Russian Federation
Russian Federation
Russian Federation
Orel, Orel, Russian Federation
Rassmotrena problema razrabotki vysokotochnoy bystrodeystvuyuschey programmy rascheta traektoriy dvizheniya rotorov. Na osnove algoritma Levenberga - Markvardta razrabotan programmnyy modul' rascheta reakciy smazochnogo sloya podshipnikov zhidkostnogo treniya. Provedeno sravnenie lineynyh i nelineynyh podhodov k resheniyu zadach dinamiki rotorov. Predstavlena kolichestvennaya ocenka tochnosti i bystrodeystviya neyrosetevogo podhoda po sravneniyu s klassicheskimi podhodami k raschetu dinamiki rotorov.
rotornye mashiny, podshipniki zhidkostnogo treniya, uravnenie Reynol'dsa, nesuschaya sposobnost', matrica zhestkosti, matrica dempfirovaniya, iskusstvennye neyronnye seti.
1. Savin, L.A. Modelirovanie rotornyh sistem s oporami zhidkostnogo treniya: monografiya / L.A. Savin, O.V. Solomin. - M.: Mashinostroenie-1, 2006. - 444 s.
2. Childs, D. Turbomachinery rotordynamics. Phenomena, modeling and analysis / D. Childs. - New York: John Wiley&Sons, 1993. - 496 p.
3. Hori, Y. Hydrodynamic lubrication / Y. Hori. - Tokyo: Yokendo Ltd, 2006. - 231 p.
4. Karkoub, M. Modelling pressure distribution in a rectangular gas bearing using neural networks / M. Karkoub, A. Elkamel // Tribology International. - 1997. - Vol. 30. - Is. 2. - P. 139-150.
5. Dongare, A.D. Predictive tool: an artificial neural network / A.D. Dongare, A.D. Kachare // International Journal of Engineering and Innovative Technology (IJEIT). - 2012. - Vol. 2. - Is. 1. - P. 209-214.
6. Qin, P. Dynamic analysis of hydrodynamic bearingrotor system based on neural network / P. Qin, Y. Shen, J. Zhu, H. Xu // International Journal of Engineering Science. - 2005. - Vol. 43. - P. 520-531.
7. Kurban, A.S. Analysis of a hydrodynamic thrust bearing with elastic deformation using a recurrent neural network / A.S. Kurban, S. Yildirim // Tribology International. - 2003. - Vol. 36. - Is. 12. - P. 943-948.
8. Asok, S.P. Neural network and CFD-based optimisation of square cavity and curved cavity static labyrinth seals / S.P. Asok, K. Sankaranarayanasamy, T. Sundararajan, K. Rajesh, G.S. Ganeshan // Tribology International. - 2007. - Vol. 40. - Is. 7. - P. 1204-1216.
9. Ghorbanian, J. Design predictive tool and optimization of journal bearing using neural network model and multiobjective genetic algorithm / J. Ghorbanian, M. Ahmadi, R. Soltani // Scientia Iranica, Transactions B: Mechanical Engineering. - 2011. - Vol. 18. - P. 1095-1105.
10. Simsir, M. Realtime monitoring and diagnostic of a low power hub motor using feedforward neural network / M. Simsir, R. Bayir, Y. Uyaroglu // Computational Intelligence and Neuroscience. - 2016. - Vol. 2016. - 13 p.
11. Samanta, B. Bearing fault detection using artificial neural networks and genetic algorithm / B. Samanta, K.R. Al-Balushi, S.A. Al-Araimi // EURASIP Journal of Applied Signal Processing. - 2004. - Vol. 3. - P. 366-377.
12. Chen, S.Y. Application of a recurrent wavelet fuzzyneural network in the positioning control of a magneticbearing mechanism / S.Y. Chen, Y.C. Hung, Y.H. Hung, C.H. Wu // Computers & Electrical Engineering. - 2016. - Vol. 54. - P. 147-158.
13. Kornaev, A.V. Application of artificial neural networks to calculation of oil film reaction forces and dynamics of rotors on journal bearings / A.V. Kor-naev, N.V. Kornaev, E.P. Kornaeva, L.A. Savin // International Journal of Rotating Machinery. - 2017.
14. Salvadori, M.G. Numerical methods in engineering / M.G. Salvadori, M.L. Baron. - 2 ed. - N. J.: Englewood Cliffs, 1966. - 302 p.
15. Oficial'nyy sayt GNU Octave. - URL: http://www.gnu.org/software/octave (data obrascheniya: 04.01.2016).
