Adaptive Fuzzy Sliding Mode Control of a Pressure-Controlled Artificial Ventilator. (24th June 2021)

• Record Type: Journal Article
• Authors: Mehedi, Ibrahim M.; Shah, Heidir S. M.; Al-Saggaf, Ubaid M.; Mansouri, Rachid; Bettayeb, Maamar
• Other Names: Singh Dilbag Academic Editor.
• Is Part Of: Journal of healthcare engineering. Volume 2021(2021)
• Publication Date: 2021-06-24
• Subjects: Hospital buildings -- Environmental engineering -- Periodicals; Medical technology -- Periodicals; Medical informatics -- Periodicals; 610.28
• DOI: 10.1155/2021/1926711
• Languages: English
• ISSNs: 2040-2295

Abstract

Abstract : This paper presents the application of adaptive fuzzy sliding mode control (AFSMC) for the respiratory system to assist the patients facing difficulty in breathing. The ventilator system consists of a blower-hose-patient system and patient's lung model with nonlinear lung compliance. The AFSMC is based on two components: singleton control action and a discontinuous term. The singleton control action is based on fuzzy logic with adjustable tuning parameters to approximate the perfect feedback linearization control. The switching control law based on the sliding mode principle aims to minimize the estimation error between approximated single fuzzy control action and perfect feedback linearization control. The proposed control strategy manipulated the airway flow delivered by the ventilator such that the peak pressure will remain under critical values in presence of unknown patient-hose-leak parameters and patient breathing effort. The closed-loop stability of AFSMC will be proven in the sense of Lyapunov. For comparative analysis, classical PID and sliding mode controllers are also designed and implemented for mechanical ventilation problems. For performance analysis, numerical simulations were performed on a mechanical ventilator simulator. Simulation results reveal that the proposed controller demonstrates better tracking of targeted airway pressure compared with its counterparts in terms of faster convergence, less overshoot, and small tracking error. Hence, the proposed controller provides useful insight for its application to real-world scenarios.