Soft Sensor Modeling Based on Auxiliary Error Probability Density Function Shape Control
详细信息 查看官网全文
- 英文论文题名：Soft Sensor Modeling Based on Auxiliary Error Probability Density Function Shape Control
- 论文作者：Huifeng Tian ; Li Jia
- 英文论文作者：Huifeng Tian ; Li Jia ; Shanghai Key Laboratory of Power Station Automation Technology ; Department of Automation ; College of Mechatronics Engineering and Automation ; Shanghai University ; College of Electric and Information Engineering ; Jiangsu University of Science and Technology
- 年：2017
- 作者机构：Shanghai Key Laboratory of Power Station Automation Technology,Department of Automation,College of Mechatronics Engineering and Automation,Shanghai University;College of Electric and Information Engineering,Jiangsu University of Science and Technology;
- 英文论文关键词：Neuro-fuzzy Model ; Auxiliary Error ; Probability Density Function ; Extreme Learning Machine ; Least Square Support Vector Machine
- 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：TP212
- 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：521k
- 原文格式：D
- 会议级别：全国
摘要
Soft sensor has been widely used for estimating product quality or other important process variables when online analyzers are not available. In order to cope with estimation performance deterioration when process variables abruptly change, a new soft sensor modeling method based on auxiliary error neuro-fuzzy model is proposed. The model mean square error(MSE) is used as an evaluating index in traditional data-driven modeling, while only seeks the minimum error function from the vision of a single sample without considering the spatial state of model error data points. To overcome this shortcoming, the auxiliary error model and probability density function(PDF) are combined to adjust the model parameter by controlling auxiliary error PDF shape to track a given target PDF. Furthermore, soft sensor model parameters are determined by means of gradient descent method. The actual operation process data of coal-fired power plant are selected as the modeling data to justify the effectiveness of the proposed method, experimental results show that the prediction accuracy and generalization ability of combining auxiliary error neuro-fuzzy model(AENFM) and PDF-based soft sensor modeling method are superior to other three data-driven methods using MSE criterion. The results indicate that the proposed method can be applied to soft sensor modeling of complex nonlinear system.
Soft sensor has been widely used for estimating product quality or other important process variables when online analyzers are not available. In order to cope with estimation performance deterioration when process variables abruptly change, a new soft sensor modeling method based on auxiliary error neuro-fuzzy model is proposed. The model mean square error(MSE) is used as an evaluating index in traditional data-driven modeling, while only seeks the minimum error function from the vision of a single sample without considering the spatial state of model error data points. To overcome this shortcoming, the auxiliary error model and probability density function(PDF) are combined to adjust the model parameter by controlling auxiliary error PDF shape to track a given target PDF. Furthermore, soft sensor model parameters are determined by means of gradient descent method. The actual operation process data of coal-fired power plant are selected as the modeling data to justify the effectiveness of the proposed method, experimental results show that the prediction accuracy and generalization ability of combining auxiliary error neuro-fuzzy model(AENFM) and PDF-based soft sensor modeling method are superior to other three data-driven methods using MSE criterion. The results indicate that the proposed method can be applied to soft sensor modeling of complex nonlinear system.
Soft sensor has been widely used for estimating product quality or other important process variables when online analyzers are not available. In order to cope with estimation performance deterioration when process variables abruptly change, a new soft sensor modeling method based on auxiliary error neuro-fuzzy model is proposed. The model mean square error(MSE) is used as an evaluating index in traditional data-driven modeling, while only seeks the minimum error function from the vision of a single sample without considering the spatial state of model error data points. To overcome this shortcoming, the auxiliary error model and probability density function(PDF) are combined to adjust the model parameter by controlling auxiliary error PDF shape to track a given target PDF. Furthermore, soft sensor model parameters are determined by means of gradient descent method. The actual operation process data of coal-fired power plant are selected as the modeling data to justify the effectiveness of the proposed method, experimental results show that the prediction accuracy and generalization ability of combining auxiliary error neuro-fuzzy model(AENFM) and PDF-based soft sensor modeling method are superior to other three data-driven methods using MSE criterion. The results indicate that the proposed method can be applied to soft sensor modeling of complex nonlinear system.
引文
[1]M.Kano,Y.Nakagawa.Data-based process monitoring,process control,and quality improvement:Recent developments and applications in steel industry[J].Computers&Chemical Engineering,2008,32(1):12-24.
[2]K.Fujiwara,M.Kano,S.Hasebe,etc.Soft sensor development using correlation-based just-in-time modeling[J].AICh E Journal,2009,55(7):1754-1765.
[3]R.Grbi?,D.Sli?kovi?,P.Kadlec.Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models[J].Computers&Chemical Engineering,2013,58(22):84-97.
[4]C.Shang,F.Yang,D.Huang,etc.Data-driven soft sensor development based on deep learning technique[J].Journal of Process Control,2014,24(3):223-233.
[5]W.Yan,D.Tang,Lin Y.A data-driven soft sensor modeling method based on deep learning and its application[J].IEEE Transactions on Industrial Electronics,2016,(99):1-1.
