Cascaded ANN Algorithm for Speed Control of Switched Reluctance Motor in EV Applications

Solar photovoltaic (PV) technology is a revolutionary concept for charging electric vehicles (EVs), and it has a variety of technological and financial benefits. A cascaded artificial neural network (ANN) for switching reluctance motor (SRM) driving with front end circuit integration is fascinating for EV. Because of its simple design, high reliability, high fault tolerance capacity, and low production cost, SRM has these advantages. The high torque ripples, running vibrations, and acoustic noise, however, are the principal drawbacks of SRM. The Cascaded ANN theory for SRM drives proposes a solution to this problem by utilising benefits such as a wide power range, minimal resonance of torque, and vibration-free responsiveness with adjustable speed regulation. The Luo converter is included in the suggested architecture to increase output voltage and decrease output ripples. To regulate the SRM motor's speed, a Cascaded ANN Controller is suggested. The main objective of this study is to improve the recommended controller, which provides outstanding performance and high robustness. Simulink and MATLAB are employed. The minimum time required to deploy a cascaded ANN is 0.01 seconds for 2000 rpm and 0.02 seconds for 2500 rpm.