Two degree of freedom PID based inferential control of continuous bioreactor for ethanol production. (May 2017)

• Record Type: Journal Article
• Authors: Pachauri, Nikhil; Singh, Vijander; Rani, Asha
• Is Part Of: ISA transactions. Volume 68(2017:May)
• Page Start: 235
• Page End: 250
• Publication Date: 2017-05
• Subjects: Bioreactor -- ADALINE -- LMPNN -- BRBNN -- PID -- 2-DOF-PID; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2017.03.014
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: This article presents the development of inferential control scheme based on Adaptive linear neural network (ADALINE) soft sensor for the control of fermentation process. The ethanol concentration of bioreactor is estimated from temperature profile of the process using soft sensor. The prediction accuracy of ADALINE is enhanced by retraining it with immediate past measurements. The ADALINE and retrained ADALINE are used along with PID and 2-DOF-PID leading to APID, A2PID, RAPID and RA2PID inferential controllers. Further the parameters of 2-DOF-PID are optimized using Non-dominated sorted genetic algorithm-II and used with retrained ADALINE soft sensor which leads to RAN2PID inferential controller. Simulation results demonstrate that performance of proposed RAN2PID controller is better in comparison to other designed controllers in terms of qualitative and quantitative performance indices. Highlights: Fast and economic composition measurements are performed with the help of soft sensors using secondary measurement to facilitate composition control. The estimator performance is enhanced by retraining ADALINE based soft sensor using immediate past measurements. 2-DOF-PID and retrained ADALINE based soft sensor are used in proposed inferential control scheme. The parameters of 2-DOF-PID with retrained ADALINE are optimized with the help of NSGA-II optimization algorithm. The performance of NSGA-II tuned 2-DOF-PID controller with retrained ADALINE soft sensor proves to be the most efficient in comparison to the other designed inferential controllers.