Abstract
Problem of aircraft structural components (wing, fuselage, tail) optimization is considered. Solution of this problem is very computationally intensive, since it requires at each iteration a two-level process. First from previous iteration an update step at full component level must be performed in order to take into account internal loads and their sensitivities in the whole structure involved by changes in local geometry. Second numerous local analyzes are run on isolated elements (for example, super stiffeners) of structural components in order to calculate mechanical strength criteria and their sensitivities depending on current internal loads. An optimization step is then performed from combined global-local sensitivities. This bi-level global-local optimization process is then repeated until convergence of load distribution in the whole structure. Numerous calculations of mechanical strength criteria are necessary for local analyzes and results in great increase of the time between two iterations. In this work an effective method for speeding up the optimization process was elaborated. The method uses surrogate models of optimization constraints (mechanical strength criteria) and provides reduction of the structure optimization computational time from several days to a few hours.
Keywords
- Buckling analysis
- Approximation
- Mixture of experts
- HDA
- Composite structure
- Surrogate modeling
- Optimization
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Belyaev, M., Lyubin, A.: Some features of optimization problem arising in construction of multidimensional approximation. In: Proceedings of the Conference for Young Scientists and Engineers “Information Technology and Systems—2011”, Gelendzhik, Russia, pp. 415–422 (2011)
Belyaev, M.G., Burnaev, E.V., Lyubin, A.D.: Parametric dictionary selection for approximation of multidimensional dependency. In: Proceedings of All-Russian Conference “Mathematical Methods of Pattern Recognition (MMPR-15)”, Petrozavodsk, 11–17 September 2011, pp. 146–150 (2011)
Belyaev, M., Burnaev, E., Yerofeyev, P., Prikhodko, P.: Comparative performance of nonlinear regression initialization methods. In: Proceedings of the Conference for Young Scientists and Engineers “Information Technology and Systems—2011”, Gelendzhik, Russia, pp. 315–320 (2011)
Bettebghor, D., Bartoli, N., Grihon, S., Morlier, J., Samuelides, M.: Surrogate modelling approximation using a mixture of experts based on EM joint estimation. Struct. Multidiscip. Optim. 43(2), 243–259 (2011)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Berlin (2006)
Burnaev, E.V., Grihon, S.: Construction of the metamodels in support of stiffened panel optimization. In: Proceedings of the International Conference on Mathematical Methods in Reliability, Moscow, Russia, pp. 124–128 (2009)
Burnaev, E., Prikhodko, P.: Theoretical properties of procedure for construction of regression ensemble based on bagging and boosting. In: Proceedings of the Conference for Young Scientists and Engineers “Information Technology and Systems—2011”, Gelendzhik, Russia, pp. 438–443 (2011)
Burnaev, E., Prikhodko, P.: Approaches to dimensionality estimation in the effective dimensionality reduction based on Gaussian processes. In: Information Technologies and Systems 2012, Petrozavodsk, August 19–25. Springer, Berlin (2012)
Burnaev, E.V., Belyaev, M.G., Prihodko, P.V.: About hybrid algorithm for tuning of parameters in approximation based on linear expansions in parametric functions. In: Proceedings of the 8th International Conference “Intellectualization of Data Processing” (IDP-2010), Cyprus, 17–24 October 2011, pp. 200–203 (2011)
Burnaev, E.V., Zaytsev, A.A., Yanovich, Yu.A.: Consolidation of data with different fidelity on basis of Gaussian processes. In: Proceedings of the Conference “Information Technologies and Systems”, pp. 60–65 (2012)
Chiles, J.-P., Delfiner, P.: Geostatistics. Modeling Spatial Uncertainty. Wiley, New York (1999)
DATADVANCE: www.datadvance.net
Dolan, E., More, J.: Benchmarking optimization software with performance profiles. Math. Program., Ser. A 91, 201–213 (2002)
Forrester, A., Sobester, A., Keane, A.: Engineering Design via Surrogate Modeling. A Practical Guide. Wiley, New York (2008)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, Berlin (2008)
Haykin, S.S.: Neural Networks: A Comprehensive Foundation. Williams, Baltimore (2006)
http://www-03.ibm.com/systems/technicalcomputing/platformcomputing/products/lsf/index.html
Kuleshov, A.P., Bernstein, A.V., Burnaev, E.V.: Adaptive models of complex systems based on data handling. In: Proceedings of the Third International Conference on Inductive Modelling, Kyiv, Ukraine, pp. 64–71 (2010)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numer. 8, 143–195 (1999)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Wang, G., Shan, S.: Review of metamodeling techniques in support of engineering design optimization. J. Mech. Des. 129(3), 370–381 (2007)
Acknowledgements
E. Burnaev, M. Belyaev, and P. Prikhodko were partially supported by the Laboratory for Structural Methods of Data Analysis in Predictive Modeling, MIPT, RF government grant, ag. 11.G34.31.0073.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Grihon, S., Burnaev, E., Belyaev, M., Prikhodko, P. (2013). Surrogate Modeling of Stability Constraints for Optimization of Composite Structures. In: Koziel, S., Leifsson, L. (eds) Surrogate-Based Modeling and Optimization. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-7551-4_15
Download citation
DOI: https://doi.org/10.1007/978-1-4614-7551-4_15
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-7550-7
Online ISBN: 978-1-4614-7551-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)