Identification of three phase induction motor incipient faults using neural network
19 Sep 2004-pp 30-33
TL;DR: In this paper, the applicability/feasibility of artificial neural network (ANN) technique for the detection and identification of incipient faults in an induction motor has been explored, where the authors used the graphical user interface (GUI) of neural network tool box under Matlab environment.
Abstract: The induction motors are most widely used motors in industrial, commercial and residential sectors because of enormous merits of these over other types of available electrical motors. These motors work under various operating stresses, which deteriorate their motor conditions giving rise to faults. The early detection of these deteriorating conditions in incipient phase and its removal/correction is very necessary for the prevention of any external faults/failure of induction motors reducing repair costs and motor outage time. Fault detection using analytical methods is not always possible because it requires a perfect knowledge of the motor model. The artificial neural network techniques are rather easy to develop and to perform. These networks can be applied when the information about the system is obtained from measurements, which later can be used in the training procedures of the neural networks. Neural detectors can be designed from simulation or experimental tests. In the present paper the applicability/feasibility of artificial neural network (ANN) technique for the detection and identification of incipient faults in an induction motor has been explored. Radial basis function (exact fit) approach has been used for ANN training and test. The applicability of the graphical user interface (GUI) of neural network tool box under Matlab environment has been explored in this paper. The various types of faults have been considered. Three phase instantaneous voltages and currents are utilized in proposed approach. Simulated fault current and voltage data have been used for testing of trained network.
Citations
More filters
01 Jan 1986
TL;DR: Condition monitoring of electrical machines is recognised as being crucially important to reliable and economical plant operation, particularly in large installations.
Abstract: Condition monitoring of electrical machines is recognised as being crucially important to reliable and economical plant operation, particularly in large installations. Choice of monitoring parameters is discussed. Practically viable condition monitoring schemes are proposed.
76 citations
01 Jan 2010
TL;DR: A review of the researches on the fault diagnosis and fault tolerant control of induction motors for the last six years as well as the classification of the faults is presented in this article, highlighting agrees, disagrees and tradeoffs in the reviewed topics.
Abstract: The present contribution presents a review of the researches on the fault diagnosis and fault tolerant control of induction motors for the last six years as well as the classification of the faults which is another interested topics of this research finally the drawback of the method used in the fault diagnosis of the induction motor. The emphasis is on highlighting agrees, disagrees and tradeoffs in the reviewed topics. Sorting and classification is another goal. More attention is paid for the researches done in the last six years, and a brief description is presented for each issue. Extensive number of papers is reviewed and appointed in the present preview, to provide quantitative description for each agree or disagree
52 citations
Cites methods from "Identification of three phase induc..."
...…of external faults using artificial neural network Ahmed F. Abd El-Halim et al (2004) presents N N schemes control for I.M drive systems Arfat Siddique et al (2004) presents incipient faults of three phase I.M. using NN identification T.G. Amaral et al (2007) presents the image processing…...
[...]
...Dias C.G et al (2006) investigate the Hall effect in the fault diagnosis of rotor broken bar through neural in the large induction motors Jing Yang et al (2007) presents the sensorless speed estimation of line connected using RNN Sri R. Kolla et al (2007) presents the NN based fault identification in the induction motors Erdal Kilic et al (2007) presents RBF Neural Network Based on Dynamical PCA for the fault identification in the induction motor M. Abul Masrur et al (2007) presents the model based fault diagnosis in the induction motor using ANN Kaijam M. (2005) presents the neural network in the torque estimation and d-q transform Hua Su et al (2007) presents the induction condition monitoring using NN modeling Qing He et al (2007) presents the fault diagnosis of induction motor using the NN Bogdan Pryymak et al (2006) presents the optimization of flux by NN using a model of losses in induction motor drives Mochammad Facta et al (2006) present a Comparison of On line control of Three Phase Induction Motor Using RBF and B-Spline Neural Network El -Sayed M et al (2007) present monitoring and diagnosis of external faults using artificial neural network Ahmed F. Abd El-Halim et al (2004) presents N N schemes control for I.M drive systems Arfat Siddique et al (2004) presents incipient faults of three phase I.M. using NN identification T.G. Amaral et al (2007) presents the image processing for neuro-fuzzy classifier in detection and fault diagnosis of I....
[...]
TL;DR: The improved decision structure diagnoses faulted rotors with 100% accuracy and classified rotor faults 98.33% accuracy, and the spectrum is achieved with low definition.
Abstract: The detection of broken rotor bars and broken end-ring in three-phase squirrel cage induction motors by means of improved decision structure. The structure consists of current signal analysis (CSA), Artificial Neural Network (ANN) and diagnosis algorithm. Effects of broken bars and end-ring on current signal and feature extraction are in the CSA. The rotor cage faults are classified by using ANN. And result matrixes of ANN are considered two different ways for diagnosis. Then the diagnoses are compared with each other. In this study six different rotor faults, which are one, two, three broken bars, bar with high resistance, broken end-ring and healthy rotor, are investigated. The effects of different rotor faults on current spectrum, in comparison with other fault conditions, are investigated by analyzing side-bands in current spectrum. To reduce bad effects of changing of distance between the side-band and main component on the detection and classification of the faults, the spectrum is achieved with low definition. Thus, the improved decision structure diagnoses faulted rotors with 100% accuracy and classified rotor faults 98.33% accuracy.
