•  
  •  
 

Journal of System Simulation

Abstract

Abstract: Chemical processes are often characterized by nonlinearity and multi-phase, a soft sensor model based on the hierarchical ensemble of Gaussian process regression is proposed. First, the Gaussian mixture model is used to divide the process data into different operation phases. Then, the principal component analysis of each stage is carried out, and the model data are divided into several subspaces, according to the contribution of each auxiliary variable in the principal component space, and the corresponding Gaussian process regression model is built. The subspace model output is fused by means to obtain the first level ensemble output. Finally, the posterior probability is used to fuse the model local prediction to obtain the second level ensemble output. The validity of the proposed method is verified by the experimental simulation of industrial data.

First Page

2042

Revised Date

2017-08-28

Last Page

2051

CLC

TP274

Recommended Citation

Zhao Shuai, Shi Xudong, Xiong Weili. A Hierarchical Integrated Soft Sensing Modeling Method for Gauss Process Regression[J]. Journal of System Simulation, 2019, 31(10): 2042-2051.

DOI

10.16182/j.issn1004731x.joss.17-0374

Share

COinS