|
|
|
| An Assessment Method for Identifying Thermal Aging Condition of Oil-Paper Insulation Utilizing Factor Vectors of Partial Discharge |
| Liao Ruijin, Wang Ke, Zhou Tianchun, Yang Lijun, Xiao Zhongnan |
| State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing University Chongqing 400044 China |
|
|
|
|
Abstract It is theoretically significant to study on the aging condition assessment of oil-paper insulation based on partial discharge (PD) instead of traditional chemical methods. Moreover, practical application value still exists after refining transformer oil. In this paper, PD of the test samples with different aging degrees was measured after a thermally accelerated aging experiment. Then ten principal component factors were extracted from 29 statistical parameters. The aging condition of oil-paper was characterized utilizing a unit circle. Using the aging radius R as the single objective, an assessment model was established based on a three-layer BP neural network which was trained by genetic algorithm (GA) and Levenberg-Marquardt (LM) algorithm respectively. Finally, the test samples were recognized by the trained GA-BP and LM-BP network. It has been found that GA-BP network has the advantages of higher recognition rates comparing with LM-BP network.
|
|
Received: 02 June 2009
Published: 04 March 2014
|
|
|
|
|
|
[1] Wang M, Vandermaar A J, Srivastava K D. Review of condition assessment of power transformers in service[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2002, 18(6): 12-25.
[2] 朱德恒, 谈克雄. 电绝缘诊断技术[M]. 北京: 中国电力出版社, 1998.
[3] Saha T K. Review of modern diagnostic techniques for assessing insulation condition in aged transformers[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2003, 10(5): 903-917．
[4] Bozzo R, Gemme G, Guastavino F, et al. Aging diagnosis of insulation systems by PD measurements— Extraction of partial discharge features in electrical treeing[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 1998, 5(1): 118-124.
[5] Contin A, Gulski E, Cacciari M, et al. Inference of PD in electrical insulation by charge-height probability distribution: Diagnosis of insulation system degradation[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 1998, 5(1): 110-117.
[6] Del Casale M D L. On multistress aging of epoxy resins: PD and temperature[J]．IEEE Transactions on Dielectrics and Electrical Insulation, 2001, 8(2): 299-303.
[7] Stone G C, Warren V. Effect of manufacturer, winding age and insulation type on stator winding partial discharge levels[J]. IEEE Electrical Insulation Magazine, 2004, 20(5): 13-17.
[8] 乐波, 谢恒堃. 基于模糊输出BP神经网络的电机主绝缘老化状态评估方法[J]. 中国电机工程学报, 2005, 25(2): 76-81.
[9] 廖瑞金, 杨丽君, 孙才新, 等. 基于局部放电主成分因子向量的油纸绝缘老化状态统计分析[J]. 中国电机工程学报, 2006, 26(14): 114-119.
[10] 杨丽君, 廖瑞金, 孙才新, 等. 基于Fisher判别法的纸绝缘老化阶段识别[J]. 电工技术学报, 2005, 20 (8): 33-37.
[11] Li Jian, Grzybowski S, Yang Lijun, et al. Statistical parameters of partial discharge used to recognize aged oil-paper insulation[C]. Proceedings of 27th Interna- tional Conference on Power Modulator, Arlington, 2006: 75-80.
[12] 廖瑞金, 梁帅伟, 周天春, 等. 天然酯-纸绝缘老化速度减缓及其原因分析[J]. 电工技术学报, 2008, 23 (9): 32-37.
[13] 王万华. 变压器绝缘老化诊断中应注意的问题[J]. 高电压技术, 1995, 21(3): 79-82.
ing, 1995, 21(3): 79-82.
[14] Del Casale M D L, Schifani R, Testa L, et al. Partial discharge test using CIGRE method II upon nanocomposite epoxy resins[C]. IEEE International Conference on Solid Dielectrics, Winchester. UK, 2007: 341-344.
[15] 杨丽君, 孙才新, 廖瑞金, 等. 油纸绝缘老化状态判别的局部放电特征量[J]. 电力系统自动化, 2007, 31(10): 55-60.
[17] 周建华, 胡敏强. 自构形神经网络在变压器故障诊断中的应用[J]. 电工技术学报, 2004, 19(9): 77-81.
[17] 陈国良, 王煦法, 庄镇. 遗传算法及其应用[M]. 北京: 人民邮电出版社, 1996.
[18] Pan C, Chen W, Yun C. Fault diagnostic method of power transformers based on hybrid genetic algorithm evolving wavelet neural network[J]. IET Electric Power Applications, 2008(2): 71-76.
[19] 毛颖科, 关志成, 王黎明, 等. 基于BP人工神经网络的绝缘子泄漏电流预测[J]. 中国电机工程学报, 2007, 27(27): 7-12. |
|
|
|
2010, Vol. 25 
