Mechanical Property Prediction of Strip Model Based on PSO-BP Neural Network

钢铁研究学报(英文版), 2008, 15(3): 87-91.

^1, , ^2, , ^3, , ^4,

1.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

2.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

3.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

4.Zhangjiagang Pohang Stainless Steel Co Ltd, Zhangjiagang 215000, Jiangsu, China

基金项目: Natural Science Foundation of Anhui Provincial Education Department of China(2006KJ080A)

Mechanical Property Prediction of Strip Model Based on PSO-BP Neural Network

WANG Ping ^1, , HUANG Zhen-yi ^2, , ZHANG Ming-ya ^3, , ZHAO Xue-wu ^4,

1.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

2.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

3.School of Metallurgy and Mate, rials, Anhui University of Technology, Ma'anshan 243002, Anhui, China;Anhui Key Laboratory of Metal Materials and Processing, Ma'anshan 243002, Anhui, China

4.Zhangjiagang Pohang Stainless Steel Co Ltd, Zhangjiagang 215000, Jiangsu, China

Keywords： particle swarm optimization algorithm

Mechanical property prediction of hot roiled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimization algo-rithm-particle swarm optimization (PSO) is adopted. The algorithm is combined with the BP rapid training algo- rithm, and then, a kind of new neural network (NN) called PSO-BP NN is established. With the advantages of glob-al optimization ability and the rapid constringeney of the BP rapid training algorithm, the new algorithm fully shows the ability of nonlinear approach of multilayer feedforward network, improves the performance of NN, and provides a favorable basis for further on-line application of a comprehensive model.

参考文献

[1]	LIU Xiang-hua;WANG Guo-dong;DU Lin-xiu.New Generation Plain Steel in China (Today and Tomorrow)[M].沈阳:东北大学出版社,2003
[2]	WU Di;ZHAO Xian-ming;HE Chun-yu .Research on Structural Property Prediction Model for High Carbon Steel Rolled on High Speed Wire Rolling Mill[J].Iron and Steel,2003,38(03):43.
[3]	ZHENG Hui;WANG ghao-dong;WANG Guo-dong et al.Mechanical Property Prediction for Hot Rolled SS400 Strip by Artificial Neural Network Model[J].Iron and Steel,2002,37(07):41.
[4]	MO Chun-li;LI Qiang;LI Dian-zhong et al.Prediction of the Properties for Hot Rolled Strip by Using Regression and Neural Network[J].ACTA METALLURGICA SINICA,2003,39(10):1110.
[5]	邱红雷,胡贤磊,刘相华,王国栋.人工神经网络在中厚板轧机轧制力预报中的应用[J].材料与冶金学报,2002(02):150-153.
[6]	王秀梅,吕程,王国栋,刘相华.轧制力预报中的神经网络和数学模型[J].东北大学学报（自然科学版）,1999(03):319.
[7]	张凤琴,刘娟,徐建忠,刘相华,王国栋.粗轧过程轧制力BP神经网络预报[J].上海金属,2004(04):38-40.
[8]	王邦文,杨海波,于晓东,赵伦.步长BP人工神经网络的轧制力模型研究[J].冶金设备,2001(06):1-7.
[9]	张延华,刘相华,王国栋.BP神经网络和数学模型在中厚板板凸度预报中的综合应用[J].塑性工程学报,2005(04):58-61.
[10]	周颖,郑德玲,王英,鞠磊.基于人工免疫的RBF神经网络在钢筋性能预报中的应用[J].北京科技大学学报,2005(01):123-125.
[11]	Clerc M;Kennedy J .The Particle Swarm-Explosion,Stability,and Convergence in a Multidimensional Complex Space[J].IEEE Transactions on Evolutionary Computation,2002,6(01):58.
[12]	周驰,高亮,高海兵.基于粒子群优化算法的约束布局优化[J].控制与决策,2005(01):36-40.
[13]	李爱国,覃征,鲍复民,贺升平.粒子群优化算法[J].计算机工程与应用,2002(21):1-3,17.

上一张下一张

计量

下载量()
访问量()

作者相关

在本站搜索
在百度学术搜索
在万方数据库搜索
在CNKI搜索

文章评分

您的评分：
1

0%
2

0%
3

0%
4

0%
5

0%

材料期刊网

Mechanical Property Prediction of Strip Model Based on PSO-BP Neural Network

参考文献