為了確保電力系統供電品質與可靠性，系統保護佔了極重要的地位，當電力系統遭受天然災害及人為意外事故時，調度人員必須儘速找出故障位置及原因，並加以隔離，再經由復電策略恢復停電區域之電力供應，以縮短停電時間。一套完整監控系統(SCADA System)與智慧型偵測系統(Artificial Intelligence based Detection System)，將有助於提升調度人員處理與排除故障的能力，若電力系統發生緊急事故時，調度員常依據保護電驛及斷路器動作的記錄，來判斷系統發生故障的區域與類型，由人力處理與解讀的方式，不僅無法縮短事故處理時間，當面對大規模事故時將無法應付，尤其面對數量過多的訊號、不明確訊號、誤動作訊號、或多重事故的訊號，增加調度員解讀的困難度。


本文提出以類神經網路(Artificial Neural Networks)應用於變電所故障區域之偵測。利用機率神經網路(Probability Neural Networks，PNN)建構故障區域偵測(Fault Section Detection)之系統以判定故障發生之區域。依據主保護與後衛保護規劃之跳脫資料作為訓練資料，執行偵測工作時則依保護設備動作情形判定故障區域，主要的情形包括單一故障、多個故障、單一故障或者多個故障包含誤動作之信號。另外，本文也提出以模糊理論為基礎作為故障類型偵測(Fault Type Detection)，以改善傳統二值邏輯單一極限值的不適當性，也更適用於不明確情形下(故障接地電阻、故障點位置、負載大小)之實際配電系統。最後本文以台電某一典型的二次變電所為例，驗證本文所提方法之可行性。

Power system protection is important for service reliability and quality assurance. Various faults may occur due to natural and artificial calamity. To reduce the outage duration and promptly restore power services, fault section estimate has to be done effectively with appeared fault alarms. Dispatchers could study the changed statuses of primary/back-up relays and circuit breakers to identify the fault section and fault types. It is difficult to process too many alarms under various conditions in a large power system. Single fault, multiple faults, single and multiple faults could coexist with the failed operation of relays and circuit breakers, or with the erroneous data communication. Dispatchers
need more time to process the many uncertainties before identifying the fault.


This thesis presents the use of artificial intelligence for fault section detection in substation with neural networks. Probabilistic Neural Networks (PNN) are proposed for fault detection system in substation. The proposed methodology will use primary/back-up information of protective relays and circuit breakers to detect the fault sections involving single fault, multiple faults, or fault with the failure operation of the relays and circuit breakers. This paper also presents a fuzzy theory-based method to identify fault types. It is derived to improve the inadequacy of making decisions by selecting a fixed threshold value and has the capability of non-deterministic decision making with a prior knowledge of uncertainties in fault location, fault resistance and the a size of loads. The proposed approach has been tested on a typical taipower system with accurate results.

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 4

第二章 國內電力調度控制自動化系統之介紹 5

2.1 前言 5
2.2 台電調度自動化系統架構 5
2.2.1階層調度控制 7
2.2.2調度系統軟體功能 10
2.2.3調度系統硬體架構 11
2.3 SCADA系統 12
2.3.1 SCADA系統硬體設備 12
2.3.2 SCADA系統軟體設備 19
2.4自動化系統下之事故處理及現行方式之缺點 23

第三章 類神經網路應用於故障區域之偵測 24

3.1前言 24
3.2類神經網路之介紹 24
3.2.1類神經網路模型 25
3.2.2類神經網路架構 27
3.2.3類神經網路的運作 29
3.2.4類神經網路的選用 30
3.3機率類神經網路 31
3.4偵測系統之設計 34
3.5解釋單元之架構 40
3.6本章結論 47

第四章 模糊理論應用於故障類型之偵測 48

4.1前言 48
4.2模糊理論之介紹 48
4.2.1二值邏輯與模糊集合 50
4.2.2模糊集合之定義及基本運算 52
4.3故障分析及模糊推論機之建構 54
4.3.1 歸屬函數及模糊規則庫之建立 54
4.3.2 故障類型之推論流程 63
4.4本章結論 64

第五章 系統實例整合測試 65

5.1系統簡介 65
5.2 測試一：單一故障且有保護設備發生誤動作 65
5.3 測試二：多重故障且無保護設備發生誤動作 70
5.4 測試三：多重故障且有保護設備發生誤動作 74
5.5 本章結論 77
第六章 結論與未來的研究方向 78
6.1 結論 78
6.2 未來研究方向 80
參考文獻 81
附錄 85

