The Research Based On The3-DOF Helicopter Model

The helicopter has significant features such as taking off and landing vertically, hoveringin the air, flying around and so on, so has been widely used in the military fields and civilianfields. Its flight control system is a typical multiple input-multiple output system, with strongcoupling and nonlinear channel characteristics.it is a complex objects in controlengineering.Researchers in recent years aroused intense interest in study this system.Thehelicopter model system can partly simulate the helicopter’s posture and flight, has been widelyused in control theory teaching, researching, and network laboratory building.This dissertation did the research on control arithmetic and theory based on the3-dofhelicopter system produced by the googol tech Ltd.First, analyzed the helicopter system’s composition modeling according to thecharacteristics of each degrees of freedom motion and selecting appropriate state variables toget the system state equation. Then particle swarm optimization (PSO) was introduced.Traditional control theory is based on the accuratemodel of the controlled objects, such as PIDand LQR control. When it comes to complex system such as the helicopter system, thetraditional theory is not applicable. So we introduced fuzzy neural network (FNN) to deal withsuch problem. In this paper, the PID controller adjusted by the fuzzy RBF neural network isdesigned. PSO is used to optimize the neural network parameters.This paper presents a novel adaptive variable structure (AVS) method to design a fuzzyneural networks (FNN).This AVS-FNN is based on radical basis function（RBF） neurons,which have center and width vectors. The networkperforms sequential learning through slidingdata window reflecting system dynamic changes, and dynamic growing-and-pruning thestructure of FNN.In recent years, inverse system method has been used to realize linear decoupling controlof general nonlinear system. We used AVS-FNN neural network as identifier and the inversesystem was introduced.The feasibilityofa theory must be tested for certification through the physical. Finally, weintroduced the real time theory and carried out experience in Matlab under the controlsimulation. In the Simulink environment, real-time control simulation was experienced.Experiment results show that the algorithm is feasible, and can get an ideal control.Finally,wehave realized the windows application software of PID controller to the helicopter system withVC++.