Design And Comparative Analysis Of Optimized Fopid Controller Using Neural Network Algorithm

Fractional-Order-Proportional-Integral-Derivative (FOPID) controllers are an extension of PID controllers and a field of research nowadays. FOPID controllers are popular amongst researchers for providing more degrees of freedom and broad applicability. In recent years, various metaheuristic algorithms and modified hybrid algorithms have been applied to tune these controllers. The aim of this paper is to design a FOPID controller with high versatility, accuracy and good control quality. In this research paper, first, a novel tuning method based on Neural Network Algorithm (NNA) has been used to optimize parameters of FOPID controller namely K P , K I , K D , λ and μ. Simulation results based on two control problems and comparison with applied PID techniques namely, Genetic Algorithm (GA), Zeigler Nichols (ZN) Technique, Ant Colony Optimization (ACO) and Multi-Objective Ant Colony Optimization (MOACO) for set point tracking, load rejection capability, noise suppression and model uncertainties have been carried out. As per findings of simulation results based on two control problems, NNA-FOPID has been found a good competitor amongst other Metaheuristic Algorithms based PID controllers.