|本期目录/Table of Contents|

[1]朱霄珣,徐搏超,焦宏超,等.遗传算法对SVR风速预测模型的多参数优化[J].电机与控制学报,2017,21(02):70-75.[doi:10.15938/j.emc.2017.02.009]
 ZHU Xiao-xun,XU Bo-chao,JIAOHong-chao,et al.Windspeed prediction mettiod based on SVR and multi-parameter optimization of GA [J].,2017,21(02):70-75.[doi:10.15938/j.emc.2017.02.009]
点击复制

遗传算法对SVR风速预测模型的多参数优化(PDF)
分享到:

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:
21
期数:
2017年02
页码:
70-75
栏目:
出版日期:
2017-02-01

文章信息/Info

Title:
Windspeed prediction mettiod based on SVR and multi-parameter optimization of GA
作者:
?朱霄珣徐搏超焦宏超韩中合
?(华北电力大学能源动力与机械工程学院,河北保定071003)
Author(s):
?ZHU Xiao-xun XU Bo-chao JIAOHong-chao HANZhong-he
?(Department of Power Engineering Nortli China Electric Power University Baoding 071003,China)
关键词:
遗传算法支持向量机空间重构多参数优化风速预测
Keywords:
genetic algorithms support vector machines space reconstruction multiobjective optimiza-tion wind speed prediction
分类号:
TM 614
DOI:
10.15938/j.emc.2017.02.009
文献标志码:
A
摘要:
实验分析发现:通过相空间重构法求出的篏入维数E和时间延迟t往往不是支持向量回归机(S V R)预测模型的最优参数。针对此问题,建立了一种基于遗传算法(GA)的多参数同步优化的S V R预测方法。利用G A方法对E、t和S V R模型中的惩罚因子C、核函数宽度r进行同步优化获得全局最优解,建立S V R风速预测模型。对比单纯优化C、r的模型,以2组风速数据为例进行实验研究,建立的模型预测误差约为6.5 6%和7.74%。而对比模型的误差为12.00%和9.30%。这一结果表明,同时对E、t、C、r进行优化的模型相对于单纯优化C、r的模型,预测精确度大大提高。
Abstract:
Phase space reconstruction was used to apply in the prediction of wind speed time series for characteristic factors extraction. After several experiments, embedding dimension E and time delay t, which were typical parameters of phase space reconstruction, might not be the optimum values for support vector regression model. For solving this problem, a multi-parameter optimization method based on genet- ic algorithm was proposed to optimize embedding dimension E, time delay?t and othier support vector re-gression model parameters ( penalty parameter C, kernel function parameter y) synchronously. Twogroups of wind speed time series were predicted by using this method and the prediction errors are 6. 56% and 7.74%. The errors of t!ie contrast met!iod (optimize C,?r only) are 12. 00% and 9. 30%. The re-sults show that tiie optimal selection of E,t, C r is necessar- Compared witii the contrast model, this method can greatly improve the prediction accuracy.

参考文献/References:

-

相似文献/References:

[1]赵永平,孙健国.基于薄壁管法的稀疏最小二乘支持向量回归机[J].电机与控制学报,2009,(04):581.
 ZHAO Yong-ping,SUN Jian-guo.Thin wall tube method based sparse least squares support vector regression[J].,2009,(02):581.
[2]李军,赵峰.最小二乘小波支持向量机在非线性控制中的应用[J].电机与控制学报,2009,(04):620.
 LI Jun,ZHAO Feng.Application to nonlinear control using least squares wavelet support vector machines[J].,2009,(02):620.
[3]王艳,陈欢欢,沈毅,等.有向无环图的多类支持向量机分类算法[J].电机与控制学报,2011,(04):85.
 WANG Yan,CHEN Huan-huan,SHEN Yi.Multi-class support vector machine based on directed acyclic graph[J].,2011,(02):85.
[4]王德成,林辉.一种SVM不平衡分类方法及在故障诊断的应用[J].电机与控制学报,2012,(09):48.
 WANG De-cheng,LIN Hui.Imbalanced pattern classification method based on support vector machine and its application on fault diagnosis[J].,2012,(02):48.
[5]陈君,彭小奇,宋彦坡,等.特征空间最小数据分布最大间隔支持向量机[J].电机与控制学报,2013,(03):105.
 CHEN Jun,PENG Xiao-qi,SONG Yan-po,et al.Support vector machine with minimum-data distribution and maximum-margin in feature space[J].,2013,(02):105.
[6]田慕琴,王秀秀,宋建成,等. 笼型异步电动机转子断条故障诊断方法[J].电机与控制学报,2015,19(06):14.[doi:10. 15938/j. emc.2015.06.003]
 TIAN Mu-qin,WANG Xiu-xiu,SONG Jiancheng,et al. Diagnosis method of rotor bar broken faultin cage asynchronous motor[J].,2015,19(02):14.[doi:10. 15938/j. emc.2015.06.003]
[7]田慕琴,王秀秀,宋建成,等. 笼型异步电动机转子断条故障诊断方法[J].电机与控制学报,2015,19(06):14.[doi:10. 15938/j. emc.2015.06.003]
 TIAN Mu-qin,WANG Xiu-xiu,SONG Jiancheng,et al. Diagnosis method of rotor bar broken faultin cage asynchronous motor[J].,2015,19(02):14.[doi:10. 15938/j. emc.2015.06.003]

备注/Memo

备注/Memo:
收稿日期:2016 -03 -02
基金项目:教育部中央高校基本科研业务费专项资金资助项目(2015MS102)
作者简介:朱霄珣(1985—),男,博士,讲师,研究方向为热力设备状态监测与故障诊断、清洁能源发电等;
徐搏超(1992—),男,硕士研究生,研究方向为清洁能源发电;
焦宏超(1990—),男,硕士,研究方向为清洁能源发电;
韩中合(1964—),男,教授,博士生导师,研究方向为热力设备状态监测与故障诊断、清洁能源发电等。
更新日期/Last Update: 2017-03-30