最小二乘支持向量机预测绝缘子等值附盐密度

A Prediction Model for Insulator's ESDD Based on Least Square Support Vector Machine

考虑到气象因子条件对绝缘子的等值附盐密度影响复杂,难以建立精确数学模型等问题,提出了一种最小二乘支持向量机的绝缘子在一定的气象因子条件下的等值附盐密度预测新模型。以温度、湿度、风速等主要气象因子为输入,绝缘子等值附盐密度为输出,通过最小二乘支持向量机模型,拟合输入与输出之间的复杂非线性函数关系。以现场采集的气候数据为样本对模型进行学习训练,用训练好模型预测绝缘子在一定气候条件下的等值附盐密度。实践表明该方法具有建模速度快、预测精度高、操作简便等优点,不仅克服了常规的BP预测模型的不足,而且性能优于标准支持向量机预测模型。

In consideration of the problem that equal salt deposit density of insulator is complexly influenced by climate factors and accurate model is difficult to construct, a novel prediction model of insulator＇s ESDD under different climate conditions is proposed based on least square support vector machine （LS-SVM）. With five main climate factors including temperature, humidity, wind velocity, and so on as inputs, ESDD of insulator as output, the nonlinear mapping between input and output is fitted through LS-SVM. Collecting and processing field data as learning samples to train the model, the insulator＇s ESDD under certain climate condition is hence predicted by the trained model. Experimental results demonstrate that the model based on LS-SVM is constructed more rapidly than the standard SVM-based model, and its prediction error is smaller. Moreover, the present model gains better prediction accuracy and speed compared with the BP model.