Title :
JITL based local monitoring method for transitions of multiphase batch processes
Author :
Feifan Shen ; Zhihuan Song ; Zhiqiang Ge
Author_Institution :
State Key Lab. of Ind. Control Technol., Zhejiang Univ., Hangzhou, China
Abstract :
Quality-relevant monitoring for multiphase batch processes is necessary. Between-phase transitions carry significant quality information and need particular attentions. In this paper, a Just-in-time-learning (JITL) based method is introduced to identify transitions and update modeling dataset of transitions. Due to the non-Gaussian distribution of the samples in the local model, a PLS-SVDD based method is proposed for modeling and monitoring. Fed-batch penicillin fermentation process is tested for performance evaluation of the proposed method.
Keywords :
batch processing (industrial); fermentation; just-in-time; learning (artificial intelligence); process monitoring; production engineering computing; quality management; support vector machines; JITL based local monitoring method; PLS-SVDD based method; between-phase transitions; fed-batch penicillin fermentation process; just-in-time-learning based method; multiphase batch process transitions; nonGaussian distribution; performance evaluation; quality-relevant monitoring; support vector data description; Batch production systems; Industrial control; Laboratories; Matrix decomposition; Monitoring; Substrates; Fault detection/accommodation;
Conference_Titel :
American Control Conference (ACC), 2014
Conference_Location :
Portland, OR
Print_ISBN :
978-1-4799-3272-6
DOI :
10.1109/ACC.2014.6858792
