Fuzzy PID Control for Respiratory Systems
Fuzzy PID Control for Respiratory Systems
Mehedi, Ibrahim M.;Shah, Heidir S. M.;Al-Saggaf, Ubaid M.;Mansouri, Rachid;Bettayeb, Maamar
2021-06-24 00:00:00
Hindawi Journal of Healthcare Engineering Volume 2021, Article ID 7118711, 6 pages https://doi.org/10.1155/2021/7118711 Research Article 1,2 1 1,2 3 IbrahimM.Mehedi , HeidirS.M.Shah, UbaidM.Al-Saggaf , RachidMansouri , and Maamar Bettayeb Department of Electrical and Computer Engineering (ECE), King Abdulaziz University, Jeddah 21589, Saudi Arabia Center of Excellence in Intelligent Engineering Systems (CEIES), King Abdulaziz University, Jeddah 21589, Saudi Arabia Laboratoire de Conception et Conduite des Systemes de Production (L2CSP), Tizi Ouzou, Algeria Electrical Engineering Department, University of Sharjah, Sharjah, UAE Correspondence should be addressed to Ibrahim M. Mehedi; imehedi@kau.edu.sa Received 31 May 2021; Revised 8 June 2021; Accepted 12 June 2021; Published 24 June 2021 Academic Editor: Dilbag Singh Copyright © 2021 Ibrahim M. Mehedi et al. (is is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (is paper presents the implementation of a fuzzy proportional integral derivative (FPID) control design to track the airway pressure during the mechanical ventilation process. A respiratory system is modeled as a combination of a blower-hose-patient system and a single compartmental lung system with nonlinear lung compliance. For comparison purposes, the classical PID controller is also designed and simulated on the same system. According to the proposed control strategy, the ventilator will provide airway flow that maintains the peak pressure below critical levels when there are unknown parameters of the patient’s hose leak and patient breathing effort. Results show that FPID is a better controller in the sense of quicker response, lower overshoot, and smaller tracking error. (is provides valuable insight for the application of the proposed controller. until the 1950s. A mechanical ventilator used mechanical 1. Introduction bellows and valves to cycle gas into the lungs, while a simple (e world has been shocked by the COVID-19 disease since proportional (P) or proportional-integral (PI) controller was its outbreak was first detected in Wuhan, China, in De- used [9]. Later, microprocessors were used to implement cember 2019. It was then declared as a global pandemic by those controllers, and since then, there have been numerous the World Health Organization (WHO) three months later, closed-loop control proposals. and at the time of writing, more than 174 million people Closed-loop control in mechanical ventilators can be worldwide have been infected with the disease with close to 4 categorized based on how much the system interacts with million deaths recorded [1, 2]. (e analysis shows that acute patients. A class 1 control loop features no backward inter- respiratory failure (ARF) is the leading cause of death [3], action from the patient to the device, whereas in the class 2 and one study found that 40 percent of critically ill COVID- control loop, interaction between the patient and device is possible. In both classes, control signals are measured inside 19 patients developed acute respiratory distress syndrome (ARDS) which requires invasive incubation and ventilation the device. A class 3 control loop is called physiological [4–7]. Such therapies can be provided by an intensive care compensatory control loops due to the fact that it uses the unit’s (ICU) device called a mechanical ventilator that is physiological parameter as its control variable instead of the used to assist or replace the spontaneous breathing of a physical one [10]. In this paper, a pressure-based ventilation patient [8]. controller under the class 2 category is developed where the Mechanical ventilators were first used to assist in ven- control objective is to track a set-point target airway pressure. tilation as early as the 18th century, but the first closed-loop Having a reputation as the most reliable industrial system for mechanical ventilation did not become available controller, the PID controller has been used widely in 2 Journal of Healthcare Engineering mechanical ventilators. One of the earliest implementa- desired pressure, (p ), the hose which connects the re- out tions of PID controller on a mechanical ventilator since spiratory module to the patient, and the patient’s lung. (e the introduction of the microprocessor can be found in airway pressure p is measured using a pressure sensor that aw Ohlson works [11]. PID, however, has some limitations: it is placed inside the module. (e control objective is to track did not perform well when the system’s dynamics are not the measured pressure so that it follows the target set-point constant. An example of this is the relationship between p . (erefore, the error equation can be described as target ventilation and pressure. During ventilation, pressure follows: must be adjusted according to the level of ventilation to e � p − p . (1) target aw prevent lung injury. To improve controller performance, Dai et al. [12] used two separate algorithms where the PD (e air from the blower flows (Q ) through the hose out algorithm is used during the initial phase while PI al- with the resistance of R into the lung (Q ) with the hose pat gorithm will be activated when the output pressure started resistance of R for inhalation process. (e patient then lung to be constant. Besides this, other techniques were also exhales the air back to the hose where some of it will flow out used to improve PID controller performance in the me- of the leak (Q ) with the resistance of R . (e leak also leak leak chanical ventilation system including the use of optimi- prevents some of the exhaled air to be inhaled back by the zation techniques called pressure evaluate correction patient in the next cycle. (us, we can write the patient flow module (PECM) [13], an automatic tuning of PID gains equation as follows: using particle swarm optimization (PSO) [14, 15] and Q � Q − Q , (2) repetitive control [8]. pat out leak In this paper, we proposed a fuzzy PID (FPID) controller Here, the blower flow, leak flow, and patient flow can be for airway pressure set-point tracking of mechanical ven- obtained by pressure differences over resistance as follows: tilation. Fuzzy reasoning is used to evaluate the changes of p − p the system’s dynamic through the measured set-point error out aw Q � , (3) out and the rate of change of error which, in turn, updates the hose PID tuning parameters based on the rules set. (e process of updating the tuning parameters is done in an online manner. aw Q � , (4) leak (e proposed controller is then simulated on a respiratory leak system model which consists of a blower-hose-patient p − p system model and a single compartmental lung model which aw lung Q � . (5) pat is obtained from the works of Hunnekens et al. [16] and lung Bates [17], respectively. (e fuzzy logic-based controller has been imple- (e lung pressure can be described by the following mented in many applications including the longitudinal differential equation: autopilot of an unmanned aerial vehicle (UAV) [18], controlling the speed of the conveyor system [19], sim- p � Q . (6) lung pat lung ulating the tissue differentiation process [20], and in- duction motor control [21]. (e primary purpose of this (e lung dynamic can be written by combining (3)–(6) proposed controller is to enhance the performance of the as follows: PID controller on a respiratory system where some of its p − p mechanical parameters are not constant, specifically, lung aw lung p _ � . (7) lung compliance, which can be increased or decreased C R lung lung according to the lung volume. Substituting and rewriting (3)–(5) in (2) results in the (e rest of this paper is organized as follows: Section 2 presents the details of the mathematical model for the following relation for the airway pressure: blower-hose-patient system and single lung compartmental 1/R p + 1/R p lung lung hose out model and also presents a brief explanation about lung p � . (8) aw compliance. (e details of the proposed controller design are 1/R + 1/R + 1/R lung hose leak discussed in Section 3, while the simulation results, analysis, By substituting the airway pressure expression in (8) into and comparison between PID and FPID are presented in the differential equation for the lung dynamic (6), the fol- Section 4. Section 5 concludes the work. lowing may be achieved: 2. Mathematical Model of Respiratory Systems −