Partial Discharge Classification Using Novel Parameters and a Combined PCA and MLP Technique
|
|
- Leona Manning
- 6 years ago
- Views:
Transcription
1 Partial Discharge Classification Using Novel Parameters and a Combined PCA and MLP Technique C. Chang and Q. Su Center for Electrical Power Engineering Monash University, Clayton VIC 3168 Australia Abstract: Partial discharge (PD) detection is an important means of testing high voltage equipment because it provides important information about the condition of the insulation system. For condition monitoring purposes, it is vital to identify the type of defects when monitoring discharge activities inside an insulation system. With the help of a new PD measuring and analyzing system, PD source identification using multidimensional feature vector is regarded as a necessary step for the diagnosis of insulation condition. In this paper, new fingerprints derived from physically related PD parameters are presented and fed into a hybrid neural network (NN) for classification. It is proved that the output of a principal component analysis (PCA) network connected to a multi-layer perceptron network (MLP) with backpropagation training algorithm can work successfully with the new fingerprints. 1. INTRODUCTION PDs are localized electrical discharges that behave as a sequence of electrical stress concentrations in insulation material or on the surface of the insulation. They can be detected as electrical pulses having duration of nanoseconds. It is understood that PD distribution patterns are characterized by phase angle ϕ and discharge magnitude θ. In another word, PD distribution patterns include these two parameters [1,, and 1]. The distribution of discharge power loss, which is accumulated PD pulse energy during a chosen reference time interval, can be measured at the terminal of a test object due to the apparent charge magnitudes. The distribution can be derived from the ϕ-θ plane as shown in figure 1. (a) (b) Figure 1 distribution patterns of ϕ-θ-p (a) Air corona from a rod-to-plane arrangement (b) PD from an epoxy resin stator bar sample (c) PD from an oil-impregnated pressboard sample (c) Recently, PD source identification has been carried out in a way of extracting fingerprints primarily from patterns of phase and pulse height resolved PD (PRPD, PHPD) distributions. The limitation of this approach is mainly due to (1) PRPD and PHPD distribution patterns are difficult to be directly associated with the physical process inside an insulation defect. () Some important properties that related to PD pulse-to-pulse characteristics may be missed [,3]. The pulse-to-pulse sequence analysis is based on the fact that a PD event in a sequence is not independent due to the impact from the remaining residuals produced by previous PD events. The reliable identification of discharge source is likely to be successful if physically related discharge fingerprints are provided. To understand the physical basis of PD transients, Pedersen etc. [3,4] studied the fundamental theory of induced charge in an ellipsoidal void. Having adopted a dipole representation, the influence of void parameters upon the induced charge has also been studied. It indicates that the induced charge is dependent on void location, geometry, field orientation, and type
2 of gas, gas pressure, as well as the permittivity of bulk dielectric [5-7]. Specifically, the induced charge can be divided into two components: (1) component q is directly related to the space µ charge in a void and () component q represents p the charge associated with the change in dielectric polarization. Hence, it is appropriate to investigate the discharge patterns that composed of different format in terms of discharge magnitude, voltage and time separation between consecutive PD events. Consequently, fingerprints extracted from V M T ( VMT) distribution patterns become meaningful due to the co-relationship with the physical process inside a defect. The distribution patterns of VMT represent different PD source has shown in figure. local learning rules to build the largest and second largest etc. principal components. The extracted fingerprints from the VMT patterns will be reconstructed by PCA procedure. The output of that will be fed into a MLP network for training.. DISCHARGE MEASURING SYSTEM The test circuit is set up according to figure 3. The applied voltage was started from its inception level and then increased gradually. Using a new discharge detector, PD pulses were detected when they beyond the threshold level. PD pulses were measured in the bandwidth of 1KHz-MHz. HF Filter U~ Ck Ca CD CC PDD Personal Computer (a) Figure 3PD measuring system U~ high-voltage supply CC connecting cable CD coupling device and preamplifier Ck test object Ca coupling capacitor. PDD partial discharge detector (b) 3. CONSECUTIVE DISCHARGES Apparently, comparing with PRPD and PHPD patterns, discharge patterns derived from voltage and charge differences as well as the time separation between consecutive pulses exhibit a characteristic distribution that more related to the physical mechanism of a defect. (c) Figure. distribution patterns of VMT (a) Air corona from a rod-to-plane arrangement (b) PD from a epoxy resin stator bar sample (c) PD from an oil-impregnated pressboard sample PCA is a statistical procedure that can project a very large dimensional data onto a smaller dimensional space while preserving the maximum variance about the input data. PCA can be implemented with As discussed earlier that a propriety interpretation of the induced charge produced in a single void would require the knowledge of the void location, geometry and dimensions, gas components and its pressure [8]. For a given void, there is no direct linkage between the size of the void and the magnitude of induced charge. However, it has been proved that the magnitude of induced charge is dependent on the orientation of the void with respect to the external field direction [4]. Therefore it is physically meaningful to use the distribution characteristics of consecutive PD pulses as illustrated in figure 4.
