本論文提出以可拓方法結合混沌理論應用於三相同步發電機之故障診斷，參考國際電機電子協會相關文獻統計，以最常發生的事故作為故障類型的分類，包含碳刷故障、三相不平衡與絕緣劣化等進行故障診斷。藉由示波器針對每一種類進行電壓及電流訊號的量測與擷取，並用Matlab撰寫混沌同步檢測演算程式，再將量測到的訊號透過混沌同步檢測運算產生混沌誤差散佈圖，以獲得各類故障種類之混沌眼座標特徵，再以可拓診斷方法診斷三相同步發電機的故障狀況。本方法經由實測分析結果顯示，其診斷之平均準確率達100％，此外在加入±10％雜訊量時，仍可達74%之準確率。本研究所提出之方法除可有效辨識三相同步發電機之故障類型外，可大幅減少特徵擷取資料量，更能有效地檢測訊號的微小變動，即時監測三相同步發電機之運轉狀態。

This thesis proposes a fault diagnosis method based on the extension method combined with the chaos theory to applied in the three-phase synchronous generator. Firstly, according to the related statistics of the Institute of Electrical and Electronics Engineers (IEEE), the most common accident is used for the classification of fault types, including carbon brush failure, three-phase imbalance and insulation degradation. The signals of the fault types were measured by a high frequency oscilloscope, and use Matlab to write chaos synchronization detection algorithm to obtain the Chaotic eye features of the fault type. Second, the X-Y coordinates of the Chaotic eyes were used as the clustering features for fault diagnosis, and used the extension daignosis method to diagnose the fault type of three-phase synchronous generators. The results of this proposed method show that the average accuracy of the diagnosis is 100%, and the accuracy is still 74% when ± 10% of the amount of noise is added. The proposed method can greatly reduce the amount of features extraction data, and more effectively detect the small changes of the fault's signal, which can be used the real-time monitoring tool of the three-phase synchronous generator.

中文摘要 I
Abstract II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
符號說明 IX
第一章緒論 1
1. 1 研究動機 1
1. 2 文獻回顧 6
1. 3 論文架構 7
第二章同步發電機故障診斷系統架構 9
2. 1三相同步發電機故障診斷系統架構 9
2. 2正常三相同步發電機 11
2. 3碳刷故障之三相同步發電機 13
2. 4三相不平衡發電同步發電機 15
2. 5絕緣劣化三相同步發電機 17
第三章系統診斷方法 20
3. 1混沌理論 21
3.1.1羅倫茲主僕系統 21
3.1.2混沌眼特徵擷取 22
3. 2本文所提診斷方法 23
3.2.1 可拓理論 24
3.2.2可拓診斷方法 25
3. 3倒傳遞類神經演算法 33
3.3.1 架構設定 34
第四章實測結果與討論 38
4.1人機介面功能 38
4.1.1電壓與電流數據讀取 38
4.1.2數據讀取 39
4.1.3混沌圖計算與顯示 40
4.1.4故障辨識診斷 40
4. 2發電機故障類別診斷之實測結果 41
4. 3故障類別辨識之實測結果 48
第五章三相同步發電機實驗結論及未來展望 52
5. 1實驗結論 52
5. 2 未來展望 53
參考文獻 54

