Metaheuristic Patient Estimation Based Patient-Specific Fuzzy Aggregated Artificial Pancreas Design

详细信息    查看全文

• 作者：V. Kirubakaran ; T. K. Radhakrishnan ; N. Sivakumaran
• 刊名：Industrial & Engineering Chemistry Research
• 出版年：2014
• 出版时间：October 1, 2014
• 年：2014
• 卷：53
• 期：39
• 页码：15052-15070
• 全文大小：1059K
• ISSN：1520-5045

文摘

Patient-specific artificial pancreas design has been receiving increasing attention lately. In this article, using the chaotic bat algorithm (CBA), Hovorka鈥揥ilinska (H鈥揥) model parameters are estimated from nominal H鈥揥 virtual patient data. Using this identified H鈥揥 model for the virtual patient, multiple empirical second-order plus delay time (SOPDT) models representing glucose鈥搃nsulin dynamics are derived for the range of blood glucose concentrations (BGCs) considered. Clustering of these models using the k-means algorithm yields three distinct clusters. Implicitly enumerated multiparametric model predictive controllers (mpMPCs) are designed using the cluster representatives. A fuzzy logic aggregation (FLA) of prediction and control improves the design parsimony. An insulin on board (IOB) safety trigger is designed using FLA of multiple full-order linearized CBA-estimated H鈥揥 models. The FLA-based mpMPC along with IOB and meal estimation are implemented on an embedded platform and by hardware-in-the-loop (HIL) simulation. In silico trials of the regulation of multiple meal disturbances are performed on the nominal H鈥揥 patient in MATLAB through serial communication. With meal estimation errors and varying insulin sensitivity, a very good low blood glucose index (LBGI) of <1 is observed. Control variability grid analysis (CVGA) also supports efficient elimination of hypoglycemic exposure by the designed artificial pancreas.