Sensorless control of switched reluctance motors through artificial neural network with a fuzzy interface

Switched resistance motors, are becoming increasingly used in industrial and hybrid electric vehicle (HEV) applications. But improving SRM performance is still a crucial field for study, especially with regard to their inherent benefit of accurate rotor position estimate, which is closely related to operational effectiveness. Rotor position sensing has traditionally required the incorporation of specialized sensors, which has led to difficulties like increased costs, complicated alignment, limited size, and maintenance requirements. In order to overcome these constraints, this work promotes the creation of sensorless motor control schemes that make use of cutting edge Artificial intelligence methods such as fuzzy logic and Adaptive Neuro-Fuzzy Inference System (ANFIS).To provide robust control, the suggested sensorless control systems make use of inputs such bus voltage, rotor speeds, torque instructions, and SRM parameters. The effectiveness of these methods is thoroughly assessed by painstaking simulation experiments, confirming their capacity to attain accurate control and high-performance operation. To further illuminate the benefits of sensorless control implementations, this research also does a comparison analysis between the two suggested soft computing approaches and their sensor-based equivalents. In the end, this research advances the field of SRM technology, opening the door to more dependable, economical, and efficient motor control systems in a variety of industrial and automotive applications.