Hostname: page-component-cd9895bd7-dk4vv Total loading time: 0 Render date: 2024-12-28T02:21:38.680Z Has data issue: false hasContentIssue false
  • English
  • Français

Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Published online by Cambridge University Press:  19 September 2007

Sean Hanna
Sean Hanna
Affiliation:
University College London, London, United Kingdom
Get access Rights & Permissions [Opens in a new window]

Abstract

Structural optimization is usually handled by iterative methods requiring repeated samples of a physics-based model, but this process can be computationally demanding. Given a set of previously optimized structures of the same topology, this paper uses inductive learning to replace this optimization process entirely by deriving a function that directly maps any given load to an optimal geometry. A support vector machine is trained to determine the optimal geometry of individual modules of a space frame structure given a specified load condition. Structures produced by learning are compared against those found by a standard gradient descent optimization, both as individual modules and then as a composite structure. The primary motivation for this is speed, and results show the process is highly efficient for cases in which similar optimizations must be performed repeatedly. The function learned by the algorithm can approximate the result of optimization very closely after sufficient training, and has also been found effective at generalizing the underlying optima to produce structures that perform better than those found by standard iterative methods.

Keywords

Machine LearningOptimizationStructuresSupport Vector Machines
Type
Research Article
Information
AI EDAM , Volume 21 , Issue 4 , November 2007 , pp. 351 - 366
Copyright
Copyright © Cambridge University Press 2007

