CIESC Journal ›› 2013, Vol. 64 ›› Issue (3): 788-800.DOI: 10.3969/j.issn.0438-1157.2013.03.003

Previous Articles     Next Articles

Modeling of soft sensor for chemical process

CAO Pengfei, LUO Xionglin   

  1. Research Institute of Automation, China University of Petroleum, Beijing 102249, China
  • Received:2012-06-04 Revised:2012-07-20 Online:2013-03-05 Published:2013-03-05
  • Supported by:

    supported by the National Basic Research Program of China(2012CB720500).

化工过程软测量建模方法研究进展

曹鹏飞, 罗雄麟   

  1. 中国石油大学自动化研究所,北京 102249
  • 通讯作者: 罗雄麟
  • 作者简介:曹鹏飞(1988—),男,博士研究生。
  • 基金资助:

    国家重点基础研究发展计划项目(2012CB720500)。

Abstract: In the commercial chemical process,many primary product variables cannot be measured online,and soft sensor is an important means to solve this problem.Soft sensing modeling is the core issue of soft sensor.The relationship between soft sensing modeling and identification and nonlinear modeling is presented.The dynamic relationship between quality variables and variables that are easy to measure exists between the increments,and identification depends on incremental data,while soft sensing modeling depends on the measured data to get the relationship.Nonlinear modeling establishes the static relationship between these variables,ignoring the dynamic characteristics,which soft sensing modeling should take into account.With deeper understanding of the chemical process properties,the types and structures of soft sensing model have undergone a great change in the last decades,and soft sensing modeling method evolves from mechanism modeling to data-driven modeling,from linear modeling to nonlinear modeling,and from static modeling to dynamic modeling.The development of the soft sensing modeling method is reviewed.The advantages and disadvantages of the proposed methods are analyzed,and the applications of these methods are shown.In the end,the hot issues and the directions of development of soft sensing modeling method are presented.

Key words: soft sensor, modeling, identification, nonlinear modeling, data-driven modeling, nonlinear dynamic modeling

摘要: 软测量仪表是解决化工过程中质量变量难以实时测量的重要手段。软测量仪表的核心问题是软测量建模。阐述了软测量建模与辨识和非线性建模的关系:质量变量和易测变量的动态关系存在于增量之间,辨识模型依赖于增量数据,软测量建模则是依赖于实测变量数据来获取这个动态关系;非线性建模建立了变量间的静态关系,忽略了对象动态特性,而软测量建模要兼顾对动态特性的表征。随着人们对过程特性的认识加深,软测量建模方法不断发展,经历了从机理建模到数据驱动建模,从线性建模到非线性建模,从静态建模到动态建模的过程。详细讨论了软测量建模的发展过程,众多建模方法的优缺点及适用情况和现在建模的热点,最后对软测量建模方法进行了总体展望。

关键词: 软测量, 建模, 辨识, 非线性建模, 数据驱动建模, 非线性动态建模

CLC Number: