Hybrid optimization techniques based automatic artificial respiration system for corona patient

Abstract

Artificial ventilation is widely used for various respiratory problems of human beings. The oxygen level of the corona patients has to be maintained for smooth breathing which is very difficult. For achieving this state, the air pressure should be controlled in the respiration system that has a piston mechanism driven by a motor. An Automatic respiration system model is designed and controller parameters are tuned using hybrid Optimization techniques. Hybrid Controllers like genetic algorithm based Fractional Order Proportional Integral Derivative controller (FOPID), Fmincon-Pattern search Algorithm based Proportional Integral Derivative (PID) controller, and Hybrid Model predictive control (MPC) – Proportional Integral Derivative (PID) controllers were designed and verified. Integral Square Error is considered as the objective function of the optimization technique to find the controller parameters. The output responses of all three hybrid controllers are compared based on the error indices, time domain specifications, set-point tracking and Convergence speed graph. The genetic algorithm-based FOPID controller gives better results when compared with the Fmincon-Pattern search Algorithm based Proportional Integral Derivative (PID) controller and Hybrid Model predictive control (MPC) – Proportional Integral Derivative (PID) for the proposed artificial ventilation system.

Keywords

• artificial respiration
• genetic algorithm
• fmincon
• pattern search
• hybrid mpc-pid
• fopid