EUVIMEDEUVIMED entdecken
Crossref

Solid Rocket Motor Design-Classification Using a Genetic-Algorithm-Optimized Neural Network Ensemble

Griffin A. DiMaggio, Roy J. Hartfield, Mark Carpenter

Journal of Aerospace Information Systems · 2026-07 · 23 (7) · 624-634

DOI: 10.2514/1.i011730 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Aerospace Information Systems, 2026-07. Verfasst von Griffin A. DiMaggio und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensemble deep-learning methods are developed to swiftly differentiate between similar solid rocket motor variants using early-flight trajectory data. Two classes of rockets were defined, and fly-out data were generated using a 6-DOF code. Three studies were conducted, each with varying levels of similarity between the two classes. The individual model architectures were optimized with a genetic algorithm, and comparisons were made with unoptimized (weaker learning) ensembles. Ensembles consisting of optimized models achieved a few percent increase in classification accuracy over the best individual model accuracies.

Zitieren

APA

DiMaggio, G. A., Hartfield, R. J., & Carpenter, M. (2026). Solid Rocket Motor Design-Classification Using a Genetic-Algorithm-Optimized Neural Network Ensemble. Journal of Aerospace Information Systems, 23(7), 624-634. https://doi.org/10.2514/1.i011730

Vancouver

DiMaggio GA, Hartfield RJ, Carpenter M. Solid Rocket Motor Design-Classification Using a Genetic-Algorithm-Optimized Neural Network Ensemble. Journal of Aerospace Information Systems. 2026;23(7):624-634. doi:10.2514/1.i011730

BibTeX
@article{DiMaggio2026,
  author = {DiMaggio, Griffin A. and Hartfield, Roy J. and Carpenter, Mark},
  title = {Solid Rocket Motor Design-Classification Using a Genetic-Algorithm-Optimized Neural Network Ensemble},
  journal = {Journal of Aerospace Information Systems},
  year = {2026},
  volume = {23},
  number = {7},
  pages = {624--634},
  doi = {10.2514/1.i011730}
}
Kostenlos starten →