Title :
Soft sensor of glutamate concentration using extreme learning machine
Author :
Rongjian Zheng ; Feng Pan
Author_Institution :
Key Lab. of Adv. Process Control for Light Ind. (Minist. of Educ.), Jiangnan Univ., Wuxi, China
Abstract :
Soft sensors have been widely used in biochemical process to estimate process variables that are difficult to measure online. In this paper, glutamate concentration is an important parameter of product quality for fermentation process, soft sensor was used to estimate glutamate concentration. In order to realizing real-time measurement of glutamate concentration, firstly analysing fermentation working principle and major factor, soft-sensor based on extreme learning machine was set up to predict glutamate concentration, then, the soft measurement model is compared to soft-sensor based on support vector machine, the learning capacity and generalization performance is also tested, the experimental results show that the application of extreme learning machine has a better ability to prediction glutamate concentration.
Keywords :
biotechnology; fermentation; learning (artificial intelligence); product quality; production engineering computing; support vector machines; biochemical process; extreme learning machine; fermentation process; generalization performance; glutamate concentration; learning capacity; product quality; soft measurement model; soft sensor; support vector machine; Artificial neural networks; Biomass; Chemical engineering; Computational modeling; Computers; Process control; Support vector machines; extreme learning machine; glutamate fermentation; soft-sensor; support vector machine;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2014 11th World Congress on
DOI :
10.1109/WCICA.2014.7053004