SCI和EI收录∣中国化工学会会刊

Chinese Journal of Chemical Engineering ›› 2014, Vol. 22 ›› Issue (2): 146-152.DOI: 10.1016/S1004-9541(14)60007-0

• 过程系统工程与过程安全 • 上一篇    下一篇

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

吕业, 杨慧中   

  1. Key Laboratory of Advanced Process Control for Light Industry of Jiangnan University, Wuxi 214122, China
  • 收稿日期:2012-08-10 修回日期:2012-10-06 出版日期:2014-02-05 发布日期:2014-01-28
  • 通讯作者: YANG Huizhong
  • 基金资助:

    Supported by the National Natural Science Foundation of China (61273070) and the Foundation of Priority Academic Program Development of Jiangsu Higher Education Institutions.

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

LÜ Ye, YANG Huizhong   

  1. Key Laboratory of Advanced Process Control for Light Industry of Jiangnan University, Wuxi 214122, China
  • Received:2012-08-10 Revised:2012-10-06 Online:2014-02-05 Published:2014-01-28
  • Contact: YANG Huizhong
  • Supported by:

    Supported by the National Natural Science Foundation of China (61273070) and the Foundation of Priority Academic Program Development of Jiangsu Higher Education Institutions.

摘要: 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: feature extraction, weighted kernel Fisher criterion, classification, soft sensor

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.

Key words: feature extraction, weighted kernel Fisher criterion, classification, soft sensor