Responsive image
博碩士論文 etd-0612103-180817 詳細資訊
Title page for etd-0612103-180817
論文名稱
Title
應用人工智慧於電力系統諧波源與位置偵測
Power System Harmonic Sources and Location Detection with Artificial Intelligence
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
98
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2003-05-30
繳交日期
Date of Submission
2003-06-12
關鍵字
Keywords
電力諧波、小波網路、類神經網路、機率神經網路、非線性負載
non-linear loads, Artificial Neural Network, Probabilistic Neural Network, Power Harmonics, Wavelet Probabilistic Network, PNN
統計
Statistics
本論文已被瀏覽 5668 次,被下載 11413
The thesis/dissertation has been browsed 5668 times, has been downloaded 11413 times.
中文摘要
近年來由於電力電子設備廣泛的應用,電力諧波(Power Harmonics)造成之影響日漸嚴重,由於非線性負載的特性造成大量諧波注入電力系統,嚴重諧波污染影響電力品質,包括不斷電系統、整流器、變頻器等等之非線性負載在現代化工廠中已是不可或缺之設備,但其衍生之電力諧波問題,卻使得設備誤動作,電力電容器燒毀,造成工廠之重大損失等問題。

為了確保電力系統的電力品質,在電力系統中找出諧波源(Harmonic Sources)是一項重要的課題,本文提出以類神經網路(Artificial Neural Network)應用於電力系統諧波源與位置偵測。將根據負載諧波源的特性,透過諧波潮流分析程式,分析各種負載產生不同頻率之諧波成份,依據各種頻譜圖樣作為訓練資料,期望能執行偵測諧波源之工作。提出以機率神經網路(Probabilistic Neural Networks)與小波網路(Wavelet Probabilistic Network)應用於諧波源位置偵測(Harmonic Source Location)。根據負載諧波源的特性,透過諧波潮流分析程式,分析各種負載產生不同頻率之諧波成份,依據各種頻譜圖樣作為訓練資料,期望能執行偵測諧波源之工作。

本文提出的諧波源偵測系統,以IEEE-14 bus系統在個人電腦上模擬測試驗證其可行性。

Abstract
The technology of power electronics is used increasingly during recent years, and the electronic power facilities are used more and more in the power system. The non-linear electronic loads produce heavy harmonic currents and could significantly degrade the power quality. Nonlinear loads, including the un-interruptible power supply, motor control and converter, etc, are important equipment in a modern factory, however, these nonlinear loads could lead to power facility malfunction and capacitor damage. The harmonics would eventually cause severe unexpected capital loss.

Identification of harmonic sources location becomes an important study for power quality. An effective tool is thus helpful for the harmonic source locating. This paper proposes a method to deal with the harmonic sources and location detection in the power system by using the artificial neural network (ANN). The non-linear loading characteristics are studied by the power flow analysis, and then the proposed methodology uses the Probabilistic Neural Networks(PNN)and wavelet-probabilistic network (WPN) for harmonic source locating.

An IEEE 14-bus power system is used for study to show the effectiveness of the proposed approach.

目次 Table of Contents
目 錄
摘要 I
Abstract III
目錄 V
圖目錄 VIII
表目錄 X

第一章 緒論 1

1.1 研究動機 1
1.2 研究背景及方法 1
1.3 論文內容概述 3

第二章 諧波源偵測之研究背景及問題描述 5

2.1諧波之定義 5
2.1.1前言 5
2.1.2傅立葉級數及電力諧波之基本定義 5
2.1.3諧波失真率之定義 7
2.2 諧波產生之原因 9
2.3 諧波之影響 10
2.4諧波管制之標準 15
2.4.1諧波源需管制評估之對象 15
2.4.2諧波管制標準 16
2.4.3台灣電力公司諧波管制標準 18
2.5電力系統諧波潮流分析模型 19
2.5.1元件模型 19
2.5.2諧波負載潮流 25

第三章 研究方法介紹 28

3.1前言 28
3.2類神經網路介紹 28
3.2.1類神經網路模型 29
3.2.2人工神經元模型 32
3.2.3常用的非線性轉換函數 33
3.2.4類神經網路的組成 35
3.3類神經網路的種類與特性 36
3.3.1以學習策略分類 36
3.3.2以網路架構分類 37
3.3.3類神經網路的選用 38
3.3.4類神經網路的特性 39
3.4小波理論 40
3.4.1 Fourier Analysis 簡介 40
3.4.2短時傅氏轉換—STFT簡介 41
3.5小波(Wavelet)特性 43
3.6小波轉換種類 45