3 PD Difference (pc) PD Magnitude (pc) Discharge Magnitude Change vs. Time Interval Time Separation (ms) Discharge Magnitude vs. Time Interval difference between consecutive pulses is regard as a parameter for the reliable identification of PD source [11, 1]. This is due to the parameter is proportional to the local field change at the defect site, which is necessary to compensate for the superposed space charge field and thus to reattain the inception field after a preceding discharge pulse. Hence, the change of discharge magnitude, applied voltage, and the time interval in consecutive PD events contain the information in regard to the physical properties of discharge mechanism in a void. A matrix scatter plot is shown in figure 5 in which the relationship among T, V, and M of different PD source can be visually examined. (a) VD Time Interval (ms) 1-1 Discharge Magnitude Change vs Voltage Change 1 5 QD PD Difference (pc) TD Voltage Difference (KV) Voltage Change Sequence (b) VD Normalized V Difference (n) QD TD -. 1 Normalized V Difference(n-1) Figure 4 consecutive PD patterns from a rod-toplane arrangement (c) TVM Distribution Patterns VD - -5 Obviously, using TVM pattern to represent discharge characteristics has distinct advantages comparing with other patterns such as PRPD and PHPD patterns. The change of q p denotes the physical process inside the insulation, which can be represented by the change of discharge magnitude between consecutive discharge events, due to q is µ assumed as a constant for a fixed void location. The time separation between consecutive discharge pulses indicates the time required for discharge initiation and development, which is also related to the physical mechanism of discharge [8,9]. Voltage QD TD Figure 5 Scatter matrix plot of TVM pattern (a) PD from a rod-to-plane arrangement (b) PD from an epoxy resin stator bar sample (c) PD from an oil-impregnated pressboard sample
4 Figure 5 has shown the matrix plots that are helpful to examine two-variable relationships among three variables at once. With the matrix plot, it is useful to identify the meaningful relationship in a single graph. The M- T relation is located at the left bottom of the matrix plot and this pattern is chosen for further analysis. The investigation is continued using the marginal distribution in both T and M axes as illustrated in figure 6. One of the main tasks in feature extraction is to find the similarities among the same type of PD source and at the meanwhile to discover the dissimilarities between different type of PD source. As illustrated in the following diagrams from figure 7 to 9, the T- M patterns produced from three different discharge sources are displayed and compared. Figure 7 PD from a rod-plane arrangement Figure 6marginal distribution patterns of T- M from different discharge source 5. FEATURE EXTRACTION The mapping of T- M distribution is quite dissimilar for different types of discharge source as shown in figure 6. With the same type of discharge source, the T- M distribution will also be varied due to the difference in physical properties of void shape, orientation, surface conductivity, gas pressure external stress and the degree of aging etc. Figure 8PD from a pressboard sample
5 As seen from these T- M patterns, the histogram distributions of either T or M are quite different due to the discharge activities are different under different voltage. The relationship of such a change is not easy to describe just by visual examination. Under the arrangement of dividing the entire distribution area into 6 X 6 windows, the fingerprints can be extracted to represent the mapping of T- M pattern. It is understandable that the more number of window used to describe the histogram distribution will obviously produce more accurate results but at the expanse of computing resources. Therefore the arrangement must be based on the balance between the accuracy and the computing power. procedure, which condensed the input data down to 5 principal components. The number of principal components selected was a trade-off between training efficiency and accurate results [13,14]. Figure 1 A combined topology of PCA and MLP The terminating condition in the unsupervised segment was determined first. The termination of the training was controlled by both the maximum epochs and the weights changed by less than the specified value from one epoch to the next. The learning rate of unsupervised learning usually performs better when it starts out high and then gradually decays during training. As for the supervised learning segment, the training terminates when the MSE drops below the specified threshold. The stop criteria were setup on the basis of cross validation data set, which stops the network when the MSE of the cross validation set increases by the threshold specified. It is actually an indication whether the network has begun to overtrain [15]. The error between the network output and the desired one is an important measure for the success of training. The active cost function is defined as: Figure 9PD from an epoxy resin stator bar 6. PD SOURCE CLASSIFICATION With the measuring system shown in figure 3, every acquisition of PD data was performed for a period of 1 second. The network topology is in figure 1 where a PCA is connected to a MLP. The MLP has one hidden layer with 33 neurons and was trained using backpropagation (BP) training algorithm [14]. PCA is an unsupervised linear procedure that finds a set of uncorrelated features from the input. MLP is able to perform nonlinear classification from the calculated principle components. This hybrid arrangement selects the number of principal components extracted from the 6 X 6 input. With this approach, PCA was regard as a data reduction 1 J t) = ( N ( di ( t) yi ( t)) (5.1) i= 1 Here d is the desired output value and y is the actual output value. N is the number of exemplar and t is the time from the beginning of the training. The convergence of the active cost function J (t) of MLP and a combined PCA and MLP are shown in figure 11 and 1 respectively. Compared with a MLP network, a combined PCA and MLP neural network has better performance in terms of PD source classification using data extracted from the mapping of T- M pattern. After being trained, the network calculate the output value according to input data and trained weights. The calculated outputs and the desired outputs are shown in figure 13.
