部分放電量測週期對地下電纜接頭瑕疵識別影響之研究

簡易檢索 / 詳目顯示

回結果列表

研究生：	Bharath Kumar Boyanapalli Bharath Kumar Boyanapalli
論文名稱：	部分放電量測週期對地下電纜接頭瑕疵識別影響之研究 Study of Partial Discharges Measurement Cycle Effect on Defect Recognition for Underground Cable Joints
指導教授：	張建國 Chien-Kuo Chang
口試委員:	李俊耀 Chun-Yao Lee 張宏展 Hong-Chan Chang 郭政謙 Cheng-Chien Kuo 吳瑞南 Ruay-Nan Wu 張建國 Chien-Kuo Chang 黃維澤 Wei-Tzer Huang 陳鴻誠 Hung-Cheng Chen
學位類別：	博士 Doctor
系所名稱：	電資學院 - 電機工程系 Department of Electrical Engineering
論文出版年：	2023
畢業學年度：	111
語文別：	英文
論文頁數：	91
中文關鍵詞：	partial discharge measurement cycles 、feature extraction 、defect recognition 、convolutional neural networks
外文關鍵詞：	partial discharge measurement cycles, feature extraction, defect recognition, convolutional neural networks
相關次數：	點閱：220 下載：4
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

上一筆

In this study, the effects of different partial discharges (PDs)
measurement cycles on defect recognition of power cable joints are
presented. The measurement cycles of 40, 80, 120, 200, and1200 are
considered to analyze the recognition accuracy. PD measurement data
is collected by considering a total of 14 sets of power cable joints having
three types of pre-fabricated artificial defects. The popular Phase
Resolved Partial Discharges (PRPD) feature extraction procedure is
used to extract the PD features and the and observing the effects of the
considered measurement cycles on the n-q-ø pattern is used in the
recognition method while using the different measurement cycles with
a deep learning model, convolutional neural network (CNN) to evaluate
the training and testing accuracies of defect recognition for individual
cycles and compare the results. The results show that the performance
of 200 measurements cycles-based CNN model is sufficient to have the
effective PD defect recognition accuracy compared to other lesser
cycles. The total recognition accuracy obtained from a 200 cycles-based
CNN was 100%, whereas that of the other lesser cycles based-CNN was
about 96%. In addition, an important application of setting threshold
value to overcome the failure cases in defect recognition are discussed.

Abstract.................................................................................................I
Acknowledgement ..............................................................................II
Table of contents................................................................................III
List of figures...................................................................................... V
List of tables....................................................................................VIII
Chapter 1 Introduction...................................................................... 1
1.1 Research background and motivation ....................................... 1
1.2 Research purpose and objectives ............................................. 3
1.3 Significance of work and contribution..................................... 5
1.4 Thesis outline ........................................................................... 6
Chapter 2 Partial Discharge Measurement System and
Experimental Setup............................................................................. 7
2.1.Introduction of partial discharge .............................................. 7
2.1.1 Partial discharge definition .............................................. 8
2.1.2 Classification of partial discharge.................................... 9
2.1.2 Detection methods of partial discharge.......................... 12
2.2 High voltage cable introduction ............................................. 16
2.3 Production of experimental artificial defects......................... 20
2.4 PD experimental setup............................................................ 22
2.5 PD data collection from defect samples................................. 25
Chapter 3 Partial Discharge Data Acquisition and Analysis....... 27
3.1 Data preprocessing and noise suppression............................. 27
3.2 PD data reduction ................................................................... 28
3.3 Feature extraction ................................................................... 31
3.4 Phase resolve N-Q-Φ Pattern at different PD measurement
cycles....................................................................................... 33
Chapter 4 Defect Recognition using Convolutional Neural
Networks……….................................................................................38
4.1 Introduction of CNN ............................................................. 38
IV
4.2 Theory of CNN architecture.................................................. 40
4.3 Loss function......................................................................... 49
4.4 Optimial algorithm................................................................ 50
4.5 Confusion index .................................................................... 51
4.6 Establishment of CNN .......................................................... 52
4.6.1 Architeture of CNN.................................................... 55
4.7 modeling of CNN.................................................................. 57
Chapter 5 Results and Discussion of n-q-φ Pattern Recognition
. ............................................................................................................ 61
5.1 Training CNN with different measurement cycles................. 61
5.2 Testing CNN with different measurement cycles................... 65
5.3 Comparison of training and testing accuracies for different
measurement cycles .............................................................. 66
5.4 Comparison of testing accuracies for different measurement
cycles with CNN trained with 200 Cycles............................ 67
Chapter 6 Conclusion and Future Work ....................................... 69
References .......................................................................................... 70
                                