36 citations
TL;DR: A new methodology for evaluation and classification of insulation conditions with the aid of K-means clustering and of a classifier based on ANNs (artificial neural networks) is proposed.
30 citations
01 Jan 2009
TL;DR: In this paper, an experimental study of classification and diagnosis of different number of broken rotor bars and broken end-ring in the three-phase squirrel cage induction motors is presented, where the motor current signal is used for obtaining of effects of broken bars and end-rings in the rotor.
Abstract: Abstract—In this paper an experimental study of classification and diagnosis of different number of broken rotor bars and broken end-ring in the three-phase squirrel cage induction motors is presented. Six different faulted rotors are investigated. These faults are one, two, three broken bars, broken end-ring, a bar with high resistance and healthy rotor. The base structure of the study consist of current signal analysis (CSA), feature extraction, Artificial Neural Network (ANN) and diagnosis algorithm. The motor current signal is used for obtaining of effects of broken bars and end-ring in the rotor. To get sight of the effects the current signal that is in the time domain is transformed time-frequency domain via Short Time Fourier Transform (STFT). And the spectrums are averaged and normalized on the time axis. The rotor cage faults are classified with ANN by using these spectrums. And result matrixes of ANN are considered improved decision structure. Thus the faulted rotors are diagnosed at 100% accuracy and classified 98,33% accuracy. Index Terms—Broken rotor bars, rotor faults diagnosis, classification of rotor faults, short time Fourier transform.
13 citations
References
More filters
Book•
16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Abstract: From the Publisher:
This book represents the most comprehensive treatment available of neural networks from an engineering perspective. Thorough, well-organized, and completely up to date, it examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Written in a concise and fluid manner, by a foremost engineering textbook author, to make the material more accessible, this book is ideal for professional engineers and graduate students entering this exciting field. Computer experiments, problems, worked examples, a bibliography, photographs, and illustrations reinforce key concepts.
29,130 citations
"Identification of three phase induc..." refers methods in this paper
...Implicit knowledge is built into a neural network by training it. Several types of A" structures and training algorithms have been proposed in literature [2, 4 ]....
[...]
Book•
18 Mar 1993
TL;DR: In this article, the effects of time harmonics on various space-phasor loci, harmonic amplitude estimation Monitoring of the rotor speed and the rotor angle Monitoring various machine parameters Diagnosis, condition monitoring Bibliography Index
Abstract: Introduction Summary of space phasor theory On-line signal processing of space-phasor quantities The effects of time harmonics on various space-phasor loci, harmonic amplitude estimation Monitoring of the rotor speed and the rotor angle Monitoring various machine parameters Diagnosis, condition monitoring Bibliography Index
640 citations
03 Jun 1991
TL;DR: In this article, the authors attempt to identify the various causes of stator and rotor failures in three-phase squirrel cage induction motors, and a specific methodology is proposed to facilitate an accurate analysis of these failures.
Abstract: The authors attempt to identify the various causes of stator and rotor failures in three-phase squirrel cage induction motors. A specific methodology is proposed to facilitate an accurate analysis of these failures. It is noted that, due to the destructive nature of most failures, it is not easy, and is sometimes impossible, to determine the primary cause of failure. By a process of elimination, one can usually be assured of properly identifying the most likely cause of the failure. It is pointed out that the key point in going through this process of elimination is to use the basic steps of analyzing the failure class and pattern, noting the general motor appearance, identifying the operating condition at the time of failure, and gaining knowledge of the past history of the motor and application. >
603 citations
"Identification of three phase induc..." refers background in this paper
...Fmher these techniques are quite expensive too [1,3,6]....
[...]
02 Oct 1994
TL;DR: In this article, a new method for online induction motor fault detection is presented, which utilizes artificial neural networks to learn the spectral characteristics of a good motor operating online, which may contain many harmonics due to the load which correspond to normal operating conditions.
Abstract: A new method for online induction motor fault detection is presented in this paper. This system utilizes artificial neural networks to learn the spectral characteristics of a good motor operating online. This learned spectrum may contain many harmonics due to the load which correspond to normal operating conditions. In order to reduce the number of harmonics which are continuously monitored to a manageable number, a selective frequency filter is employed. This frequency filter only passes those harmonics which are known to be of importance in fault detection, or which are continuously above a set level, to a neural net clustering algorithm. After a sufficient training period, the neural network signals a potential failure condition when a new cluster is formed and persists for some time. Since a fault condition is found by comparison to a prior condition of the machine, online failure prediction is possible with this system without requiring information on the motor or load characteristics. The detection algorithm was implemented and its performance verified on various fault types.
316 citations