The complexity of helicopter flight dynamics makes modeling and helicopter system identification a very difficult task. Most of the traditional techniques used for nonlinear dynamical system identification require a model structure to be defined a priori. In case of helicopter dynamics, defining a priori model is difficult due to its complexity and the interplay between various subsystems. In this work we present a Particle Swarm Optimization (PSO) driven recurrent neural network model for the identification of helicopter dynamics using flight data, based on the popular Nonlinear Auto Regressive eXogeneous input network (NARX) model. The proposed model is capable of identifying the helicopter dynamics without any a. priori knowledge about the system under study. This model successfully circumvents one the major drawbacks of the very popular NARX model, without losing its numerous advantages. The current model is developed with the NARX model as the substrate; a single hidden layer perceptron network based architecture along with tapped delay lines is employed for modelling the dynamical systems. This is coupled with an II-Tier PSO-framework for evolving the order of the system. The model is used to approximate the flight data. Simulations have been carried out for identifying the longitudinally uncoupled dynamics. Results of identification indicate a quite close correlation between the actual and the predicted response of the helicopter. Further, the proposed model has been compared with the conventional NARX model.
展开▼
