Page 235 - Neural Network Modeling and Identification of Dynamical Systems

226 6. NEURAL NETWORK SEMIEMPIRICAL MODELING OF AIRCRAFT MOTION

[16] Roskam J. Airplane flight dynamics and automatic [29] Wang KC, Iliff KW. Application of system identification
flight control. Part II. Lawrence, KS: DAR Corporation; to aircraft at NASA Langley Research Center. J Aircr
1998. 2004;41(4):752–64.
[17] Cook MV. Flight dynamics principles. Amsterdam: El- [30] Dietterich TG. Machine-learning research: Four current
sevier; 2007. directions. AI Mag 1997;18(7):97–136.
[18] Hull DG. Fundamentals of airplane flight mechanics. [31] Joshi P, Kulkarni P. Incremental learning: Areas and
Berlin: Springer; 2007.
[19] Stevens BL, Lewis FL, Johnson E. Aircraft control and methods — a survey, vol. 2. Int J Data Min Knowl
simulation: Dynamics, control design, and autonomous Manag Process 2012;2(5):43–51.
systems. 3rd ed. Hoboken, New Jersey: John Wiley & [32] Niewald PW, Parker SL. Flight-test techniques em-
Sons, Inc.; 2016. ployed to successfully verify F/A-18E in-flight lift and
[20] Nguyen LT, Ogburn ME, Gilbert WP, Kibler KS, drag. J Aircr 2000;37(2):194–200.
Brown PW, Deal PL. Simulator study of stall/post-stall [33] Mulder JA, van Sliedregt JM. Estimation of drag and
characteristics of a fighter airplane with relaxed longi- thrust of jet-propelled aircraft by non-steady flight-test
tudinal static stability. NASA TP-1538; Dec. 1979. maneuvers. Delft Univ. of Technology, Memorandum
[21] Sonneveld L. Nonlinear F-16 model description. The M-255, Dec. 1976.
Netherlands: Control & Simulation Division, Delft Uni- [34] Cybenko G. Approximation by superposition of
versity of Technology; June 2006. a sigmoidal function. Math Control Signals Syst
[22] Haykin S. Neural networks: A comprehensive founda-
1989;2(4):303–14.
tion. 2nd ed. Upper Saddle River, NJ, USA: Prentice [35] Hornik K, Stinchcombe M, White H. Multilayer feed-
Hall; 1998.
[23] Hamel PG, Jategaonkar RV. Evolution of flight vehicle forward networks are universal approximators. Neural
system identification. J Aircr 1996;33(1):9–28. Netw 1989;2(5):359–66.
[24] Hamel PG, Kaletka J. Advances in rotorcraft system [36] Gorban AN. Generalized approximation theorem and
identification. Prog Aerosp Sci 1997;33(3–4):259–84. computational capabilities of neural networks. Sib J Nu-
[25] Jategaonkar RV, Fischenberg D, von Gruenhagen W. mer Math 1998;1(1):11–24 (in Russian).
Aerodynamic modeling and system identification from [37] Muja M, Lowe DG. Scalable nearest neighbor algo-
flight data — recent applications at DLR. J Aircr rithms for high dimensional data. IEEE Trans Pattern
2004;41(4):681–91. Anal Mach Intell 2014;36(11):2227–40.
[26] Klein V. Estimation of aircraft aerodynamic parameters [38] Egorchev MV, Tiumentsev YV. Neural network based
from flight data. Prog Aerosp Sci 1989;26(1):1–77. semi-empirical approach to the modeling of longitudi-
[27] Iliff KW. Parameter estimation for flight vehicles. J Guid nal motion and identification of aerodynamic character-
Control Dyn 1989;12(5):609–22.
[28] Morelli EA, Klein V. Application of system identifica- istics for maneuverable aircraft. Tr MAI 2017;(94):1–16
tion to aircraft at NASA Langley Research Center. J (in Russian).
Aircr 2005;42(1):12–25.