Wavelet ANN based stator internal faults protection scheme for 3-phase induction motor
15 Jun 2010-pp 1457-1461
TL;DR: In this article, the wavelet decomposition of three-phase stator currents is carried out with Bior5.5 and the normalized peak d1 coefficients of these currents are fed to a feedforward neural network to classify various faults.
Abstract: This paper proposes a protection scheme based on Wavelet Multi Resolution Analysis and Artificial neural network which detects and classifies various possible stator winding fault of a three-phase induction motor such as inter turn faults, line to ground faults and line to line faults. The wavelet decomposition of three-phase stator currents is carried out with Bior5.5. The maximum value of absolute peak d1 coefficients of three-phase currents is defined as fault index which is compared with a predefined threshold to detect the fault. The normalized peak d1 coefficients of these currents are fed to a Feedforward neural network to classify various faults. The algorithm has been tested for various incidence angles and proved to be simple, reliable and effective in detecting and classifying the various stator winding faults.
Citations
More filters
TL;DR: Stockwell transform (ST) is used to analyze the stator current signals for diagnosis of various motor conditions such as healthy, stator winding interturn shorts, and phase to ground faults.
Abstract: In this article, Stockwell transform (ST) is used to analyze the stator current signals for diagnosis of various motor conditions such as healthy, stator winding interturn shorts, and phase to ground faults. ST decomposes the current signals into complex ST matrix whose magnitude has been utilized for the fault detection. The nature of the fault, that is, ground or interturn is identified using the zero sequence currents followed by postfault detection. Two separate frequency bands are defined to extract the features which are fed to two different support vector machine (SVM) models for faulty phase detection for both types of faults. Under both cases, a heuristic feature selection approach is utilized to find the optimal features for classification purposes. Average classification accuracy of 96% has been achieved for both types of faults.
42 citations
TL;DR: The obtained results proved that the DWER is an accurate and robust indicator to diagnose the ITSC fault, this is confirmed by ANN results which gave the best results with the Bayesian regularized Elman network model that has the highest performance with minimal error rate.
37 citations
01 Jan 2016
TL;DR: Evaluation of performance and accuracy enhancement of one step ahead with 10 minutes time series resolution of wind power forecasting through Adaptive Wavelet Neural Network (AWNN), using real time data of a wind farm with two wind power turbines establishes that the proposed model outperforms the standard approaches.
Abstract: In recent days, accuracy enhancement of wind power forecasting is essential for integrating large amounts of wind power into the national electricity grid to mitigate its intermittency. This paper contributes evaluation of performance and accuracy enhancement of one step ahead with 10 minutes time series resolution of wind power forecasting through Adaptive Wavelet Neural Network (AWNN), using real time data of a wind farm with two wind power turbines. The effectiveness of this work is compared with Artificial Neural Networks (ANNs) and Adaptive Neuro-Fuzzy Inference System (ANFIS) standard approaches and the results established that the proposed model outperforms the standard approaches.
8 citations
TL;DR: An all-purpose, effective, and simple method for asynchronous motor monitoring is used and could successfully classify all the defects at an excellent rate and even separate mechanical faults from electrical ones.
Abstract: In this article, a type of diagnostic tool for an asynchronous motor powered from a frequency converter is proposed. An all-purpose, effective, and simple method for asynchronous motor monitoring is used. This method includes a single vibration measuring device fixed on the motor’s housing to detect faults such as worn-out or broken bearings, shaft misalignment, defective motor support, lost phase to the stator, and short circuit in one of the phase windings in the stator. The gathered vibration data are then standardized and continuous wavelet transform (CWT) is applied for feature extraction. Using morl wavelets, the algorithm is applied to all the datasets in the research and resulting scalograms are then fed to a complex deep convolutional neural network (CNN). Training and testing are done using separate datasets. The resulting model could successfully classify all the defects at an excellent rate and even separate mechanical faults from electrical ones. The best performing model achieved 97.53% accuracy.
8 citations
Dissertation•
11 Aug 2014
TL;DR: In this article, the authors propose a level-level-level approach to the problem of homonymity in homonym-level homonymization, i.e., homonym level.
Abstract: level
1 citations
References
More filters
TL;DR: The fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors are introduced.
