论文部分内容阅读
In viewof the limitations in the prediction of polluttion flash oltage by least sq regression,a method too predict pollution flashover voltage by robust regression is proposed.According to testing voltage and the data of salt deposit density (ρsDD) and non-soluble deposit density (ρNSDD),the regression coefficient is solved by a complex weighting least square iteration algorithm.In iterative calculations,the weight function is adopted,in which the weight coefficient is the function of the residual error of last iteration to weaken the influence of singular values on the regression coefficient.The characteristic exponent denoting ρSDD influence and characteristic exponent denoting ρNSDD influence are mapped by the regression coefficient,and thus the pollution flashover voltage of insulators can be predicted.Through the comparison of test results,robust regression results and least squares regression results,the effectiveness of the proposed robust regression-based forecasting method is verified.