计算机工程与应用Issue(15)：223-227,5.DOI:10.3778/j.issn.1002-8331.1208-0259
基于PLS分析的高压绝缘子污秽等级判定
Determination of pollution class for high-voltage insulators based on Partial Least Squares regression analysis
摘要
Abstract
In view of the characteristics of multi-correlation of infrared thermography of polluted insulators, a method based on partial least squares regression analysis is proposed to determine the pollution class of high voltage insulators. On the premise of preserving the original data to the maximum extent, the partial least squares regression equation between the characteristic parameters of high-voltage insulator contamination and contamination grades is built, and through analyzing the importance of indicators of variable projection of the regression model equation, the effect degree of various charac-teristic parameters on contamination grades is obtained. The method solves the multi-correlation problem of the indepen-dent variables effectively, and quantifies the relationship between the characteristic parameters and contamination grades. The test result shows that, judging the high-voltage insulator contamination grades by applying partial least squares regres-sion analysis is scientific and reliable, with high accuracy and strong practicability.关键词
绝缘子污秽等级/特征量/偏最小二乘(PLS)/模型方程/变量投影重要性指标Key words
insulators pollution class/characteristic parameters/Partial Least Squares(PLS)regression/model equation/variable importance in projection分类
信息技术与安全科学引用本文复制引用
宋宛净,姚建刚,张彦,匡少林,孙谦..基于PLS分析的高压绝缘子污秽等级判定[J].计算机工程与应用,2014,(15):223-227,5.基金项目
科技部科技型中小企业技术创新基金项目（No.11C26214302812）。 （）
