臺灣博碩士論文加值系統

由於電子產品廣泛的被使用，對於電力品質的要求也相對提高。為了瞭解電力品質干擾事件發生的原因，須先取得電力品質干擾的相關電壓與電流信號，進而判斷何種干擾事故發生。因此，在電力系統監控中，確認及辨識干擾的電壓及電流訊號是相當重要的工作。
本論文提出兩個方法作電力品質干擾事件之辨識。一是利用隱藏式馬可夫模型作電力品質干擾事件之辨識，首先建立各種干擾訊號的隱藏式馬可夫模型，當隱藏式馬可夫模型建立之後，就可應用於線上測試，再利用其前向演算法與後向演算法將測試訊號進行辨識，得到辨識結果。
二是以含有Ｋ-平均法的自組織映射網路作電力品質干擾事件之辨識，利用含有Ｋ-平均法的自組織映射網路將參考訊號進行訓練，得到映射圖。當取得映射圖後，最後利用此自組織映射網路將測試訊號進行辨識，進而得到辨識結果。
兩種方法分別改變其內部參數，做了一些探討與分析，且於辨識過程中加入雜訊，以求更精確、客觀之辨識結果。

Because of widespread use of the sensitive electronic products, the requirements of power quality will be further emphasized. In order to know the reasons of occurrence for power quality disturbances, we need to get the signals of voltage/current disturbances that can be used to recognize what kind of disturbance event happen. Therefore, identification and recognition of voltage and current disturbances in power system is an important task in power system monitoring. This paper presents two approaches based on hidden Markov models and SOFM network withＫ-Means for recognition of power quality disturbances.
The first presents an approach based on hidden Markov models for recognition of power quality disturbances. The feature extraction and vector quantization of disturbance signals are first made. Then, the hidden Markov models for each disturbance event are constructed. Finally, the test signals can be recognized by a forward algorithm and backward algorithm to obtain the results. Some discussions which include the characteristics of hidden Markov models and vector quantization are made to obtain better results.
The second presents an approach based on SOFM network withＫ-Means algorithm for recognition of power quality disturbances. The feature extraction of disturbance signals are first made. Then, the SOFM network withＫ-Means algorithm for all disturbance data are trained to obtain map. Finally, the test signals can be recognized with map by SOFM network to obtain the results. Some discussions which include the characteristics of SOFM network withＫ-Means algorithm and enter noise disturbances are made to obtain better results.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究方法 1
1.3 論文大綱 2
第二章 電力品質干擾事件之辨識 5
2.1 前言 5
2.2 文獻回顧 5
2.3 本論文辨識系統架構 7
2.3.1 訊號之獲取 7
2.3.2 訊號特徵參數擷取 8
2.3.2.1 離散傅立葉轉換 8
2.3.2.2 小波轉換 9
2.4 本文所採用的電力品質干擾事件訊號 10
2.5 本章結論 21
第三章 利用隱藏式馬可夫模型於電力品質干擾事件之辨識 22
3.1 前言 22
3.2 向量量化 24
3.3 隱藏式馬可夫模型 26
3.3.1 前向演算法 27
3.3.2 後向演算法 28
3.4 應用隱藏式馬可夫模型於電力品質干擾事件之辨識 30
3.5 測試與結果之探討 32
3.5.1 快速傅立葉轉換與小波轉換之特徵參數擷取之探討 33
3.5.2 資料庫參考樣本數目多寡之探討 35
3.5.3 隱藏層的狀態數目多寡之探討 36
3.5.4 向量量化技術及編碼簿大小之探討 37
3.5.5 雜訊干擾對辨識結果的影響之探討 38
3.6 本章結論 38
第四章 利用含有K-平均法的自組織映射網路於電力品質干擾事件之辨識 39
4.1 前言 39
4.2 自組織映射網路簡介 39
4.3 含有K-平均法的自組織映射網路 44
4.4 測試與結果之探討 52
4.4.1 快速傅立葉轉換與小波轉換之特徵參數擷取之探討 53
4.4.2 參考樣本訓練數目多寡之探討 55
4.4.3 雜訊干擾對辨識結果的影響之探討 56
4.4.4 映射圖大小之探討 57
4.4.5 有無含有K-平均法的自組織映射網路辨識系統之比較 58
4.5 本章結論 59
第五章 結論與未來展望 60
5.1 結論 60
5.2 未來展望 61
作者簡介 62
參考文獻 63

