Battery discharge forecast applied in Unmanned Aerial Vehicle

• Autorzy: Souza, D. A. , Pinto, V. P. , Nascimento, L. B. P. , Torres, J. L. O. , Gomes, J. P. P. , Sá Junior, J. J. M. , Almeida, R. N. C.

Warianty tytułu

PL

Przewidywanie procesu rozładowania baterii w pojazdach typu dron

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a comparative study methodology for the prediction of Li-Po (Lithium Ion Polymer) batteries discharge in UAVs (Unmanned Aerial Vehicles) using four approaches based on Artificial Neural Networks (ANNs) using Multilayer Perceptron (MLP) and Extreme Learning Machine (ELM) techniques, Polynomial Regression, and Kalman Filter (KF). The information estimates are important to assist in making decisions on which missions can be addressed to UAVs when supplied by such batteries. The data series for the experiments are obtained from tests carried out on a test bench.

PL

W artykule przedstawiono stadium porównawcze metodologii przewidywania procesu rozładowania baterii litowych wykorzystujących sieci neuronowe. Baterie te były stosowane w pojazdach typu dron.

Słowa kluczowe

PL

sztuczna sieć neuronowa; bateria; filtr Kalmana; wielomian regresji; UAV

EN

artificial neural network; battery; Kalman filter; polynomial regression; UAVs

• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2016
• Tom: R. 92, nr 2
• Strony: 185--192
• Opis fizyczny: Bibliogr. 11 poz., rys., tab., wykr.

Twórcy

autor

Souza, D. A.

• Federal University of Ceará (UFC), Sobral-CE, Brazil,

autor

Pinto, V. P.

• Federal University of Ceará (UFC), Sobral-CE, Brazil,

autor

Nascimento, L. B. P.

• Federal University of Ceará (UFC), Sobral-CE, Brazil

autor

Torres, J. L. O.

• Department of Electrical Engineering, Federal University of Ceará (UFC), Sobral-CE, Brazil

autor

Gomes, J. P. P.

• Department of Computer Science and Institute, Federal University of Ceará (UFC), Fortaleza-CE, Brazil

autor

Sá Junior, J. J. M.

• Federal University of Ceará (UFC), Sobral-CE, Brazil

autor

Almeida, R. N. C.

• Department of Electrical Engineering, Federal University of Ceará (UFC), Sobral- CE, Brazil

Bibliografia

• [1] Bole, B.; Daigle, M and Gorospe, G. (2014). Online prediction of battery discharge and estimation ofparasitic loads for an electric aircraft. Proceedings of the European Conference of thePrognostics and Health Management Society, Nantes.
• [2] Huggins, R. (2008). Advanced Batteries: Materials ScienceAspects, 1st ed., Springer.
• [3] Gyro-200ED-X8. available in: www.gyrofly.com. br
• [4] Rojas, R., (1996). Neural Networks: A Systematic Introduction. Springer, Berlin.
• [5] Ali Khadem, Gholam-Ali Hossein-Zadeh. (2014). Estimation of direct nonlinear effective connectivity using information theory and multilayer perceptron. Journal of Neuroscience Methods, Volume 229, Pages 53-67. doi:10.1016/j.jneumeth.2014.04.008
• [6] Sang-Hoon Oh. (2011). Error back-propagation algorithm for classification of imbalanced data. Neurocomputing. doi:10.1016/j.neucom.2010.11.024
• [7] G. B. Huang, Q. Y. Zhu, and C. K. Siew. (2006).Extreme learning machine: theory and applications. Neurocomputing. doi:10.1016/j.neucom.2005.12.126
• [8] Magee, Lonnie (1998). Nonlocal Behavior in Polynomial Regressions. The American Statistician (American Statistical Association) 52 (1): 20–22. doi:10.2307/2685560
• [9] Chui, Charles K.; Chen, Guanrong. (2009).Kalman Filtering with Real-Time Applications. 4th ed. New York: Springer. 229 p. vol. 17
• [10] Orchard M. E. and Vachtsevanos G. J. (2009). A particlefiltering approach for on-line fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control, No. 31; pp. 221-246.
• [11] Chi Keong Reuben Lim, David Mba. (2015). Switching Kalman filter for failure prognostic. Mechanical Systems and Signal Processing, Volumes 52–53. doi:10.1016/j.ymssp.2014.08.006

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.

Identyfikatory

DOI

10.15199/48.2016.02.49