This paper presents a novel approach that combines correlation and Artificial Neural Network (ANN) techniques in the context of direct torque control (DTC) to demonstrate the feasibility and effectiveness of integrating a photovoltaic (PV) system with a switched reluctance motor (SRM). The proposed approach eliminates the need for repetitive measurements of experimental methodological factors and the angle of rotation by introducing a new mathematical model that comprehensively represents these variables. This model enables the calculation of the SRM speed for various combinations of methodological factors (E, T) and the angle of rotation. The correlation output, specifically the speed correlation, is utilized to extract the angle of rotation, which serves as input to the ANN along with solar irradiation and temperature data. Consequently, the ANN is employed to calculate the optimal speed of the SRM under different environmental conditions, ensuring optimal performance at any given moment. Additionally, this study investigates the correlation between SRM speed, solar radiation, and the rotor position. Notably, the magnetic equivalent circuit, being a conceptual representation, proves to be highly suitable for conducting studies and simulations related to direct torque control. Overall, the proposed methodology provides a promising foundation for integrating PV systems with SRMs, enhancing their performance and efficiency while reducing the need for extensive experimental measurements. The combined use of correlation and ANN offers an innovative approach for optimizing SRM speed and its response to varying environmental conditions, showcasing its potential in sustainable and energy-efficient applications.

ANN, SRM, DTC, Correlation, PV array.