6 presenting results obtained for the identification of insulation defects of different type. 8. REFERENCES Figure 11 Active cost function of a combined neural network during training Figure 1 Active cost function of a MLP neural network during training Comparison between Real and Desired Output Value Real output R Real output R1 Desried output R Desired outpu R1 Examplar Figure 13 Comparison between the calculated and the desired outputs 7. CONCLUSION Partial discharge is a complex phenomenon and the pulse-to-pulse distributions are dependent on defect void location, geometry, surface conductivity, field orientation and applied voltage. Based on the theoretical analysis that the change of discharge magnitude within the consecutive PD events is closely related with the PD proprieties. The derived T- M pattern is practically useful and it is also demonstrated that the successful classification of different discharge source has been achieved. PCA is efficient to extract information globally from input space by projecting a high-dimensional data set to a smaller-dimensional output space. It is can be used as a data preprocessor for MLP. The prospect of this approach has been verified by [1] R. Bartnikas, A Commentary on Partial Discharge Measurement and Detection, IEEE Trans. on Dielectrics and Electrical Insulation, Vol., pp , [1] C. Chang and Q. Su, "Comparison between Pattern Recognition Techniques for Partial Discharge Identification", AUPEC'98, the UT, Hobart, Tasmania, 7-3 Sept. 1998, pp [] C. Chang, Q. Su, Partial Discharge Distribution Pattern Analysis Using Combined Statistical Parameters, IEEE PES Winter Meeting, Singapore, January 4-8, [3] C. Chang and Q. Su, "Statistical Characteristics of Discharges from A Rod-Plane Arrangement", AUPEC'99, the University of Northern Territory, Darwin, 7-9 Sept [4] A. Pedersen On the Electrical Breakdown Gaseous Dielectrics An Engineering Approach, IEEE Trans. on Electrical Insulation, Vol. 4 No. 5, pp , October [5] A. Pedersen, G. C. Crichton, The Theory and Measurement of Partial Discharge Transients, IEEE Trans. on Electrical Insulation, Vol. 6 No. 3, pp , June [6] G. C. Crichton, P. W. Karlsson and A. Pedersen, Partial Discharges in Ellipsoidal and Spheroidal Voids, IEEE Trans. on Electrical Insulation, Vol. 4 No., pp , April [7] A. Pedersen, G. C. Crichton and I. W. McAllister, Partial Discharge Detection: Theoretical and Practical Aspects, IEE Proc-Sci. Meas. Technology, Vol.14, No. 1, pp. 9-36, January [8] R. J. Van Brunt, "Stochastic Properties of Partial- Discharge Phenomena", IEEE Trans. on Dielectrics and Electrical Insulation, Vol. 6, No. 5, October 1991, pp [9] R. J. Van Brunt and E. W. Cernyar, "Importance of Unraveling Memory Propagation Effects in Interpreting Data on Partial Discharge Statistics", IEEE Trans. on Electrical Insulation, Vol. 8 No. 6, pp , December [1] E. Gulski and F. H. Kreuger "Computer-Aided Recognition of Discharge Sources", IEEE Trans. on Electrical Insulation, Vol. 7, No. 1, pp. 8-9, February 199. [11] Martin Hoof, Bernd Freisleben and Rainer Patsch, "PD Source Identification with Novel Discharge Parameters Using Counterpropagation Neural Networks", IEEE Trans. on Dielectrics and Electrical Insulation, Vol. 4 No. 1, pp. 17-3, February [1] Rainer Patsch and Martin Hoof, "Physical Modeling of Partial Discharge Patterns", IEEE Internation Conference on Conduction and Breakdwon in Solid Dielectrics, June -5, 1998, Vasteras, Sweden. [13] J. T. Tou and R. C. Gonzalez, Pattern Recognition Principles, Addison-Wesley Publishing, 1974 [14] Y. Linde, A. Buzo and R. Gray, An Algorithm for Vector Quantization Design, IEEE Trans. On Communications, COM , 198. [15] Gallant and White, On Learning Derivatives of an Unknown Function with MLPs, Neural Networks 5 (1), ,199.
Measurement Of Partial Discharge (PD) In High Voltage Power Equipment
First International Conference on Emerging Trends in Engineering, Management and Scineces December 28-3, 214 (ICETEMS-214)Peshawar,Pakistan Measurement Of Partial Discharge (PD) In High Voltage Power Equipment
More informationSimulation Model of Partial Discharge in Power Equipment
Simulation Model of Partial Discharge in Power Equipment Pragati Sharma 1, Arti Bhanddakkar 2 1 Research Scholar, Shri Ram Institute of Technology, Jabalpur, India 2 H.O.D. of Electrical Engineering Department,
More informationPartial Discharge Analysis of a Solid Dielectric Using MATLAB Simulink
ISSN (Online) 2321 24 Vol. 4, Issue 6, June 2 Partial Discharge Analysis of a Solid Dielectric Using MATLAB Simulink C Sunil kumar 1, Harisha K S 2, Gouthami N 3, Harshitha V 4, Madhu C Assistant Professor,
More informationPULSE-SEQUENCE ANALYSIS OF PARTIAL DISCHARGES IN POWER TRANSFORMERS
PULSE-SEQUENCE ANALYSIS OF PARTIAL DISCHARGES IN POWER TRANSFORMERS Anne Pfeffer 1*, Stefan Tenbohlen 1 and Stefan Kornhuber 2 1 Institute of Power Transmission and High Voltage Technology, Pfaffenwaldring
More informationPartial Discharge Patterns in High Voltage Insulation
22 IEEE International Conference on Power and Energy (PECon), 2-5 December 22, Kota Kinabalu Sabah, Malaysia Partial Discharge Patterns in High Voltage Insulation Hazlee Illias, Teo Soon Yuan, Ab Halim
