الفهرس 
صفحة العنوانOnly 14 pages are availabe for public view
 |  | from | 181 |  |  |
| | | from | 181 | | |
Abstract
ype 1 Diabetes Mellitus (T1DM) is a chronic disease which is spread worldwide. The main cause of this disease is that the pancreas of type 1 diabetic patients does not produce insulin. Thus, insulin therapy is required for T1DM patients to maintain their Blood Glucose (BG) level within the normal range. Exogenous insulin is usually administered by multiple daily injections (MDI), from 3 to 5 times a day. This method of insulin therapy is unsuitable and painful. Therefore, a closed-loop control system, which is known as Artificial Pancreas (AP), is to be used by patients with T1D to maintain their BG level at the normal range during daily life.
In this thesis, an Adaptive Nonlinear Model Predictive Control (ANMPC) algorithm for blood glucose regulation in type 1 diabetic patients is developed. The proposed closed-loop control system uses nonlinear model predictive control (NMPC) which is based on Feed Forward Neural Network (FFNN), Fuzzy Logic Controller (FLC) and an Adaptation paradigm. Due to the delay between the moment of insulin injection and the moment of insulin interaction with the blood glucose, MPC is required to compensate for this delay