臺灣博碩士論文加值系統

隨著科技的進步，人民對用電的品質需求愈來愈高，電力系統發生擾動將使得電壓、電流偏離額定值，可能導致用戶端的設備嚴重損害，並造成損失，因此輸電線路的故障預測，是電力系統中重要的研究項目之一。在電力系統發生故障之前，如果能快速的診斷出故障種類和位置，則電力公司可以免於突發性故障，並節省人力上的調動、減少停電時間以及停電時間上的損失。
本論文利用電力品質分析儀紀錄電力異常事件，使用離散小波轉換與離散傅立葉轉換擷取電力異常波形之特徵，並結合機器學習技術中的支撐向量機統整所有異常事件，利用此技術使得故障預測準確率上升，從而提供快速、準確的故障判斷。

With the advance of technologies, the need of better quality of electricity for living becomes an important issue. The disturbances occurred in the power system may cause voltage and current deviation from their nominals. It can result in serious damages or equipment malfunctions. Therefore, the forecast of transmission line fault is one of the crucial studies in the power system. If an incipient fault occurs in the power system, rapid forecasting of the fault location can avoid upcoming series faults and reduce outage times, as well as mitigate losses.
In this thesis, power quality meters are adopted to record the fault event in the power system. To precisely forecast the incipient fault event, support vector machine (SVM) is combined with discrete wavelet transform (DWT) and discrete Fourier transform (DFT) to extract features from numerous abnormal event of a grid. Results show that the proposed method can provide fast and accurate fault forecast in the power system.

ACKNOWLEDGMENTS i
中文摘要 ii
ABSTRACT iii
TABLE OF CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES viii
I. INTRODUCTION 1
1.1 Motivations 1
1.2 Research Methods 2
1.3 Contributions 3
1.4 Thesis Organization 4
II. REVIEW OF SUPPORT VECTOR MACHINE CLASSIFICATION 6
2.1 Linear Binary Classification 6
2.2 Overview of Support Vector Machine 8
2.3 Kernel Trick 13
2.4 Multi-Classification 15
III. METHODS TO DETECT WAVEFORM ABNORMALITY AND EXTRACT FEATURES 16
3.1 Signatures of Power Quality Disturbances 16
3.2 Wavelet Analysis Methods 20
3.2.1 Detection Based on Approximate Coefficients 20
3.2.2 Detection Based on Detailed Coefficients 21
3.3 Discrete Fourier Transform 22
IV. INTELLIGENT HYBRID METHODS-BASED APPROACH FOR INCIPIENT FAULT DETECTION AND CLASSIFICATION 24
4.1 Overview of Different Kernel Functions 24
4.2 Literature Review of Different Waveform Feature Selections 25
4.3 Proposed Solution Algorithm 27
V. CASE STUDY 31
5.1 Data Collection 31
5.2 Simulation Cases 32
5.2.1 Power Disturbance Types Classification 32
5.2.2 Real Fault Types Classification 35
5.2.3 Discussions 38
VI. CONCLUSIONS AND FUTURE WORKS 41
6.1 Conclusions 41
6.2 Future Works 42
REFERENCES 43
VITA 46
 

