The suspension system of maglev train has intrinsic nonlinear characteristics. The identification processing ability of nonlinear terms and the control accuracy of control algorithm have an important influence on the suspension stability of the train. Especially when the track stiffness is weak, it is easier to affect the suspension stability under the action of small deformation, resulting in the phenomenon of point dropping/rail smashing. Starting from the nonlinear dynamic modelling of maglev suspension system, this paper focuses on the system parameter identification of nonlinear terms and the design of nonlinear control algorithm. Based on Hopfield neural network, the error function and network identification scheme are constructed. In addition, in order to further improve the control accuracy and system robustness, radial basis function (RBF) network adaptive control is carried out based on the identified system model, and the control performance is improved by RBF network approximation principle. Through the numerical simulation analysis, it can be found that the identification effect is good. Moreover, the proposed control algorithm has an obvious effect on improving the control performance and system robustness, which verifies the reliability of the identification results and the control algorithm.

磁悬浮列车的悬挂系统具有内在的非线性特性。非线性项的辨识处理能力和控制算法的控制精度对列车的悬架稳定性有重要影响。尤其是当轨道刚度较弱时，在小变形的作用下更容易影响悬挂稳定性，导致点落/撞轨现象。本文从磁悬浮系统非线性动力学建模出发，重点研究非线性项的系统参数辨识和非线性控制算法的设计。基于Hopfield神经网络，构建了误差函数和网络识别方案。此外，为了进一步提高控制精度和系统鲁棒性，基于识别出的系统模型进行径向基函数（RBF）网络自适应控制，利用RBF网络逼近原理提高控制性能。通过数值模拟分析可以发现识别效果良好。此外，所提出的控制算法对提高控制性能和系统鲁棒性有明显的效果，验证了辨识结果和控制算法的可靠性。