More informationHigh Field Electrical Conduction and Breakdown in Solid Dielectrics
High Field Electrical Conduction and Breakdown in Solid Dielectrics R.S.Pote 1, V.N.Gohokar 2, D.G.Wakde 3, R.S.Kankale 4 Associate Professor, Department of Electrical Engineering, SSGMCOE, Shegaon, India
More informationSimulation of Partial Discharge in High Voltage Power Equipment
International Journal on Electrical Engineering and Informatics Volume 3, Number 2, 2011 Simulation of Partial Discharge in High Voltage Power Equipment Asima Sabat and S. Karmakar Department of Electrical
More informationPartial Discharge Classification Using Acoustic Signals and Artificial Neural Networks
Proc. 2018 Electrostatics Joint Conference 1 Partial Discharge Classification Using Acoustic Signals and Artificial Neural Networks Satish Kumar Polisetty, Shesha Jayaram and Ayman El-Hag Department of
More informationA heuristic complex probabilistic neural network system for partial discharge pattern classification
J. Indian Inst. Sci., Sep. Oct. 2005, 85, 279 294 Indian Institute of Science. A heuristic complex probabilistic neural network system for partial discharge pattern classification B. KARTHIKEYAN*, S. GOPAL
More informationPARTIAL DISCHARGE MEASUREMENTS ON GENERATORS USING A NOISE GATING SYSTEM
Abstract PARTIAL DISCHARGE MEASUREMENTS ON GENERATORS USING A NOISE GATING SYSTEM Q. SU Department of Electrical & Computer Systems Engineering Monash University, Clayton VIC 3168 Email: qi.su@eng.monash.edu.au
More informationHow to Use the Method of Multivariate Statistical Analysis Into the Equipment State Monitoring. Chunhua Yang
4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 205) How to Use the Method of Multivariate Statistical Analysis Into the Equipment State Monitoring
More informationThe University of New South Wales. School of Electrical Engineering and Telecommunications. High Voltage Systems ELEC9712. Appendix Partial Discharge
The University of New South Wales School of Electrical Engineering and Telecommunications High Voltage Systems ELEC9712 Appendix Partial Discharge Content Introduction Quantities measured Test circuits
More informationIN HOUSE CALIBRATION OF PD DETECTOR SYSTEM FOR FIELD TEST RESULT RELIABILITY
IN HOUSE CALIBRATION OF PD DETECTOR SYSTEM FOR FIELD TEST RESULT RELIABILITY Avinash Raj 1, Chandan Kumar Chakrabarty 1, Rafidah Ismail 1 and Basri Abdul Ghani 2 1 College of Engineering, University Tenaga
More informationPD Solutions. On-Line PD Measurement Devices
On-Line PD Measurement Devices 1. Longshot Device (see Figure 1) The measurement system applied is based around the wideband (0-400 MHz) HVPD- Longshot partial discharge test unit which utilizes a high-speed
More informationCHAPTER 2. v-t CHARACTERISTICS FOR STANDARD IMPULSE VOLTAGES
23 CHAPTER 2 v-t CHARACTERISTICS FOR STANDARD IMPULSE VOLTAGES 2.1 INTRODUCTION For reliable design of power system, proper insulation coordination among the power system equipment is necessary. Insulation
More informationBasics of Partial Discharge. Prepared for 2015 Phenix RSM Meeting January 2015
Basics of Partial Discharge Prepared for 2015 Phenix RSM Meeting January 2015 Definitions and History Standard Definitions Fundamentally, what is a Partial Discharge An electric discharge which only partially
More informationRadiated EMI Recognition and Identification from PCB Configuration Using Neural Network
PIERS ONLINE, VOL. 3, NO., 007 5 Radiated EMI Recognition and Identification from PCB Configuration Using Neural Network P. Sujintanarat, P. Dangkham, S. Chaichana, K. Aunchaleevarapan, and P. Teekaput
More informationCHAPTER 5 CONCEPT OF PD SIGNAL AND PRPD PATTERN
75 CHAPTER 5 CONCEPT OF PD SIGNAL AND PRPD PATTERN 5.1 INTRODUCTION Partial Discharge (PD) detection is an important tool for monitoring insulation conditions in high voltage (HV) devices in power systems.
More informationUHF PD-DIAGNOSIS AT HIGH VOLTAGE CABLE TERMINATIONS INTERNATIONAL CASE STUDIES
UHF PD-DIAGNOSIS AT HIGH VOLTAGE CABLE TERMINATIONS INTERNATIONAL CASE STUDIES D. Götz*, H.T. Putter* *Megger Germany INTRODUCTION High voltage termintions are essential components in high voltage cable
More informationInvestigation of PD Detection on XLPE Cables
Investigation of PD Detection on XLPE Cables Hio Nam O, T.R. Blackburn and B.T. Phung School of Electrical Engineering and Telecommunications The University New South Wales, Australia Abstract- The insulation
More informationPrognostic Modeling for Electrical Treeing in Solid Insulation using Pulse Sequence Analysis
Nur Hakimah Binti Ab Aziz, N and Catterson, Victoria and Judd, Martin and Rowland, S.M. and Bahadoorsingh, S. (2014) Prognostic modeling for electrical treeing in solid insulation using pulse sequence
More informationTHE PROPAGATION OF PARTIAL DISCHARGE PULSES IN A HIGH VOLTAGE CABLE
THE PROPAGATION OF PARTIAL DISCHARGE PULSES IN A HIGH VOLTAGE CABLE Z.Liu, B.T.Phung, T.R.Blackburn and R.E.James School of Electrical Engineering and Telecommuniications University of New South Wales
More informationFAULT IDENTIFICATION IN TRANSFORMER WINDING
FAULT IDENTIFICATION IN TRANSFORMER WINDING S.Joshibha Ponmalar 1, S.Kavitha 2 1, 2 Department of Electrical and Electronics Engineering, Saveetha Engineering College, (Anna University), Chennai Abstract
More informationTarget Classification in Forward Scattering Radar in Noisy Environment
Target Classification in Forward Scattering Radar in Noisy Environment Mohamed Khala Alla H.M, Mohamed Kanona and Ashraf Gasim Elsid School of telecommunication and space technology, Future university
More informationIEEE (2016) (2016). IEEE.,
Corr, Edward and Siew, W. H. and Zhao, Weijia (16) Long term testing and analysis of dielectric samples under DC excitation. In: IEEE Electrical Insulation Conference (16). IEEE., This version is available
