Online attitude controlling of Longitudinal Autopilot for General Aviation Aircraft using Artificial Neural Networks

摘要

This paper describes the attitude control of a Longitudinal Autopilot for General Aviation Aircraft is controlled by Artificial Neural Network PID (ANN-PID) controller. The conventional methods for finding gains of servo elevator and rate gyro are based on root locus and Offline PID controlling methods. But these methods are poor at disturbance rejection. Hence this paper proposes an online controller by using artificial neural networks. The uniqueness with this controller is automatic tuning of PID gains for various disturbance occurrences in the system. First the system is designed with closed loop offline PID controlling techniques and Lead/Lag compensators for various values of disturbances and observed that the system response is degraded, finally ANN-PID controller is designed for the system for various values of disturbances. The entire system is modeled and simulated by using MATLAB/ Simulink software. The results show that the proposed ANN-PID controller has good disturbance rejection than offline PID controlling tuning methods.