本論文提出一配電級油浸式變壓器油中氣體分析診斷系統，利用類神經網路之技術，達到判斷配電級變壓器正、異常之效果，其中類神經網路採用三種網路架構個別比較，倒傳遞網路架構、徑向基網路架構及機率神經網路架構，依據975筆資料進行網路架構設計，並以試誤法測試出最佳模型，以20筆故障資料及5982筆歷史資料做為測試資料，觀察三種網路架構之判斷結果，並做比較，其中倒傳遞網路架構經過適當的設計可達最佳之判斷效果，其次為徑向基網路架構，最後為機率神經網路架構，最後針對其判斷結果皆可達到96%的準確度，證明配電級油浸式變壓器油中氣體分析診斷系統為可行且準確的。

In this thesis, an oil-immersed distribution transformer dissolved gas analysis and diagnosis system are presented. The diagnosis adopts artificial neural network technique to evaluate the normality status of the oil-immersed type transformer. Three kinds of artificial neural network architectures, BPNN, RBFNN and PNN, were compared using 975 data, and then used trial and error method to find out the best model. After find out the best model using 20 data that is confirmed abnormal and 5892 historical data to observe and compare the ability of judgment along three kinds of network architectures. Test result discovers that the BPNN shows the best judgment accuracy, the next is RBFNN, the last is PNN. All three kinds show that their judgment accuracy are over 96%. Therefore, the feasible and accurate of the diagnosis system, ANN based on oil-immersed dissolved gas analysis are proved.

[1] 洪浡荏，「應用類神經網路於電力變壓器老化壽命損失估測」，國立台北科技大學電機工程系碩士學位論文，2010。
[2] M. Wang, A. J. Vandermaar, and K. D. Srivastava, “Review of Condition Assessment of
Power Transformers in Service, ” IEEE Transactions on Electrical Insulation, vol. 18,
pp.12-25, 2002.
[3] 胡立翔，「智慧型電力變壓器油中氣體診斷系統」，私立聖約翰科技大學電機工程系碩士學位論文，2012年7月。
[4] 顏志丞，「基於變壓器油中氣體分析之故障可信度研究及設備管理系統開發」，國立台北科技大學電機工程系碩士學位論文，2010。
[5] S. A. Ward, “Evaluating Transformer Condition Using DGA Oil Analysis,” IEEE
Transactions on Electrical Insulation and Dielectric Phenomena, pp.463-468, 2003.
[6] E. Chaidee and W. Tippachon, “Failure Statistics and Condition Evaluation for
Power Transformer Maintenance,” IEEE Transactions on Power and Energy
Engineering, pp.1-4, 2011.
[7] A. Setayeshmehr, A. Akbari, H. Borsi, and E. Gockenbach, “A Procedure for Diagnosis
and Condition based Maintenance for Power Transformers,” IEEE Transactions on
Electrical Insulation, pp.504-507, 2004.
[8] M. K. Pradhan and T. S. Ramu, “On the Estimation of Elapsed Life of Oil-immersed
Power Transformers,” IEEE Transaction on Power Delivery, vol. 20, pp.1962-1969,
2005.
[9] 台灣電力公司供電處，「供電單位變電設備維護手冊」，2002。
[10] J. L. Guardado, J. L. Naredo, P. Moreno, and C.R. Fuerte, “A Comparative Study of
Neural Network Efficiency in Power Transformers Diagnosis Using Dissolved Gas
Analysis,” IEEE Transactions on Power Delivery, vol. 16, pp.643-647, 2001.
[11] K. V. Satyanarayana, C. C. Reddy, T. P. Govindan, M. Mandlik, and T. S. Ramu,
“Application of Artificial Intelligence for the Assessment of the Status of Power
Transformers,” IEEE Transactions on Electrical Insulation, pp.104-107, 2008.
[12] M. R. Zaman, “Experimental Testing of the Artificial Neural Network Based
Protection of Power Transformers,” IEEE Transactions on Power Delivery, vol. 13,
pp. 510-517, 1998.
[13] Y. Zhang, X. Ding, Y. Liu, and P. J. Griffin, “An Artificial Neural Network Approach
to Transformer Fault Diagnosis,” IEEE Transactions on Power Delivery, vol. 11,
pp. 1836-1841, 1996.
[14] A. H. Zhou, H. Song, H. Xiao, and X. H. Zeng, “Power Transformer Fault Diagnosis
Based on Integrated of Rough Set Theory and Neural Network, ” IEEE Transactions
on Intelligent System Design and Engineering Application, pp. 1463-1465, 2012.
[15] K. I. Annapoorani, D. B. Umamaheswari, “Fault Prediction Based on Dissolved Gas
Concentration from Insulating Oil in Power Transformer Using Neural Network,”
IEEE Transactions on Properties and Applications of Dielectric Materials, pp.1-4,
2012.
