目前電力輸配系統現有維修保養模式，多屬於事故後維修，故無法即時反應電力變壓器之設備狀態給維修保養人員並採取適合的對應措施。由於事故後維修為採用被動的方式監控變壓器狀態，因此容易造成不可挽回的設備毀壞或龐大的財務損失。本研究則針對電力輸配系統中之核心設備─電力變壓器，利用即時監控設備收集實際於台灣與澳洲兩國運轉中的電力變壓器資訊，以探討電力變壓器整體健康狀況所帶來的影響。在所收集的資訊中有許多訊息，包含油品、油溫、油中溶解氣體含量、糠醛含量、電器與設備位置等關於變壓器的訊息，而本研究以探討電應力與熱應力所造成之故障為研究目的，故從所收集的眾多資訊中擷取九種油中溶解氣體含量為故障診斷因子，並先透過主成份分析法找出影響電力變壓器設備健康狀態的關鍵因子。另外，本研究將開發故障診斷平台並將倒傳遞類神經網路演算法導入其中，而將透過主成份分析法所擷取出的關鍵因子則作為倒傳遞類神經網路之輸入因子，以建立即時故障診斷模型，設備管理者或維修保養人員則可透過故障診斷平台即時獲取電力變壓器之健康狀況。依據故障診斷平台所提供之電力變壓器之健康資訊，則能夠提供足夠且彈性的時間制定最合適的維修保養活動，並降低設備損壞之機率或因為嚴重故障而產生的額外成本。

he traditional maintenance activities in the power transmission and distribution system are usually based on post-accident repairs and periodic maintenance. Thus the maintenance personnel cannot immediately know the health status of transformers and take appropriate reactive measures. Monitoring the status of transformers passively can cause irreparable equipment destruction or huge financial loss. In view of this, this research uses the real-time monitoring equipment to collect the empirical data of operational transformers of Taiwan and Australia and analyzes the impact of the overall health status of transformers. The dataset of transformer from Taiwan and Australia contains much information, such as quality of the oil, the oil temperature, dissolved gas contents, furfural contents, electrical appliances and equipment position. However, this research focuses on the transformer failures which results from electrical stress and thermal stress. We extract nine kinds of dissolved gas contents (i.e. O2, H2, N2, CO2, CO, CH4, C2H6, C2H4 and C2H2) to diagnose the health status of transformers and identify the key factors which affect the health status of transformers by Principal component analysis. In addition, this research develops a fault diagnosis platform and embeds Principal Component Analysis (PCA) and Back-Propagation Artificial Neural Network (BP-ANN) into the platform. The key factors extracted by PCA are put into the fault diagnosis platform as input and a fault diagnosis model is established. The fault diagnosis model can help equipment owners, maintenance personnel or relevant units acquire the information of transformers immediately. The instant information provides adequate and flexible time for relevant units to develop the most appropriate maintenance strategy which can reduce the probability of transformer failure and extra cost by a serious fault.

1. Arshad, M., Islam S. M. and Khaliq A., 2004, “Power Transformer Asset Management,” Power System Technology, November 21-24, Singapore, China, Vol. 2, pp. 1395 - 1398.
2. Abu-Elanien, A. E.B. and Salama, M.M.A., 2010, “Asset management techniques for transformers,” Electric Power Systems Research, Vol. 80, Issue 4, pp. 456-464.
3. Booth, C. and McDonald, J.R., 1998, “The use of artificial neural networks for condition monitoring of electrical power transformers,” Neurocomputing, Vol. 23, Issue 1-3, pp. 97-109.
4. Bhalla D., Bansal R.K. and Gupta H.O., 2012, “Function analysis based rule extraction from artificial neural networks for transformer incipient fault diagnosis,” Electrical Power and Energy Systems, Vol. 43, Issue 1, pp. 1196-1203.
5. Cybenko, G., 1989, “Approximation by superpositions of a sigmoidal function,” Mathematical Control, Signals, and Systems, Vol. 5, No. 4, pp. 303-314.
6. Chelbi, A. and Ait-Kadi, D., 2004, “Analysis of a production/inventory system with randomly failing production unit submitted to regular preventive maintenance,” European Journal of Operational Research, Vol. 156, Issue 3, pp. 712-718.
