臺灣博碩士論文加值系統

大型電力變壓器是電力系統中最重要且昂貴的設備之一，其運作狀態將直接影響電力系統的安全，變壓器故障可能導致電源中斷及利潤損失，因此，盡早檢測出變壓器初期故障，達到減少及預防後續問題即能提高電力系統之可靠性。本文選用變壓器油中溶解氣體進行故障診斷，溶解氣體的數值將為變壓器內部隱患提供了間接的重要依據，溶解氣體分析(Dissolved Gas Analysis, DGA)是用於診斷變壓器初期故障最受歡迎及最有效的方法，由於氣體數據及操作的可變性，利用傳統方法識別變壓器故障特徵並不容易。因此，本文應用倒傳遞類神經網路(Back-Propagation Neural Network, BPNN)進行訓練及測試，以提高系統診斷效率及準確性。
實驗結果證明，應用倒傳遞類神經網路辨識變壓器故障與傳統IEC比值法相較之下，可以提升約40%的準確率，不但可補足傳統IEC比值法的誤判，也證明了此方法可以在變壓器初期故障檢測的可靠性。

The large power transformer is one of the most important and expensive equipment in the power system. The operating situation of transformer will directly affect the safety of the power system, and the fault of the transformer may cause the power interruption and the profit loss. Therefore, early detection of the initial fault of transformers, reduction and prevention of the fault can improve the reliability of power system.In this paper, we use the dissolved gas in transformer oil for fault diagnosis. The data of dissolved gas will provide an indirect basis for the internal hidden trouble of transformers. Dissolved Gas Analysis (DGA) is the most popular and effective method for diagnosing transformer’s initial failure; however, due to the variability of gas data and operation, it is not easy to identify the characteristic of transformer’s fault by traditional methods. Therefore, in this paper, we used the algorithm of BP (Back-Propagation BP) neural network to train and test to improve the efficiency and accuracy of system diagnosis.
The experimental results show that, using BP neural network to identify the transformer fault can improve the accuracy of about 40% than the traditional IEC ratio method, which can not only make up the error of traditional IEC ratio method, but also prove the reliability of this method in the initial fault detection of the transformer.

摘 要……………………………………………………………………………… i
Abstract……………………………………………………………...…………… ii
誌 謝……………………………………………………………………………... iii
目 錄……………………………………………………………………………... iv
圖目錄……………………………………………………………………………. vi
表目錄…………………………………………………………………………… vii
第一章 緒論……………………………………………………………………… 1
1.1 研究背景與動機…………………………………………………… 1
1.2 研究目的與方法…………………………………………………… 4
1.3 國內外文獻探討…………………………………………………… 5
1.4 論文架構…………………………………………………………… 7
第二章 變壓器油中氣體分析及故障診斷……………………………………… 8
2.1 前言…………………………………………………………………. 8
2.2 變壓器故障分析…………………………………………………... 10
2.3 變壓器故障原因與型式…………………………………………... 12
2.4 溶解氣體分析…………….……………………………………….. 18
第三章 類神經網路介紹……………………………………………………….. 27
3.1 類神經網路介紹…………………………………………………... 27
3.2 倒傳遞類神經網路………………………………………………... 29
第四章 實驗方法及結果……………………………………………………….. 33
4.1 實驗方法…………………………………………………………... 33
4.2 實驗結果…………………………………………………………... 38
第五章 結論及未來展望……………………………………………………….. 64
5.1 結論………………………………………………………………... 64
5.2 未來展望…………………………………………………………... 65
參考文獻………………………………………………………………………… 66
附錄……………………………………………………………………………… 70

