NN-based modelling of a 2DOF TRMS using RPROP learning algorithm

Abstract

This paper presents a neural network (NN) based nonlinear dynamic modelling approach for a Twin Rotor MIMO System (TRMS), in terms of its 2 degree of freedom (DOF) dynamics. The TRMS is a highly nonlinear system with significant cross-coupling between its horizontal and vertical axes. It is perceived as an aerodynamic test rig representing the control challenges of modern air vehicles. Accurate dynamic modelling is a prerequisite to address such challenges satisfactorily. A feedforward neural network has been trained using resilient propagation (RPROP) learning algorithm. The trained NN based model has been tested with a set of data that are different from those used for training purpose. For more validation the power spectral density (PSD) of the model is compared with that of the real TRMS and also the correlation validations of the test results are presented in order to show the effectiveness of the proposed model. The results show that the developed model can adequately represent the highly nonlinear features of the system.