[1] S. Surya, W. M. Grady, J. Edward, L. Jeff, and B. C. Siddharth, “A Scalable PQ Event Identification System,” IEEE Trans. on Power Delivery, Vol. 15, No. 2, pp. 738-743, 2000.
[2] J. H. Bollen, and Y. H. Gu, “Categorization and Analysis of Power System Transients,” IEEE Trans. on Power Delivery, Vol. 20, No. 3, pp. 2298-2306, 2005.
[3] S. Santoso, W. M. Grady, E. J. Powers, J. Lamoree, and S. C. Bhatt, “Characterization of Distribution Power Quality Events with Fourier and Wavelet Transforms,” IEEE Trans. on Power Delivery, Vol.15 No. 1, pp. 247–254, 2000.
[4]A. M. Youssef, T. K. Abdel-Galil, E. F. El-Saadany, and M. M. A. Salama, “Disturbance Classification Utilizing Dynamic Time Warping Classifier,” IEEE Trans. on Power Delivery, Vol. 19, No. 1, pp. 272-278, 2004.
[5]J. Chung, J. Edward, W. M. Grady, and S. C. Bhatt, “Power Disturbance Classifier using a Rule-Based Method and Wavelet Packet-Based Hidden Markov Model,” IEEE Trans. on Power Delivery, Vol. 17, No. 1, pp. 233-241, 2002.
[6] E. Styvaktakis, H. J. Bollen, and Y. H. Gu, “Expert System for Classification and Analysis of Power System Events,” IEEE Trans. on Power Delivery, Vol. 17, No. 2, pp. 423-428, 2002.
[7]P. K. Dash, S. Mishra, M. M. A. Salama, and A. C. Liew, “Classification of Power System Disturbances using a Fuzzy Expert System and A Fourier Linear Combiner,” IEEE Trans. on Power Delivery, Vol. 15, No. 2, pp. 472–477, 2000.
[8] J. H. Huang, M. Negnevitsky, and D. T. Nguyen, “A Neural-Fuzzy Classifier for Recognition of Power Quality Disturbances,” IEEE Trans. on Power Delivery, Vol. 17, No. 2, pp. 609-616, 2002.
[9] T. X. Zhu, S. K. Tso, and K. L. Lo, “Wavelet-Based Fuzzy Reasoning Approach to Power-Quality Disturbance Recognition,” IEEE Trans. on Power Delivery, Vol. 19, No. 4, pp. 1928-1935, 2004.
[10] S. Santoso, E. J. Powers, W. M. Grady, and D. T. Nguyen, “Wavelet based FSCL-LVQ Neural Networks for Power Quality Disturbance Classification,” in Proc. IASTED Int. Conf. Power and Energy Syst, Las Vegas, NV. 8-10, 1999.
[11] Z. L. Gaing, “Wavelet-Based Neural Network for Power Disturbance Recognition and Classification,” IEEE Trans. on Power Delivery, Vol. 19, No. 4, pp. 1560-1568, 2004.
[12]M. Wang, P. Ochenkowski, and A. Mamishev, “Classification of Power Quality Disturbances using Time-Frequency Ambiguity Plane and Neural Networks,” Proceedings of the IEEE Power Engineering Society Summer Meeting, Vol. 2, pp. 1246–1251, 2001.
[13] Y. Y. Hong, and C. W. Wang, “Switching Detection/Classification using Discrete Wavelet Transform and Self-Organizing Mapping Network,” IEEE Trans. on Power Delivery, Vol. 20, No. 2, pp.1662-1668, 2005.

[14] R. N. Bracewell, The Fourier Transform and Its Applications, Boston: McGraw Hill, 2000.
[15] Y. Y. Tan, Wavelet Theory and Its Application to Pattern Recognition, Singapore: World Scientific, 2000.
[16] V. Martin, and K. Jelena, Wavelets and subband coding, N.J: Prentice Hall PTR, 1995.
[17] 王耀諄，電力品質，高立圖書有限公司，2005。
[18] 關羽慶，利用動態時間扭曲法與粒子群最佳化演算法於電力品質干擾事件之辨識分類，國立雲林科技大學電機工程系研究所碩士論文，2005。
[19] H. T. Yang, and C. C. Liao, “A De-Noising Scheme for Enhancing Wavelet-Based Power Quality Monitoring System,” IEEE Trans. on Power Delivery, Vol. 16. No. 3, pp. 353–360, 2001.
[20] H. Zhang, P. Liu, and O. P. Malik, “Detection and Classification of Power Quality Disturbances in Noisy Conditions,” IEE Proc-Gener. Transm. Distrib Vol. 150. No. 5, pp. 567–572, 2003.
[21] S. V. Vaseghi, and B. P. Milner, “Noise Compensation Methods for Hidden Markov Model Speech Recognition in Adverse Environments,” IEEE Trans. on Speech and Audio Processing, Vol. 5. No.1, pp.11–21, 1997.
[22] L. I. MacDonald, and W. Zucchini, Hidden Markov and Other Models for Discrete-Valued Time Series, London: Chapman & Hall, 1997.
[23] 唐華南，以隱藏式馬可夫模型、向量量化與語言文法為基礎的中文語音辨識，國立雲林科技大學電子與資訊工程研究所碩士論文，2001。
[24] 王小川，語音訊號處理，全華科技圖書股份有限公司，2004。
[25]A. Gersho, R. M. Gray, and R. Gallager, Vector Quantization and Signal Compression, Norwell, MA : Kluwer,1991.
[26]M. C. Su, and H. T. Chang, “Fast Self-Organizing Feature Map Algorithm,” IEEE Trans. on Neural Networks, Vol. 11. No. 3, pp. 721–733, 2000.
[27] T. Kohonen, ”The Self-Organizing Map,” Proceedings of the IEEE, Vol. 78, No. 9, pp.1464-1480, 1990.