[1] 台灣電力公司網站資料參考網址: https://www.taipower.com.tw。
[2] T. Bhavani Shanker, H. N. Nagamani, Deepthi Antony, Gururaj S Punekar, “Case studies on transformer fault diagnosis using dissolved gas analysis” IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), pp.1-3, 2017.
[3] Jawad Faiz, Milad Soleimani, “Dissolved gas analysis evaluation in electric power transformers using conventional methods a review” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 11, No. 10, pp.1239-1248, 2017.
[4] Ibrahim B. M. Taha, Diaa-Eldin A. Mansour, Sherif S. M. Ghoneim, Nagy I. Elkalashy, “Conditional probability-based interpretation of dissolved gas analysis for transformer incipient faults” IET Generation, Transmission & Distribution, Vol. 11, No. 4, 2017.
[5] R. R. Rogers, “IEEE and IEC Codes to Interpret Incipient Faults in Transformers, Using Gas in Oil Analysis” IEEE Transactions on Electrical Insulation, Vol. EI-13, No. 5, 1978.
[6] Ibrahim B. M. Taha, Sherif S. M. Ghoneim, Abdulaziz. S. A. Duaywah, “Refining DGA methods of IEC Code and Rogers four ratios for transformer fault diagnosis” IEEE Power and Energy Society General Meeting (PESGM), pp. 1-5, 2016
[7] 童耀宗，變壓器油中氣體分析診斷，台電公司訓練所講義，93年01月。
[8] A. Kumar, H. A. Vidya, G. Balagopal Reddy, “Modified fuzzy logic technique for power transformer fault prediction”, International Conference on Smart grids, Power and Advanced Control Engineering (ICSPACE), pp.338-343, 2017.
[9] R N Patel, H S Thakur, “Integrated fuzzy approach for incipient fault detection in power transformers”, Industrial Electronics and Applications Conference (IEACon), 2016 IEEE.
[10] Masoud Noori, Reza Effatnejad, Payman Hajihosseini, “Using dissolved gas analysis results to detect and isolate the internal faults of power transformers by applying a fuzzy logic method”, IET Generation, Transmission & Distribution. Vol. 11, No. 10, pp.2721-2729, 2017.
[11] Maria-Cristina Nitu, Ancuta-Mihaela Aciu, Claudiu-Ionel Nicola, “Power transformer fault diagnosis using fuzzy logic technique based on dissolved gas analysis and furan analysis”, OPTIM&ACEMP, 2017 Conf.
[12] 葉元彰，應用模糊理論於油浸式電力變壓器故障診斷，國立彰化師範大學電機工程學系，碩士論文，民國99年。
[13] Mohammad Ali Akhtar Siddique, Shabana Mehfuz, “Artificial neural networks based incipient fault diagnosis for power transformers”, IEEE India Conference (INDICON), pp.1-6, 2015.
[14] Kavya Venugopal, Phalgun Madhusudan, A. Amrutha, “Artificial neural network based fault prediction framework for transformers in power systems”, International Conference on Computing Methodologies and Communication (ICCMC), pp.520-523, 2017.
[15] Tapsi Nagpal, Yadwinder Singh Brar, “Neural network based transformer incipient fault detection”, International Conference on Advances in Electrical Engineering (ICAEE), pp.1-5, 2014.


[16] Wei-Song Lin, Chin-Pao Hung, Mang-Hui Wang, “CMAC-based fault diagnosis of power transformers”, Neural Networks, IJCNN '02. Proceedings of the 2002 International Joint Conference on USA.
[17] Yan Luo, Yuanbin Hou, Gaiye Liu, Changying Tang, “Transformer fault diagnosis method based on QIA optimization BP neural network”, IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pp. 1623-1626, 2017.
[18] Sherif S.M. Ghoneim, Ibrahim B.M. Taha, and Nagy I. Elkalashy, “Integrated ANN-Based Proactive Fault Diagnostic Scheme for Power Transformer Using Dissolved Gas Analysis”, IEEE Trans. Dielectr. Electr. Insul, Vol. 23, pp. 1838-1845, 2016.
[19] 李瑞璋，“油浸電力變壓器之壽命評估”(台北城市科技大學碩士論文)，民國103年。
[20] 羅華強，“類神經網路-MATLAB的應用”,高立圖書有限公司, 2005年。
[21] 周鵬程，“類神經網路入門-活用MATLAB”，全華科技圖書股份有限公司，2002年。
[22] 台灣電力公司“異常變壓器故障型態調查研究期末報告”，台灣電力公司八十三年度研究發展專題，民國83年9月。
[23] 台灣電力公司，“供電單位變電設備維護手冊”，民國98年。
[24] Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale, Orlando De Jesús, “Neural Network Design, 2/e”, 2014.

[25] Yu Heqi, Chen Chang zheng, Zhang Sheng, “Intelligent diagnosis Based on neural network. Beijing: Metallurgical Industry Press, 2000.