Enhanced artificial transgender longicorn algorithm & recurrent neural network based enhanced DC-DC converter for torque ripple minimization of BLDC motor

Abstract

This paper proposes an enhanced DC-DC converter with hybrid control method for torque ripple minimization of BLDC motor. Initially, a BLDC motor is controlled with an enhanced Cuk converter. The application of a switched inductor is used to update the Cuk converter operation. In this method, the control mechanism incorporates two control loops, namely, the speed control loop and torque control loop, which are utilized to recover the execution of BLDC. Thus, the proposed system is the combined performance of the Enhanced Artificial Transgender Longicorn Algorithm (EATLA) and Recurrent Neural Network (RNN) to improve control loop operations. In the Artificial Transgender Longicorn Algorithm (ATLA), the crossover and mutation approach are used as part of the scattering process to build the accuracy search process. In this article, the EATLA-RNN algorithm for limiting speed and torque error of BLDC motor is explored. However, the proposed method output is subject to input of the speed and torque controllers. The proposed topology with the controller is executed on MATLAB/Simulink workstation, and torque ripple minimization is analyzed toother existing approaches such as particle swarm optimization (PSO) and bacterial foraging (BF) algorithm.