate the proposed theoretical approach.

/pdf/models-for-bearing-damage-detection-in-induction-motors-46p5xyjvnj.pdf

Models for bearing damage detection in induction motors using stator current monitoring

This paper presents signal methods dedicated to the fault detection in the mechanical part of an induction drive: bearing damage, eccentricity and rotor unbalance An experimental bench test is described and used to create and characterise these faults Two methods for bearing faults detection are also detailed: the cepstrum and an original method (parcels summation method) These algorithms are tested on synthetical and real signals

Investigations of algorithms for bearing fault detection in induction drives

This paper compares two observer structures for the diagnosis of a space vector modulation fed and vector controlled induction machine. The first one is a model reference adaptive system (MRAS). The second one is the extended Kalman filter (EKF), corresponding to a stochastic approach of the modelling errors. The comparison between these two observers is made in order to compare their accuracy and performance to estimate the stator resistance. Simulation and experimental results show the effectiveness of these extended observers to monitor the drive.

Comparison of two extended observers for the resistance estimation of an induction machine

The authors present an approach to detecting and localizing faults in a chopper and its supply. The proposed technique is based on an estimation of the state variables, a comparison with measured state variables, and a generation of residuals. These residuals are then treated in a diagnostic module where the defects are detected and a preliminary localization is performed. This localization is then confirmed in a confirmation module, in order to avoid false alarms and to distinguish between system defects and instrument defects. This approach is tested by a realistic simulation, and the results are verified experimentally. >

https://ieeexplore.ieee.org/iel2/637/6472/00254500.pdf

G. Rostaing

Papers

Models for Bearing Damage Detection in Induction Motors Using Stator Current Monitoring

Models for bearing damage detection in induction motors using stator current monitoring

Investigations of algorithms for bearing fault detection in induction drives

Comparison of two extended observers for the resistance estimation of an induction machine

How to detect and to localize a fault in a DC/DC converter?