23 January 2017 Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes
Author Affiliations +
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.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Li Wang, Xiangguang Chen, Kai Yang, 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); doi: 10.1117/12.2265322; https://doi.org/10.1117/12.2265322
PROCEEDINGS
8 PAGES


SHARE
Back to Top