電力系統包含發電、輸電及配電三大部份，輸電為發電與配電之間的

連絡線路，主要的功能是由發電廠傳送電力至配電系統，並與其他區域之

電力系統互相連接的職責，遍佈的範圍相當廣泛。隨著國家經濟的成長與

科技的進步，需要更穩定的電力品質及更充裕的電力供應，為了增加供電

可靠度的考量，促使鄰近區域的電力系統互相連接，輸電網路的分佈的範

圍相對變廣，由於架空輸電線大部分曝露在室外，易遭受天然災害或人為

因素的破壞，若事故現場為於人口較多的地區，容易被發現且經由用戶通

告後，電力公司保線人員可立即趕赴事故現場進行修復，對於人員極少進

入的偏僻地區，必須派相關人員循線找尋事故點，阻撓我們搜尋的進度及

耗費相當多的時間，基於上述的原因促使我們對輸電線故障定位之研究，

以提供一套有效的方法尋找故障點。


本論文主要應用類神經網路理論，藉由訓練資料教導類神經網路具有

故障定位的功能，除了尋找故障事故點外，同時改善影響定位的缺點，由

於故障電阻在實際情況下並非定值，會隨著地質與環境因素而改變，將影

響故障定位的準確性，針對故障點偏移這項缺失，我們將推導估算故障電

阻的方法，以及修正故障定位曲線的規則，以改善故障定位的結果受故障

電阻的影響，接著建立單線接地、雙線接地、三相短路接地、與線對線故

障之故障定位曲線，使故障定位的功能適用於這四種類型故障，最後由電

腦模擬以驗證所提方法的可行性。本論文提出的方法將提供電力公司保線

人員一個參考位置，節省搜尋所耗費的時間。

An electric power system consists of the generating stations, the transmission

lines, and the distribution systems. Transmission lines are the connecting links

between the generating stations and the distribution systems. With the rapid

growth of economy and technology, the demand for large blocks of power,

power quality and increased reliability suggested the interconnection of

neighboring systems. Transmission lines are elements of a network which

connects the generating plants to the distribution systems, and could extend

hundreds of miles . Because of the long distances traversed by transmission

lines over open area, they tend to fade by natural and artificial calamity imposed

on the power system. It maybe easy to discover the fault with sufficient

information in the populous region. When fault occurs in the remote region, it is

difficult to identify the outage location. An efficient and reliable technique is

thus desirable to resolve the problem.


This dissertation presents the fault location for high voltage lines with

Artificial Neural Network( ANN ) method. Beside the fault location, this

research also improve the problem further by considering the fault resistance.

The fault resistance may not remain the same due to the variation of

environmental factors. The fault location may involve errors owing to the fault

resistance. An algorithms has been developed in this dissertation to calculate

fault resistance and revise the ANN training data for three-phase fault, double

line-to-ground fault, single line-to-ground fault, and line-to-line fault. To verify

the effectiveness of the method, practical transmission lines were used for tests.

The results proved that the method could be used to identify the fault location

effectively and help dispatchers determine a reference distance.