圖 目 錄
圖1-1 論文之研究流程圖 3
圖2-1 電力系統示意圖 6
圖2-2 調度控制系統階層連繫圖 8
圖2-3 台電階層調度控制系統架構圖 9
圖2-4 事故處理流程圖 23
圖3-1 單一生物神經元模型 26
圖3-2 順向神經網路架構圖 28
圖3-3 回授神經網路架構圖 28
圖3-4 機率神經網路架構圖 32
圖3-5 簡易之配電系統圖 34
圖3-6 自動化電驛狀態取樣接線圖 35
圖3-7 保護設備操作過程 37
圖3-8 變電所示意圖 38
圖3-9 故障區間偵測系統架構圖 39
圖3-10 邏輯解釋單元流程圖 41
圖4-1-a 饋線B相發生單線接地故障之電流變化情形 55
圖4-1-b 饋線B相發生單線接地故障之電壓變化情形 55
圖4-2-a 饋線AB相發生接地故障之電流變化情形 56
圖4-2-b 饋線AB相發生單線接地故障之電壓變化情形 56
圖4-3-a 饋線AB相發生短路故障之電流變化情形 56
圖4-3-b 饋線AB相發生短路故障之電壓變化情形 57
圖4-4-a 饋線發生三相短路故障之電流變化情形 57
圖4-4-b 饋線發生三相短路故障之電流變化情形 57
圖4-5 發生單相接地故障在不同故障位置下電流變化之統計圖(20ohm) 58
圖4-6 發生單相接地故障在不同故障位置下電流變化之統計圖(30ohm) 58
圖4-7 發生單相接地故障在不同故障位置下電壓變化統計圖(20ohm) 58
圖4-8 發生單相接地故障在不同故障位置下電壓變化之統計圖(30ohm) 59
圖4-9 單相接地故障電流之相減分析 59
圖4-10 兩相接地故障電流之相減分析 59
圖4-11 單相接地故障電壓之相減分析 60
圖4-12 兩相接地故障電壓之相減分析 60
圖4-13 中性點電流之分析 60
圖4-14 饋線電流之歸屬函數 61
圖4-15 中性點電流之歸屬函數 61
圖4-16 匯流排電壓之歸屬函數 61
圖4-17 輸出變數之10個歸屬函數 62
圖4-18 模糊推論機架構 63
圖4-19 模糊推論流程圖 64
圖5-1 鹽埕變電所單線圖 66
圖5-2 測試範例1之故障情形 67
圖5-3 測試範例1故障區間診斷之結果 68
圖5-4 測試範例1故障類型模糊推論之結果 69
圖5-5 測試範例2之故障情形 70
圖5-6 測試範例2故障區間診斷之結果 71
圖5-7-1測試範例2故障類型模糊推論之結果 72
圖5-7-2測試範例2故障類型模糊推論之結果 73
圖5-7-3測試範例2故障類型模糊推論之結果 73
圖5-8 測試範例3之故障情形 74
圖5-9 測試範例3故障區間診斷之結果 75
圖5-10-1測試範例3故障類型模糊推論之結果 76
圖5-10-2測試範例3故障類型模糊推論之結果 77

表 目 錄
表2-1 調度系統軟體功能劃分表 10
表3-1 生物體與生物模型對照表 26
表3-2 機率神經網路相關資料 38
表3-3 電驛事實關係表 40
表4-1 傳統集合與FUZZY集合基本精神的比較表 52
表4-2 模糊規則表 62

[1] C. Fukui and J. Kawakami, “An Expert System for Fault Section

Estimation Using Information from Protective Relay and Circuit

breaker“IEEE Trans. on Power delivery, Vol.1, No.4, October 1986,

pp. 83-91.

[2] Eleri Cardozo and Sarosh N. Talukdar, “A Distributed Expert System

for Fault Diagnosis, “IEEE Trans. on Power Systems, Vol.3, No.2, May

1988, pp. 641-646.

[3] Adly A. Girgis and Melisa B. Johns, “A Hybrid Expert System for

Faulted Section Identification, Fault Type Classification and Section of

Fault Location Algorithms, “IEEE Tran. on Power Delivery, Vol.4,

No.2, April 1989, pp. 978-985.

[4] Y.Y. Hsu, F.C. Lu, Y. Chien, J.P. Liu, J.T. Lin, H.S. Yu, and R.T.

Kuo, “An Expert System for Locating Distribution System Faults,

“IEEE Trans. on Power Delivery, Vol.5, No.2, April 1990, pp. 366-371.

[5] C.A. Protopapas, K.P. Psaltiras and A.V. Machias, “An Expert System

for Substation Fault Diagnosis and Alarm Processing, “IEEE Trans. on

Power Delivery, Vol.6, No.2, April 1991, pp. 648-655.

[6] F.S. Wen and C.S. Chang, “Probabilistic Approach for Fault-section

Estimation in Power Systems Based on a Refined Genetic Algorithm,

“IEE Proc.-Gener. Transm. Distrib., Vol.144, No.2, March 1997, pp.

160-168.

[7] F.S. Wen and C.S. Chang, “Tabu Search approach to Alarm

Processing in Power System, “IEE Proc.-Gener. Transm. Distrib.,

Vol.144, No.1, January 1997, pp. 31-38.


