论文信息 - Identifying heteroclinic connections using artificial neural networks

Identifying heteroclinic connections using artificial neural networks

Abstract This paper demonstrates the usage of artificial neural networks (ANN) to identify heteroclinic connections in astrodynamical 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.

Daniel J. Scheeres | Stijn De Smet | D. Scheeres | Stijn De Smet

[1] Kenneth Levenberg. A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[2] Ronald Davis,et al. Neural networks and deep learning , 2017 .

[3] Hecht-Nielsen. Theory of the backpropagation neural network , 1989 .

[4] Shane D. Ross,et al. Heteroclinic connections between periodic orbits and resonance transitions in celestial mechanics. , 2000, Chaos.

[5] Martin Fodslette Møller,et al. A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[6] D. Marquardt. An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[7] Daniel J. Scheeres,et al. Escaping Trajectories in the Hill Three-Body Problem and Applications , 2003 .

[8] Michael A. Arbib,et al. The handbook of brain theory and neural networks , 1995, A Bradford book.