[16] 林安志，「線上變壓器油中氣體監控診斷系統之研究」，私立崑山科技大學
電機工程系碩士學位論文，2003年6月。
[17] 大同公司，「電力變壓器簡介資料」，2012。
[18] 葛劍青，「變壓器檢修簡明手冊」，中國電子工業出版社，2008年9月。
[19] IEC Publication 60599, “Mineral Oil-impregnated Electrical Equipment in Service –
Guide to the Interpretation of Dissolved and Free Gases Analysis,” 2007.
[20] 台灣電力公司，「TPC絕緣油規範I-002」，2000。
[21] IEC Publication 60156, “Dielectric Breakdown Voltage Testing,” 1995.
[22] 童耀宗，「變壓器油取樣與油中氣體分析」，台電綜合研究所，2005年9月。
[23] IEEE Std. C57.104-1991, “IEEE Guide for the Interpretation of Gases Generated in
Oil-Immersed Transformers,” 1992.
[24] 「注油變壓器的維護管理」，日本電氣協同研究第54卷第5號，1992年2月。
[25] 錢旭曜，「變壓器油及相關故障診斷處裡技術」，中國電力出版社，2008年5月。
[26] E.Dornenburg and W.Strittmater, “Monitoring Oil Cooling Transformers by Gas Anysis, ” Brown Boveri Review,vol.61, pp.238-247, 1974.
[27] R.R.Roger, “IEEE and IEC Codes to Interpret Incipient Faults in Transformers, Using
Gas in Oil Analysis, ” IEEE Transactions on Electrical Insulation, pp.349-354, 1978.
[28] B. Falou, “ Detection of and Research for the Characteristics of an Incipient Fault
from Analysis of Dissovled Gas in the Oil of an Insulation, ” CIGRE Electra, no. 42,pp. 31-52, 1975.
[29] M. Duval, “A Review of Faults Detectable by Gas-in-oil Analysis in Transformers,”IEEE Transactions on Electrical Insulation, vol:18 , issue: 3, pp.8-17, 2002.
[30] C. Cortes and V. Vapnik, “Support-Vector Networks, ” Machine Learning, pp.1-31,1995.
[31] 葉怡成，「類神經網路之應用與實作」，儒林出版社，1999。
[32] 葉怡成，「以類神經網路預測混凝土非破壞檢測之抗壓強度」，中華工學院土木工程研究所碩士論文，1997。
[33] 羅華強，「類神經網路MATLAB的應用」，清蔚科技，2001年9月。
[34] 陳宗寶，「應用音射法於電力電纜之局部放電研究」，國立成功大學電機工程系碩士學位論文，2010年6月。
[35] 黃淑枝，「應用類神經網路預測材料聲阻抗之研究」，國立成功大學造船暨船舶機械工程研究所碩士學位論文，2003年6月。
[36] L. Zheng, W. Liu, and L. C. Lu, “Application of BP network based on free-weighting
on transformer fault diagnosis,” IEEE Transactions on Information Technology and Artificial Intelligence, pp.229-232, 2011.
[37] 陳榮志，「預測分析運用於訂購模式之研究－以A公司為例」，國立成功大學工學院工程管理系碩士學位論文，2008年6月。
[38] 李穆，「以徑向基底類神經網路建立簡立梁位移場之研究」，國立台灣科技大學營建工程系碩士學位論文，2009年6月。
[39] A. Li, X. Y. Sun, and D. H. Liu, “Application of RBF Network with Ant Colony and
Fisher Ratio to Fault Diagnosis of Oil-Immersed Transformer,” IEEE Transactions on
Natural Computation, pp.549-551, 2011.
[40] S. Seifeddine, B. Khmais, and C. Abdelkader, “Power transformer fault diagnosis
based on dissolved gas analysis by artificial neural network,” IEEE Transactions on
Renewable Energies and Vehicular Technology, pp.230-236, 2012.
[41] 曹銘介，「應用-小波機率神經網路於電力品質及特定諧波偵測之研究」，國立中山大學電機工程學系碩士學位論文，2004年6月。
[42] S. Li, X. Y. Li, and W. X. Wong, “Fault Diagnosis of Transformer Based on Probabilistic Neural Network,” IEEE Transactions on Intelligent Computation
Technology and Automation, pp.128-131, 2011,.
[43] Q. F. Niu, L. Wang, and V. P. Shi, “Realization of a Power Transformer on-line Monitoring and Diagnosis System Based on DGA and PNN,” IEEE Transactions on Computer, Mechatronics, Control and Electronic Engineering pp.210-213, 2010.
[44] 方世榮，「基礎統計學三版」，華泰文化，2008年6月。