基于IWOA-BP算法的变压器绝缘老化评估方法  

Evaluation method of transformer insulation aging state based on IWOA-BP algorithm

作　　者：邓昭宏 赵春明 冷俊 翟冠强 王昕[1] DENG Zhaohong;ZHAO Chunming;Leng Jun;Zhai Guanqiang;WANG Xin(Center of Electrical&Electronic Technology,Shanghai Jiao Tong University,Shanghai 200240,China;Electric Power Research Institute,State Grid Jilin Electric Power Co.,Ltd.,Changchun 130021,China)

机构地区：[1]上海交通大学电工与电子技术中心,上海200240 [2]国网吉林省电力有限公司电力科学研究院,吉林长春130021

出　　处：《电力科学与技术学报》2023年第5期253-261,共9页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(61673268);国网吉林省电力有限公司科技项目(2019-24)。

摘　　要：为增强变压器运行的安全性以及稳定性,提出一种基于改进的鲸鱼优化(improved whale optimization algorithm,IWOA)—反向传播(back propagation,BP)算法的变压器绝缘老化状态评估模型。建立变压器油纸绝缘模型进行极化—去极化电流(polarization and depolarization current,PDC)实验,为避免含水率对评估结果造成影响,提取综合电导率作为老化特征量;以BP神经网络为主,PDC电流数据为输入,综合电导率为输出,建立算法模型对油纸绝缘老化状态进行评估;为提升算法模型的评估效果,以加入非线性收敛因子以及自适应权重为方法对鲸鱼优化算法(whale optimization algorithm,WOA)进行改进,并以IWOA对BP神经网络进行优化,获取更优的BP权重与阈值初值,提高BP神经网络的收敛速度以及精度。最终结果证明,IWOA-BP评估模型具有一定准确性以及实用性,且在油纸绝缘寿命评估方向上有一定发展空间。In order to improve the safety and stability of transformer operation,a transformer insulation aging state evaluation model based on improved whale optimization algorithm-back propagation(IWOA-BP)algorithm is proposed.An oil-paper insulation model of transformer for polarization and depolarization current(PDC)method experiment is established.In order to avoid the influence of moisture content on the evaluation results,the comprehensive conductivity is extracted as the aging characteristic quantity.An evaluate algorithm model for the aging state of oil-paper insulation basing on BP neural network is established,in which PDC current data is the input and comprehensive conductivity is the output.In order to promote the evaluation effect of the algorithm model,the whale optimization algorithm(WOA)is improved by adding nonlinear convergence factors and adaptive weights.And IWOA is used to optimize the BP neural network to obtain better BP weights and threshold initial values.Thus,the convergence speed and accuracy of the BP neural network are improved.The final result proves that the proposed IWOA-BP evaluation model has certain accuracy and practicability,and has some development space in the direction of oil-paper insulation life evaluation.

关 键 词：变压器油纸绝缘 极化去极化电流法 综合电导率 改进的鲸鱼优化算法 

分 类 号：TM855[电气工程—高电压与绝缘技术]