Trajectory Prediction of Target Aircraft in Air Combat Based on GA-OIF-Elman Neural Network

Abstract

Trajectory prediction is a key problem in air combat situational awareness. Aiming at the problems of the traditional methods such as large degree of model simplification, too little data available and low prediction accuracy, a prediction method based on the GA-OIF-Elman neural network is proposed. The parameters of the output-input feedback Elman network are optimized by the genetic algorithm and the GA-OIF-Elman neural network is established. The trajectory prediction sample data of the target aircraft is constructed with use of the air combat trajectory data selected in the air combat maneuvering instrument and the trajectory prediction model based on the GA-OIF-Elman neural network is established. The accuracy and real-time performance of the prediction model are analyzed in simulation experiments and the results show that the prediction error of the model in different directions is not more than 3% and it takes only about 20ms to perform 200 consecutive predictions, indicating that this model can predict the trajectory of the target aircraft accurately and rapidly.