APPLICATION OF PARTICLE SWARM OPTIMIZATION FOR CONTROL OF BLDC MOTOR

• Main Author: CHEARYLNA JELAWAI, ABIK
• Format: Final Year Project Report
• Language: English
• Published: Universiti Malaysia Sarawak, (UNIMAS) 2022
• Subjects: QP Physiology
• Online Access: http://ir.unimas.my/id/eprint/40061/1/Chearylna%20Jelawai%20%20ft.pdf; http://ir.unimas.my/id/eprint/40061/

Brushless DC motors are used in many industrial settings because they are more efficient, have high torque, and take up less space. This project proposed an adaptive neuro-fuzzy inference system (ANFIS) and fuzzy proportional integral derivative (Fuzzy PID) controllers to control the speed of a brushless DC motor. The controller was further studied with an optimizer which is a particle swarm optimization algorithm. The need for this particle swarm optimization came from the fact that it was hard to meet control characteristics with normal proportional integral derivative controllers. The fuzzy logic controller works with systems that are complicated, don't work in a straight line, and are very smart. Artificial neural networks are very good at learning, adapting, being strong, and moving quickly. The adaptive neuro-fuzzy inference system is better than both fuzzy logic controllers and artificial neural networks in some ways. The simulation results for a nominal speed of 700 rpm show that the adaptive neuro-fuzzy inference system (ANFIS) controller has better control performance than the Fuzzy PID controller because it didn't overshoot and had the shortest settling time of 23 ms when it was optimized with the particle swarm algorithm for 1.5 times the nominal load. MATLAB/Simulink was used to model, control, and simulate the brushless DC motor, controllers, and optimizers. MATLAB/Simulink also played a role in the optimization process. A particle swarm optimized adaptive neuro-fuzzy inference system controller is strongly suggested for use in brushless DC motor speed control. This controller is used to make inferences about the state of the motor