Data-Driven Nonlinear Iterative Inversion Suspension Control

The commercial operation of the maglev train has strict requirements for reliability and safety suspension control system. However, due to a large number unmodeled dynamics system, it is difficult obtain precise mathematical model After system been operated long time with high load, will change wear, aging failure components, as well settlement line track. performance degraded. Therefore, this paper proposes data-driven nonlinear iterative inversion algorithm, which can achieve high-precision tracking recovery after degradation without depending on model. improved by learning measured data historical fast convergence error stable are realized in presence external noise interference. Based inverse identified based drive, framework designed. Then, input update strategy used realize rapid process. Finally, simulation experiment physical experimental platform combined. It verified that proposed levitation algorithm degrades under environment.