Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes

Li Wang; Xiangguang Chen; Kai Yang; Huaiping Jin

doi:10.1117/12.2265322

23 January 2017 Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes

Li Wang, Xiangguang Chen, Kai Yang, Huaiping Jin

Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103222E (2017) https://doi.org/10.1117/12.2265322
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China

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.

Citation Download Citation

Li Wang, Xiangguang Chen, Kai Yang, and Huaiping Jin "Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103222E (23 January 2017); https://doi.org/10.1117/12.2265322

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available