Analysis of breakdown process at U50 voltage for plane rod discharges by means of Neural Networks (original) (raw)
Related papers
2020
Incomplete release (PD) designs are critical instrument for the finding of high voltage (HV) protection frameworks. Human specialists can find conceivable protection absconds in different portrayals of the PD information. One of the most broadly utilized portrayals is stage settled PD (PRPD) designs. So as to guarantee dependable activity of HV hardware, it is vital to relate the noticeable measurable attributes of PDs to the properties of the imperfection and at last to decide the kind of the deformity. In present work, we have obtained and analysed combined use of PRPD patterns (φ-q), (φ-n) and (n-q) using statistical parameters such as skewness and kurtosis for two patterns viz. (φ-q) and (φ-n) along with mean, standard deviation, variance, skewness and kurtosis for (n-q) to detect type of PD and we have verified the obtained results by providing obtained statistical parameters as an input for training of artificial neural network (ANN) in MATLAB tools.
Analysis of Partial Discharge Source Using Artificial Neural Network
2020
Partial Discharge (PD) patterns are an important tool for the diagnosis of High Voltage (HV) insulation systems. Human experts can discover possible insulation defects in various representations of the PD data. One of the most widely used representations is phase-resolved PD (PRPD) patterns. In order to ensure reliable operation of HV equipment, it is vital to relate the observable statistical characteristics of PDs to the properties of the defect and ultimately to determine the type of the defect. In this work, we have detected PD source using Artificial Neural Network (ANN) tool in Matlab software.
International journal of engineering research and technology, 2019
Partial discharge (PD) patterns are significant tool for the diagnosis of high voltage (HV) insulation systems. Human experts can discover possible insulation defects in various representations of the PD data. One of the most widely used representations is phase-resolved PD (PRPD) patterns. In order to ensure reliable operation of HV equipment, it is crucial to relate the observable statistical characteristics of PDs to the properties of the defect and ultimately to determine the type of the defect. In present work, we have obtained and analysed combined use of PRPD patterns (φ-q), (φ-n) and (n-q) using statistical parameters such as skewness and kurtosis for two patterns viz. (φ-q) and (φ-n) along with mean, standard deviation, variance, skewness and kurtosis for (n-q) to detect type of PD and we have verified the obtained results by providing obtained statistical parameters as an input for training of artificial neural network (ANN) in MATLAB tools.
Partial Discharge Classification Using Neural Networks and Statistical Parameters
Partial discharge (PD) pattern recognition is an important tool in high-voltage insulation diagnosis of power systems. A PD pattern classification approach of high-voltage power transformers based on a neural network is proposed in this paper. A commercial PD detector is firstly used to measure the 3-D PD patterns of epoxy resin power transformers. Then, the gray intensity histogram extracted from the raw 3-D PD patterns are statistically analyzed for the neural-network-based (NN-based) classification system. The system can quickly and stably learn to categorize input patterns and permit adaptive processes to access significant new information. To demonstrate the effectiveness of the proposed method, the classification ability is investigated on 120 sets of field tested PD patterns of epoxy resin power transformers. Different types of PD within power transformers are identified with rather encouraged results.
Journal of Applied Physics, 2013
The main propose of this paper is to present a physical model of long air gap electrical discharges under positive switching impulses. The development and progression of discharges in long air gaps are attributable to two intertwined physical phenomena, namely, the leader channel and the streamer zone. Experimental studies have been used to develop empirical and physical models capable to represent the streamer zone and the leader channel. The empirical ones have led to improvements in the electrical design of high voltage apparatus and insulation distances, but they cannot take into account factors associated with fundamental physics and/or the behavior of materials. The physical models have been used to describe and understand the discharge phenomena of laboratory and lightning discharges. However, because of the complex simulations necessary to reproduce real cases, they are not in widespread use in the engineering of practical applications. Hence, the aim of the work presented here is to develop a model based on physics of the discharge capable to validate and complement the existing engineering models. The model presented here proposes a new geometrical approximation for the representation of the streamer and the calculation of the accumulated electrical charge. The model considers a variable streamer region that changes with the temporal and spatial variations of the electric field. The leader channel is modeled using the non local thermo-equilibrium equations. Furthermore, statistical delays before the inception of the first corona, and random distributions to represent the tortuous nature of the path taken by the leader channel were included based on the behavior observed in experimental tests, with the intention of ensuring the discharge behaved in a realistic manner. For comparison purposes, two different gap configurations were simulated. A reasonable agreement was found between the physical model and the experimental test results. V
Neural Network Based Recognition of Partial Discharge Pattern
Partial Discharge (PD) monitoring and analysis has become imperative for utilities as well as for equipment manufacturers as it causes deterioration of insulation systems in high voltage (HV) electrical equipment. The analysis of PD includes detection, recognition & classification of PD using various advanced mathematical tools & techniques. In the artificial intelligence, Neural network methodology is one of the most popular and widely used for the analysis of PD. This work represents the generation of the partial discharge like signal using the MATLAB 7.9 software and the recognition of generated signals by artificial neural network technique. The obtained PD pattern represents the characteristics of Partial discharge signal and the discrete spectrum interference signal with it. The variants of these signals are taken as samples for the training of the neural network. The offline recognition of the PD signal has been done.
This paper presents a computational implementation of a Probabilistic Neural Network for obtaining patterns of partial discharges in power cables XLPE. The experimental measurement data of the power cables are obtained in the Laboratory Testing Equipment and Materials (LAPEM), which is a certified laboratory property of the Comisión Federal de Electricidad (CFE) in México. These data implicitly contain the patterns of partial discharges and are used to carry out the training and testing of Probabilistic Neural Network. In order to illustrate the reliability and validity of the proposed computational implementation, the results obtained by this proposed implementation are compared with those calculated by the methodologies given in the standard IEC 60270.
Energies, 2016
In order to investigate how artificial neural networks (ANNs) have been applied for partial discharge (PD) pattern recognition, this paper reviews recent progress made on ANN development for PD classification by a literature survey. Contributions from several authors have been presented and discussed. High recognition rate has been recorded for several PD faults, but there are still many factors that hinder correct recognition of PD by the ANN, such as high-amplitude noise or wide spectral content typical from industrial environments, trial and error approaches in determining an optimum ANN, multiple PD sources acting simultaneously, lack of comprehensive and up to date databank of PD faults, and the appropriate selection of the characteristics that allow a correct recognition of the type of source which are currently being addressed by researchers. Several suggestions for improvement are proposed by the authors include: (1) determining the optimum weights in training the ANN; (2) using PD data captured over long stressing period in training the ANN; (3) ANN recognizing different PD degradation levels; (4) using the same resolution sizes of the PD patterns when training and testing the ANN with different PD dataset; (5) understanding the characteristics of multiple concurrent PD faults and effectively recognizing them; and (6) developing techniques in order to shorten the training time for the ANN as applied for PD recognition Finally, this paper critically assesses the suitability of ANNs for both online and offline PD detections outlining the advantages to the practitioners in the field. It is possible for the ANNs to determine the stage of degradation of the PD, thereby giving an indication of the seriousness of the fault.