[1]G. Shiwei, L. Mingyuan, “Motor Bearing Fault online Diagnostic Technology Research, Engineering Science and Education Journal, ” vol, 12, No. 1, pp. 001 - 007, 2015.
[2]J. Ortega, J.Bigun, and D. Reynolds, “Authentication Gets Personal with Biometrics,” IEEE Signal Processing Magazine, pp. 50 - 62, March, 2004.
[3]S. w. Li, “Fault Diagnosis and Analysis of Three-Phase PermanentSynchronous Machine,” ANSYS Pervasive Engineering Simulation，Vol 22, pp. 001 - 006, October, 2010.
[4]周俊宏，機械設備故障診斷與監測系統簡介，機械工業雜誌， 2008年303期 pp.25-28。
[5]固也泰電子工業有限公司，技術部，「同步發電機概述」，發電機研習網，高雄，2014
[6]台電綜合研究所吳立成，發電機失磁保護數位模擬與分析，電驛協會會刊，2016年30期 pp.20-26。
[7]C. Ye, M. T. Coimbra, and B. V. K. Vijaya Kumar, “Investigation of Human Identification using Two-Lead Electrocardiogram (ECG) Signals, ” Biometrics: Theory Applications and Systems (BTAS), pp. 1-8, Sept., 2010.
[8]M. Salah, K. Bacha, A. Chaari, M. H. Benbouzid, “Brushless Three-Phase Synchronous Generator Under Rotating Diode Failure Conditions, ”IEEE Transactions on Energy Conversion, vol 29, pp. 594 - 601, 2014.
[9]W. Shuting, L. Luyong, L. Qing, X. Yan, Li. Heming, “A Virtual Instrument for the Rotor Winding Inter-Turn Short Circuit fault of Generator, ” 2006 International Conference on Power System Technology, pp. 1510-1109, 2004.
[10]Z. h. Chen, R. j. Xu, Z. g.Ma, “Design of a Fault Diagnosis System for Diesel Engine Generators, ”Journal of Taiwan Society of Na al Architects and Marine Engineers, Vol.24, No.3, pp. 143 - 152, 2005
[11]卜華穎，陳鴻誠，應用離散分數階傅立葉轉換於感應電動機故障診斷，國立勤益科技大學，碩士論文，2015。
[12]Z.X. Gau, Y. J.Siao, ”A Study of Ontology-Based Fault Detection and Diagnostic System for Wind Turbine, ” Taipei, Taiwan, 2010.
[13]M. T. Tsai, C. L. Chu, Y. Y. Sie, B J. Jiang, “Investigation of The Ability For Three-Phase Three-LEVEL Unity Power Factor Rectifier To Unbalance Loads And Unequal Bus Voltages Requirements, ”Journal of Technology, vol. 30, pp. 319 - 330 2015.
[14]Y. C. Huang, H. Q. Sun, H. G. Lu, “Research on Fault Diagnosis of Steam Turbine Generator, ”Journal of Taiwan Society of Na al Architects and Marine Engineers, vol.24, No.3, pp. 143 - 152, 2005.
[15]固也泰電子工業有限公司,技術部,同步發電機不對稱運轉，發電機研習網，2014年6月。
[16]J. Ortega, J.Bigun, and D. Reynolds, “Authentication Gets Personal with Biometrics, ”IEEE Signal Processing Magazine, Vol. 21, pp. 50 – 62, 2004.
[17]J. Tian, and Y. Peng, “Research of the Matlab Application in the Fingerprint Identification System, ” Image Analysis and Signal Processing (IASP), pp. 1-5, Nov.2012.
[18]C.H. Huang, C. H. Lin, and C. L. Kuo, “Chaos Synchronization-Based Detector for Power-Quality Disturbances Classification in a Power System, ”IEEE Transactions on Power Delivery, vol. 26, Issue. 2, pp. 944 - 953, Dec. 2010.
[19]H. T.Yau, and M. H. Wang, “Chaotic Eye-Based Fault Forecasting Method for Wind Power Systems, ”IET Renewable Power Generation, vol. 9, Issue. 6, pp. 593 - 599, Oct. 2015.
[20]K. Park, B. Cho, D. Lee, S. Song, J. Lee, Y. Chee, I. Kim, and S. Kim, “Hierarchical Support Vector Machine Based Heartbeat Classification using Higher Order Statistics and Hermite Basis Function,” Computers in Cardiology, pp. 229 - 232, Sep., 2008.
[21]M. Llamedo and J. P. Martinez, “An ECG classification Model Based on Multilead Wavelet Transform Features,” Computers in Cardiology, vol. 34, pp. 105 - 108, 2007.
[22]R. Silipo, W. Zong , and M. Berthold, “ECG Feature Relevance in a Fuzzy Arrhythmia Classifier,” Computers in Cardiology, pp. 679 - 682, 1999.
[23]蔡文，楊春燕，林偉初，「可拓工程方法」，全華科技圖書股份有限公司出版，2001年4月。
[24]M. H. Wang, “Application of extension theory to vibration fault diagnosis of generator sets,” IEE Proceedings-Generation, Transmission and Distribution, vol. 151, no. 4, pp. 503–508, 2004.
[25]M. H. Wang, H. T. Yau, T. Y. Wang, “Extension Sliding Mode Controller for Maximum Power Point Tracking of Hydrogen Fuel Cells,” Abstract and Applied Analysis, June 2013.
[26]T. Zhaiwei, C. Yunxiu, Z. Qiugui, C. Yuping, “Prediction of Shear Strength of Reinforced Concrete Deep Beams Using Multi - layer Reverse Transfer - Type Neural Network, ” Journal of the Chinese Institute of Civil and Hydraulic Engineering, vol. 23, No. 1, pp. 41 - 54, 2011
[27]H. C. Chen, Z. I. Lin, “Evaluation of the Deterioration State of Insulating Oil in Oil - in –Water Transformer, ”The 12th Intelligent Living Technology Conference (ILT2017), vol 1,pp. 556 - 561, 2017.
[28]L. M. Huang, W. J. Gu, “Application of Back-Propagation Neural Network on thePrediction of PM10, ” Journal of Soil and Water Conservation, vol 44, pp. 341 - 360, 2012.
[29]N. Duran, M. Çatak, M. E. Ozbek," Image enhancement using fuzzy c-means clustering based on local population balance modeling",2013 21st Signal Processing and Communications Applications Conference (SIU),vol 2, pp. 1 - 4, 2013.
[30]P. P. Dash and M. Kazerani, “Dynamic Modeling and Performance Analysis of a Grid-connected Current-Source Inverter-Based Photovoltaic System,” IEEE Trans. Sustain. Energy, vol. 2, no. 4, pp. 443 - 450, Oct., 2011.
[31]M. Jafari, Z. Malekjamshidi, L. Li, G. Z. Jian, “Performance Analysis of Full Bridge, Boost Half Bridge and Half Bridge Topologies for Application in Phase Shift Converters,” IEEE Conference Publications, pp. 1589 - 1595, 2013.
[32]P. N. Enjeti, W. Shireen, “A New Technique to Reject DC-Link Voltage Ripple for Inverters Operating on Programmed PWM Waveforms,” IEEE Trans on Power Electron, vol.7, pp. 171-180, Jan 1992.
[33]N. M. Abdel-Rahim, E. Quaicoe, “A Single-Phase Delta-Moddeated Inverter for UPS Applications,” IEEE Transactions on Power Electronics, vol. 40, no. 3, pp. 347 - 354, June 1995.
[34]Valentine, Richard, Motor Control Electronics Handbook, New York: McGraw-Hill, 1998.
[35]Y. Tan, W. H. Moase, C. Manzie, D. Neši´c, and I. Mareels, “Extremum Seeking from 1922 to 2010,” in Proc. 29th Chin. Control Conf., Beijing, China, pp. 14 - 26, Jul., 2010.
[36]K. B. Ariyur, M. Krsti´c, “Real-Time Optimization by Extremum Seeking Control. Hoboken,”NJ, USA: Wiley, 2003.