Artillery Electro-hydraulic Servo System, The Neural Network Identification And Adaptive Control

As the neural network can approximate any nonlinear function and have strong learning ability, it is getting more and more applications.The paper firstly expounds the basic problem and theory of neural network, a typical multi-layer feed-forward artificial neural networks named BP network has been studied. But traditional BP neural network has many defects, such as slow training velocity and converge to a local minimum point, LM-BP algorithm and GA-BP algorithm has much better performance.Electro-hydraulic servo system in the artillery exhibit highly nonlinear behavior. A system model which concludes the nonlinear factors was presented based on the SimHydraulic toolbox of Simulink analysis system. The approach can gain the actual characteristic of the system through simulation.On the basis of the Simulink model, the paper researches the model identification based on neural network, presents the normal structures of neural network identification, discusses the neural network identification for nonlinear system. According to a set of test data of System, the paper has made system identifications of positive model based on neural networks, and analyses identification result.As neural network adaptive control not only has the good robustness as that in the adaptive systems, but also has the ability of self-learning and good fault-tolerant, three adaptive control strategies are introduced in this paper. Combining the reference model adaptive control, the paper researches the neural network model reference adaptive control of electro-hydraulic servo system, and presents simulation results.According to the results of the simulation and experiments, the neural network self-adapting controller has the high quality of performance.