Identifying Heteroclinic Connections using Artificial Neural Networks

摘要

This paper demonstrates the usage of artificial neural networks (ANN) to identify heteroclinic connections in as-trodynamical systems. The ANN architecture is applied to find heteroclinic connections, or lack thereof, in the Earth-Moon circular restricted three body problem from L_1 to L_2 Lyapunov orbits for Jacobi values between 3.07 and 3.17. The predicted heteroclinic connections are within 0.1-1 % of the arclength along the periodic orbit from their true locations.