29-LQP-ARJCS 20251230000000 Lumina Quest Publishing m.arslansohail@gmail.com Lumina Quest Publishing Advanced Research Journal of Computer Science Adv. Res. J. Comput. Sci. 3134-884X 10.66590/arjcs https://lquestpub.com/archives.php?journal=advanced-research-journal-of-computer-science 12 30 2025 12 30 2025 2 2 10.66590/arjcs20250202 https://lquestpub.com/articles-list.php?journal=advanced-research-journal-of-computer-science&volume=2&issue=2 AI-Driven Control Optimization in Electromagnetic Levitation Train Systems Rida Afzal Magnetic levitation (Maglev) systems operate based on the principles of electromagnetic attraction and repulsion to achieve contactless suspension and transportation. However, Maglev train dynamics are inherently nonlinear and open-loop unstable, making control design a challenging task. This study focuses on the modeling, analysis, and control of a nonlinear Maglev system using three advanced control strategies: NARMA-L2, Model Reference Control (MRC), and Model Predictive Control (MPC). The performance of these controllers is evaluated through simulation under step input conditions to assess their effectiveness in achieving precise position control and system stability. Comparative results demonstrate that the NARMA-L2 controller outperforms the other approaches in terms of accuracy, response time, and robustness. Furthermore, the proposed control strategy enhances system stability and improves ride comfort and handling characteristics of the Maglev train. 12 30 2025 12 30 2025 1 4 10.66590/arjcs2025020201 https://lquestpub.com/article/10.66590/arjcs2025020201