Research On Adaptive Control System Of A Weapon Rocket Blasting Blasting Device

Electro-hydraulic servo system is widely used in aerospace,machine tools,steel manufacturing and other fields because of its advantages of fast response,high control precision and large output power.However,electro-hydraulic servo system has nonlinear factors such as flow-pressure characteristic,dead zone,saturation friction,and the traditional control method can not satisfy the control performance of the system.As the neural network has the advantage of arbitrarily approaching nonlinear function and parallel computing,fuzzy logic control is a systemic reasoning method which can make full use of expert's experience and can convert fuzzy language information of input quantity into control output through fuzzy inference rules and widely used to solve the problems of modeling and control of complex nonlinear systems in industrial fields.Therefore,this paper put the electro-hydraulic servo system of a certain weapon rocket explosive minesweepers as research object,and utilizing genetic neural network identify the system model,meanwhile,utilizing fuzzy wavelet neural network adaptive control strategy control the system performance.Firstly,the structure and working flow of electro-hydraulic servo system of rocket explosive minesweepers are introduced,and on the basis of the working principle of the system,a system joint simulation data acquisition model based on AMESim and Simulink software is designed.The data of the input and output model of the system are obtained through the joint simulation,and constructing the transfer function model of the system.Due to the transfer function-based mathematical model can not accurately describe the nonlinear characteristics of the rocket explosive minesweepers system,this paper introduces the system identification method to obtain the model which can closely describe the actual system.The two methods of BP neural network and genetic algorithm optimizing BP neural network are designed to model the system.By analyzing and comparing the results of the two identification models,the identification model of BP neural network optimized by genetic algorithm is more close to the actual system,and has stronger anti-interference ability and better generalization ability.On the basis of the identification model,the self-tuning control as the design basis of the system control strategy,the controller of wavelet neural network and fuzzy wavelet neural network are designed respectively.Building the system simulation model,it is concluded that the fuzzy wavelet neural network self-tuning control can satisfy the system performance requirements through MATLAB simulation analysis.Finally,the fuzzy wavelet neural network self-tuning control strategy is tested on the hydraulic experiment platform.The experimental results show that the system is controlled by fuzzy neural network self-tuning control strategy has fast response speed and high control precision and reaches the expected control effect.