Neural Network Based Modelling and Prediction for the Coating Weight of HDGL Process
详细信息 查看官网全文
- 英文论文题名：Neural Network Based Modelling and Prediction for the Coating Weight of HDGL Process
- 论文作者：Zai-Sheng Pan ; Tian-Lin Wang ; Shao-Liang Wang ; Peng Chen
- 英文论文作者：Zai-Sheng Pan ; Tian-Lin Wang ; Shao-Liang Wang ; Peng Chen ; Institute of Cyber-Systems and Control ; Zhejiang University ; Zhejiang SUPCON Research CO. ; LTD.
- 年：2017
- 作者机构：Institute of Cyber-Systems and Control,Zhejiang University;Zhejiang SUPCON Research CO.,LTD.;
- 英文论文关键词：coating weight ; neural network ; data process ; gain analysis ; predictive accuracy
- 会议召开时间：2017-07-26
- 会议录名称：第36届中国控制会议论文集（B）
- 英文会议录名称：Proceedings of the 36th Chinese Control Conference（B）
- 语种：英文
- 分类号：TG174.44;TP183
- 学会代码：KZLL
- 会议名称：第36届中国控制会议
- 会议地点：中国辽宁大连
- 主办单位：中国自动化学会控制理论专业委员会
- 学会名称：中国自动化学会控制理论专业委员会
- 页数：5
- 文件大小：582k
- 原文格式：D
- 会议级别：全国
摘要
To deal with the difficulties of large time-varying delay,seriously nonlinear and strong disturbance in the hot-dip galvanizing line(HDGL) control,this paper proposes a novel ANN based modelling and prediction method for the coating weight,the proposed method is then applied to a real plant at Valin LY Steel Co.,Loudi,China.The prediction model is built through data pre-processing,data clustering and model training,with the model deviation being corrected through bias-update.The comparisons between measured coating weight and model prediction of a real HDGL process show the effectiveness of the proposed method,and the rationality of the prediction model is further verified though gain analysis between major input and output of HDGL process.
To deal with the difficulties of large time-varying delay,seriously nonlinear and strong disturbance in the hot-dip galvanizing line(HDGL) control,this paper proposes a novel ANN based modelling and prediction method for the coating weight,the proposed method is then applied to a real plant at Valin LY Steel Co.,Loudi,China.The prediction model is built through data pre-processing,data clustering and model training,with the model deviation being corrected through bias-update.The comparisons between measured coating weight and model prediction of a real HDGL process show the effectiveness of the proposed method,and the rationality of the prediction model is further verified though gain analysis between major input and output of HDGL process.
To deal with the difficulties of large time-varying delay,seriously nonlinear and strong disturbance in the hot-dip galvanizing line(HDGL) control,this paper proposes a novel ANN based modelling and prediction method for the coating weight,the proposed method is then applied to a real plant at Valin LY Steel Co.,Loudi,China.The prediction model is built through data pre-processing,data clustering and model training,with the model deviation being corrected through bias-update.The comparisons between measured coating weight and model prediction of a real HDGL process show the effectiveness of the proposed method,and the rationality of the prediction model is further verified though gain analysis between major input and output of HDGL process.
引文
[1]J.Adams,et al.,Coating mass control on no.2 galvanizing line at LTV steel's Indiana Harbor works,Iron and Steel Eng.,73(1):22-27.1996.
[2]N.Guelton,A.Lerouge,Coating weight control on ArcelorMittal's galvanizing line at Florange Works,Control Engineering Practice,18(10):1220-1229.2010.
[3]Y.Zhang,F.Shao,et al.,Thickness control of hot dip galvanizing coating based on fuzzy adaptive model,Journal of Shenyang University of Technology,34(5),576-580.2012
[4]K.Shin,H.Park,W.Chung,Synthesis method for the modelling and robust control of coating weight at galvanizing process,ISIJ International,46(10),pp 1442-1451.2006.
[5]P.Akhil,M.Gupta,D.Zanwar,Process Parameter Optimization for Zinc Coating Weight Control in Continuous Galvanizing Line,International Journal of Scientific&Engineering Research,3(11),1:6.2012.
[6]Y.Z.Lu,S.W.Markward,Development and Application of an Integrated Neural System for an HDCL,IEEE Transactions on Neural Networks,8(6):146-156.1997.
[7]Y.Z.Lu,S.W.Markward,Development and application of an integrated neural system for a HDCL,Proceedings of the American Control Conference,1995:2302-2306.
[8]E.S.Ahmed,T.Abdelazim,A.Noureldin,Neural network modeling of time-dependent creep deformations in masonry structures,Nerual Comput&Applic,19:583-594.2010.
[9]A.Monteiro,H.Elbern,S.Galmarini,et al.,Bias Correction Techniques to Improve Air Quality Ensemble Predictions Focus on O3 and PM Over Portugal,Environ Model Assess,18:533-546.2013.
[10]C.Cortes,M.Mohri,et al.,Sample Selection Bias Correction Theory,5254:38-53.2008.
[2]N.Guelton,A.Lerouge,Coating weight control on ArcelorMittal's galvanizing line at Florange Works,Control Engineering Practice,18(10):1220-1229.2010.
[3]Y.Zhang,F.Shao,et al.,Thickness control of hot dip galvanizing coating based on fuzzy adaptive model,Journal of Shenyang University of Technology,34(5),576-580.2012
[4]K.Shin,H.Park,W.Chung,Synthesis method for the modelling and robust control of coating weight at galvanizing process,ISIJ International,46(10),pp 1442-1451.2006.
[5]P.Akhil,M.Gupta,D.Zanwar,Process Parameter Optimization for Zinc Coating Weight Control in Continuous Galvanizing Line,International Journal of Scientific&Engineering Research,3(11),1:6.2012.
[6]Y.Z.Lu,S.W.Markward,Development and Application of an Integrated Neural System for an HDCL,IEEE Transactions on Neural Networks,8(6):146-156.1997.
[7]Y.Z.Lu,S.W.Markward,Development and application of an integrated neural system for a HDCL,Proceedings of the American Control Conference,1995:2302-2306.
[8]E.S.Ahmed,T.Abdelazim,A.Noureldin,Neural network modeling of time-dependent creep deformations in masonry structures,Nerual Comput&Applic,19:583-594.2010.
[9]A.Monteiro,H.Elbern,S.Galmarini,et al.,Bias Correction Techniques to Improve Air Quality Ensemble Predictions Focus on O3 and PM Over Portugal,Environ Model Assess,18:533-546.2013.
[10]C.Cortes,M.Mohri,et al.,Sample Selection Bias Correction Theory,5254:38-53.2008.