Enviar artigo por via de e-mail Identification of the Dynamics of a Moving Object with the Use of Neural Networks
- Autores: Zolotukhin Y.N.1, Kotov K.Y.1, Svitova A.M.1, Semenyuk E.D.1, Sobolev M.A.1
-
Afiliações:
- Institute of Automation and Electrometry, Siberian Branch
- Edição: Volume 54, Nº 6 (2018)
- Páginas: 617-622
- Seção: Modeling in Physical and Technical Research
- URL: https://journals.rcsi.science/8756-6990/article/view/212628
- DOI: https://doi.org/10.3103/S8756699018060109
- ID: 212628
Citar
Acesso aberto
Acesso está concedido
Somente assinantes
Resumo
A method for identification of the dynamics of a quadrotor-type vehicle is proposed. The method is based on the Elman recurrent neural network, which corresponds to the canonical form of a dynamic system in the space of states and does not require structural correction. The results of a numerical experiment reveal the convergence of the network learning algorithm with the use of an extended Kalman filter.
Sobre autores
Yu. Zolotukhin
Institute of Automation and Electrometry, Siberian Branch
Email: kotov@idisys.iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
K. Kotov
Institute of Automation and Electrometry, Siberian Branch
Autor responsável pela correspondência
Email: kotov@idisys.iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
A. Svitova
Institute of Automation and Electrometry, Siberian Branch
Email: kotov@idisys.iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
E. Semenyuk
Institute of Automation and Electrometry, Siberian Branch
Email: kotov@idisys.iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
M. Sobolev
Institute of Automation and Electrometry, Siberian Branch
Email: kotov@idisys.iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
Arquivos suplementares
