A Closed-loop Insulin Infusion System Based on Adaptive Generalized Predictive Control

Abstract

The invention discloses a closed-loop insulin infusion system based on adaptive generalized predictive control. The system comprises a blood glucose value detection module, a controller, an insulin pump and a program module, wherein the blood glucose value detection module is used for acquiring a blood glucose value, and an output end of the blood glucose value detection module is connected with an input end of the controller through signals; the insulin pump is used for infusing insulin, and an input end of the insulin pump is connected with an output end of the controller through signals; and the program module is executed by the controller, is used for acquiring the blood glucose value of a user through the blood glucose value detection module and regulating the infusion rate of the insulin pump through combination of a CARIMA model, a minimum variance control algorithm, an adaptive reference curve and adaptive softening factors. The slope of the reference curve is regulated according to the condition of the user by virtue of the adaptive reference curve, and values of the adaptive softening factors can be flexibly regulated according to different blood glucose values, so that the infusion rate of the insulin pump can be controlled in real time, and personalized treatment is better realized.

Description

technical field [0001] The invention relates to the field of insulin pump infusion volume estimation, and more specifically, relates to a closed-loop insulin infusion system based on adaptive generalized predictive control. Background technique [0002] Diabetes affects approximately 422 million adults worldwide and kills 1.5 million people each year. Type 1 diabetes, also known as insulin-dependent diabetes, is characterized by apoptosis of insulin-secreting cells in the pancreas and insufficient insulin secretion. Although the exact cause of type 1 diabetes is not clear, daily insulin infusion can effectively control the blood sugar level of diabetic patients, thereby improving the quality of life of patients. The artificial pancreas can effectively detect the blood sugar level of diabetic patients, and accurately calculate the infusion time and amount of insulin. The artificial pancreas mainly includes three parts: continuous blood glucose monitoring (CGM), intelligent ...

AI Technical Summary

Problems solved by technology

A lower softening factor can ensure that the generalized predictive control has a higher tracking speed, but it affects the robustness of the system

Although the artificial pancreas system can quickly respond to blood sugar changes, it has the defect of poor system stability

Conversely, a higher softening factor can ensure the robustness of the system, but sacrifices the tracking speed of the system

It is manifested that although the artificial pancreas system is relatively stable, it is slow to respond to fluctuations in blood sugar

Images