[6]L.Jia,M.S.Chiu,S.S.Ge.A noniterative neuro-fuzzy based identification method for Hammerstein processes[J].Journal of Process Control,2005,15(7):749-761.
[7]L.Jia,K.Yuan.The probability density function based neuro-fuzzy model and its application in batch processes[J].Neurocomputing,2015,(148):216-221.
[8]L.Jia,M.S.Chiu,S.S.Ge.Iterative identification of neuro-fuzzy-based Hammerstein model with global convergence[J].Industrial&Engineering Chemistry Research,2005,44(6):1823-1831.
[9]Q.L.Xu,W.H.Lin,C.Zhao,etc.Prediction of oxygen-content in industrial boiler based on PCA-LSSVM.Computers and Applied Chemistry,2012,29(7):834-838.
[10]X.L.Li,N.Li,Y.J.Sun,etc.Research on flame radical imaging and extreme learning machine to prediction of NOx emissions.Journal of System Simulation,2016,28(5):1179-1185.
[11]L.Jia,K.Yuan.Auxiliary error and probability density function based neuro-fuzzy model and its application in batch processes[J].Chinese journal of chemical engineering,2015,23(12):2013-2019.
[12]J.L.Ding,T.Y.Chai,H.Wang.Offline modeling for product quality prediction of mineral processing using modeling error PDF shaping and entropy minimization[J].IEEE Transactions on Neural Networks,2011,22(3):408-19.
[13]R.P.Good,D.Kost,G.A.Cherry.Introducing a unified PCA algorithm for model size reduction[J].IEEE Transactions on Semiconductor Manufacturing,2010,23(2):201-209.
[14]J.Tang,L.Zhao,W.Yu,etc.Soft sensor modeling of ball mill load via principal component analysis and support vector machines[J].Lecture Notes in Electrical Engineering,2009,67(67):803-810.
[15]P.Kadlec,B.Gabrys,S.Strandt.Data-driven Soft Sensors in the process industry[J].Computers&Chemical Engineering,2009,33(4):795-814.
[16]P.Kadlec,R.Grbi?,B.Gabrys.Review of adaptation mechanisms for data-driven soft sensor[J].Computers&Chemical Chemical Engineering,2011,35(1):1-24.
[2]K.Fujiwara,M.Kano,S.Hasebe,etc.Soft sensor development using correlation-based just-in-time modeling[J].AICh E Journal,2009,55(7):1754-1765.
[3]R.Grbi?,D.Sli?kovi?,P.Kadlec.Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models[J].Computers&Chemical Engineering,2013,58(22):84-97.
[4]C.Shang,F.Yang,D.Huang,etc.Data-driven soft sensor development based on deep learning technique[J].Journal of Process Control,2014,24(3):223-233.
[5]W.Yan,D.Tang,Lin Y.A data-driven soft sensor modeling method based on deep learning and its application[J].IEEE Transactions on Industrial Electronics,2016,(99):1-1.
[6]L.Jia,M.S.Chiu,S.S.Ge.A noniterative neuro-fuzzy based identification method for Hammerstein processes[J].Journal of Process Control,2005,15(7):749-761.
[7]L.Jia,K.Yuan.The probability density function based neuro-fuzzy model and its application in batch processes[J].Neurocomputing,2015,(148):216-221.
[8]L.Jia,M.S.Chiu,S.S.Ge.Iterative identification of neuro-fuzzy-based Hammerstein model with global convergence[J].Industrial&Engineering Chemistry Research,2005,44(6):1823-1831.
[9]Q.L.Xu,W.H.Lin,C.Zhao,etc.Prediction of oxygen-content in industrial boiler based on PCA-LSSVM.Computers and Applied Chemistry,2012,29(7):834-838.
[10]X.L.Li,N.Li,Y.J.Sun,etc.Research on flame radical imaging and extreme learning machine to prediction of NOx emissions.Journal of System Simulation,2016,28(5):1179-1185.
[11]L.Jia,K.Yuan.Auxiliary error and probability density function based neuro-fuzzy model and its application in batch processes[J].Chinese journal of chemical engineering,2015,23(12):2013-2019.
[12]J.L.Ding,T.Y.Chai,H.Wang.Offline modeling for product quality prediction of mineral processing using modeling error PDF shaping and entropy minimization[J].IEEE Transactions on Neural Networks,2011,22(3):408-19.
[13]R.P.Good,D.Kost,G.A.Cherry.Introducing a unified PCA algorithm for model size reduction[J].IEEE Transactions on Semiconductor Manufacturing,2010,23(2):201-209.
[14]J.Tang,L.Zhao,W.Yu,etc.Soft sensor modeling of ball mill load via principal component analysis and support vector machines[J].Lecture Notes in Electrical Engineering,2009,67(67):803-810.
[15]P.Kadlec,B.Gabrys,S.Strandt.Data-driven Soft Sensors in the process industry[J].Computers&Chemical Engineering,2009,33(4):795-814.
[16]P.Kadlec,R.Grbi?,B.Gabrys.Review of adaptation mechanisms for data-driven soft sensor[J].Computers&Chemical Chemical Engineering,2011,35(1):1-24.