基于最小二乘支持向量机的复杂气象条件下绝缘子等值附盐密度的预测  

Insulator ESDD Predicting under Various Meteorological Conditions Based on Least Squares Support Vector Machines

作　　者：帅海燕[1] 

机构地区：[1]武汉交通职业学院,湖北武汉430065

出　　处：《机电产品开发与创新》2016年第6期27-29,共3页Development & Innovation of Machinery & Electrical Products

基　　金：湖北省教育厅科学技术项目(B20128702)

摘　　要：以"光传感器输变电设备盐密在线监测系统"提供的数据为依据,建立了一种基于最小二乘支持向量机的智能预测模型,该模型以温度(T)、相对湿度(H)、风速(WV)、气压(P)、雨量(R)等五个变量为输入参数,等值附盐密度为输出参数。用网格搜索法对最小二乘支持向量机最优参数的进行自动选取,提高了预测的快速性和准确性。结果表明该模型预测的等值附盐密度与实测结果基本一致。According to the data provided by ＂Optical Sensor System for the ESDD Monitoring of Transmission Equipment＂,an intellectual prediction model based on least squares support vector machines（LS-SVM） is built,whose input variables are temperature（T）,humidity（H）,wind velocity（WV）,air pressure（P） and rainfall（R）,and output variable is equal salt deposit density（ESDD）. Through Grid Search Method,the optimal parameters of LS-SVM are selected automatically,which has improved the speed and accuracy of the forecasting. The simulated results show that the predicted ESDD data are very close to the on-line measured ones.

关 键 词：等值附盐密度预测 最小二乘支持向量机 气象条件 绝缘子 网络搜索法 

分 类 号：TM72[电气工程—电力系统及自动化]