More informationPATTERN CLASSIFICATION OF PARTIAL DISCHARGE IN LV WINDING OF 1- TRANSFORMER USING PCA
International Journal of Information Technology and Knowledge Management January-June 2011, Volume 4, No. 1, pp. 1-5 PATTERN CLASSIFICATION OF PARTIAL DISCHARGE IN LV WINDING OF 1- TRANSFORMER USING PCA
More informationEvaluation and Limitations of Corona Discharge Measurements An Application Point of View
Evaluation and Limitations of Corona Discharge Measurements An Application Point of View P. Mraz, P. Treyer, U. Hammer Haefely Hipotronics, Tettex Instruments Division 2016 International Conference on
More informationUSING DAMPED AC VOLTAGES
MODERN & TESTING DIAGNOSIS OF POWER CABLES USING DAMPED AC VOLTAGES BY EDWARD GULSKI AND ROGIER JONGEN, Onsite HV Solutions ag, Switzerland AND RALPH PATTERSON, Power Products & Solutions LLC, United States
More informationInternational Journal of Advance Engineering and Research Development. Comparison of Partial Discharge Detection Techniques of Transformer
Scientific Journal of Impact Factor(SJIF): 3.134 International Journal of Advance Engineering and Research Development Volume 2,Issue 7, July -2015 e-issn(o): 2348-4470 p-issn(p): 2348-6406 Comparison
More informationCharacteristics of Insulation Diagnosis and Failure in Gas Turbine Generator Stator Windings
J Electr Eng Technol Vol. 9, No. 1: 280-285, 2014 http://dx.doi.org/10.5370/jeet.2014.9.1.280 ISSN(Print) 1975-0102 ISSN(Online) 2093-7423 Characteristics of Insulation Diagnosis and Failure in Gas Turbine
More informationPARTIAL DISCHARGE MEASUREMENT ANALYSIS ON RING MAIN UNIT
PARTIAL DISCHARGE MEASUREMENT ANALYSIS ON RING MAIN UNIT Vaibhav Patil 1, Er. Harpreet Singh 2, Er Prashant Rade 3, 1 M Tech scholar, Institute Of Engineering And Technology, Alwar Rajasthan,India. 2 Associate
More informationEnhanced MLP Input-Output Mapping for Degraded Pattern Recognition
Enhanced MLP Input-Output Mapping for Degraded Pattern Recognition Shigueo Nomura and José Ricardo Gonçalves Manzan Faculty of Electrical Engineering, Federal University of Uberlândia, Uberlândia, MG,
More informationPartial Discharge Characteristics of Micro-gaps
Proc. ESA Annual Meeting on Electrostatics 2008, Paper J3 1 Partial Discharge Characteristics of Micro-gaps Mithila H*, Poornima A*, Adnan B, Subhankar D, Balachandra TC *, Asokan T GE India Technology
More informationPD Diagnostic Applications and TechImp solutions
PD Diagnostic Applications and TechImp solutions Condition Assessment Solutions for Electrical Systems. PD based innovative tools for the Condition Based Maintenance. MD-04.05.004 - rev. 00-29/08/2006
More informationPARTIAL DISCHARGE MEASUREMENT ON ROTATING MACHINES
PARTIAL DISCHARGE MEASUREMENT ON ROTATING MACHINES Engr. IÑIGO V. ESCOPETE, JR. ITC Level 2 Certified Thermographer PHIL-NCB NDT-UT Level 2 Partial Discharge testing is a Condition Based Maintenance tool
More informationNOISE REDUCTION AND SOURCE RECOGNITION OF PARTIAL DISCHARGE SIGNALS IN GAS-INSULATED SUBSTATION
NOISE REDUCTION AND SOURCE RECOGNITION OF PARTIAL DISCHARGE SIGNALS IN GAS-INSULATED SUBSTATION JIN JUN NATIONAL UNIVERSITY OF SINGAPORE 2005 NOISE REDUCTION AND SOURCE RECOGNITION OF PARTIAL DISCHARGE
More informationAdaptive Multi-layer Neural Network Receiver Architectures for Pattern Classification of Respective Wavelet Images
Adaptive Multi-layer Neural Network Receiver Architectures for Pattern Classification of Respective Wavelet Images Pythagoras Karampiperis 1, and Nikos Manouselis 2 1 Dynamic Systems and Simulation Laboratory
More informationWhy partial discharge testing makes good sense
Why partial discharge testing makes good sense PD measurement and analysis have proven to be reliable for detecting defects in the insulation system of electrical assets before major damage or a breakdown
More informationPartial Discharge Monitoring and Diagnosis of Power Generator
Partial Discharge Monitoring and Diagnosis of Power Generator Gao Wensheng Institute of High Voltage & insulation tech. Electrical Eng. Dept., Tsinghua University Wsgao@tsinghua.edu.cn Currently preventive
More informationSuppression of Pulse Interference in Partial Discharge Measurement Based on Phase Correlation and Waveform Characteristics
Journal of Energy and Power Engineering 9 (215) 289-295 doi: 1.17265/1934-8975/215.3.8 D DAVID PUBLISHING Suppression of Pulse Interference in Partial Discharge Measurement Based on Phase Correlation and
More informationModel and Computer Simulation of Partial Discharge Patterns in Natural Liquid Insulation for High Voltage Application
Model and Computer Simulation of Partial Discharge Patterns in Natural Liquid Insulation for High Voltage Application Suwarno and Heri Sutikno Abstract Electric power is widely used worldwide due to its
More informationAbstract. 1 Introduction
Using optical couplers to monitor the condition of electricity infrastructure S.G. Swingler, L. Hao, P.L. Lewin and D.J. Swaffield The Tony Davies High Voltage Laboratory, University of Southampton, Southampton
More informationTesting and PD Diagnosis of MV Cable Systems with DAC Voltage Educational Session May St Pete Beach, Fl
Testing and PD Diagnosis of MV Cable Systems with DAC Voltage Educational Session May 26 2011 St Pete Beach, Fl HDW ELECTRONICS, INC. THE BEST IN CABLE FAULT LOCATING TECHNOLOGY by Henning Oetjen Frank
More informationChapter 2 Channel Equalization
Chapter 2 Channel Equalization 2.1 Introduction In wireless communication systems signal experiences distortion due to fading [17]. As signal propagates, it follows multiple paths between transmitter and
More informationPartial discharge diagnostics on very long and branched cable circuits
