Please use this identifier to cite or link to this item: http://ena.lp.edu.ua:8080/handle/ntb/50764
Title: Neural network approach to direct parameter adaptation of longitudinal autopilots
Authors: Azarskov, V. N.
Zhiteckii, L. S.
Nikolaienko, S. A.
Manziuk, M. S.
Volkov, Yu. N.
Affiliation: National Aviation University
Int. Centre of Information Technologies and Systems
Bibliographic description (Ukraine): Neural network approach to direct parameter adaptation of longitudinal autopilots / V. N. Azarskov, L. S. Zhiteckii, S. A. Nikolaienko, M. S. Manziuk, Yu. N. Volkov // Автоматика/Automatiсs – 2018 : матеріали XXV Міжнародної конференція з автоматичного управління, 18–19 вересня 2018 року, Львів. — Львів : Видавництво Львівської політехніки, 2018. — С. 175–176. — (Controlling the aerospace craft, marine vessels and other moving objects).
Bibliographic description (International): Neural network approach to direct parameter adaptation of longitudinal autopilots / V. N. Azarskov, L. S. Zhiteckii, S. A. Nikolaienko, M. S. Manziuk, Yu. N. Volkov // Avtomatyka/Automatiss – 2018 : materialy XXV Mizhnarodnoi konferentsiia z avtomatychnoho upravlinnia, 18–19 veresnia 2018 roku, Lviv. — Lviv : Vydavnytstvo Lvivskoi politekhniky, 2018. — P. 175–176. — (Controlling the aerospace craft, marine vessels and other moving objects).
Is part of: Автоматика/Automatiсs – 2018 : матеріали XXV Міжнародної конференція з автоматичного управління, 2018
Conference/Event: XXV Міжнародна конференція з автоматичного управління "Автоматика/Automatiсs – 2018"
Journal/Collection: Автоматика/Automatiсs – 2018 : матеріали XXV Міжнародної конференція з автоматичного управління
Issue Date: 18-Sep-2018
Publisher: Видавництво Львівської політехніки
Place of the edition/event: Львів
Lviv
Temporal Coverage: 18–19 вересня 2018 року, Львів
UDC: 681.5
Keywords: aircraft
longitudinal autopilot
flight regime
parameter adaptation
neural network
Number of pages: 2
Page range: 175-176
Start page: 175
End page: 176
Abstract: An improvement of longitudinal autopilots consisting of the digital PI and P controllers is addressed in this paper. In order to achieve a good performance of these autopilots a direct adaptation of their three parameters is proposed. To this end, the two-circuit feedback is added by the feedforward circuit containing a neural network which needs to be trained offline. The input signals of this neural network correspond to the airspeed and the altitude of an aircraft whereas its output signals are the three controller parameters to be adjusted if flight regime changes. The behavior of a new longitudinal autopilot is studied by simulation experiments.
URI: http://ena.lp.edu.ua:8080/handle/ntb/50764
ISBN: 978-966-941-208-9
Copyright owner: © Національний університет “Львівська політехніка”, 2018
References (Ukraine): 1. Zhiteckii L.S., Azarskov V.N., Pilchevsky A.Yu., Solovchuk K.Yu. Design of digital autopilot for lateral motion control of an aircraft based on l1-optimization approach. Int. Journal of Engineering Research and Application, 2016. Vol. 6, P. 70–79.
2. Azarskov, V. N., Kucherov, D. P., Nikolaienko, S. A., Zhiteckii, L. S. Asymptotic behavior of gradient learning algorithms in neural network models for the identification of nonlinear systems. American Journal of Neural Networks and Applications, 2015. No 1, P. 1–10.
3. Zhiteckii, L.S., Azarskov, V.N., Nikolaienko, S.A., Solovchuk, K.Yu. Some features of neural networks as nonlinearly parameterized models of unknown systems using an online learning algorithm. Journal of Applied Math. and Physics, 2018. Vol.6, No.1, P. 247–263.
References (International): 1. Zhiteckii L.S., Azarskov V.N., Pilchevsky A.Yu., Solovchuk K.Yu. Design of digital autopilot for lateral motion control of an aircraft based on l1-optimization approach. Int. Journal of Engineering Research and Application, 2016. Vol. 6, P. 70–79.
2. Azarskov, V. N., Kucherov, D. P., Nikolaienko, S. A., Zhiteckii, L. S. Asymptotic behavior of gradient learning algorithms in neural network models for the identification of nonlinear systems. American Journal of Neural Networks and Applications, 2015. No 1, P. 1–10.
3. Zhiteckii, L.S., Azarskov, V.N., Nikolaienko, S.A., Solovchuk, K.Yu. Some features of neural networks as nonlinearly parameterized models of unknown systems using an online learning algorithm. Journal of Applied Math. and Physics, 2018. Vol.6, No.1, P. 247–263.
Content type: Article
Appears in Collections:Автоматика / Automatiсs. – 2018 р.



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.