This paper analyzes the performance of neural networks to be used for identification and optimal control of active pneumatic suspensions of high speed railway vehicles. It is shown that neural networks can be efficiently trained to identify the dynamics of the nonlinear pneumatic suspensions. Neural networks can be also trained to function as optimal nonlinear controllers, which improves the suspension performance. The performance of the nonlinear suspension with a neuro-controller is compared with that of a LQ controller designed after linearizing the suspension components around the equilibrium point. © 1995, The Japan Society of Mechanical Engineers. All rights reserved.