doi: 10.18698/2309-3684-2018-4-5771
The paper introduces a neural network implemented to classify air frame surface ele-ments. Within the research, we generated a sample containing the surface parameters of classification objects. In order to avoid errors associated with different measurement scales, the criteria were scaled. According to synthetic data, the neural network was trained, and the proposed model was verified. The optimal configuration of the neural network was determined experimentally. As a criterion of optimality, we used the proportion of correct answers from the test and training samples, and carried out calibration and modification of individual model parameters. The classification results of the test sample by the optimal network were summarized in the error matrix. The most significant result was achieved when distinguishing the class of ellipsoids. Separate blocks of the matrix show that the neural network accurately distinguishes the classes of ellipsoids and hyperboloids. The study proposes some ideas for further modification of the algorithm in order to increase the proportion of correct answers when distinguishing the class of paraboloids.
[1] Krasnov N.F. Osnovy aerodinamicheskogo rascheta. Aerodinamika tel vrash-cheniya, nesushchikh i upravlyayushchikh poverkhnostey. Aerodinamika le-tatelnykh apparatov [Fundamentals of aerodynamic calculation. Aerodynamics of bodies of revolution, bearing and control surfaces. Aerodynamics of aircraft]. Moscow, Vysshaya shkola Publ., 1981, 496 p.
[2] Shinkyu J., Kazuhisa C., Shigeru O. Data minig for aerodynamic design space. Journal of Aerospace Computing, Information and Communication, 2005,
vol. 2, no. 11, pp. 452–496.
[3] Paul G.T. Advanced Computational Fluid and Aerodynamics. Cambridge, Cambridge University Press, 2016, 578 p.
[4] Wei Wei, Rong Mo, Qingming Fan. Knowledge extraction for aerodynamic simulation data compressor rotor. Procedia Engineering, 2011, no. 15, pp. 1792–1796.
[5] Kotenev V.P., Raclav R.A., Sapozhnikov D.A., Chernyshev I.V. Matemati-
cheskoe modelirovanie i chislennye metody – Mathematical Modeling and Computational Methods, 2017, no. 3, pp. 83–1044.
[6] Callan R. The Essence of Neural Networks. Prentice Hall Europe, 1999, 232 p.
[In Russ.: Callan R. Osnovnye kontseptsii nejronnyh setey. Moscow, Vilyams Publ., 2001, 287 p.].
[7] Haykin S. Neural Networks: A Comprehensive Foundation. Prentice Hall, 2nd ed., 1998, 842 p. [In Russ.: Haykin S. Neyronnye seti: polny kurs. Moscow, Vilyams Publ., 200, 1104 p.].
[8] Jones M.T. AI Application Programming. Programming Series, 2005, 496 p.
[In Russ.: Jones M.T. Programmirovanie iskusstvennogo intellekta v prilozhe-niiakh. Moscow, DMK-Press Publ., 2011, 312 p.].
[9] Rutkovskaya D., Pilinskiy M., Rutkovskiy L. Neyronnye seti, geneticheskie
algoritmy i nechetkie sistemy [Neural networks, genetic algorithms and fuzzy systems]. Moscow, Goryachaya liniya – Telekom Publ., 2006, 452 p.
[10] Goldstein, B.S., Ehriel, I.M., Rerle, R.D. Intellektualnye seti [Intelligent Net-works]. Moscow, Radio i svyaz Publ., 2000, 500 p. (In Russ.)
[11] Kruglov V.V., Borisov V.V. Iskusstvennye neyronnye seti. Teoriya i praktika
[Iskusstvennye nejronnye seti. Teoriya i praktika]. Moscow, Goryachaya liniya – Telekom Publ., 2002, 382 p.
[12] Galushkin A.I. Teoriya neyronnykh setey. Kn. 1: Uchebnoe posobie dlya vuzov [Theory of neural networks. Book 1: textbook for universities]. Moscow, IPRZHR Publ., 2000, 416 p.
[13] Gallant S.L. Neutral Network Learning and Expert Systems. Cambridge, Massa-chusetts, MIT Press., 1993, 364 p.
[14] Sanger T.D. Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks, 1989, no. 2, pp. 459–473.
[15] Kolmogorov A.N. Doklady AN SSSR (Proceedings of the USSR Academy of Scien-
ces), 1958, vol. 114, no. 5, pp. 953–956.
[16] Napalkov A. V., Pragina L. L. Mozg cheloveka i iskusstvenny intellekt [Human brain and artificial intelligence]. Moscow, MSU Publ., 1985, 120 p.
[17] Penrose R. The Emperor's New Mind: Concerning Computers, Minds, and the Laws of Physics. Popular Science Ser., Oxford University Press, 1 ed., 2002,
640 p. [In Russ.: Penrose R. Novyy um korolya: o kompyuterakh, myshlenii
i zakonakh fiziki. Moscow, Editoriya URSS Publ., 2003, 384 p.].
[18] Minsky M., Papert S. Perceptrons: An Introduction to Computational Geometry. Cambridge, Massachusetts, MIT Press., 1969, 258 p.
[19] David L. P., Alan K. M. Artificial intelligence. Cambridge University Press, 2017, 760 p.
[20] Rosenblatt F. Principles of Neurodynamics. New York, Spartan Books. 1962, 616 p.
[21] Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning. New York, Springer, 2nd ed., 2009, 745 p.
Булгаков В.Н., Рацлав Р.А., Сапожников Д.А., Чернышев И.В. Моделирование нейронной сети для решения задачи классификации элементов корпуса летательного аппарата. Математическое моделирование и численные методы, 2018, № 4, с. 57–71.
Количество скачиваний: 549