7. Chen, C., Brown, D., Sconyers, C., Zhang, B., Vachtsevanos G. and Orchard, M.E., 2012, “An integrated architecture for fault diagnosis and failure prognosis of complex engineering systems,” Expert Systems with Applications, Vol. 39, Issue 10, pp.9031-9040.
8. Dou, D., Yang, J., Liu, J. and Zhao, Y., 2012, “A rule-based intelligent method for fault diagnosis of rotating machinery,” Knowledge-Based Systems, Vol. 36, pp. 1-8.
9. Dunstan, N., 2008, “Generating domain-specific web-based expert systems,” Expert Systems with Applications, Vol. 35, Issue 3, pp.686-690.
10. Fu, Z. Xu, F. Zhou, Y. and Zhang, X.S., 2005, “Pig-vet: a web-based expert system for pig disease diagnosis,” Expert Systems with Applications, Vol. 29, Issue 1, pp. 93-103.
11. Fei, S.W. and Zhang, X.B., 2009, “Fault diagnosis of power transformer based on support vector machine with genetic algorithm,” Expert Systems with Applications, Volume 36, Issue 8, pp. 11352-11357.
12. Ghunem, R.A., El- Hag, A.H. and Assaleh, K., 2010, “Prediction of furan content in transformer oil using Artificial Neural Networks (ANN),” IEEE International Symposium on Electrical Insulation (ISEI), San Diego, CA, USA, June 6-9, pp. 1-4.
13. Hotelling, H., 1933. “Analysis of a complex of statistical variables into principal components, Journal of Educational Psychology, Vol. 24, pp. 417-441 and 498-520.
14. Hebb, D., 1949, “The organization of behavior”, Wiley.
15. Hornik, K., Stinchcombe, M., and White, H., 1989, “Multi-layer feedforward networks are universal approximations,” Neural Networks, Vol. 2, No. 5, pp. 359-366.
16. Hair, J., Anderson, R., Tathan, R., and Black, W., 1998, Multivariate Data Analysis, Macmillan, NJ.
17. Hastings, N.A.J., 2010, Physical Asset Management, Springer.
18. Hwang, G.J., Chen, C.Y., Tsai, P.S. and Tsai, C.C., 2011, “An expert system for improving web-based problem-solving ability of students,” Expert Systems with Applications, Vol. 38, Issue 7, pp. 8664-8672.
19. International Electrotechnical Commission, 2007, “IEC 60599 Ed. 2.1 b: 2007 Mineral oil-impregnated electrical equipment in service - Guide to the interpretation of dissolved and free gases analysis,” May 15.
20. Institute of Electrical and Electronics Engineers, 2009, “C57.104-2008 IEEE Guide for the interpretation of gases generated in oil-Immersed transformers,” February 2, pp. 1-27.
21. Li, J. and Shen, S.T., 2007, “Research on the Algorithm of Avionic Device Fault Diagnosis Based on Fuzzy Expert System,” Chinese Journal of Aeronautics, Vol. 20, Issue 3, pp. 223-229.
22. Lu, K.Y. and Sy, C.C., 2009, “A real-time decision-making of maintenance using fuzzy agent,” Expert Systems with Applications, Vol. 36, Issue 2, pp.2691-2698.
23. Mohamed, E.A., Abdelaziz, A.Y. and Mostafa, A.S., 2005, “A neural network-based scheme for fault diagnosis of power transformers,” Electric Power Systems Research, Vol. 75, Issue 1, pp. 29-39.
24. Ma, L., 2007, “Condition Monitoring in Engineering Asset Management,” Asia-Pacific Vibration Conference (APVC), August 6-9, Sapporo, Japan, 1-16.
25. Pearson, K., 1901, “On lines and planes of closest fit to systems of points in space,” Philosophical Magazine, Vol. 2, No. 6, pp. 559-572.
26. PAS 55-1 and -2: Asset Management: Specification for the optimized management of physical infrastructure asset, 2004, British Standards Institution, UK.
27. PAS 55-1: Asset Management: Specification for the optimized management of physical assets, 2008, British Standards Institution, UK.
