以智慧型混合方法進行輸電系統 故障徵兆檢測及分類

Intelligent Hybrid Methods-Based Approach for Incipient Fault Detection and Classification of a Transmission System

張博鈞(Po Chun Chang)

指導教授 ： 張文恭

國立中正大學/工學院/電機工程學系/碩士(2015年)

摘要

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。

關鍵字

小波轉換 ； 智慧電網 ； 故障預測 ； 支撐向量機 ； 電力品質 ； 傅立葉轉換

並列摘要

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.

並列關鍵字

discrete wavelet transform ； smart grid ； fault forecast ； support vector machine ； power quality ； discrete Fourier transform

參考文獻

[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.

[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.