采用局部放电因子向量评价油纸绝缘热老化状态的一种方法.PDFVIP

20 10 年 9 月 电 工 技 术 学 报 Vol.25 No. 9 第 25 卷第 9 期 TRAN SACTION S OF CHINA ELECTROTECHNICAL SOCIETY Sep . 20 10 采用局部放电因子向量评估油纸绝缘热老化状 态的一种方法 廖瑞金 汪可 周天春 杨丽君 肖中男 （重庆大学输配电装备及系统安全与新技术国家重点实验室 重庆 400044） 摘要 替传统化学方法，研究采用局部放电来评估变压器油纸绝缘的老化状态具有理论 意义，并且在变压器滤油后也存在实际应用价值。文章在单因子加速热老化试验的基础上测量 了不同老化阶段试品的局部放电，并利用因子分析方法从局部放电29 个统 特征参数中提取 了 10 个主成分因子向量。引入单位圆描述了油纸绝缘的老化状态，建立了以老化半径R 为单 一目标的三层BP 神经网络评估模型。分别采用遗传算法GA 和LM 算法对网络进行了训练， 并对测试样本进行了老化状态识别，结果表明GA-BP 网络较LM-BP 网络对老化具有更高的识 别率。 关键 ：油纸绝缘 热老化状态评估 局部放电 遗传算法 BP 神经网络 中图分类号：TM835 An Assessment Method for Identifying Thermal Aging Condition of Oil-Paper Insulation Utilizing Factor Vectors of Partial Discharge L iao Ruij in Wang K e Zhou Tianchun Yang L ij un X iao 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 obj ective, 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 te