28. Rosenblatt, F., 1957, “The Perceptron: A perceiving and recognizing automaton,” Technical Report, No. 85-460-1.
29. Rumelhart, D.E., Hinton, G.E., and Williams, R.J., 1986, “Learning internal representations by error propagation,” Parallel Distributed Processing: Explorations in Microstructure of Cognition, Vol. 1, pp. 318-363.
30. Roberts C., Dassanayake, H.P.B., Lehrasab, N. and Goodman, C.J., 2002, “Distributed quantitative and qualitative fault diagnosis: Railway junction case study,” Control Engineering Practice, Vol. 10, Issue 4, pp. 419-429.
31. Su, K.W., Hwang, S.L. and Liu T.H., 2000, “Knowledge architecture and framework design for preventing human error in maintenance tasks,” Expert Systems with Applications, Vol. 19, No. 3, pp. 219-228.
32. Sun, Y.J, Zhang S., Miao, C.X. and Li J.M., 2007, “Improved BP Neural Network for Transformer Fault Diagnosis,” Journal of China University of Mining and Technology, Vol. 17, Issue 1, pp. 138-142.
33. Sakthivel,N.R., Sugumaran,V. andNair, B.B., 2009, “Comparison of decision tree-fuzzy and rough set-fuzzy methods for fault categorization of mono-block centrifugal pump,” Mechanical Systems and Signal Processing, Vol. 24, Issue 6, pp. 1887-1906.
34. Tseng, D.C., Chung, I.L., Tsai, P.L. and Chou, C.M., 2011, “Detect classification for LCD color filters using neural-network decision tree classifier,” International Journal of Innovative Computing, Information and Control (ICIC 2011), Vol. 7, No. 7, pp. 3695-3707.
35. Trappey, A.J.C., Trappey, C.V., Sun, Y., Ma, L., and Chen, K.J., 2012, “A group method of data handling for oil-immersed transformer life cycle assessment,” 2012 International Conference on Advanced Manufacture (ICAM 2012), March 4-8, 2012, Jiaoxi, Yilan County, Taiwan.
36. Upadhyaya, B.R., ZHAO, K. and Lu B., 2003, “Fault monitoring of nuclear power plant sensors and field devices,” Progress in Nuclear Energy, Vol.43. No. 1-4, pp.337-342.
37. Wang, S., Zhou, Q. and Xiao, F., 2010, “A system-level fault detection and diagnosis strategy for HVAC systems involving sensor faults,” Energy and Buildings, Vol. 42, Issue 4, pp. 477-490.
38. Widrow, B., 1962, "Generalization and information storage in networks of adaline neurons,” Self-organizing Systems, pp. 435-461.
39. Werbos, P., 1974, “The roots of backpropagation,” Wiley Interscience, Canada.
40. Waeyenbergh, G., Pintelon, L., 2002, “A framework for maintenance concept development,” int.J.Production Economics, Vol. 77, Issue 3, pp. 299-313.
41. Wu, J.D., Chiang, P.H., Chang, Y.W. and Shias, Y.J., 2008, “An expert system for fault diagnosis in internal combustion engines using probability neural network,” Expert Systems with Applications, Vol. 34, Issue 4, pp. 2704-2713.
42. Xiao, F., Wang, S., Xu, X. and Ge, G., 2009, “An isolation enhanced PCA method with expert-based multivariate decoupling for sensor FDD in air-conditioning systems,” Applied Thermal Engineering, Vol. 29, Issue 4, pp. 712-722.
43. Yan, T., Cui, D. and Tao, Y., 2007, “A New Evolutionary Neural Network Algorithm Based on Improved Genetic Algorithm and its Application in Power Transformer Fault Diagnosis,” International Conference on Bio-Inspired Computing: Theories and Applications, September 14-17, China, pp. 1-5.
44. Zurada, J.M., 1992, “Introduction to Artificial Neural Systems,” West Publishing Company, Minnesota.
45. Zhang, G., Patuwo, B.E., and Hu, M.Y., 1998, “Forecasting with artificial neural networks: the state of the art,” International Journal of Forecasting, Vol. 14, No. 1, pp. 35-62.
