Hybrid orbit propagator based on neural networks. Multivariate time series forecasting approach

  1. Hans Carrillo 1
  2. Edna Segura 1
  3. Rosario López 1
  4. Iván Pérez 1
  5. Juan Félix San-Juan 1
  1. 1 Universidad de La Rioja
    info

    Universidad de La Rioja

    Logroño, España

    ROR https://ror.org/0553yr311

Konferenzberichte:
16th International Conference on Soft Computing Models in Industrial and Environmental Applications – SOCO 2021
  1. Hugo Sanjurjo González (ed. lit.)
  2. Iker Pastor López (ed. lit.)
  3. Pablo García Bringas (ed. lit.)
  4. Héctor Quintián (ed. lit.)
  5. Emilio Corchado (ed. lit.)

Verlag: Springer

ISSN: 2194-5357

ISBN: 978-3-030-87868-9

Datum der Publikation: 2022

Ausgabe: 1401

Seiten: 695-705

Kongress: 16th International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO (16º. 2021. Bilbao)

Art: Konferenz-Beitrag

DOI: 10.1007/978-3-030-87869-6_66 GOOGLE SCHOLAR
Institutionelles Repository: lockOpen Access Editor

Zusammenfassung

The orbital trajectory of artificial satellites around the Earthrequires frequent corrections in response to different perturbation forces.The necessary maneuvers can be designed in simulated space environ-ments by propagating Two Line Elements with orbit propagators such asSGP4, which provides the orbital position information at a given epoch.In this work, a hybrid orbit propagator based on a neural network modelis developed. Compared with previous models, the proposed neural net-work shows generalization capabilities for different space objects, whichimplies a potential benefit for the accuracy of any classical orbit propa-gator.