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

This paper presents a review of the developments in the field of diagnosis of electrical machines and drives based on artificial intelligence (AI). It covers the application of expert systems, artificial neural networks (ANNs), and fuzzy logic systems that can be integrated into each other and also with more traditional techniques. The application of genetic algorithms is considered as well. In general, a diagnostic procedure starts from a fault tree developed on the basis of the physical behavior of the electrical system under consideration. In this phase, the knowledge of well-tested models able to simulate the electrical machine in different fault conditions is fundamental to obtain the patterns characterizing the faults. The fault tree navigation performed by an expert system inference engine leads to the choice of suitable diagnostic indexes, referred to a particular fault, and relevant to build an input data set for specific AI (NNs, fuzzy logic, or neuro-fuzzy) systems. The discussed methodologies, that play a general role in the diagnostic field, are applied to an induction machine, utilizing as input signals the instantaneous voltages and currents. In addition, the supply converter is also considered to incorporate in the diagnostic procedure the most typical failures of power electronic components. A brief description of the various AI techniques is also given; this highlights the advantages and the limitations of using AI techniques. Some applications examples are also discussed and areas for future research are also indicated.

Recent developments of induction motor drives fault diagnosis using AI techniques

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

Mechanical imbalances and bearing faults account for a large majority of the faults in a machine, particularly for small-medium size machines. Therefore, their diagnosis is an intensively investigated field of research. Recently, many research activities were focused on the diagnosis of bearing faults by current signals. This paper compares the bearing fault detection capability obtained with the vibration and current signals. The paper contribution is the use of a simple and effective signal processing technique for both current and vibration signals, and a theoretical analysis of the physical link between faults, modeled as a torque disturbance, and current components. The focus of the paper is on the theoretical development of the correlation between torque disturbances and the amplitude of the current components, together with a review of fault models used in the literature. Another contribution is the re-creation of realistic incipient faults and their experimental validation. Radial effects are visible only in case of large failures that result in air-gap variations. Experiments are reported that confirm the proposed approach.

Diagnosis of Bearing Faults in Induction Machines by Vibration or Current Signals: A Critical Comparison

Early diagnosis of faults in induction machines is an extensively investigated field, for cost and maintenance savings. Mechanical imbalances and bearing faults account for a large majority of faults in a machine, especially for small-medium size machines. Therefore their diagnosis is an intensively investigated field or research. Recently many research activities were focused on the diagnosis of bearing faults by current signal. Stator current components are generated at predictable frequencies related to the electrical supply and mechanical frequencies of bearing faults. However their detection is not always reliable, since the amplitude of fault signatures in the current signal is very low. This paper compares the bearing fault detection capability obtained with vibration and current signals. To this aim a testbed is realized that allows to test vibration and current signal on a machine with healthy or faulty bearings. Signal processing techniques for both cases are reviewed and compared in order to show which procedure is best suited to the different type of bearing faults. The paper contribution is the use of a simple and effective signal processing technique for both current and vibration signals, and a theoretical analysis of the physical link between faults and current components including torque ripple effects. As expected because of the different nature of vibration and current, bearing fault diagnosis is effective only for those fault whose mechanical frequency rate is quite low. Experiments are reported that confirm the proposed approach.

Diagnosis of Bearing Faults of Induction Machines by Vibration or Current Signals: A Critical Comparison

This paper deals with the electric tracing of the load variation of an induction machine supplied by the mains. A load problem, like a torque dip, affects the machine supply current and consequently it should be possible to use the current pattern to detect features of the torque pattern, using the machine itself as a torque sensor. But current signature depends on many phenomena and misunderstandings are possible. At first the effect of different load anomalies on current spectrum, in comparison with other machine problems like rotor asymmetries, are investigated. Reference is made to low frequency torque disturbances, which cause a quasistationary machine behavior. Simplified relationships, validated by simulation results and by experimental results, are developed to address the current spectrum features. In order to detect on-line anomalies, a current signature extraction is performed by the time-frequency spectrum approach. This method allows the detection of random faults as well. Finally it is shown that a neural network approach can help the torque pattern recognition, improving the interpretation of machine anomalies effects.

G. Crellet

Papers

Monitoring of induction motor load by neural network techniques