Adaptive TS fuzzy MPC based on Particle Swarm Optimization-Cuckoo Search algorithm. (December 2022)

• Record Type: Journal Article
• Authors: Taieb, Adel; Salhi, Hichem; Chaari, Abdelkader
• Is Part Of: ISA transactions. Volume 131(2022)
• Page Start: 598
• Page End: 609
• Publication Date: 2022-12
• Subjects: Adaptive Model Predictive Control -- Takagi–Sugeno -- Cuckoo Search -- Particle Swarm Optimization -- Nonlinear system; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2022.05.018
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: A novel technique to building an adaptable fuzzy model predictive control (AFMPC) is suggested in this study, based on the algorithm Particle Swarm Optimization-Cuckoo Search (PSOCS). This technique combines the particle swarm optimization (PSO) algorithm's iterative scheme with the Cuckoo Search (CS) algorithm's searching approach. To identify the system parameters at each time step, an on-line adaptive fuzzy identification is used. Based on a predictive technique, these factors are utilized to generate the goal function. The PSOCS method is then used to solve the optimization issue and select the best control signal. The suggested controller's utility is demonstrated using an experimental communicating three-tank system, in which the proposed approach-based PSOCS algorithm outperforms both the approach-based CS and the approach-based PSO algorithms. Highlights: Formulate a PSOCS algorithm and analyzes its performance by numerical computing. The PSOCS is applied to calculate the predictive control of a nonlinear system. The PSOCS is able to handle a nonlinear system manipulated under hard constraints. The WRLS is used to adapt the consequent parameters in a recursive way.