[1] Eigner and K. Rethmeier, "An overview on the current status of
partial dicharge measurements on AC high voltage cable
accessories," IEEE Elect. Insul. Mag., vol. 32, no. 2, pp. 48-55,
Mar.-Apr. 2016.
[2] E. M. Lalitha and L. Satish, "Wavelet analysis for classification
of multi-source PD patterns," IEEE Elect. Insul. Mag., vol. 7,
pp. 40-47, 2000.
[3] E. Gulski and A. Krivda, "Neural networks as a tool for
recognition of partial discharges," IEEE Elect. Insul. Mag., vol.
28, pp. 984-1001, 1993.
[4] J. K. Wong et al., "Investigation of partial discharge severity at
XLPE cable without termination," Power and Energy (PECon),
2014 IEEE International Conference, pp. 13-16, 2014.
[5] IEC 60270: High voltage test techniques partial discharge
measurements," International Electrotechnical Commission.
[6] M. Allahbakhshi and A. Akbari, "A method for discriminating
original pulses in online partial discharge measurement,"
Measurement, vol. 44, pp. 148-158, 2011.
[7] W. J. K. Raymond et. al "Feature pruning for partial discharge
classification using indfeat and relief algorithm," 2018 IEEE
2nd International Conference on Dielectrics (ICD), pp. 1-4,
2018.
[8] N. Sahoo, M. Salama and R. Bartnikas, "Trends in partial
discharge pattern classification: A survey," IEEE Trans. on
Diele. and Electr. Insul., vol. 12, no. 2, pp. 248-264, Apr. 2005.
72
[9] Q. Khan et. Al., "Partial discharge detection and diagnosis in
gas insulated switchgear: State of the art," IEEE Electr. Insul.
Mag., vol. 35, no. 4, pp. 16–33, Jul./Aug. 2019.
[10] R. Umamaheswari and R. Sarathi, "Identification of partial
discharges in gas insulated switchgear by ultra-high-frequency
technique and classification by adopting multi-class support
vector machines," Elect. Pow. Comp. and Sys., vol. 39, no. 14,
pp. 1577–1595, 2011.
[11] Y. Wang et al., "Separating multi-source partial discharge
signals using linear prediction analysis and isolation forest
algorithm," IEEE Trans. on Instr. and Meas., vol. 69, no. 6, pp.
2734-2742, Jun. 2020
[12] K. B. Lee, S. Cheon and C. O. Kim, "A convolutional neural
network for fault classification and diagnosis in
semiconductor manufacturing processes," IEEE Trans. on
Sem. Manu., vol. 30, no. 2, pp. 135-142, May 2017.
[13] M. Karimi et al., "Partial discharge classification using deep
belief networks," 2018 IEEE/PES Transmission and
Distribution Conference and Exposition (T&D), pp. 1061-
1070, 2018.
[14] H. Song, J. Dai, G. Sheng and X. Jiang, "GIS partial discharge
pattern recognition via deep convolutional neural network
under complex data source," IEEE Trans. Dielect. Elect. Insul.,
vol. 25, pp. 678-685, 2018.
[15] T. Shahsavarian et al., "A Review of Knowledge-Based
Defect Identification via PRPD Patterns in High Voltage
Apparatus," IEEE Access, vol. 9, pp. 77705-77728, 2021.
73
[16] N.C. Sahoo, M. Salama and R. Bartnikas, “Trends in partial
discharge pattern classification: A survey,” IEEE Trans.
Dielect. Elect. Insul., vol. 12, no. 2, pp. 248-264, Apr. 2005.
[17] W. Min et al., “An overview of state-of-the-art partial
