Adaptive non-linear model inversion control of a twin rotor multi-input multi-output system using artificial intelligence

Abstract

This paper investigates the development of an adaptive dynamic non-linear model inversion control law for a twin rotor multi-input multi-output system (TRMS) utilizing artificial neural networks and genetic algorithms. The TRMS is an aerodynamic test rig representing the control challenges of modern air vehicles. A highly non-linear one degree of freedom mathematical model of the TRMS is considered in this study and a non-linear inverse model is developed for the pitch channel. In the absence of model inversion errors, a genetic algorithm-tuned proportional-derivative (PD) controller is used to enhance the tracking characteristics of the system. An adaptive neural network element is integrated, thereafter, with the feedback control system to compensate for model inversion errors. In order to show the effectiveness of the proposed method in the simulation environment an inversion error has deliberately been provided as an uncertainty in the real situation. Square and sinusoidal reference command signals are used to test the control system performance, and it is noted that an excellent tracking response is exhibited in the presence of inversion errors caused by model uncertainty.