Indirect Adaptive PID Controller Neural Networks optimization for VTOL Trainer

Abstract

In this paper a full approach of controlling the pitch angle of a VTOL trainer is presented. In fact, an Indirect Adaptive PID control strategy (IAPID-NN) optimized by Neural Networks Approach is developed to be applied to control the pitch angle of a VTOL trainer that allows the switch from hovering to horizontal flight. This strategy is then compared to a PID classical controller to demonstrate its benefits on the overall system control. The goal of this work is to concept a smart IAPID controller based on neural networks able to supervise the system for an optimized behavior while tracking a desired trajectory. Many challenges could arise if the VTOL is navigating in hostile environments presenting disturbances in the form of load torque applied to the overall system. The system has to quickly perform tasks while ensuring stability and accuracy and must behave rapidly with regards to decision making facing disturbances. This technique offers some advantages over conventional control methods namely the classical PID controller. Simulation results are obtained with the use of Matlab/Simulink environment and are founded on a comparative study between PID and IAPID-NN controllers based on disturbances. These simulation results are satisfactory and have demonstrated the effectiveness of the proposed IAPID-NN approach. In fact, this controller has relatively smaller errors than the PID controller and has a better capability to reject disturbances. In addition, it has proven to be highly robust and efficient facing disturbances.