第四章 類神經網路於諧波源偵測架構與人機介面 47

4.1前言 47
4.2機率類神經網路 48
4.2.1貝氏分類器 48
4.2.2機率神經網路演算法 51
4.3小波網路 52
4.3.1簡介 52
4.3.2小波轉換 54
4.3.3小波網路演算法 55
4.4諧波源位置偵測系統之設計 57
4.5訓練資料之建立 62
4.6諧波源偵測系統 65
4.7結合小波分析之諧波源偵測系統設計 66
4.8人機介面之建構與偵測架構之結合 71

第五章 系統實例整合測試與討論 73

5.1系統簡介 73
5.2測試模擬__PNN機率神經網路之諧波源位置偵測 74
5.3測試模擬__量測儀表之擺置位置 80
5.4測試模擬__小波網路之諧波源位置偵測 85
5.5 PNN機率神經網路與小波網路偵測架構之比較分析 88
5.6平滑參數 值之決定與測試 90
5.7本章結論 91

第六章 結論與未來的研究方向 92

6.1 結論 92
6.2 未來研究方向 93


參考文獻 95
參考文獻 References
參考文獻


[1] IEEE Recommended Practices and Requirements for Harmonic Control in Electrical Power Systems ANSI/IEEE Std 519-1992.
[2] Flinn, D.G., Dugan, R.c., “A Database for Diverse Power System Simulation Applications”, IEEE Transactions on Power System, vol. 7, no. 2, May 1992,PP 784-790.
[3] Melhorn, J. McGranaghan, MF., “Interpretation and Analysis of Power Quality Measurements” , IEEE Transactions on Industry Applications, Nov/Dec, 1995.PP1363-1370.
[4] T. S. Key and J. S. Lai,“Comparison of Standards and Power Supply Design Options for Limiting Harmonic Distortion,”IEEE Trans. On Ind. Appl., Jul./Aug. 1993, PP 668-695.
[5] Jos Arrillaga, Math h. J. Bollen and Neville R. Watson ” power quality following deregulation”. Proceedings of the ieee, vol. 88, no. 2, February 2000,pp.246-261。
[6] M. Najjar and G. T. Heydt, “A Hybrid Nonlinear Least Squares Estimation of Harmonic Signal Levels in Power Systems, ”IEEE Trans. on Power delivery, Vol.6, No.1, Jan. 1991, pp. 282-288.
[7] J. E. Farach, W. M. Grady and A. Arapostant, “An Optimal Procedure for Placing Sensors and Estimating the Locations for Hramonic Sources in Power System, ”1992 PES Summe Meeting, Seattle, WA, July 12-16, 1996, Paper 497-8 PWRD.
[8] Y.-Y. Hong and Y.-C. Chen, “Application of Algorithms and Artificial-intelligence Approach for Locating Multiple Harmonics in Distribution System, ”IEE Proc.-Gener. Transm. Distrib., Vol. 146, No. 3, May 1999, pp.325-329.
[9] 吳家宏,”類神經網路應用於電力系統諧波源位置之偵測”,國立台北科技大學電機與能源研究所碩士論文,2000年。
[10] R. K. Hartana and G. G. Richards, “Harmonic Source Monitoring and Identification Using Neural Network, “IEEE Transaction on Power Systems, Vol. 5, No.4, November 1990, pp. 1098-1104.
[11] N. Pecharanin, H. Mitsui, and M. Sone, “Harmonic Detection by Using Neural Network, ” IEEE International Conference on Neural Network, Vol. 2, 1995.
[12] A.A.Mohd. Zin, Md. Rukonuzzaman, H. Shaibon, and K.L. Lo, “Neural Network Approach of Harmonics Detection, ”1998 International Conference on Energy Management and Power Delivery, Vol. 2, 1998, pp. 467-472.
[13] N. Pecharanin, H. Mitsui, and M. Sone, “An Application of Neural Network for Harmonic Detection in Active Filter, ”IEEE World Congress on Computational Intelligence, International Conference on Neural Network, Vol. 6, 1994.
[14] N. Pecharanin, “An Application of Neural Network to Harmonic Detection in Active Filter, “WCCI-ICNN’94, Proc. Vol.6, No.684, P.3756 (1994).
[15] Ying-Yi Hong and Yau-Ching Chen, “Application of Algorithms and Artificial –Intelligence Approach for Identifying Locations of Harmonic Sources in Distribution Systems, ” Proceedings of the 19th Symposium on Electrical Power Engineering, Taiwan, November 1998, pp. 884-888.