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Adeli, H., & Cheng, N. (1993). Integrated genetic algorithm for optimisation of space structures. Journal of Aerospace Engineering 6(4), 315–328.CrossRefGoogle Scholar
Arciszewski, T., & Ziarko, W. (1990). Inductive learning in civil engineering: rough sets approach. Microcomputers in Civil Engineering 5(1), 19–28.CrossRefGoogle Scholar
Astley, R.J., Harrington, J.J., & Stol, K.A. (1997). Mechanical modelling of wood microstructure, an engineering approach. IPENZ Transactions 24(1), 21–29.Google Scholar
Bendsøe, M.P., & Kikuchi, N. (1988). Generating optimal topologies in structural design using a homogenization method. Computer Methods in Applied Mechanics and Engineering 71(2), 197–224.CrossRefGoogle Scholar
Bendsøe, M.P., & Sigmund, O. (1999). Material interpolation schemes in topology optimisation. Archives of Applied Mechanics 69, 635–654.Google Scholar
Bendsøe, M.P., & Sigmund, O. (2003). Topology Optimisation: Theory, Methods and Applications. Berlin: Springer.Google Scholar
Chen, Y.M. (2002). Nodal based evolutionary structural optimisation methods. PhD Thesis. University of Southhampton.Google Scholar
Duda, R.O., Hart, P.E., & Stork, D.G. (2001). Pattern Classification. New York: Wiley.Google Scholar
Duffy, A.H.B. (1997). The “what” and “how” of learning in design. IEEE Expert: Intelligent Systems and Their Applications 12(3), 71–76.CrossRefGoogle Scholar
Hanna, S. & Haroun Mahdavi, S. (2004). Modularity and flexibility at the small scale: evolving continuous material variation with stereolithography. In Fabrication: Examining the Digital Practice of Architecture Beesley, P., Cheng, W., & Williamson, R., Eds.), pp. 76–87. Toronto: University of Waterloo School of Architecture Press.Google Scholar
Hanna, S., & Haroun Mahdavi, S. (2006). Inductive machine learning of microstructures: estimating a finite element optimisation using support vector machines. In Design Computing and Cognition '06 (Gero, J.S., Ed.), pp. 563–582. Dordrecht: Springer.CrossRefGoogle Scholar
Haroun Mahdavi, S., & Hanna, S. (2003). An evolutionary approach to microstructure optimisation of stereolithographic models. Proc. CEC2003, Congr. Evolutionary Computation., pp. 723–730, Canberra, Australia.Google Scholar
Haroun Mahdavi, S., & Hanna, S. (2004). Optimising continuous microstructures: a comparison of gradient-based and stochastic methods. Proc. SCIS & ISIS 2004, Joint 2nd Int. Conf. Soft Computing and Intelligent Systems and 5th Int. Symp. Advanced Intelligent Systems, p. WE-7-5, Yokohama, Japan.Google Scholar
Kicinger, R., Arciszewski, T., & De Jong, K. (2005). Parameterized versus generative representations in structural design: an empirical comparison. Proc. GECCO '05, pp. 2007–2014.CrossRefGoogle Scholar
Meiler, J., & Baker, D. (2003). Coupled prediction of protein secondary and tertiary structure. Proceedings of the National Academy of Sciences of the United States of America 100(21), 12105–12110.CrossRefGoogle ScholarPubMed
Murawski, K., Arciszewski, T., & De Jong, K. (2000). Evolutionary computation in structural design. Engineering with Computers 16(3–4), 275–286.CrossRefGoogle Scholar
Murdoch, T., & Ball, N. (1996). Machine learning in configuration design. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 10(2), 101–113.CrossRefGoogle Scholar
Neocleous, C.C., & Schizas, C.N. (1995). Artificial neural networks in marine propeller design. Proc. ICNN'95 Int. Conf. Neural Networks, Vol. 2, pp. 1098–1102New York: IEEE Computer Society Press.Google Scholar
Pezeshk, S., & Camp, C.V. (2002). State of the art on the use of genetic algorithms in design of steel structures. In Recent Advances in Optimal Structural Design. New York: ASCE.Google Scholar
Ping, Y. (1996). Development of genetic algorithm based approach for structural optimisation. PhD Thesis. Singapore: Nanyang Technological University.Google Scholar
Quinlan, J.R., (1993). C4.5: Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann.Google Scholar
Reich, Y. (1997). Machine learning techniques for civil engineering problems. Computer-Aided Civil and Infrastructure Engineering 12(4), 295–310.CrossRefGoogle Scholar
Reich, Y., & Barai, S.V. (1999). Evaluating machine learning models for engineering problems. Artificial Intelligence in Engineering 13, 257–272.CrossRefGoogle Scholar
Schoenhauer, M. (1996). Shape representations and evolution schemes. Proc. 5th Annual Conf. Evolutionary Programming, pp. 121–129.Google Scholar
Schwabacher, M., Ellman, T., & Hirsh, H. (1998). Learning to set up numerical optimisations of engineering designs. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 12(2), 173–192.CrossRefGoogle Scholar
Shea, K., & Cagan, J. (1998). Topology design of truss structures by shape annealing. In Proc. DETC98: 1998 ASME Design Engineering Technical Conf., pp. 1–11New York: ASME.Google Scholar
Sischka, J., Hensel, M., Menges, A., & Weinstock, M. (2004). Manufacturing complexity. Architectural Design 74(3), 72–79.Google Scholar
Suykens, J.A.K., Van Gestel, T., De Brabanter, J., De Moor, B., & Vandewalle, J. (2002). Least Squares Support Vector Machines. Singapore: World Scientific.CrossRefGoogle Scholar
Szczepanik, W., Arciszewski, T., & Wnek, J. (1996). Empirical performance comparison of selective and constructive induction. Engineering Applications of Artificial Intelligence 9(6), 627–637.CrossRefGoogle Scholar
Vapnik, V. (1995). The Nature of Statistical Learning Theory. New York: Springer–Verlag.CrossRefGoogle Scholar
Von Buelow, P. (2002). Using evolutionary algorithms to aid designers of archictural structures. In Creative Evolutionary Systems Bentley, P.J., & Corne, D.W., Eds.). San Francisco, CA: Morgan Kaufmann.Google Scholar
Wang, L.H., Liu, J., Li, Y.F., & Zhou, H.B. (2004). Predicting protein secondary structure by a support vector machine based on a new coding scheme. Genome Informatics 15(2), 181–190.Google ScholarPubMed