Simulation of nonlinear identification and control of Unmanned Aerial Vehicle: An Artificial Neural Network approach

Artificial Neural Networks (ANNs) are widely applied nowadays for classification, identification, control, diagnostics, recognition, etc. They can be implemented for identification of dynamic systems. The concept of ANN is highly used in design and simulation of control system of Unmanned Aerial Vehicles (UAVs). Controller design for UAV is subject to time varying and non-linear model parameters. The objective of this work is to simulate the nonlinear identification of a dynamic system which is based on its response to standard signals. The non linear identification of the state space methods is based on model reference control. For model reference control, the controller is a neural network that is trained to control a plant so that it follows a reference model. The neural network plant model is used to assist in the controller training. In this paper we simulate the modeling capabilities of a state space neural network, to act as an observer for a non-linear process allowing a simultaneous estimation of parameters and states.