ADynamic AI Controllerfor aField-Oriented ControlledBLDC Motorto Achieve the Desired AngularVelocity and Torque

Abstract

Compared to traditional motor controlling techniques, the modern Artificial Intelligent (AI) controllers have many advantages. During the past decades, stochastic search and heuristic optimization algorithms such as Genetic Algorithm (GA) and Simulated Annealing (SA) have effectively enhanced the performance of motor control applications. This paper presents a metaheuristic adaptive fuzzy logic-particle swarm optimization control mechanism to optimize the speed regulation of the electric current space vector-controlled BLDC motor while modelling in MATLAB Simulink environment. This is a part of the designed and developed AI controller, for stability and traction control of a four-wheel drive electric rover. To identify the behaviour of the parameters and the algorithm of the proposed controller, this developed simulation model was utilized by taking into account only the behaviour of a one BLDC motor. In the proposed TSK-PSO-FL controller, the PSO technique is utilized to define the heuristic fuzzy associative matrix and another separately dedicated zero-order fuzzy logic controller (TSK-FLC) utilized to optimize the PSO parameters online such as the swarm hyperspace (population size), inertia weights and the acceleration. Simulated test results are presented, analyzed and compared with the developed hardware test model in addition to the newly published research work. Moreover, in addition to the simulation model, the proposed TSK-PSO-FLC was tested on a 3-ph / 250W power BLDC motor in real-time operation. The analyzed test results are clearly showing that the proposed control mechanism has been optimized and enhanced the speed regulation performance of the BLDC motor significantly while increasing the frequency of the desired input trajectory.