Comparative Analysis of Data-Driven Models for DC Motors with Varying Payloads

DC motors are widely used in various industrial applications, and accurately predicting their performance under different payload conditions is crucial for optimal control and efficient system design. In recent years, data-driven modeling techniques have gained significant attention as effective tools for capturing the complex dynamics of DC motors. This study conducts a comparative assessment of diverse data-driven models applied to DC motors operating under different load conditions. A number of model structures have been tested which include continuous-time transfer function, discrete-time transfer function, and Auto-Regressive with eXogenous input (ARX). Results reveal that the ARX and second-order continuous time transfer function models outperform the rest with accuracies of at least 94%.