常用的地下電纜絕緣材料為交鏈聚乙烯(corss-linked polyethylene, XLPE)，絕緣會因劣化而故障造成經濟損失及危害。因此需建立一套即時監測系統，長期量測局部放電資料以進行絕緣狀態評估來預防此事故的發生。
本文利用插針試驗模擬實際上的瑕疵劣化，被試物為取自地下電纜的交鏈聚乙烯切片。從試驗開始至絕緣破壞，局部放電信號將以固定間隔時間持續地被記錄。每次量測的資料會經過濾波和化簡處理，以及特徵萃取後，形成具有放電特性的特徵值。為了有效且即時性地評估絕緣狀態，本文提出以決策樹的架構，配合吉尼索引法找出最佳的特徵值組合與狀態分類，其結果得以簡明易懂的if-then規則表示。
經由測試與分析得知，最為適合的特徵值有放電總和區域平均放電量斜率、正半週放電次數區域重心及負半週放電次數區域重心。此機制在原始信號未經小波濾波處理的情況下依然有效，中期辨識成功率為91.9%、末期辨識成功率為100%。綜合而言，平均辨識成功率達93.7%，代表本文提出的絕緣診斷機制實為可行。

The cross-linked polyethylene (XLPE) is the common insulation material for underground cable. The failure of electric apparatus due to insulation deterioration, it caused economic losses and damage. Therefore, to establish a real-time monitoring system for long-term measuring partial discharge to assess the insulation condition and prevent accident is necessary.
This thesis used the cross-linked polyethylene with an inserted needle to simulate the deterioration of defect. Partial discharge signal will be recorded at regular interval during whole test. After filtering, simplification and feature extraction, each measurement data will become discharge characteristics. In order to effectively and real-time assess insulation condition, this paper proposed the decision tree structure, with the Gini index method, to find the best combination of characteristic values and status classification. The results of decision tree can be expressed as simple "if-then" rules.
Through testing and analysis, the most suitable partial discharge characteristics are the slope of district-average of discharge summation, the regional center of discharge number in positive half cycle and the regional center of discharge number in negative half cycle. This mechanism for the original signal, which is processed without wavelet filtering, is still valid. The medium-term success rate of recognition is 91.9%, and the final-term success rate of recognition is 100%. In conclusion, the average success rate of recognition is 93.97% that means the mechanism proposed is feasible.

[1] F. Guastavino and B. Cerutti, “Tree growth monitoring by means of digital partial discharge measurements,” IEEE transactions on Dielectrics and Electrical Insulation, Vol. 10, No. 1, pp. 65-72, Feb. 2003.

[2] G. J. Paoletti and A. Golubev, “Partial discharge theory and technologies related to medium-voltage electrical equipment,” IEEE Transactions on Industry Applications, Vol. 37, No.1, pp.90-103, Jan./Feb. 2001.

[3] N. C. Sahoo, M. M. A. Salama and R. Bartnikas, “Trends in Partial Discharge Pattern Classification: A Survey,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 12, No. 2, pp. 248-264, Apr. 2005.

[4] 董崴，「應用類神經網路於即時性評估交鏈聚乙烯絕緣狀態之研究」，碩士論文，國立台灣科技大學，民國九十七年。

[5] S. M. Strachan, S. Rudd, S. D. J. McArthur, M. D. Judd and S. Meijer and E. Gulski, ”Knowledge-Based Diagnosis of Partial Discharges in Power Transformers,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 15, No. 1. pp. 259-268, Feb. 2008.

[6] 陳振銘，「地下電纜絕緣樹枝現象之劣化趨勢研究」，碩士論文，國立台灣科技大學，民國九十六年。

[7] 林育勳，「數位局部放電量測應用於模鑄式比流器絕緣狀態之評估」，博士論文，國立台灣科技大學，民國九十三年。

[8] 張云濤，龔玲編，「資料探勘原理與技術」，五南出版社，民國九十六年。

[9] 曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯，「資料探勘」，旗標出版股份有限公司，民國九十四年。

[10] 陳慶明，「應用決策樹機制於即時性評估交鏈聚乙烯絕緣狀態之研究」，碩士論文，國立台灣科技大學，民國九十七年。

[11] T. K. Abdel-Galil, R. M. Sharkawy, M. M. A. Salama and R. Bartnikas, “Partial Discharge Pattern Classification Using the Fuzzy Decision Tree Approach,” IEEE Transactions on Instrumentation and Measurement, Vol. 54, No. 6, pp.2258-2263, Dec. 2005.

[12] F. Petzold, H. Schlapp, E. Gulski, P. Seitz and B. Quak “Advanced Solution for On-site Diagnosis of Distribution Power Cables,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 15, No. 6, pp. 1584-1589, Dec. 2008.

[13] C. Zhou, M. Michel, D.M. Hepburn and X. Song, “On-line partial discharge monitoring in medium voltage underground cables,” IET Science Measurement Technology, Vol. 3, Iss. 5, pp. 354–363, 2009.

[14] E. Gulski, P. Cichecki, F. Wester, J. Smit, R. Bodega, T. Hermans, P. Seitz, B. Quak and F. Vries “On-site Testing and PD Diagnosis of High Voltage Power Cables,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 15, No. 6, pp. 1691-1700, Dec. 2008.

[15] Y. Tian, P. L. Lewin, A. E. Davies,S. J. Sutton and S. G. Swingler”, Partial Discharge Detection in Cables Using VHF Capacitive Couplers,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 10, No. 2, pp. 343-353,Apr. 2003.

[16] 張建國，「地下電纜接頭局部放電線上監控系統之研製」，碩士論文，國立台灣科技大學，民國九十五年。

[17] 潘彥竹，「局部放電量測系統之研製」，碩士論文，國立台灣科技大學，民國九十三年。

[18] Tao Hong and M. T. C. Fang, “Detection and Classification of Partial Discharge Using a Feature Decomposition-Based Modular Neural Network,” IEEE Transactions on Instrumentation and Measurement, Vol. 50, No. 5, pp.1349-1354, Oct. 2001.

[19] D. Dey, B. Chatterjee, S. Chakravorti and S. Munshi, “Cross-wavelet Transform as a New Paradigm for Feature Extraction from Noisy Partial Discharge Pulses,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 17, No. 1, pp. 157-166, Feb. 2010.

[20] “High-voltage test techniques – partial discharge measurements”, IEC 60270, 2000.