采用稳健回归算法的绝缘子污闪电压预测方法  

A Method to Predict Pollution Flashover Voltage of Insulators Based on Robust Regression

作　　者：王少华[1] 叶自强[1] 陈金法[1] 梅冰笑[1] 罗盛[1] 

机构地区：[1]浙江省电力试验研究院,浙江省杭州市310014

出　　处：《电网技术》2010年第12期131-135,共5页Power System Technology

基　　金：浙江省电力公司重点科技项目(ZDK069-2010)的资助

摘　　要：针对利用最小二乘法预测污闪电压存在的局限性,提出了一种基于稳健回归的绝缘子污闪电压预测方法:根据试验电压与盐密和灰密数据,通过复加权最小二乘迭代算法求解回归系数;迭代计算中采用权重函数,权重系数为上次迭代的残差的函数,以此减少奇异值对回归系数的影响;由回归系数映射出盐密影响特征指数和灰密影响特征指数,并预测绝缘子的污闪电压。通过比较试验数据与稳健回归及最小二乘回归的预测结果,验证了基于稳健回归的污闪电压预测方法的有效性。In view of the limitation in the prediction of pollution flashover voltage by least squares regression, a method to predict pollution flashover voltage by robust regression is proposed. According to testing voltage and the data of salt deposit density （SDD） and non-soluble deposit density （NSDD）, the regression coefficient is solved by complex weighting least square iteration algorithm; in iterative calculation the weight function, in which the weight coefficient is the function of the residual error of last iteration to weaken the influence of singular values on regression coefficient; the characteristic exponent denoting SDD influence and characteristic exponent denoting NSDD influence are mapped by regression coefficient, thus the pollution flashover voltage of insulators can be predicted. Comparing the prediction results by the data from tests, robust regression and least square regression respectively, the effectiveness of the proposed robust regression-based predicting method is verified.

关 键 词：绝缘子 污闪电压预测 稳健回归 最小二乘回归 

分 类 号：TM85[电气工程—高电压与绝缘技术]