ELASTIC AND DISSIPATIVE MATERIAL PROPERTIES DETERMINATION USING COMBINATION OF FEM AND COMPLEX ARTIFICIAL NEURAL NETWORKS
Abstract
The application of the complex artificial neural networks (CANN) to the inverse identification problem of the elastic and dissipative properties of deformable solids is considered. The additional information to the inverse problem is components of the displacement vector measured in a set of points at the solid boundary (positional measurement). This solid performs harmonic oscillations in the first resonant frequency. The process of displacement measurement is simulated using the calculation of finite elements software ANSYS, the building of the amplitude-frequency characteristics (AFC) of the displacement, and of the selection of their values for a set of frequencies (frequency measurement). In the given numerical example, problems on the accurate identification of the elastic modulus, and material quality depending on the number of measure points and their location, as well as on the neural network architecture and the length of the training process performed by the complex-value error back propagation (CBP) algorithm are investigated.
Keywords
complex-valued artificial neural networks,
identification of mechanical properties,
finite element method.
Supporting agencies: The research is done with the partial financial support from RFFI (grants nos. 13-01-00196-a, 13-01-00943-a).
About the Authors
Arkady Nikolayevich Solovyev
Don State Technical University, Russia
Russian Federation
Russian Federation
Truong Giang Nguyen Duy
Don State Technical University, Russia
Russian Federation
Russian Federation
References
1. Haykin, S. Neural Network: a comprehensive foundation / S. Haykin. — 2nd edition. — [S. l.] : Prentice Hall, 1998. — 842 p.
2. Идентификация трещиноподобных дефектов в упругих элементах конструкций на основе эволюционных алгоритмов / А. А. Краснощёков [и др.] // Дефектоскопия. — 2011. — № 6. — С. 67‒78.
3. Liu, S. W. Detection of cracks using neural networks and computational mechanics / S. W. Liu [et al.] // Computer methods in applied mechanics and engineering. — 2002. — Vol. 191. —
4. Pp. 2831‒2845.
5. Hasan, T. An application of neural networks for harmonic coefficients and relative phase shifts detection / T. Hasan, T. Feyzullah // Expert Systems with Applications. — 2011. — Vol. 38, iss. 4. — Pp. 3446‒3450.
6. Khandetsky, V. Signal processing in defect detection using back-propagation neural networks / V. Khandetsky, I. Antonyuk // NDT&E International. — 2002. — Pp. 483‒488.
7. Adaptive multilayer perceptron networks for detection of cracks in anisotropic laminated plates / Y. G. Xu [et al.] // International journal of solids and structures. — 2001. — Vol. 38. — Pp. 5625‒5645.
8. Korczak, P. Using neural network models for predicting mechanical properties after hot plate rolling processes / P. Korczak, H. Dyja, E. Łabuda // Journal of Materials Processing Technology. — 1998. — Vol. 80‒81. — Pp. 481‒486.
9. Mira, T. Predicting mechanical properties of elastomers with neural networks / T. Mira, S. Zoran, L. Uros // Polymer. — 2007. — Vol. 48. — Pp. 5340‒5347.
10. Ghaisari, J. Artificial neural network predictors for mechanical properties of cold rolling products / J. Ghaisari, H. Jannesari, M. Vatani // Advances in Engineering Software. — 2012. — Vol. 45. — Pp. 91‒99.
11. Iztok, P. Determination of scrap/supply probability curves for the mechanical properties of aluminium alloys in hot extrusion using a neural network-like approach / P. Iztok, T. Milan, K. Goran // Expert Systems with Applications. — 2012. — Vol. 39. — Pp. 5634‒5640.
12. Determination of the influence of processing parameters on the mechanical properties of the Ti-6Al-4V alloy using an artificial neural network / Y. Sun [et al.] // Computational Materials Science. — 2012. — Vol. 60. — Pp. 239‒244.
13. Nitta, T. A back-propagation algorithm for complex numbered neural networks / T. Nitta // Proceedings International Joint Conference on Neural Networks, IEEE, Nagoya. — 1993. —
14. Pp. 1649‒1652.
15. Nitta, T. An extension of the back-propagation algorithm to complex numbers / T. Nitta // Neural Network. — 1997. — Vol. 10. — Pp. 1391‒1415.
16. Hirose, A. Complex-valued neural networks: Theories and applications / A. Hirose, E. River // The Series on innovative intelligence. — 2003. — 388 p.
17. Li, C. Complex-valued wavelet network / C. Li, X. Liao, J. Yu // Journal of Computer and System Sciences. — 2003. — Vol. 67. — Pp. 623‒632.
18. Nitta, T. Complex-valued neural networks: utilizing high-dimensional parameters / T. Nitta // Information Science Reference. — 2009. — 504 p.
19. Белоконь, А. В. Новые схемы конечно-элементного динамического анализа пьезоэлек-трических устройств / А. В. Белоконь, А. В. Наседкин, А. Н. Соловьёв // Прикладная математика и механика. — 2002. — Т. 66, № 3. — С. 491‒501.
20. Новацкий, В. Теория упругости / В. Новацкий. — Москва : Мир, 1976. — 872 с.
Review
For citations:
Solovyev A.N., Nguyen Duy T. ELASTIC AND DISSIPATIVE MATERIAL PROPERTIES DETERMINATION USING COMBINATION OF FEM AND COMPLEX ARTIFICIAL NEURAL NETWORKS. Vestnik of Don State Technical University. 2014;14(2):84-92. (In Russ.) https://doi.org/10.12737/4540
Views:
484
Email this article 