discharge analysis techniques for condition monitoring,”
IEEE Elect. Insul. Mag., vol. 31, no. 6, pp. 22–35, Dec. 2015.
[18] M. Karimi et al., "A novel application of deep belief networks
in learning partial discharge patterns for classifying corona,
surface and internal Discharges," IEEE Trans. Ind. Electr, vol.
67, no. 4, pp. 3277-3287, Apr. 2020.
[19] W. J. K. Raymond et al., "Partial discharge classifications:
Review of recent progress," Measurement, vol. 68, pp. 164-
181, 2015.
[20] Chong Wan Xin et al “Effects of shorter phase-resolved
partial discharge duration on PD classification accuracy” Inter.
Jour. of Power Electr. and Drive Sys. (IJPEDS) vol. 11, No. 1,
Mar. 2020, pp. 326~332.
[21] H. Ma, J. C. Chan, T. K. Saha and C. Ekanayake, "Pattern
recognition techniques and their applications for automatic
classification of artificial partial discharge sources," IEEE
Trans. Dielect. Elect. Insul., vol. 20, no. 2, pp. 468-478, Apr.
2013.
[22] C. -K. Chang, B. K. Boyanapalli and R. -N. Wu, "Application
of fuzzy entropy to improve feature selection for defect
recognition using support vector machine in high voltage
cable joints," IEEE Trans. Dielect. Elect. Insul., vol. 27, no. 6,
pp. 2147-2155, Dec. 2020.
[23] X. Peng et al., "A convolutional neural network-based deep
learning methodology for recognition of partial discharge
74
patterns from high-voltage cables," IEEE Trans. on Pow. Del.,
vol. 34, no. 4, pp. 1460-1469, Aug. 2019
[24] F. Duan, "Induction motor parameters estimation and faults
diagnosis using optimization algorithms," PhD. dissertation,
University of Adelaide, Australia, School of Electrical and
Electronic Engineering, 2014.
[25] C. K. Chang, C. S. Lai and R. N. Wu, "Decision tree rules for
insulation condition assessment of pre-molded power cable
joints with artificial defects," IEEE Trans. Dielect. Elect.
Insul., vol. 26, no. 5, pp. 1636- 1644, 2019.
[26] S. T. Li and J. Y. Li, "Condition monitoring and diagnosis of
power equipment: Review and prospective," High Voltage,
Vol. 2, No. 2, 2017.
[27] "High-voltage test techniques - partial discharge
measurements," IEC 60270, 3rd ed., 2000.
[28] Hsuan-Hao Chang " Insulation status assessment of power
cable joints based on partial discharges pulse sequence
analysis and convolutional neural network," Master Thesis,
National Taiwan University of Science and Technology,
Taiwan, Department of Electrical Engineering, 2022.
[29] MM Yaacob et al “Review on Partial Discharge Detection
Techniques Related to High Voltage Power Equipment Using
Different Sensors” Photonic Sensors, vol. 4, no. 4, 325–337,
2014.
[30] MPD-Article-PD-Measurement-Coupling-Methods-2020
ENU.pdf
[31] 台灣電力公司，配電技術手冊(四)地下配電線路設計，
民國 85 年。
75
[32] 台灣電力公司，高壓單芯交連 PE 電纜(A043)，材料規範，
民國 102 年。
[33] C. -K. Chang, B. K. Boyanapalli and R. -N. Wu, "Adaptive
adjustment of threshold criterion in predicting failure for
medium voltage power cable joints," IEEE Trans. Dielect.
Elect. Insul., vol. 28, no. 3, pp. 955-963, Jun. 2021.
[34] C. -K. Chang, H. -H. Chang and B. K. Boyanapalli,
"Application of pulse sequence partial discharge based
