The identification model construction on electrohydraulic position servo system based on neural networks was studied to use in nonlinear model of the system.The relationship of dynamic model input and output was analyzed and the neural network weights and threshold were optimized using the genetic algorithm,and a basic structure of neural network identification model was presented.A realtime electrohydraulic servo test bench was built with the xPC technique.The test bench step output was used to identify in the improved BP neural network and the sinusoidal output was used to verify in experiment.Experiment results show that the high precision is gained and the credibility is verified on neural network identification model structure,and which is applied in nonlinear system model identification.