Aircraft Model Based On Three Degrees Of Freedom Pid Neural Network Control

PID neural network,which is based on classical PID control,realized through neural network which has self study function,has a good control effect.Involving neural network and PID controller in an organic whole,the PIDNN controller,which has the merit of any PID controller for its simple construction and definite physical meaning of parameters,and of the self-learning and adaptive functions of a neural network.The 3D hover model system is simple and intuitionisticas a laboratory setup but is complicated as a controlled unit.It is a high order,unstable,multi-variable,non-linear and cross-coupling 3-DOF multi-input multi-output complex system,which can be stable by adopting effective control method.So,in the paper,a PID neural network controller was studied in detail.The work is listed as follows:Firstly,models are developed in this thesis.Multi-Input and Multi-Output System Models of the Helicopter are developed in Matlab,including model of the horizontal part of system,model of the vertical part of system,model of the pitch part of system and 3-DOF model of system.Secondly,a PIDNN controller is designed for 3D model hover.The simulation result indicates that the system,compared to the BP-PID control method,possesses the advantages of high precision,quick response speed and is of great adaptability and robustness.It proved that PID neural network has preferably self study and self adapting decoupling control ability through simulation.The system which inosculates the decoupling and controller,is easy to implement and applicable for multivariate decoupling control.It makes the decoupled system have better dynamic behavior and static characteristic.Especially,it makes parameters astringe fast when determining initial value of network according to PID control law.