A neural network adaptive sliding mode controller is proposed for overhead crane with nonlinear and externally disturbance. Firstly, the dynamic model of overhead crane is established by Lagrange method; Then, based on the hierarchical sliding mode controller, the adaptive update rate of the radial basis function (RBF) neural network weights is designed. The RBF neural network is used to compensate the uncertain upper bound caused by the nonlinear and external disturbance in the system, and the particle swarm optimization algorithm is used to optimize the controller parameters. The stability of the system is proved by constructing a Lyapunov function; Finally, one set of simulation experiments and one set of validation experiments on a established experimental platform were designed. The simulation results showed that under the influence of nonlinear and externally disturbance, the neural network adaptive sliding mode controller can quickly achieve the positioning of the trolley and the load swing suppression, the controller can eliminate the influence of uncertain upper bound on the system. The experimental results also show that the designed controller can make the overhead crane reach the control target, and has a certain ability to resist disturbance.