Affiliations: [a] Department of Electronic Engineering, Feng-Chia University, Taichung, Taiwan
| [b] Department of Metabolism and Endocrinology, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation and School of Medicine, Tzu Chi University
| [c] Department of Automatic Control Engineering, Feng-Chia University, Taichung, Taiwan
| [d]
“Aurel Vlaicu” University of Arad, Romania
| [e]
Vasile Goldis Western University of Arad, Romania
| [f] Electrical Engineering Department, National Institute of Technology, Assam, India
Abstract: This paper presents an identifier based intelligent adaptive fuzzy control scheme with regulating blood glucose concentration in normoglycemic level of 70 mg/dl for type 1 diabetic patients. The identifier is built with fuzzy neural network (FNN) to predict the blood glucose concentration of the diabetic patient. The fuzzy based controller with generic operating regimes which cluster all the adaptive control rules is designed to robustly reject the multiple meal disturbances resulting from food intake and deal with the parametric uncertainties in model and measurement noise. All the parameters of the FNN and of the fuzzy logic system are tuned by backpropagation (BP), to achieve the control objectives. The numerical simulations are performed to show that the set point tracking, meal disturbances and measurement noise rejection can be realized within this method.
