VESTNIK of Samara University. Aerospace and Mechanical EngineeringVESTNIK of Samara University. Aerospace and Mechanical Engineering2542-04532541-7533Samara National Research University1104410.18287/2541-7533-2022-21-4-44-51Research ArticleCalculation of aircraft lever-float valves using neural networksPushkarevD. O.<p>Postgraduate Student of the Department of Aircraft Maintenance</p>pushkarevdobez@mail.ruhttps://orcid.org/0000-0003-1549-7585KiselevD. Yu.<p>Candidate of Science (Engineering), Associate Professor of the Department of Aircraft Maintenance</p>eat@inbox.ruhttps://orcid.org/0000-0002-1478-3734KiselevYu. V.<p>Candidate of Science (Engineering), Associate Professor of the Department of Aircraft Maintenance</p>zamivt@ssau.ruhttps://orcid.org/0000-0003-0492-0878Samara National Research University1801202321444511701202317012023Copyright © 2023, VESTNIK of Samara University. Aerospace and Mechanical Engineering2023<p>The possibility of using neural networks in aviation is shown, in particular in products intended for use in aviation technology. The possibility of using neural networks throughout the entire life cycle of aviation equipment products is analyzed. The advantages that can be obtained using neural networks are described. The main stages of creating a neural network model are analyzed and a description of each stage is presented. The difficulties associated with the practical application of models based on artificial intelligence are shown. The calculation of the operation of a lever-float valve is presented and a neural network model is made for its calculation using real operation and test data.</p>Нейронная сетьрычажно-поплавковый клапантеория механизмов и машинмашинное обучениеуравнение моментовNeural networklever-float valvetheory of mechanisms and machinesmachine learningequation of moments[Russell S.J., Norving P. Artificial intelligence: a modern approach. Prentice-Hall, 2021. 1136 p.][Nikolenko S., Kadurin A., Arkhangel'skaya E. Glubokoe obuchenie [Deep learning]. SPb: Piter Publ., 2018. 480 p.][Rashid T. Make your own neural network. Kindle Edition, 2016. 222 p.][Brink K., Richards J., Fetherolf M. Real-world machine learning. Manning Publ., 2016. 264 p.][Goodfellow I., Bendgio Y., Courville A. Deep learning. MIT Press, 2016. 800 p.][Flach P. Machine learning: The art and science of algorithms that make sense of data. Cambridge University Press, 2012. 410 p.][Karelin V.S. Proektirovanie rychazhnykh i zubchato-rychazhnykh mekhanizmov: spravochnik [Design of linkage and geared linkage mechanisms. Reference guide]. Moscow: Mashinostroenie Publ., 1986. 180 p.][Sumskiy S.N. Raschet kinematicheskikh i dinamicheskikh kharakteristik ploskikh rychazhnykh mekhanizmov: spravochnik [Calculation of kinematic and dynamic characteristics of plain lever mechanisms. Reference guide]. Moscow: Mashinostroenie Publ., 1980. 312 p.][Frolov K.V., Popov S.A., Musatov A.K., Lukichev D.M., Skvortsova N.A., Nikonorov V.A., Savelova A.A., Petrov G.N., Remezova N.E., Akopyan V.M. Teoriya mekhanizmov i mashin: ucheb. dlya vtuzov [Theory of mechanisms and machines. Textbook for universities]. Moscow: Vysshaya Shkola Publ., 1987. 496 p.][Haykin S. Neural networks: a comprehencive foundation. Prentice Hall, 1999. 842 p.][GOST R 58849-2020. Civil aircraft. Development procedures. General provisions. Moscow: Standartinform Publ., 2020. 61 p. (In Russ.)]