Comparison of several data‐driven non‐linear system identification methods on a simplified glucoregulatory system example. Issue 17 (1st November 2014)

• Record Type: Journal Article
• Authors: Marconato, Anna; Schoukens, Maarten; Tiels, Koen; Widanage, Widanalage Dhammika; Abu‐Rmileh, Amjad; Schoukens, Johan
• Is Part Of: IET control theory & applications. Volume 8:Issue 17(2014)
• Page Start: 1921
• Page End: 1930
• Publication Date: 2014-11-01
• Subjects: patient treatment -- closed loop systems -- nonlinear control systems -- identification -- sugar -- diseases -- blood -- state‐space methods -- control system synthesis -- medical control systems -- artificial organs; advanced data‐driven nonlinear system identification techniques -- simplified glucoregulatory system modelling -- artificial pancreas -- Type 1 diabetes mellitus treatment -- nonlinear model -- closed‐loop controller design -- glucose level regulation -- model‐based controller -- patient behaviour -- insulin‐glucose system -- state‐space model -- block‐oriented model -- blood; Control theory -- Periodicals; Automatic control -- Periodicals; 629.8312
• DOI: 10.1049/iet-cta.2014.0534
• Languages: English
• ISSNs: 1751-8644

Abstract

Abstract : In this study, several advanced data‐driven non‐linear identification techniques are compared on a specific problem: a simplified glucoregulatory system modelling example. This problem represents a challenge in the development of an artificial pancreas for Type 1 diabetes mellitus treatment, since for this application good non‐linear models are needed to design accurate closed‐loop controllers to regulate the glucose level in the blood. Block‐oriented as well as state‐space models are used to describe both the dynamics and the non‐linear behaviour of the insulin–glucose system, and the advantages and drawbacks of each method are pointed out. The obtained non‐linear models are accurate in simulating the patient's behaviour, and some of them are also sufficiently simple to be considered in the implementation of a model‐based controller to develop the artificial pancreas.