目 錄



誌謝 i
中文摘要 ii
英文摘要 iii
目錄 iv
圖目錄 vi
表目錄 vii


第一章 緒論 1

1.1 研究動機 1

1.2 研究背景及方法 2

1.3 論文內容概述 4


第二章 類神經網路介紹 6

2.1 前言 6

2.2 類神經網路模型 6

2.3 類神經網路架構 8

2.4 類神經網路的運作 10

2.5 類神經網路的選用 11


第三章 類神經網路學習法則 14

3.1 前言 14

3.2 指導性學習法則 14

3.2.1 回傳演算法( BP ) 15

3.2.2 Levenberg-Marquardt演算法( LM ) 19

3.3 指導性與非指導性學習法則之結合 22

3.4 學習法則討論 24
第四章 故障電阻估算 25

4.1 故障電阻估算的原由 25

4.2 單線接地故障估算法 26

4.3 雙線接地故障估算法 29

4.4 三相短路故障估算法 32

4.5 線對線故障估算法 34

4.6 估算法的討論 37


第五章 類神經網路的訓練 40

5.1 前言 40

5.2 故障電壓與電流之處理 41

5.3 訓練資料的建立 43

5.4 神經網路的訓練 49

5.5 故障定位曲線的修正 52

5.5.1 訓練資料的修正係數 53

5.5.2 訓練資料的修正與訓練 55

5.6 故障定位功能的討論 58


第六章 測試與討論 59

6.1 前言 59

6.2 問題的描述與測試 60

6.2.1 學習法則的測試 62

6.2.2 考慮故障電阻變化之測試 66

6.2.3 故障定位曲線修正測試討論 72

6.3 本章結論 74


第七章 結論 76

7.1 結論 76
7.2 未來發展 77


參考文獻 78

參考文獻



第一章參考文獻

[1] Thomas Dalstein, Thomas Friedrich, Bernd Kulicke and Dejan Sobajic, ”
Multi Neural Network Based Fault Area Estimation For High Speed Protective Relaying, “IEEE Transactions on Power Delivery, Vol.11, No.2, pp. 740-747, April 1996.

[2] Thomas Dalstein and Bernd Kulicke, ” Neural Network Approach To Fault Classification For High Speed Protective Relaying, “IEEE Transactions on Power Delivery, Vol.10, No.2, pp. 1002-1011, April 1995.

[3] T.S. Sidhu, H. Singh, and M.S. Sachdev, ”Design, Implementation and Testing of An Artificial Neural Network Based Fault Direction Discriminator for Protecting Transmission Lines, “ IEEE Transactions on Power Delivery, Vol.10, No.2, pp. 697-706, April 1995.

[4] Hong-Tzer Yang, Wen-Yeau Chang and Ching-Lien Huang, ”A New Neural Network Approach To On-Line Fault Section Estimation Using Information
Of Protective Relays And Circuit Breakers, “ IEEE Transactions on Power Delivery, Vol.9, No.1, pp. 220-229, January 1994.

[5] Adly A. Girgis and Melisa B. Johns, ” A Hybrid Expert System For Faulted
Section Identification, Fault Type Classification And Selection of Fault
Location Algorithms, “ IEEE Transactions on Power Delivery, Vol.4, No.2,
pp. 978-985, April 1988.

[6] Elerl Cardozo and Sarosh N. Talukdar, ” A Distributed Expert System For
Fault Diagnosis, “ IEEE Transactions on Power Delivery, Vol.3, No.2, pp. 641-646, May 1988.

[7] 江瑞利，林祺祥〝 類神經網路應用於捷運供電系統警報處理之研究〝第二十屆電力研討會，第1247頁至1251 頁。

第二章參考文獻

[8]林昇甫，洪成安，〝 神經網路入門與圖樣辨識〝全華科技圖書股
份有限公司，第一章與第六章，民國八十五年。

[9]秉昱科技，〝 模糊邏輯與類神經模糊實例說明〝儒林圖書有限公
司，第三章，民國八十七年。

[10] Jacek M. Zurada ,” Artificial Neural Systems“, 1992 .


第三章參考文獻

[11]林昇甫，洪成安，〝 神經網路入門與圖樣辨識〝全華科技圖書股
份有限公司，第三章與第六章，民國八十五年。

[12] Martin T. Hagon, Howaed B. Demuth, and Mark Beale, “Neural Network
Design, ”Chapter12, pp. 19-31.

第四章參考文獻

[13] M. S. Sachdev, R. Agarwal, ” A Technique For Estimating Transmission
Line Fault Locations from Digital Impedance Relay Measurements, “
IEEE Transactions on Power Delivery, Vol.3, No.1, pp. 121-129, January
1988.

[14] Adly A. Girgis, David G. Hart, and William L. Peterson, ” A New Fault
Location Technique For Two- And Three-Terminal Lines, “ IEEE
Transactions on Power Delivery, Vol.7, No.1, pp. 98-107, January 1992.

