Enhancing sensorless control of SRM through instantaneous direct torque control with MGAO-CANN technique

Switched reluctance motors (SRMs) have gained prominence in various industrial applications due to their robustness and simplicity. One critical aspect of enhancing SRM efficiency is precise control, often necessitating complex sensor systems for accurate feedback. This research addresses this challenge by proposing a sensorless control system based on instantaneous direct torque control (IDTC) techniques. The study introduces a novel architecture integrating a DC power supply, (n + 1) diodes, and (n + 1) switches, forming a foundation for SRM control without the need for additional sensors. The core innovation lies in the implementation of a modified genetic algorithm optimized cascaded artificial neural network (MGAO-CANN) controller. This controller refines control signals through genetic algorithm optimization and neural network computations, optimizing the motor’s performance. To enhance system stability and prevent rapid fluctuations, a hysteresis current controller (HCC) is employed, ensuring smooth operation. The research’s focal point is the application of instantaneous direct torque control, enabling real-time and precise adjustments to motor torque. By eliminating the necessity for extra sensors, the proposed system not only reduces costs significantly but also enhances SRM efficiency and responsiveness. The validation of proposed research simulated using MATLAB/Simulink and the outcomes reveals that the developed approach promises a ground breaking advancements in the realm of motor control technology.