Design of enhanced active suspension system with metaheuristic-based LQG control and ANFIS-based actuation

• Nitish ^[2] ; Amit Kumar Singh ^[1]
  1. [1] National Institute Of Technology

     National Institute Of Technology

     Japón

     
  2. [2] Chitkara University Institute of Engineering and Technology, Chitkara University, Chandigarh, India
• Localización: Mechanics based design of structures and machines, ISSN 1539-7734, Vol. 53, Nº. 9, 2025, págs. 6196-6227
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • In the railway sector, achieving faster operational speeds while maintaining passenger comfort is still significant. Various strategies for this purpose have been studied, but an influencing method has not yet been revealed. Therefore, this study investigates a novel method for reducing vibrations using an active suspension system and sophisticated control strategies. Particularly, the combination of an adaptive neuro-fuzzy inference system (ANFIS) and a linear quadratic Gaussian controller tuned with equilibrium optimization (EO-LQG) is used. A 27-degree-of-freedom analytical model of a railway vehicle, including wheel-rail contact forces and track irregularities, forms the basis of the study. The acceleration responses of the vehicle’s body are assessed in the time and frequency domain under random track excitations. The ride comfort enhancement capability of the proposed model is also evaluated using Sperling’s methods and the simulated results were compared with the experimental results. The robust analysis of proposed control strategies was also performed. Finally, the comparative analyses of the results have been performed with passive systems and the classical tuning methods. The findings suggest that the EO-LQG controller offers a promising solution for enhancing ride comfort, as it can reduce vehicle accelerations by 24.97–38.77 % with robust performance.