[15] KOUICHI TSUJI, HIKONI YANAGIDA, HIROSHI SASAKI, and
SHIGERU ABE, ” Development of Fault Characterization Equipment
( FCAREC ) for Power Transmission Lines, “ IEEE Transactions on Power
Delivery, Vol.7, No.1, pp. 133-138, January 1992.

[16] Zhang Qingchao, Zhang Yao, Song Wennan, and Fang Dazhong, ”
Transmission Line Fault Location for Single-Phase-To-Earth Fault on
Non-Direct-Ground Neutral System, “ IEEE Transactions on Power
Delivery, Vol.13, No.4, pp. 1086-1092, October 1997.

[17] Adly A. Girgis, David L. Lubkeman, and Jun Zhu, ” Automated Fault
Location and Diagnosis on Electric Power Distribution Feeders , “ IEEE
Transactions on Power Delivery, Vol.12, No.2, pp. 801-808, April 1997.

[18] Yan Tian, Li Erxue , and Yang Shiyou, “ Improved Simulated Annealing
Algorithm and Its Application in Fault-Location Of Power Transmission
Lines, “ IEEE, pp. 1135-1137, 1998.

[19] Toshihisa Funabashi, Hitomi Otoguro, Yoshihige Mizuma, Takaaki Kai,
Satoko Akiyama, Laurent Dube, and Akihiro Ametani, “Digital
Fault Location for High Resistance Grounded Transmission Lines, “
IEEE Transactions on Power Delivery, Vol.14, No.1, pp. 80-85, January
1999.

[20]陳士麟等，〝 配電高壓幹線事故定位系統〝，行政院國家科學委員會
電力科技產業學術合作研究計劃，民國八十七年。

[21]林惠民等，〝 類神經網路應用於輸電線故障定位之研究〝第二十屆電
力研討會，第803頁至807頁。
[22]林義讓，林清樺 編著，〝 電機設備保護〝，全華科技圖書股份有限公
司，第一章及第九章，民國八十一年。

[23]吳天得 編著，〝 變電工程〝，全華科技圖書股份有限公司，第218頁
至219頁，民國八十三年。

第五章參考文獻

[24]Murty V.V. Yalla, Beckwith Electric Company, “A Digital Multifunction
Protective Relay, “IEEE Transactions on Power Delivery, Vol.7, No.1, pp.
193-199, January 1992.

[25]A. G. Phadke, “A New Measurement Technique for Tracking Voltage
Phasors Local System Frequency and Rate Change of Frequency, “ IEEE
Transactions on Power Apparatus and Systems, Vol.PAS-102, No.5, pp.
1025-1037.

[26]Alessandro Ferrero, Silvia Sangiovanni, and Ennio Zappitelli, “A Fuzzy
Approach to Fault-Type Identification in Digital Relaying, “IEEE Trans. on
Power Delivery, Vol.10, No.1, pp. 169-175, January 1995.

[27]Alessandro Ferrero and G. Superti-Furga, “A New Approach to the
Definition of Power Components in Three-Phase Systems Under
Nonsinusoidal Conditions, “IEEE Trans. Instr. Meas., Vol. IM-40, 1991,
pp. 568-577.

[28]Huisheng Wang and W. W. L. Keerthipala, ” Fuzzy-Neural Approach to
Fault Classification for Transmission Line Protection, “IEEE Transactions
On Power Delivery, Vol.13, No.4, pp.1093-1101, October 1998.

[29]王順忠等，〝多功能數位保護電驛之研製〝，行政院國家科學委員會電
力科技產業學術合作研究計劃，民國八十七年。

[30]薛小生，黃郁東 編著，〝工業配電〝，大中國圖書出版公司，民國八
十二年。

第六章參考文獻

[31]台灣電力公司輸發變電系統常數，第1頁至第15頁。

[31]民國八十八年台電一次系統單、三相故障電流及接地方式檢討，民國
八十八四月。

[網站1]http://www.taipower.com.tw/