Safety Analysis of High-Speed Maglev Trains Based on Fuzzy Neural Network-Controlled Suspension Systems

This paper examines the safety behavior of high-speed maglev trains subjected to track irregularities by formulating a nonlinear vehicle–bridge coupled model that incorporates the inherent nonlinear effects of electromagnetic forces. To improve robustness and adaptability, a suspension control method integrating backstepping control, fuzzy logic, and neural network techniques (BFNNC) is introduced. Validation against experimental data from the Shanghai Maglev line confirms the model’s reliability and accuracy. Comparative simulations under different track irregularity scenarios reveal that conventional backstepping control (BSC) fails to maintain suspension gaps within safe limits when disturbances are severe, whereas the proposed BFNNC approach effectively mitigates gap fluctuations, ensuring operation within the designated safety margin. The findings demonstrate that the fuzzy–neural network–enhanced backstepping strategy substantially strengthens system stability and disturbance resistance, highlighting its promise for future high-speed maglev applications.