[16] Chia-Hung Wu and Chao-Rong Chen, “Apply Artificial Neural Network to Power System in Detecting the Positions of the Harmonic Sources, ” Proceedings of the 21th Symposium on Electrical Power Engineering, Taiwan, November 2000, pp. 329-333.
[17] N. Pecharanin, H. Mitsui, and M. Sone, “Harmonic Detection by Using Neural Network, ”IEEE International Conference on Neural Network, Vol. 2, 1995, pp. 923-926.
[18] P. Pillay and A. Bhattacharjee, “Application of Wavelet to Model Short-Term Power System Disturbances, ”IEEE Transaction on Power System, Vol. 1, No. 4, November 1996, pp. 2031-2037.
[19] Leopoldo Angrisani, Pasquale Daponte, and Massimo D’ Apuzzo, Wavelet Network-Based Detection and Classification of Transients, ”IEEE Transaction on Instrumentation and Measurement, Vol. 50, No. 50, October 2001, pp. 1425-1435.
[20] Yann-Chang Huang and Chao-Ming Huang, “Evolving Wavelet Network for Power Transformer Condition Monitoring, ”IEEE Trans. on Power Delivery, Vol.17, No.2, April 2002, pp. 412-416.
[21] Gary Chang W. K., IEEE Power Engineering Society Tutorial On Harmonics Modeling and Simulation, Chapter 3, 1998.
[22] Dan W. Patterson, “ Artificial Neural Networks: Theory and Applications, ”Prentice Hall, 1996.
[23] Seymour Lipschutz, “Theory and Problems of Data Structures, ”McGRAW-Hill Book Company, 1986.
[24] Zastrow,O.W., ”Recommended Practice for Voice Frequency Electrical Noise Tests of Distribution Transformers” ,IEEE Trans., COM-21, 1973, pp.1448-1455
[25] Cumming, P.G. “Estimating Effect of System Harmonic on Losses and Temperature Rise if Squirrel-Cage Motors,” IEEE Trans.on IA,Vol.22,No. 6. pp1121-1126,1986
[26] 周翌生,「電力系統諧波問題之探討」,電機月刊,第六卷第十期,第139頁至143頁
[27] 台鵬,「防護高諧波障害電力電容器之保護對策」,電機月刊,第三卷第八期,第106頁至108頁
[28] 台灣電力公司,「諧波管制標準之研擬」,台電工程月刊,1992
[29] 江榮城,陳士麟和顏世雄,“諧波管制標準之研提”,台灣工程月刊,第526 期,民國八十一年六月,pp.36-42.
[30] 江榮城,”諧波電力潮流分析與濾波器設計”,國立中山大學電機工程研究所碩士論文,1990年。
[31] David C.Robertson, Octavia I.Camps, Jeffrey S.Mayer and William B.Gish, “Wavelet and Electromagnetic Power System Transients”, IEEE Transaction on Power Delivery, Vol. 11, No. 2, April 1996, pp.1050-1056.
[32] Johan Driesen, Thierry Van Craenenbroeck, Roland Reekmans and Daniel Van Dommelen, “Analysing Time-Varying Power System Harmonics Using Wavelet Transform”, IEEE Instrumentation and Measurement Technonlgy Conference, Brussels, Belgium, June 4-6, 1996, pp.474-479.
[33] Charles K.Chui, Wavelets: A Mathematical Tool for Signal Processing, SIAM Press, 1997.
[34] 單維彰,凌波初步,全華科技圖書股份有限公司.
[35] Tsutomu Oyama, “Fault Section Estimation in Power System Using Boltzmann Machine, “Proceedings of Second Forum on Artificial Neural Network Applications to Power Systems (ANNPS’93), Japan, 1993, pp. 1-7.
[36] Yann-Chang Huang and Chao-Ming Huang, “Evolving Wavelet Network for Power Transformer Condition Monitoring, ”IEEE Trans. on Power Delivery, Vol.17, No.2, April 2002, pp. 412-416.
[37] 江榮城,”電力品質實務書(一)”,全華科技圖書股份有限公司,民國九十年七月。
[38] 江榮城,”電力品質實務書(二)”,全華科技圖書股份有限公司,民國九十年七月。

電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:校內外都一年後公開 withheld
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code