11 Nordic Insulation Symposium Stockholm, June 11-13, 2001 Partial discharge diagnostics on very long and branched cable circuits Nico van Schaik, E. Fred Steennis, Wim Boone and Dick M. van Aartrijk KEMA
More informationFigure 1. Artificial Neural Network structure. B. Spiking Neural Networks Spiking Neural networks (SNNs) fall into the third generation of neural netw
Review Analysis of Pattern Recognition by Neural Network Soni Chaturvedi A.A.Khurshid Meftah Boudjelal Electronics & Comm Engg Electronics & Comm Engg Dept. of Computer Science P.I.E.T, Nagpur RCOEM, Nagpur
More informationAn Hybrid MLP-SVM Handwritten Digit Recognizer
An Hybrid MLP-SVM Handwritten Digit Recognizer A. Bellili ½ ¾ M. Gilloux ¾ P. Gallinari ½ ½ LIP6, Université Pierre et Marie Curie ¾ La Poste 4, Place Jussieu 10, rue de l Ile Mabon, BP 86334 75252 Paris
More informationChapter 5. Signal Analysis. 5.1 Denoising fiber optic sensor signal
Chapter 5 Signal Analysis 5.1 Denoising fiber optic sensor signal We first perform wavelet-based denoising on fiber optic sensor signals. Examine the fiber optic signal data (see Appendix B). Across all
More informationCONDITION MONITORING OF MEDIUM VOLTAGE ELECTRICAL CABLES BY MEANS OF PARTIAL DISCHARGE MEASUREMENTS
136 CONDITION MONITORING OF MEDIUM VOLTAGE ELECTRICAL CABLES BY MEANS OF PARTIAL DISCHARGE MEASUREMENTS H. van Jaarsveldt* and R. Gouws** School of Electrical, Electronic and Computer Engineering, North-West
More information2012 IEEE. Personal use of this material is permitted. Permission from
This document is published in: Ardila-Rey, J.A.; Martinez-Tarifa, J.M.; Robles, G.; Rojas-Moreno, M.; Albarracin, R.;, "A Partial Discharges acquisition and statistical analysis software," Instrumentation
More informationExtended analysis versus frequency of partial discharges phenomena, in support of quality assessment of insulating systems
Extended analysis versus frequency of partial discharges phenomena, in support of quality assessment of insulating systems Romeo C. Ciobanu, Cristina Schreiner, Ramona Burlacu, Cristina Bratescu Technical
More informationInternational Conference on Information Sciences, Machinery, Materials and Energy (ICISMME 2015)
International Conference on Information Sciences Machinery Materials and Energy (ICISMME 2015) Research on the visual detection device of partial discharge visual imaging precision positioning WANG Tian-zheng
More informationMulti-Resolution Wavelet Analysis for Chopped Impulse Voltage Measurements
Multi-Resolution Wavelet Analysis for Chopped Impulse Voltage Measurements EMEL ONAL Electrical Engineering Department Istanbul Technical University 34469 Maslak-Istanbul TURKEY onal@elk.itu.edu.tr http://www.elk.itu.edu.tr/~onal
More informationEFFECT OF INTEGRATION ERROR ON PARTIAL DISCHARGE MEASUREMENTS ON CAST RESIN TRANSFORMERS. C. Ceretta, R. Gobbo, G. Pesavento
Sept. 22-24, 28, Florence, Italy EFFECT OF INTEGRATION ERROR ON PARTIAL DISCHARGE MEASUREMENTS ON CAST RESIN TRANSFORMERS C. Ceretta, R. Gobbo, G. Pesavento Dept. of Electrical Engineering University of
More informationCharacterization of LF and LMA signal of Wire Rope Tester
Volume 8, No. 5, May June 2017 International Journal of Advanced Research in Computer Science RESEARCH PAPER Available Online at www.ijarcs.info ISSN No. 0976-5697 Characterization of LF and LMA signal
More informationVisualization of the Ionization Phenomenon in Porous Materials under Lightning Impulse
Visualization of the Ionization Phenomenon in Porous Materials under Lightning Impulse A. Elzowawi, A. Haddad, H. Griffiths Abstract the electric discharge and soil ionization phenomena have a great effect
More informationSoftware System for Finding the Incipient Faults in Power Transformers
Software System for Finding the Incipient Faults in Power Transformers Nikolina Petkova Technical University of Sofia, Department of Theoretical Electrical Engineering, 1156 Sofia, Bulgaria Abstract In
More informationDIAGNOSIS OF STATOR FAULT IN ASYNCHRONOUS MACHINE USING SOFT COMPUTING METHODS
DIAGNOSIS OF STATOR FAULT IN ASYNCHRONOUS MACHINE USING SOFT COMPUTING METHODS K. Vinoth Kumar 1, S. Suresh Kumar 2, A. Immanuel Selvakumar 1 and Vicky Jose 1 1 Department of EEE, School of Electrical
More informationEVALUATION AND COMPARISON OF ON-LINE PD DETECTION METHODS FOR HIGH-VOLTAGE POWER CABLE
EVALUATION AND COMPARISON OF ON-LINE PD DETECTION METHODS FOR HIGH-VOLTAGE POWER CABLE Ju-Chu Hsieh 1, Cheng-Chi Tai 1, Ching-Chau Su 1, Chien-Yi Chen 1, Ting-Cheng Huang 1, Yu-Hsun Lin 2 1 Department
More informationA Novel Fuzzy Neural Network Based Distance Relaying Scheme
902 IEEE TRANSACTIONS ON POWER DELIVERY, VOL. 15, NO. 3, JULY 2000 A Novel Fuzzy Neural Network Based Distance Relaying Scheme P. K. Dash, A. K. Pradhan, and G. Panda Abstract This paper presents a new
More informationPERFORMANCE PARAMETERS CONTROL OF WOUND ROTOR INDUCTION MOTOR USING ANN CONTROLLER
PERFORMANCE PARAMETERS CONTROL OF WOUND ROTOR INDUCTION MOTOR USING ANN CONTROLLER 1 A.MOHAMED IBRAHIM, 2 M.PREMKUMAR, 3 T.R.SUMITHIRA, 4 D.SATHISHKUMAR 1,2,4 Assistant professor in Department of Electrical
More informationDigital Signal Processing for the Detection and Location of Acoustic and Electric Signals from Partial Discharges
, June 30 - July 2, 2010, London, U.K. Digital Signal Processing for the Detection and Location of Acoustic and Electric Signals from Partial Discharges Jesus Rubio-Serrano, Member, IAENG, Julio E. Posada
More informationOpen Access Partial Discharge Fault Decision and Location of 24kV Composite Porcelain Insulator based on Power Spectrum Density Algorithm
Send Orders for Reprints to reprints@benthamscience.ae 342 The Open Electrical & Electronic Engineering Journal, 15, 9, 342-346 Open Access Partial Discharge Fault Decision and Location of 24kV Composite
