期刊文献+

基于改进鱼群优化支持向量机的变压器绕组热点温度预测 被引量:9

Transformer Winding Hot Spot Temperature Prediction Based on Improved Swarm Optimization Support Vector Machine
原文传递
导出
摘要 为了克服传统人工鱼群算法存在的速度慢、易陷入局部最优等缺点,引入了可变视野、变化步长、禁忌表及清除机制改进人工鱼群算法,通过改进人工鱼群算法对支持向量机模型中的惩罚变量C和RBF核参数G进行了优化。根据某市110kV变压器绕组热点温度实际运行数据,选取关联变量,确定训练集和测试集,建立了基于改进人工鱼群优化SVM的变压器绕组热点温度预测模型,通过与其他方法进行对比,验证了该预测模型具有更优的预测能力,预测效果较理想。 In order to overcome the shortcomings of traditional artificial fish swarm algorithm,such as slow speed and being easily to fall into local extremum,variable visual field and step size,tabu table and clearing strategy are introduced to improve artificial fish swarm algorithm.The penalty coefficient Cand RBF kernel parameters Gin support vector machine model are optimized by the improved artificial fish swarm algorithm.According to the actual operating data of110 kV transformer winding hot spot temperature in a city,the characteristic variables are selected to determine the training set and test set,and the transformer winding hot spot temperature prediction model is established based on the improved artificial fish swarm optimization SVM.Compared with other methods,the simulation results show that the prediction model has better performance and the prediction effect is ideal.
作者 韩祥 李志斌 张雪健 HAN Xiang;LI Zhi-bin;ZHANG Xue-jian(College of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China)
出处 《水电能源科学》 北大核心 2020年第4期154-157,125,共5页 Water Resources and Power
基金 上海市电站自动化技术重点实验室项目(13DZ2273800) 国家自然科学基金项目(61573239).
关键词 变压器绕组热点温度 人工鱼群算法 关联变量 清除机制 支持向量机 hot spot temperature in transformer winding artificial fish swarm algorithm associated variable clearing mechanism support vector machine
  • 相关文献

参考文献8

二级参考文献72

共引文献1079

同被引文献107

引证文献9

二级引证文献42

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部