基于LSSVM的机床设备电气负荷预测  

State of Texas,USA:The University of Texas at Arlington,2015.Machine Tool Equipment Electric Load Forecasting Based on LSSVM

作　　者：靳越[1,2] 何红亮 李少清[1] 孙娜[2] JIN Yue;HE Hong-liang;LI Shao-qing;SUN Na(Zhangjiakou Vocational and Technical College,Zhangjiakou,Hebei 075000;North China Electric Power University,Baoding,Hebei 071003)

机构地区：[1]张家口职业技术学院机电工程学院,河北张家口075000 [2]华北电力大学电子与通信工程系,河北保定071003

出　　处：《张家口职业技术学院学报》2023年第2期61-63,共3页Journal of Zhangjiakou Vocational and Technical College

基　　金：河北省教育厅河北省高等学校科学技术研究项目“电子技术类产业高技能人才培养模式的分析研究”(课题编号:Z2015033);张家口市科协调研课题“建立氢能产业学院对推动张家口氢能产业发展作用的研究”(课题编号:ZJKKXD10);张家口市新能源(风电)技术创新中心项目的阶段性研究成果。

摘　　要：针对机床设备中电气负荷波动性大的问题,在研究超短期负荷基本预测方法的基础上,提出利用聚类分析方法改进最小二乘支持向量机方法。该方法利用K—means方法将前期负荷序列与同期序列进行对比,并将对比结果引入至预测样本的构建中,同时利用该方法对处理后的样本进行建模训练,从而形成短期预测模型。对比分析表明,经该方法改进后的预测数据具有准确性高,适应性强的优点。On the basis of studying the basic prediction method of ultra-short-term load,in view of the fluctuations of machine tool equipment,this paper proposes a method of improving least square support vector machine by cluster analysis.It uses the K-means method to compare the pre-load sequence with the corresponding sequence,and putting the results of the comparison into the construction of the prediction sample.At the same time,this method is used to build the processed samples to form a short-term prediction model.The comparative analysis shows that the improved prediction method has the advantages of high accuracy and adaptability.

关 键 词：电气负荷 实时调度 聚类算法 最小二乘支持向量机 

分 类 号：TH-39[机械工程]