More informationDetection of Partial Discharges and its Effect on Solid Insulation used in High Voltage Cable
Detection of Partial Discharges and its Effect on Solid Insulation used in High Voltage Cable Subrata Karmakar and Soumya Mishra Department of Electrical Engineering National Institute of Technology Rourkela-769008
More informationPartial Discharge Detection For Condition Monitoring Of An 11-kV XLPE Cable-Part II
The 3 rd 5 th International Student Conference Power Engineering on Research and Optimization Development Conference SCO (PEOCO2009), Shah Alam, Selangor, MALAYSIA. 3-4 June 2009. 11-12 December 2007,
More informationSurveillance and Calibration Verification Using Autoassociative Neural Networks
Surveillance and Calibration Verification Using Autoassociative Neural Networks Darryl J. Wrest, J. Wesley Hines, and Robert E. Uhrig* Department of Nuclear Engineering, University of Tennessee, Knoxville,
More informationApplication of Multi Layer Perceptron (MLP) for Shower Size Prediction
Chapter 3 Application of Multi Layer Perceptron (MLP) for Shower Size Prediction 3.1 Basic considerations of the ANN Artificial Neural Network (ANN)s are non- parametric prediction tools that can be used
More informationLEVEL DEPENDENT WAVELET SELECTION FOR DENOISING OF PARTIAL DISCHARGE SIGNALS SIMULATED BY DEP AND DOP MODELS
International Journal of Industrial Electronics and Electrical Engineering, ISSN: 47-698 Volume-, Issue-9, Sept.-014 LEVEL DEPENDENT WAVELET SELECTION FOR DENOISING OF PARTIAL DISCHARGE SIGNALS SIMULATED
More informationNon-intrusive Measurement of Partial Discharge and its Extraction Using Short Time Fourier Transform
> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 1 Non-intrusive Measurement of Partial Discharge and its Extraction Using Short Time Fourier Transform Guomin Luo
More informationAnalysis of Partial Discharge Patterns for Generator Stator Windings
American Journal of Electrical Power and Energy Systems 2015; 4(2): 17-22 Published online March 11,2015 (http://www.sciencepublishinggroup.com/j/epes) doi: 10.11648/j.epes.20150402.11 ISSN: 2326-912X
More informationDrum Transcription Based on Independent Subspace Analysis
Report for EE 391 Special Studies and Reports for Electrical Engineering Drum Transcription Based on Independent Subspace Analysis Yinyi Guo Center for Computer Research in Music and Acoustics, Stanford,
More informationAspects of PD interpretation in HV power cables. by Edward Gulski, Piotr Cichecki, Rogier Jongen
Aspects of PD interpretation in HV power cables by Edward Gulski, Piotr Cichecki, Rogier Jongen General There are several aspects having influence on the diagnostic information and the condition judgment
More informationPARTIAL DISCHARGE MEASUREMENT
PARTIAL DISCHARGE MEASUREMENT Partial Discharges are small electrical sparks which occur predominantly at insulation imperfection. It is the phenomenon which occurs in the insulation on application of
More informationA1-209 EXPERIENCES IN IDENTIFICATION OF PARTIAL DISCHARGE PATTERNS IN LARGE HYDROGENERATORS
21, rue d'artois, F-75008 Paris http://www.cigre.org A1-209 Session 2004 CIGRÉ EXPERIENCES IN IDENTIFICATION OF PARTIAL DISCHARGE PATTERNS IN LARGE HYDROGENERATORS CARLOS AZUAJE* WILLIAM TORRES C.V.G.
More information- 400 khz) the patterns of PD were studied. Satisfactory results
IEEE Transactions on Electrical Insulation Vol. 28 No. 6, December 1993 969 Computer-aided Measurement of Partial Discharges in HV Equipment E. Gulski HV Laboratory, Electrical Engineering Department,
More informationC I R E D 21 st International Conference on Electricity Distribution Frankfurt, 6-9 June 2011
Use and Problems of On-line PD Measurement Technology on Switchgears in Guangzhou Distribution System XIONG Jun, WANG Yong, HUANG Huihong, HUANG Yanguang,LU Guojun,WU Bihua (Central Test and Researches
More informationOPTICAL EMISSION CHARACTERISTICS OF HELIUM BREAKDOWN AT PARTIAL VACUUM FOR POINT TO PLANE GEOMETRY
OPTICAL EMISSION CHARACTERISTICS OF HELIUM BREAKDOWN AT PARTIAL VACUUM FOR POINT TO PLANE GEOMETRY K. Koppisetty ξ, H. Kirkici 1, D. L. Schweickart 2 1 Auburn University, Auburn, Alabama 36849, USA, 2
More informationPrediction of Transient Transfer Functions at Cable-Transformer Interfaces
1 Prediction of Transient Transfer Functions at Cable-Transformer Interfaces Joe Y. Zhou, Member, IEEE and Steven A. Boggs, Fellow, IEEE Joe Zhou participated in this work while completing his Ph.D. at
More informationA STUDY ON THE PERFORMANCE OF IMPEDANCE MATCHING CIRCUIT IN PARTIAL DISCHARGE MEASURING SYSTEM
BORNEO SCIENCE 30: MARCH 2012 A STUDY ON THE PERFORMANCE OF IMPEDANCE MATCHING CIRCUIT IN PARTIAL DISCHARGE MEASURING SYSTEM 1 Wan Akmal Izzati W. M. Zawawi, 2 Mohamad Zul Hilmey Makmud, & 3 Yanuar Z.
More informationPHG 70 TD PD / PHG 80 TD PD
PHG 70 TD PD / PHG 80 TD PD BAUR VLF test and diagnostics system Functions Universal test and diagnostics system flexible, modular, extendable Cutting-edge testing and diagnostics technology: VLF truesinus
More informationprocess has few stages and is highly repeatable. Excellent mechanic properties and electro-magnetic compatibility. Planar design gives the height lowe
PARTIAL DISCHARGE IN PLANAR TRANSFORMER Ing. Anar MAMMADOV, Doctoral Degreee Programme (1) Dept. of Microelectronics, FEEC, BUT E-mail: xmamed00@stud.feec.vutbr.cz Supervised by Dr. Jaroslav Boušek ABSTRACT
More informationFrequency Spectrum Analysis of Electromagnetic Waves Radiated by
Frequency Spectrum Analysis of Electromagnetic Waves Radiated by Electrical Discharges HYEON-KYU CHA, SUN-JAE KIM, DAE-WON PARK, GYUNG-SUK KIL Division of Electrical and Electronics Engineering Korea Maritime
More informationTHE POWER OF LIFE. WinTech Partial Discharge based Predictive Intelligence of insulation system to eliminate power failure risk.
