Font Size: a A A

Research Of Surplus Force Suppression Strategy Of Aircraft Rudder Electro-Hydraulic Servo System

Posted on:2021-02-01Degree:MasterType:Thesis
Country:ChinaCandidate:J Y WuFull Text:PDF
GTID:2392330611468748Subject:Aeronautical Engineering
Abstract/Summary:PDF Full Text Request
Rudder is the executive component that controls the flight attitude of the aircraft.Its performance testing is completed by the aircraft rudder electro-hydraulic servo system which is used to simulate the force load on the rudder during actual work.Rudder's active movement will generate a forced flow,so that the actual force load will deviate from the commanded force load.Thereby generating surplus force reduces the control performance and loading accuracy of the system.Therefore,finding a suitable control method to suppress the surplus force is an urgent problem to be solved in the research and development of the aircraft rudder electro-hydraulic servo system.Based on current domestic and foreign research of the aircraft rudder electro-hydraulic servo system,first determining the model types and parameters of each part according to the composition structure and working principles.Then establishes the mathematical model of each part,the overall mathematical model of the system is deduced.The cause and characteristics of the surplus force under different working conditions,that is the following and differential characteristics,of the surplus force are studied.Secondly,the back propagation neural network based on the small batch gradient descent method is used to perform real-time tuning of the PID controller.The simulation experiment results show that the method suppresses the interference of surplus force to a certain extent and improves the loading accuracy,but it does not meet the requirements of system and is not universal.Therefore,a radial basis neural network PID compound controller based on improved particle swarm optimization algorithm was designed,and the annealing algorithm was used to improve the particle swarm optimization algorithm,thereby optimizing the parameters of the radial basis neural network and accelerating the convergence speed.Simulation experiment results show that this method can not only effectively suppress the interference of surplus force,but also significantly improve the loading accuracy.
Keywords/Search Tags:Aircraft rudder electro-hydraulic servo system, Surplus force, Mini-batch gradient descent, Radial basis neural network, Particle swarm optimization
PDF Full Text Request
Related items