Share Email Print
cover

Proceedings Paper

Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes
Author(s): Li Wang; Xiangguang Chen; Kai Yang; Huaiping Jin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Batch processes are always characterized by nonlinear and system uncertain properties, therefore, the conventional single model may be ill-suited. A local learning strategy soft sensor based on variable partition ensemble method is developed for the quality prediction of nonlinear and non-Gaussian batch processes. A set of input variable sets are obtained by bootstrapping and PMI criterion. Then, multiple local GPR models are developed based on each local input variable set. When a new test data is coming, the posterior probability of each best performance local model is estimated based on Bayesian inference and used to combine these local GPR models to get the final prediction result. The proposed soft sensor is demonstrated by applying to an industrial fed-batch chlortetracycline fermentation process.

Paper Details

Date Published: 23 January 2017
PDF: 8 pages
Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103222E (23 January 2017); doi: 10.1117/12.2265322
Show Author Affiliations
Li Wang, Beijing Institute of Technology (China)
Xiangguang Chen, Beijing Institute of Technology (China)
Kai Yang, Beijing Institute of Technology (China)
Beijing Research and Design Institute of Rubber Industry (China)
Huaiping Jin, Beijing Institute of Technology (China)


Published in SPIE Proceedings Vol. 10322:
Seventh International Conference on Electronics and Information Engineering
Xiyuan Chen, Editor(s)

© SPIE. Terms of Use
Back to Top