SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2012, Vol. 20 ›› Issue (6): 1213-1218.

• • 上一篇    下一篇

Soft-sensing Design Based on Semiclosed-loop Framework*

汤奇峰1, 李德伟1, 席裕庚1, 尹德斌2   

  1. 1. Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China;
    2. Shanghai Xinhua Control Technology (Group) Co., Ltd, Shanghai 200241, China
  • 收稿日期:2012-04-14 修回日期:2012-05-14 出版日期:2012-12-28 发布日期:2012-12-28
  • 通讯作者: LI Dewei,E-mail:dwli@sjtu.edu.cn
  • 基金资助:
    Supported by the National Natural Science Foundation of China (60934007;61074060;61104078);the Research and Innovation Project of Shanghai Education Commission (11CXY08);the State Key Laboratory of Synthetical Automation for Process Industries.

Soft-sensing Design Based on Semiclosed-loop Framework*

TANG Qifeng1, LI Dewei1, XI Yugeng1, YIN Debin2   

  1. 1. Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China;
    2. Shanghai Xinhua Control Technology (Group) Co., Ltd, Shanghai 200241, China
  • Received:2012-04-14 Revised:2012-05-14 Online:2012-12-28 Published:2012-12-28
  • Supported by:
    Supported by the National Natural Science Foundation of China (60934007;61074060;61104078);the Research and Innovation Project of Shanghai Education Commission (11CXY08);the State Key Laboratory of Synthetical Automation for Process Industries.

摘要: Soft-sensing is widely used in industrial applications.The traditional soft-sensing structure is open-loop without correction mechanism.If the working condition is changed or there is unknown disturbance,the forecast result of soft-sensing model may be incorrect.In order to obtain accurate values,it is necessary to carry out online correction.In this paper,a semiclosed-loop framework (SLF) is proposed to establish a soft-sensing approach,which estimates the input variables in the next moment by a prediction model and calibrates the output variables by a compensation model.The experimental results show that the proposed method has better prediction accuracy and robustness than other open-loop models.

关键词: soft-sensing, neural network, semiclosed-loop framework

Abstract: Soft-sensing is widely used in industrial applications.The traditional soft-sensing structure is open-loop without correction mechanism.If the working condition is changed or there is unknown disturbance,the forecast result of soft-sensing model may be incorrect.In order to obtain accurate values,it is necessary to carry out online correction.In this paper,a semiclosed-loop framework (SLF) is proposed to establish a soft-sensing approach,which estimates the input variables in the next moment by a prediction model and calibrates the output variables by a compensation model.The experimental results show that the proposed method has better prediction accuracy and robustness than other open-loop models.

Key words: soft-sensing, neural network, semiclosed-loop framework