Artificial Neural Networks Application in Modal Analysis of Tires

Koštial, P.; Jančíková, Z.; Bakošová, D.; Valíček, J.; Harničárová, M.; Špička, I.

doi:10.2478/msr-2013-0040

Abstract

The paper deals with the application of artificial neural networks (ANN) to tires’ own frequency (OF) prediction depending on a tire construction. Experimental data of OF were obtained by electronic speckle pattern interferometry (ESPI). A very good conformity of both experimental and predicted data sets is presented here. The presented ANN method applied to ESPI experimental data can effectively help designers to optimize dimensions of tires from the point of view of their noise.

References

[1] Kováč, I., Krmela, J., Bakošová, J. (2011). Parametrizing of material input for modal analyses of FEA tire models. Metallurgical Journal, 64 (7), 73-78.
Search in Google Scholar
[2] Gaul, L., Willner, K., Hurlenbaus, S. (1999). Determination of material properties of plates from modal ESPI measurements. In 17th InternationalModal Analysis Conference (IMAC), 8-11 February 1999. Orlando, Florida: Society for Experimental Mechanics, 1756-1762.
Search in Google Scholar
[3] Caldersmith, G.W. (1984). Vibrations of orthotropic rectangular plates. Acta Acustica united with Acustica, 56 (2), 144-152.
Search in Google Scholar
[4] Kim, D.W., Lee, N.K., Na, N.K., Kwon, D. (2002). Mapping of surface residual stress field by laser interferometry using stress relaxation method. MRSProceedings, 750, Y8.7.10.1557/PROC-750-Y8.7
Search in Google Scholar
[5] Jones, R., Wykes, C. (1986). Holographic andSpeckle Interferometry, Second Edition. Cambridge University Press, 165-196.
Search in Google Scholar
[6] Špička, I., Heger, M., Franz, J. (2010). The mathematical-physical models and the neural network exploitation for time prediction of cooling down low range specimen. Archives of Metallurgy andMaterials, 55 (4), 921-926.
Search in Google Scholar
[7] Frischer, R., David, J., Vrožina, M. (2011). Neural networks usage at crystallizers diagnostics. In Proceedings of METAL 2011, 18-20 May 2011. Brno, Czech Republic: Tanger Ltd, 134-138.
Search in Google Scholar
[8] Myllykoski, P., Larkiola, J., Nylander, J. (1996). Development of prediction model for mechanical properties of batch annealed thin steel strip by using artificial neural network modelling. Journal ofMaterials Processing Technology, 60 (1-4), 399-404.10.1016/0924-0136(96)02361-8
Search in Google Scholar
[9] Jančíková, Z., Roubíček, V., Juchelková, D. (2008). Application of artificial intelligence methods for prediction of steel mechanical properties. Metalurgija, 47 (4), 339-342.
Search in Google Scholar
[10] Lee, Ch.Y., Hsieh, Y.H. (2012). Bearing damage detection of BLDC motors based on current envelope analysis. Measurement Science Review, 12 (6), 290-295.10.2478/v10048-012-0040-7
Search in Google Scholar
[11] Koštial, P., Jančíková, Z. (2012). Chosen methods of experimental data evaluation. In Proceedings of the11th Youth Symposium on Experimental SolidMechanics, 30 May - 2 June 2012. Brasov, Romania, 55-60.
Search in Google Scholar

Artificial Neural Networks Application in Modal Analysis of Tires

Abstract

Paradigm

My account