46. Zheng X., 2008, “Intelligent Fault Diagnosis of Power Transformer based on Fuzzy Logic and Rough Set Theory,” 7th World Conference on Intelligent Control and Automation (WCICA), June 22-27, Chongqing, China, pp.6858-6862.
47. Zhao, J., Zheng, R. and Li, J., 2009, “Transformer Fault Diagnosis Based on Homotopy BP Algorithm,” International Conference on Electronic Measurement and Instruments (ICEMI 2009), August 16-19, Dalian, China, pp. 4622-4626.
48. 傅粹馨，2002，「主成份分析和共同因素分析相關議題之探究」，教育與社會研究期刊，第三期，pp. 107-131。
49. 倪煒均，2009，「協同維修鏈之協商策略研究及多代理人為基之平台設計與發展」，碩士論文（指導教授：張瑞芬），國立清華大學工業工程與工程管理學系。
50. 林煜亮，「變壓器之生命週期」，電機月刊，第12卷第4期，2002年4月號，pp. 158-170。
51. 林建民及陳俊瑜，「以本質較安全設計探討油浸式變壓器危害預防」，2007年12月，第15卷第4期，pp. 380-398。
52. 李宗祐，2007，「應用階層式檢查生成法則發展於故障診斷諮詢系統-以半導體研磨液供應系統之幫浦故障為例」，碩士論文（指導教授：蔡長鈞），國立成功大學工業與資訊管理系。
53. 林啟瑋，2009，「以主成份分析及類神經網路為基之專利重要性評估方法論」，碩士論文（指導教授：張瑞芬），國立台北科技大學工業工程與管理學系。
54. 劉至中，2012，「石化工業區空氣中揮發性有機物與含硫異味物質季節變化趨勢及汙染源排放特徵之相關性分析」，碩士論文（指導教授：袁中新），國立中山大學環境工程研究所。
55. 蕭維承，2008，「以代理人為核心之工程資產管理維修鏈整合研究」，博士論文（指導教授：張瑞芬及馬林），國立清華大學工業工程與工程管理學系。
56. 周政宏，1995，「類神經網路-理論與實務」，松崗電腦圖書資料股份有限公司。
57. 周文賢，2002，「多變量統計分析」，智勝文化事業有限公司。
58. 張斐章、張麗秋及黃浩倫，2003，「類神經網路 : 理論與實務」，臺灣東華書局。
59. 鄭達才，2000，「設備維護管理：現在與未來」，中國生產力中心。
60. 鄭又新，2007，「仿蟻群聚最佳化神經網路於非線性迴歸之初步探討」，碩士論文（指導教授：張江南），國立中央大學光機電工程研究所。
61. 陳彥廷，2006，「主成份分析法在制定多變量製程能力指標上之應用研究」，碩士論文（指導教授：潘浙楠），國立成功大學統計學研究所。
62. 陳冠儒，2011，「以即時監控資訊為基之變壓器智慧維護保養建議平台-以油浸式變壓器為例」，碩士論文（指導教授：張瑞芬），國立台北科技大學工業工程與管理研究所。
63. 蔡瑞煌，1985，「類神經網路概論」，三民書局。
64. 蔡木村，2001，「電工材料認知」。
65. 蔡明勳，2003，「電力變壓器故障偵測與協波分析」，碩士論文（指導教授：林惠民），國立中山大學電機功能學系。
66. 曹菀婷，2012，「以邏輯斯模型為基之工程資產壽期預測方法及系統平台
-以油浸式變壓器為例」，碩士論文（指導教授：張瑞芬及張力元），國立清華大學工業工程與工程管理學系。
67. 葉怡成，2003，「類神經網路模式應用與實作」，儒林圖書有限公司。
68. 揚智宇，2011，「希爾伯特-黃變換結合主成份分析與類神經網路在齒輪故障程度之診斷」，碩士論文（指導教授：吳天堯及黃衍任），國立中央大學機械工程學系。
69. 吳明隆，1999年，「SPSS 統計應用實務」，松崗電腦圖書資料股份有限公司。
70. 王珍貴，2007，「應用類神經網路模式模擬颱風降雨量」，碩士論文（指導教授：周乃昉），國立成功大學水利及海洋研究所。
71. 台灣電力公司全球資訊網站，2012，http://www.taipower.com.tw/。