|
|
Rolling Force Prediction Based on Support Vectors Machine with Particle Swam Optimization |
YANG Jing-ming 1,2, CHEN Wei-ming1,2,CHE Hai-jun1,2,LV Jin3,JIA Lin1,2 |
1. College of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2. Key Lab of Industrial Computer Ctrl Eng of Hebei Province, Yanshan University, Qinhuangdao,Hebei 066004,China
3. Tianjin Design and Research Institute of Electric Drive, Tianjin 300180,China |
|
|
Abstract In order to improve the prediction accuracy of rolling force in hot rolled strip, combined with particle swarm optimization algorithm and support vector machine method to predict the rolling force, According to the principle of rolling, rolling force prediction model is established by using SVM, the parameters of SVM was optimized by particle swarm algorithm to improve the prediction accuracy. In order to further improve the precision of rolling force prediction, network based on SVM combined with mathematic model method is proposed. The acquisition of a large number of rolling data offline simulation was based on a “1 + 4” aluminum strip rolling factory. The simulation results can be seen that rolling force predicted the method of network based on SVM combined with mathematic mode, improves the speed of rolling force prediction and makes the forecast accuracy of rolling force control within 7%.
|
Received: 18 February 2014
Published: 10 December 2015
|
|
|
|
|
[1]杨景明,孙晓娜,车海军,等.基于蚁群算法的神经网络冷连轧机轧制力预报[J].钢铁,2009,44(3):52-55.
[2]席裕庚.动态不确定环境下广义控制问题的预测控制[J].控制理论与应用,2000,17(5):665-670.
[3]Kennedy J,Eberhart R. Particle swarm optimization[M].Piscataway,NJ:IEEE Press,1995:1942-1948.
[4]李爱国,覃征,鲍复民,等.粒子群优化算法 [J]. 计算机工程与应用, 2002,21:1-3.
[5]Eberhart R C,Kennrdy J.A new optimizer using particle swarm theory[C]//Proceeding of the Sixth International Symposium on Micro Machine and Human Science,Piscataway,NJ:IEEE Service Center,1995.39-43.
[6]Shi Y,Eberhart R. A modified particle swarm optimizer[C]//Proceeding of IEEE International Conference on Evolu-tionary Computation. New York,NY, USA; IEEE, 1998:69-73.
[7]Vapnik V N. The Natural of Statistical Learning Theory[M].New York: Spring-Verlag,1995.
[8]何世钧,王化祥,周勋.基于SVM的ECT图像重建算法[J].计量学报,2007,28(2):137-140.
[9]张浩然,韩正之,李昌刚.支持向量机[J].计算机科学,2002,29(12):135-137.
[10]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1);32-42.
[11]陈果,周伽.小样本数据的支持向量机回归模型参数及预测区间研究[J].计量学报,2008,29(1):92-96.
[12]孙一康,带钢热连轧的模型与控制[M].北京:冶金工业出版社, 2002.
[13]Son J S,Lee D M,et al.A Study on On-line Neural Network for Prediction for Rolling Force in Hot-Rolling Mill[J].Journal of Materials Processing Technology,2005,164:1612.
[14]Lin S W,Ying K C,Chen S C,et al.Particle swarm optimization for parameter determination and feature selection of support vector machines[J].Expert Systems with Applications,2008,35:1817-1824.
[15]邵信光,杨慧中,陈刚.基于粒子群优化算法的支持向量机参数选择及其应用[J].控制理论与应用,2006,23 (5):740-748. |
|
|
|