A strip thickness prediction method of hot rolling based on D_S information reconstruction  

作　　者：孙丽杰 邵诚 张利 

机构地区：[1]Institute of Advanced Control Technology Dalian University of Technology [2]School of Information Liaoning University

出　　处：《Journal of Central South University》2015年第6期2192-2200,共9页中南大学学报（英文版）

基　　金：Projects(61174115,51104044)supported by the National Natural Science Foundation of China;Project(L2010153)supported by Scientific Research Project of Liaoning Provincial Education Department,China

摘　　要：To improve prediction accuracy of strip thickness in hot rolling, a kind of Dempster/Shafer(D_S) information reconstitution prediction method(DSIRPM) was presented. DSIRPM basically consisted of three steps to implement the prediction of strip thickness. Firstly, iba Analyzer was employed to analyze the periodicity of hot rolling and find three sensitive parameters to strip thickness, which were used to undertake polynomial curve fitting prediction based on least square respectively, and preliminary prediction results were obtained. Then, D_S evidence theory was used to reconstruct the prediction results under different parameters, in which basic probability assignment(BPA) was the key and the proposed contribution rate calculated using grey relational degree was regarded as BPA, which realizes BPA selection objectively. Finally, from this distribution, future strip thickness trend was inferred. Experimental results clearly show the improved prediction accuracy and stability compared with other prediction models, such as GM(1,1) and the weighted average prediction model.To improve prediction accuracy of strip thickness in hot rolling, a kind of Dempster/Shafer（D_S） information reconstitution prediction method（DSIRPM） was presented. DSIRPM basically consisted of three steps to implement the prediction of strip thickness. Firstly, iba Analyzer was employed to analyze the periodicity of hot rolling and find three sensitive parameters to strip thickness, which were used to undertake polynomial curve fitting prediction based on least square respectively, and preliminary prediction results were obtained. Then, D_S evidence theory was used to reconstruct the prediction results under different parameters, in which basic probability assignment（BPA） was the key and the proposed contribution rate calculated using grey relational degree was regarded as BPA, which realizes BPA selection objectively. Finally, from this distribution, future strip thickness trend was inferred. Experimental results clearly show the improved prediction accuracy and stability compared with other prediction models, such as GM（1,1） and the weighted average prediction model.

关 键 词：grey relational degree GM（1 1） model Dempster/Shafer （D_S） method least square method thickness prediction 

分 类 号：N941.5[自然科学总论—系统科学]