Abstract: This paper is intended as a tutorial overview of induction motors signature analysis as a medium for fault detection. The purpose is to introduce in a concise manner the fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors. The paper is focused on the so-called motor current signature analysis which utilizes the results of spectral analysis of the stator current. The paper is purposefully written without "state-of-the-art" terminology for the benefit of practising engineers in facilities today who may not be familiar with signal processing.
1,396 citations
"Wavelet ANN based stator internal f..." refers background in this paper
...The motor faces various stresses during the operating conditions and these stresses might lead to several failures....
[...]
TL;DR: In this article, an analysis method is developed for modeling multi-phase cage induction motors with asymmetry in the stator, arising due to an interturn fault resulting in a disconnection of one or more coils making up a portion of a stator phase winding and any distribution and number of rotor bar and end-ring failures.
Abstract: An analysis method is developed for modeling of multi phase cage induction motors with asymmetry in the stator, arising due to an interturn fault resulting in a disconnection of one or more coils making up a portion of a stator phase winding and any distribution and number of rotor bar and end-ring failures. The approach, based on the winding functions, makes no assumption as to the necessity for sinusoidal MMF and therefore include all the space harmonics in the machine. Simulation and experimental results confirm the validity of the proposed method. >
497 citations
TL;DR: A winding-function-based method for modeling polyphase cage induction motors with inter-turn short circuits in the machine stator winding is developed and it is shown that, as a result of the nature of the cage rotor, no new frequency components of the line current spectra can appear as a consequence of the fault.
Abstract: This paper develops a winding-function-based method for modeling polyphase cage induction motors with inter-turn short circuits in the machine stator winding. Analytical consideration which sheds light on some components of the stator current spectra of both healthy and faulty machines is developed. It is shown that, as a result of the nature of the cage rotor, no new frequency components of the line current spectra can appear as a consequence of the fault. Only a rise in some of the frequency components which already exist in the line current spectra of a healthy machine can be observed. An experimental setup comprising a 3 kW delta-connected motor loaded by a generator was used to validate this approach. The experimental results obtained clearly validate the analytical and simulation results.
473 citations
"Wavelet ANN based stator internal f..." refers background in this paper
...Actually these faults start as undetected turn-to-turn winding faults that finally grow and culminate in major faults [2]....
[...]
11 Dec 2006
TL;DR: In this paper, a three-phase induction motor model which represents the motor behavior over a wide range of frequencies from 10 Hz to 10 MHz is presented, and the model is universal in the sense that common mode, differential mode and bearing circuit models are combined into one three phase equivalent circuit model.
Abstract: A three-phase induction motor model which represents the motor behavior over a wide range of frequencies from 10 Hz ? 10 MHz is presented in this paper. The model is universal in the sense that common mode, differential mode and bearing circuit models are combined into one three-phase equivalent circuit model. The proposed model is basically an extension of the low frequency IEEE Standard 112 circuit model. The proposed model was simulated and verified experimentally with results presented.
164 citations
09 Jul 2006
TL;DR: In this article, an early detection of interturn shorts during motor operation would eliminate consequential damage to adjacent coils and the stator core, then reducing repair costs and motor outage time.
Abstract: Early detection of interturn shorts during motor operation would eliminate consequential damage to adjacent coils and the stator core, then reducing repair costs and motor outage time. In addition to the benefits gained from early detection of turn insulation breakdown, significant advantages would accrue by locating the faulted coil within the stator winding. Fault location would not only increase the speed of the repair, but would also permit more optimal scheduling of the repair outage. Motor Current Signature Analysis (MCSA) method is widely used as a diagnose tool for industrial applications. On the other hand, Park's transform is the most popular transformation used in vector control algorithms. By analyzing the current spectra of dq0 Park components with MCSA method it is possible to improve earlier fault detection. Moreover, using Wavelet transform as signal analysis method it is possible to reduce signal noise effects. Experimental results clearly corroborate the main aim of the paper.
33 citations
"Wavelet ANN based stator internal f..." refers background in this paper
...The Fourier transform is, however, not appropriate to analyze a signal that has a transitory characteristic such as drifts, abrupt changes, and frequency trends....
[...]