Deep Learning Based Missile Trajectory Prediction

Accurately predicting or calculating the missile's flight path is one of the key challenges in applying the missile model to various related simulations. The traditional method used for this task is to use models and numerical integration, which requires a lot of computing resources. In this paper, a deep neural network with two hidden layers is established to predict the missile's flight trajectory, the data generated by the traditional model is used to train and test the network, and the error of the network prediction result is analyzed. Using the trained DNN to predict the missile's flight path is about four times faster than the traditional model, and the prediction error is small.