[8] Sonja Ebron, David L. Lubkeman, and Mark White, “A Neural

Network Approach to the Detection of Incipient Faults on Power

Distribution Feeders, “IEEE Trans. on Power Delivery, Vol.5, No.2,

April 1990, pp. 905-914.

[9] Edward H.P. Chan, “Using Neural Network to Interpret Multiple

Alarms, “IEEE Computer Application in Power, April 1990, pp.

33-37.

[10] H.T. Yang, W.Y. Chang, and C.L. Huang, “A New Neural Network

Approach to On-Line Fault Section Estimation Using Information of

Protective Relays and Circuit Breakers, “IEEE Trans. on Power Delivery,

Vol.9, No.1, January 1994, pp. 220-229.

[11] T. Dalstein, T. Friedrich, B. Kulicke and D. Sobajic, “Multi Neural

Network Based to Fault Area Estimation for High Speed Protective

Relaying, “IEEE Trans. on Power Delivery,Vol.11, No.2, April 1996, pp.

740-747.

[12] N. Kandial, V.K. Sood, K. Khorasani, and R.V. Patel, “Fault

Identification in An AC-DC Transmission System Using Neural

Networks, “IEEE Tran. on Power System, Vol.7, No.2, May 1992, pp.

812-819.

[13] T. Dalstein and B. Kulicke, “Neural Network Approach to

Fault Classification for High Speed Protective Relaying, “IEEE

Transaction on Power Delivery, Vol.10, No.2, April 1995,

pp.1002-1011.

[14] 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 Transaction

on Power Delivery, Vol.10, No.2, April 1995, pp. 697-706.


[15] D.V. Couty, and D.C. Jorge, “Artificial Neural Network Approach to

Distance Protection of Transmission Lines, “IEEE Transaction on

Power Delivery, Vol.13, No.1, January 1998, pp.102-108.

[16] T. 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.

[17] R.L. Jiang and Q.X. Lin, “A Neural Network Approach to

Alarm Processing of Power System in Mass Rapid Transit,

“Proceedings Of The 20TH Symposium On Electrical Power

Engineering, Taiwan, November 1999, pp. 1247-1251.

[18] 盧展南等，"配電自動化系統之控制架構研究"臺電工程月刊，

pp54-73, 1998。

[19] 鄭石洋，"變電所自動化設計手冊"臺電公司輸工處，民國80年

10月。

[20] "全面自動化調度控制第一期工程竣工報告"臺電公司電控會，民

國82年12月。

[21] 蕭一龍，"調度系統架構與設計"臺電公司，民國86年9月。

[22] "全面自動化調度控制第二期計劃可行性研究報告"臺電公司電

控會，民國78年4月。

[23] D.F. Specht, “Probabilistic Neural Network for Classification,

Mapping, or Associative Memory, ” Proc. IEEE Int. Conf.

Neural Network, San Diego, CA, Vol.1, July 1988, pp. 525-

532.

[24] K.H. Kim, J.K. Park, K.J. Hwang and S.H. Kim, “Implementation of

Hybrid Short-term Load Forecasting System Using Artificial Neural

Network and Fuzzy Expert systems ,” IEEE Trans. on Power

Systems, Vol. 10, No. 3, Aug. 1995, pp.1534-1539.

[25] A.G. Bakirtzis, J.B. Teocharis, S.J. Kiartzis and K.J. Satsios, “Short

Term Load Forecasting Using Fuzzy Neural Network ,” IEEE Trans.

on Power Systems, Vol. 10, No. 3, Aug. 1995, pp. 1518-1523.

[26] H.C. Kuo and Y.Y. Hsu, “Distribution System Load Estimation and

Service Restoration Using Fuzzy Set Approach ,” IEEE Trans. on

Power Delivery, Vol. 8, No. 4, Oct. 1993, pp. 1950-1957

[27] A. Ferrero, S. Sangiovanni and E. Zappitelli, “A Fuzzy-Set

Approach To Fault-Type Identification Digital Relaying ,” IEEE

Trans. on Power Delivery, Vol. 10, No. 1, Jan. 1995, pp. 169-175

[28] P. Jarventausta, P. Verho and J. Partanen, “Using Fuzzy Sets to

Model the Uncertainty in Fault Location Process of Distribution

Network ,” IEEE Trans. on Power Delivery, Vol. 9, No. 2, Apr.

1994, pp. 954-960

[29] 井上洋, 天笠美知夫，"模糊理論" 五南圖書出版有限公司，民國88

年。

[30] 徐揚,鄒開其，"模糊系統與專家系統" 儒林圖書有限公司，民國82年。

[31] Daniel McNeill, Paul Freiberger，"模糊邏輯"，民國84年。

[32] 蒙以正，" MATLAB 5 專業設計技巧 含SIMULINK, FUZZY及GUI

"，民國87年。

[33] 羅華強，" MATLAB5.3 SIMULINK3.0範例入門" 全華科技，民國89

年。