A Novel Gorilla Troops Optimizer-Driven ANFIS Controller for High-Performance Brushless DC Motor Control in Electric Vehicle Applications

The electric vehicles (EVs) are considered as popular choice because they offer sustainable replacement for conventional gasoline and oil-powered vehicles. Brushless direct current (BLDC) motors serve as primary power sources for traction and industrial applications as they provide essential operational advantages. The process of EV acceleration requires both steady-state and transient-state responses to be accurate for achieving smooth acceleration. This paper proposes an improved adaptive neuro-fuzzy inference system (IANFIS) controller optimized through efficient Gorilla Troops Optimizer (GTO) for controlling a 48-V BLDC motor in electric vehicle applications. The GTO method is employed to optimize the ANFIS membership functions and achieve enhanced control performance. The Matlab/Simulink platform is used to investigate the speed-control performance of the BLDC motor during acceleration and deacceleration operations. The performance of the proposed IANFIS controller performance is evaluated against conventional proportional-integral (PI) and standard ANFIS controllers by analyzing error reduction and overall system performance. The results demonstrate that, the proposed IANFIS controller achieves superior dynamic performance for BLDC motor, resulting in improved vehicle speed and distance responses, as well as reduced peak overshoot, settling time, and rise time.