Atmospheric tower soft sensor based on regression and mutual information of kernel slow features

JIANG Xinyi; DU Hongbin; LI Shaojun

doi:10.11949/j.issn.0438-1157.20161395

您当前的位置：

首页 >

文章列表页 >

Atmospheric tower soft sensor based on regression and mutual information of kernel slow features

更新时间：2025-12-10

- Atmospheric tower soft sensor based on regression and mutual information of kernel slow features
- CIESC Journal Issue 5, Pages: 1977-1986(2017)
- 作者机构：
  
  1. 华东理工大学化工过程先进控制与优化技术教育部重点实验室,上海,200237
  2. 中国石油天然气股份有限公司独山子石化研究院,新疆,克拉玛依,833699
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20161395
  CLC： P274
- Online First：05 May 2017，
  
  Published：05 May 2017
- 稿件说明：
移动端阅览
JIANG Xinyi, DU Hongbin, LI Shaojun. Atmospheric tower soft sensor based on regression and mutual information of kernel slow features[J]. CIESC Journal, 2017, (5): 1977-1986.
DOI：

JIANG Xinyi, DU Hongbin, LI Shaojun. Atmospheric tower soft sensor based on regression and mutual information of kernel slow features[J]. CIESC Journal, 2017, (5): 1977-1986. DOI： 10.11949/j.issn.0438-1157.20161395.

摘要

针对工业过程的非线性及动态特性，提出了一种新的慢特征回归软测量方法。该方法首先通过添加时延数据构造动态数据集，利用互信息最大化准则筛选变量从而减少信息冗余的影响。同时该方法在慢特征分析的基础上引入核函数扩展，加强模型处理非线性数据的能力，并将获得的核慢特征用于回归建模。核慢特征分析通过分析样本的变化，提取具有缓慢变化特征的成分，可以有效地刻画工业过程的变化趋势，提升回归模型精度。最后该方法的有效性在常压塔常顶油干点与常一线初馏点的软测量模型中得到了验证。

Abstract

A novel soft sensor method based on slow feature regression (SFR) was proposed for industrial process with nonlinear and dynamic characteristics. First

a dynamic dataset was built by adding time-delay data and information redundancy was reduced by selecting variables according to mutual information maximization criteria. Then

kernel function was introduced into slow feature analysis(SFA)to improve capability of processing nonlinear data and the kernel slow features were used for regression. Through analysis of sample variation

kernel slow feature analysis(KSFA)could extract components with slowly varying dynamics

characterize trend of industrial process effectively

and improve precision of regression modelling. Finally

effectiveness and feasibility of the proposed method were verified by soft sensor model of constant top oil dry point and constant first line dropping point in atmospheric tower.

关键词

Keywords

references

Views

301

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Effluent BOD soft measurement based on mutual information and self-organizing RBF neural network

Ensemble soft sensor modeling for dynamic liquid level of oil well based on multi-source information feature fusion

Online dynamic Gaussian process regression for dynamic liquid level soft sensing of sucker-rod pumping well

Soft sensor development based on deep extended variational autoencoder with just-in-time learning

Particle size prediction of cobalt oxalate synthesis process based on slow feature analysis and least squares support vector regression

Related Author

Wenjing LI

Meng LI

Junfei QIAO

LI Xiangyu

GAO Xianwen

LI Kun

HOU Yanbin

LI Xiangyu

Related Institution

Faculty of Information Technology, Beijing University of Technology

Beijing Key Laboratory of Computational Intelligence and Intelligent System

College of Information Science & Engineering, Northeastern University

College of Engineering, Bohai University

School of Information Science & Engineering, Northeastern University

⁰