Title :
The research on application of sliding window LS_SVMin the batch process
Author :
Xin Sun ; Xue Jin gao ; Zhi Yang jia
Author_Institution :
Coll. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., Beijing, China
Abstract :
This paper presents an improved regression algorithm of sliding window least squares support vector machine (the Sliding Window LS_SVM). This method simplifies the data within the sliding window, and selects the similar data for local modeling from a database of historical batches to predict the data within the sliding window. Combined with local modeling, the improved sliding window LS_SVM algorithm is very effective to predict the cell concentration in the penicillin fermentation process.
Keywords :
batch processing (industrial); fermentation; regression analysis; batch process; penicillin fermentation proces; regression algorithm; sliding window least squares support vector machine; Adaptation models; Batch production systems; Data models; Databases; Predictive models; Support vector machines; Training;
Conference_Titel :
American Control Conference (ACC), 2013
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4799-0177-7
DOI :
10.1109/ACC.2013.6579852