THE POWER OF LIFE WinTech Partial Discharge based Predictive Intelligence of insulation system to eliminate power failure risk. Mr. Neal Yang Pro.E.E. Engineer About Us The flaw of dielectric material
More informationCHAPTER 6 BACK PROPAGATED ARTIFICIAL NEURAL NETWORK TRAINED ARHF
95 CHAPTER 6 BACK PROPAGATED ARTIFICIAL NEURAL NETWORK TRAINED ARHF 6.1 INTRODUCTION An artificial neural network (ANN) is an information processing model that is inspired by biological nervous systems
More informationEnhancement of Speech Signal Based on Improved Minima Controlled Recursive Averaging and Independent Component Analysis
Enhancement of Speech Signal Based on Improved Minima Controlled Recursive Averaging and Independent Component Analysis Mohini Avatade & S.L. Sahare Electronics & Telecommunication Department, Cummins
More informationDecriminition between Magnetising Inrush from Interturn Fault Current in Transformer: Hilbert Transform Approach
SSRG International Journal of Electrical and Electronics Engineering (SSRG-IJEEE) volume 1 Issue 10 Dec 014 Decriminition between Magnetising Inrush from Interturn Fault Current in Transformer: Hilbert
More informationWAVELET TRANSFORM ANALYSIS OF PARTIAL DISCHARGE SIGNALS. B.T. Phung, Z. Liu, T.R. Blackburn and R.E. James
WAVELET TRANSFORM ANALYSIS OF PARTIAL DISCHARGE SIGNALS B.T. Phung, Z. Liu, T.R. Blackburn and R.E. James School of Electrical Engineering and Telecommunications University of New South Wales, Australia
More informationThe importance of partial discharge testing throughout the development and operation of power transformers
The importance of partial discharge testing throughout the development and operation of power transformers Ulrike Broniecki OMICRON Energy Solutions GmbH, Berlin Power transformers are exposed to intense
More informationMAGNETO-DIELECTRIC COMPOSITES WITH FREQUENCY SELECTIVE SURFACE LAYERS
MAGNETO-DIELECTRIC COMPOSITES WITH FREQUENCY SELECTIVE SURFACE LAYERS M. Hawley 1, S. Farhat 1, B. Shanker 2, L. Kempel 2 1 Dept. of Chemical Engineering and Materials Science, Michigan State University;
More informationAir-Gap Partial Discharge Development Stage Recognition for Power Transformer Insulation Monitoring Considering Effect of Cavity Size
University of Wisconsin Milwaukee UWM Digital Commons Theses and Dissertations August 214 Air-Gap Partial Discharge Development Stage Recognition for Power Transformer Insulation Monitoring Considering
More informationThe Effect of Practical Voltages on Maximum Amplitude of Partial Discharge with Considering Different Number of Cavities
Signal Processing and Renewable Energy March 2017, (pp.47-54) ISSN: 2008-9864 The Effect of Practical Voltages on Maximum Amplitude of Partial Discharge with Considering Different Number of Cavities Mandana
More informationGeneration of Sub-nanosecond Pulses
Chapter - 6 Generation of Sub-nanosecond Pulses 6.1 Introduction principle of peaking circuit In certain applications like high power microwaves (HPM), pulsed laser drivers, etc., very fast rise times
More informationLOW VOLTAGE PWM INVERTER-FED MOTOR INSULATION ISSUES
LOW VOLTAGE PWM INVERTER-FED MOTOR INSULATION ISSUES Copyright Material IEEE Paper No. PCIC-4-15 RAPS-1433 Abstract - The topic of how low voltage IGBT-based PWM inverters create additional insulation
More informationHVDC Transmission. Michael Muhr. Institute of High Voltage Engineering and System Performance Graz University of Technology Austria P A S S I O N
S C I E N C E P A S S I O N T E C H N O L O G Y HVDC Transmission Michael Muhr Graz University of Technology Austria www.tugraz.at 1 Definition HV High Voltage AC Voltage > 60kV 220kV DC Voltage > 60kV
More informationCHAPTER 4 MONITORING OF POWER SYSTEM VOLTAGE STABILITY THROUGH ARTIFICIAL NEURAL NETWORK TECHNIQUE
53 CHAPTER 4 MONITORING OF POWER SYSTEM VOLTAGE STABILITY THROUGH ARTIFICIAL NEURAL NETWORK TECHNIQUE 4.1 INTRODUCTION Due to economic reasons arising out of deregulation and open market of electricity,
More informationNew clustering techniques based on current peak value, charge and energy calculations for separation of partial discharge sources
Delft University of Technology New clustering techniques based on current peak value, charge and energy calculations for separation of partial discharge sources Mor, A. R.; Castro Heredia, Luis; Muñoz,
More informationINVESTIGATION ON THE TECHNOLOGIES FOR DEFECT LOCALIZATION AND CHARACTERIZATION ON MEDIUM VOLTAGE UNDERGROUND LINES
INVESTIGATION ON THE TECHNOLOGIES FOR DEFECT LOCALIZATION AND CHARACTERIZATION ON MEDIUM VOLTAGE UNDERGROUND LINES Gonzalo MAIZ, Iberdrola Distribución, (Spain), gmaiz@iberdrola.es Armando RODRIGO, Instituto
More informationA COMPARISON OF AC AND DC PARTIAL DISCHARGE ACTIVITY IN POLYMERIC CABLE INSULATION *
Morris, E.A. and Siew, W.H. (2018) A comparison of AC and DC partial discharge activity in polymeric cable insulation. In: 2017 IEEE 21st International Conference on Pulsed Power (PPC). IEEE, Piscataway,
More informationImage Extraction using Image Mining Technique
IOSR Journal of Engineering (IOSRJEN) e-issn: 2250-3021, p-issn: 2278-8719 Vol. 3, Issue 9 (September. 2013), V2 PP 36-42 Image Extraction using Image Mining Technique Prof. Samir Kumar Bandyopadhyay,
More informationAnalysis of Learning Paradigms and Prediction Accuracy using Artificial Neural Network Models
Analysis of Learning Paradigms and Prediction Accuracy using Artificial Neural Network Models Poornashankar 1 and V.P. Pawar 2 Abstract: The proposed work is related to prediction of tumor growth through
More information