convolutional neural network in pattern recognition for
underground cable joints," IEEE Trans. Dielect. Elect. Insul.,
vol. 29, no. 3, pp. 1070-1078, Jun. 2022.
[35] LAM, " Application of fuzzy entropy to improve feature
selection for defect recognition using support vector machine
in high voltage cable joints," Master Thesis, National Taiwan
University of Science and Technology, Taiwan, Department
of Electrical Engineering, 2014.
[36] C. -K. Chang and B. K. Boyanapalli, "Assessment of the
insulation status aging in power cable joints using support
vector machine," IEEE Trans. Dielect. Elect. Insul., vol. 28,
no. 6, pp. 2170-2177, Dec. 2021.
[37] Yu-Hsun Lin, Ruay-Nan Wu, and I-Hua Chung, “Novel trend
of “l” shape in PD pattern to judge the appropriate crucial
moment of replacing cast-resin current transformer,” IEEE
Trans. on Dielectr. Electr. Insul., vol. 15, no. 1, pp. 292–301,
2008
[38] N. C. Sahoo, M. M. A. Salama, and R. Bartnikas, “Trends in
partial discharge pattern classification: a survey,” IEEE Trans.
76
on Dielectr. Electr. Insul., vol. 12, no. 2, pp. 248–264, Apr.
2005.
[39] K. B. Lee, S. Cheon and C. O. Kim, “A Convolutional Neural
Network for Fault Classification and Diagnosis in
Semiconductor Manufacturing Processes,” IEEE Trans.
Semicond. Manufacturing, vol. 30, no. 2, pp. 135-142, May
2017.
[40] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradientbased learning applied to document recognition," Proceedings
of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
[41] A. Krizhevsky, I. Sutskever and G. E. Hinton, "Imagenet
classification with deep convolutional neural networks,"
Advances in neural information processing systems, 2012.
[42] 賴佳駿，基於卷積神經網路於交連聚乙烯電纜接頭之狀
態診斷及瑕疵識別研究，碩士論文，臺北，國立臺灣科
技大學電機工程系，民國 110 年。
[43] X. Peng et al., "A convolutional neural network-based deep
learning methodology for recognition of partial discharge
patterns from high-voltage cables," IEEE Trans. on Pow Del.,
vol. 34, no. 4, pp. 1460-1469, Aug. 2019
[44] M. A. Ranzato, "Deep learning lecture 6," Microsoft AI
Research
[45] D. Liu et al., "Learning temporal dynamics for video superresolution: A deep learning approach," IEEE Trans. on Imag.
Proc., vol. 27, no. 7, pp. 3432-3435, Jul. 2018.
[46] X. Glorot, A. Bordes and Y. Bengio, "Deep sparse rectifier
neural networks," Proceedings of the Fourteenth International
77
Conference on Artificial Intelligence and Statistics, PMLR
15:315-323, 2011
[47] N. Srivastava et al., "Dropout: A simple way to prevent neural
networks from overfitting," Journal of Machine Learning
Research, 2014.
[48] P. Mishra et al., "Extraction of information from handwriting
using optical character recognition and neural networks,"
2020 4th International Conference on Electronics,
Communication and Aerospace Technology (ICECA), pp.
1328-1333, 2020.
[49] C. K. Chang et al., "Partial discharge pattern recognition for
underground cable joints using convolutional neural
network," 2020 International Conference on Pervasive
Artificial Intelligence (ICPAI), pp. 234-239, 2020.

簡易檢索 / 詳目顯示

相關論文