A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion

吕业; 杨慧中

doi:10.1016/S1004-9541(14)60007-0

Your Location：

Home >

Browse articles >

A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion

过程系统工程与过程安全 | Updated：2026-01-06

- A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion
- Chinese Journal of Chemical Engineering Vol. 22, Issue 2, Pages: 146-1521004-954160007-0(2014)
- Affiliations：
  
  Key Laboratory of Advanced Process Control for Light Industry of Jiangnan University,Wuxi,China,214122
- Author bio：
- Funds：
- DOI：10.1016/S1004-9541(14)60007-0
  CLC：
- Published：2014
- Accepted：
Scan QR Code
LÜ Ye, YANG Huizhong. A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion[J]. Chin.J.Chem.Eng., 2014, 22(2): 146-152.
DOI：

LÜ Ye, YANG Huizhong. A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion[J]. Chin.J.Chem.Eng., 2014, 22(2): 146-152. DOI： 10.1016/S1004-9541(14)60007-0.

摘要

Abstract

Multi-model approach can significantly improve the prediction performance of soft sensors in the process with multiple operational conditions. However

traditional clustering algorithms may result in overlapping phenomenon in subclasses

so that edge classes and outliers cannot be effectively dealt with and the modeling result is not satisfactory. In order to solve these problems

a new feature extraction method based on weighted kernel Fisher criterion is presented to improve the clustering accuracy

in which feature mapping is adopted to bring the edge classes and outliers closer to other normal subclasses. Furthermore

the classified data are used to develop a multiple model based on support vector machine. The proposed method is applied to a bisphenol A production process for prediction of the quality index. The simulation results demonstrate its ability in improving the data classification and the prediction performance of the soft sensor.

关键词

Keywords

references

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Attention-enhanced multi-time scale LSTM for soft sensor modeling of corn starch liquefaction

Multi-timescale feature extraction method of wastewater treatment process based on adaptive entropy

Neural network-based source tracking of chemical leaks with obstacles

Balanced multiple weighted linear discriminant analysis and its application to visual process monitoring

Active training sample selection and updating strategy for near-infrared model with an industrial application

Related Author

Du Jian

Zhang Lei

Wang Yu

Li Fan

Li Yi

Tao Jin

Zhang Zhongyi

Zhuang Yu

Related Institution

COFCO Biotechnology Co., Ltd.

Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology

Engineering Research Center of Digital Community, Ministry of Education

Beijing Key Laboratory of Computational Intelligence and Intelligent System

College of Environmental Sciences and Engineering, Beijing University of Technology

⁰