[1]F. Li, W. Qiao, H. Sun, H. Wan, J. Wang, Y. Xia, et al., “Smart Transmission Grid Vision and Framework,” IEEE Trans. on Smart Grid, vol. 1, Sep. 2010, pp.168-177.
[2]M. J. Mousavi and K. L. Butler-Purry, “A Novel Condition Assessment System for Underground Distribution Applications,” IEEE Trans. on Power System, vol. 24, no. 3, Aug. 2009, pp. 1115-1125
[3]E. Byvatov, U. Fechner, J. Sadowski, and G. Schneider, “Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification,” Journal of Chemical Information and Computer Sciences, vol. 43, Sep. 2003, pp. 1882-1889.
[4]A. R. Ahmad, C. Viard-Gaudin, M. Khalid, and E. Poisson, “Comparison of Support Vector Machine and Neural Network in Character Level Discriminant Training for Online Word Recognition,” in UNITEN Students Conference on Research and Development, SCORED, 2004.
[5]M. C. Lee and C. To, “Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating The Enterprise Financial Distress,” International Journal of Artificial Intelligence & Applications, Jul. 2010, pp. 31-43.
[6]C. S. Tyagi, “A Comparative Study of SVM Classifiers and Artificial Neural Networks Application for Rolling Element Bearing Fault Diagnosis Using Wavelet Transform Preprocessing,” Proceedings of World Academy of Science, Engineering & Technolog, vol. 33, Sep. 2008, p. 319-327.
[7]L. H. Hamel, “Knowledge Discovery with Support Vector Machines” Willy, New Jersey, Unit State, 2009.
[8]S. Ekici, “Support Vector Machines for Classification and Locating Faults on Transmission Lines,” Applied Soft Computing, vol. 12, Jun. 2012, pp. 1650-1658.
[9]IEEE Recommended Practice for Monitoring Electric Power Quality, IEEE Standard 1159-1995
[10]T. S. Sidhu and Zhihan Xu, “Detection of incipient faults in distribution underground cables,” IEEE Trans. Power Del., vol. 25, no. 3, pp. 1363-1371, Jul. 2010.
[11]M. R. Mehrjou, M. H. Marhaban, and N. Misron, “An experimental study of induction motor current signature analysis techniques for incipient broken rotor bar detection,” in Power Engineering in Energy and Electrical Drives (POWERENG), 2011 International Conference on, May. 2011
[12]M. J. Mousavi, J. J. McGowan, J. Stoupis and V. D. Donde, “Apparatus and method for adaptive fault detection in MV distribution circuits,” U.S. Patent, no. 8,390,302, Mar. 2013.
[13]W. M. Lin, C. H. Wu, C. H. Lin, and F. S. Cheng, “Detection and Classification of Multiple Power Quality Disturbances with Wavelet Multi-class SVM,” IEEE Trans. on Power Delivery, vol. 23, no. 4, Oct. 2008, pp. 2575- 2582.
[14]H. Livani and C. Y. Evrenosoglu, “A Fault Classification Method in Power Systems Using DWT and SVM Classifier,” in Transmission and Distribution Conference and Exposition (T&D), 2012 IEEE PES, May 2012, pp. 1-5.
[15]L. Yan-nan and B. Guang-qing, “Power Quality Disturbance Signals Identification Based on Wavelet Packet and SVM,” in Control and Decision Conference (CCDC), 2011 Chinese, May 2011, pp. 2943-2947.
[16]M. Singh, B. Panigrahi, and R. Maheshwari, “Transmission Line Fault Detection and Classification,” in Emerging Trends in Electrical and Computer Technology (ICETECT), 2011 International Conference on, Mar. 2011, pp. 15-22.
[17]A. Ibrahim, A. Abdelaziz, S. Mekhamer, and M. Ramadan, “A Transmission Line Fault Classification Approach by Support Vector Machines,” Journal of Energy and Power Engineering, vol. 5, Mar. 2011, pp. 268-274.
[18]E. Styvaktakis, M. H. J. Bollen, and I. Y. H. Gu, “Automatic classification of power system events using RMS voltage measurements,” 2002 IEEE Power Engineering Society Summer Meeting, vol. 2, 25-25 Jul. 2002, pp. 824- 829.
[19]P. Warlyani, A. Jain, A. Thoke, and R. Patel, “Fault Classification and Faulty Section Identification in Teed Transmission Circuits Using ANN,” International Journal of Computer and Electrical Engineering, vol. 3, Dec. 2011, pp. 807-811.
[20]A. Abdollahi and S. Seyedtabaii, “Transmission Line Fault Location Estimation by Fourier & Wavelet Transforms Using ANN,” in Power Engineering and Optimization Conference (PEOCO), 2010 4th International, Jun. 2010, pp. 573-578.