Steel and Composite Structures

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Failure estimation of the composite laminates using machine learning techniques

  • Received : 2017.01.07
  • Accepted : 2017.09.02
  • Published : 2017.12.30
⟨ Previous Next ⟩

Abstract

The problem of layup optimization of the composite laminates involves a very complex multidimensional solution space which is usually non-exhaustively explored using different heuristic computational methods such as genetic algorithms (GA). To ensure the convergence to the global optimum of the applied heuristic during the optimization process it is necessary to evaluate a lot of layup configurations. As a consequence the analysis of an individual layup configuration should be fast enough to maintain the convergence time range to an acceptable level. On the other hand the mechanical behavior analysis of composite laminates for any geometry and boundary condition is very convoluted and is performed by computational expensive numerical tools such as finite element analysis (FEA). In this respect some studies propose very fast FEA models used in layup optimization. However, the lower bound of the execution time of FEA models is determined by the global linear system solving which in some complex applications can be unacceptable. Moreover, in some situation it may be highly preferred to decrease the optimization time with the cost of a small reduction in the analysis accuracy. In this paper we explore some machine learning techniques in order to estimate the failure of a layup configuration. The estimated response can be qualitative (the configuration fails or not) or quantitative (the value of the failure factor). The procedure consists of generating a population of random observations (configurations) spread across solution space and evaluating using a FEA model. The machine learning method is then trained using this population and the trained model is then used to estimate failure in the optimization process. The results obtained are very promising as illustrated with an example where the misclassification rate of the qualitative response is smaller than 2%.

Keywords

References

  1. Badallo, P., Trias, D., Marin, L. and Mayugo, J.A. (2013), "A comparative study of genetic algorithms for the multi-objective optimization of composite stringers under compression load", Compos. Part B, 47, 130-136. https://doi.org/10.1016/j.compositesb.2012.10.037
  2. Bagheri, M., Jafari, A.A. and Sadeghifar, M. (2011), "Multiobjective optimization of ring stiffened cylindrical shells using a genetic algorithm", J. Sound Vib., 330(3), 374-384. https://doi.org/10.1016/j.jsv.2010.08.019
  3. Bishop, C.M. (2006), Pattern Recognition and Machine Learning, Springer
  4. Chatzi, E.N., Hiriyur, B., Waisman, H. and Smyth, A.W. (2011), "Experimental application and enhancement of the XFEM-GA algorithm for the detection of flows in structures", Comput. Struct., 89(7-8), 556-570. https://doi.org/10.1016/j.compstruc.2010.12.014
  5. Cho, J.R., Lee, J.H., Kim, K.W. and Lee S.B. (2013), "Generalized evolutionary optimum design of fiber-reinforced tire belt structure", Steel Compos. Struct., 15(4), 451-466. https://doi.org/10.12989/scs.2013.15.4.451
  6. Falzon, B.G. and Faggiani, A. (2012), "The use of a genetic algorithm to improve the postbuckling strength of stiffened composite panel susceptible to secondary instabilities", Compos. Struct., 94(3), 883-895. https://doi.org/10.1016/j.compstruct.2011.10.015
  7. Ghiasi, H., Fayazbakhsh, K., Pasini, D. and Lessard, L. (2010), "Optimum stacking sequence design of composite materials Part II: Variable stiffness design", Compos. Struct., 93(1), 1-13. https://doi.org/10.1016/j.compstruct.2010.06.001
  8. Ghiasi, H., Pasini, D. and Lessard, L. (2009), "Optimum stacking sequence design of composite materials Part I: Constant stiffness design", Compos. Struct., 90(1), 1-11. https://doi.org/10.1016/j.compstruct.2009.01.006
  9. Hastie, T., Tibshirani, R. and Friedman, J. (2009), The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd Edition, Springer series in statistics.
  10. Kayikci, R. and Sonmez, F.O. (2012), "Design of composite laminates for optimum frequency response", J. Sound Vib., 331(8), 1759-1776. https://doi.org/10.1016/j.jsv.2011.12.020
  11. Kocak, Y, Gulbandilar, E. and Akcay, M. (2015), "Predicting the compressive strength of cement mortars containing FA and SF by MLPNN", Comput. Concrete, 15(5), 759-770. https://doi.org/10.12989/cac.2015.15.5.759
  12. Lee, D.S., Morillo, C., Bugeda, G., Oller, S. and Onate, E. (2012), "Multilayered composite structure design optimization using distributed/parallel multi-objective evolutionary algorithms", Compos. Struct., 94(3), 1087-1096. https://doi.org/10.1016/j.compstruct.2011.10.009
  13. Mohri, M., Rostamizadeh, A. and Talwalkar, A. (2012), Foundations of Machine Learning, MIT Press.
  14. Montagnier, O. and Hochard, Ch. (2013), "Optimization of hybrid high-modulus/high-strength carbon fiber reinforced plastic composite drive shafts", Mater. Des., 46, 88-100. https://doi.org/10.1016/j.matdes.2012.09.035
  15. Murphy, K.P. (2012), Machine Learning: a Probabilistic Perspective, 1st Edition, MIT Press.
  16. Murugan, S., Flores, E.I.S., Adhikari, S. and Friswell, M.I. (2012), "Optimal design of variable fiber spacing composites for morphing aircraft skin", Compos. Struct., 94(5), 1626-1633. https://doi.org/10.1016/j.compstruct.2011.12.023
  17. Ozcan, G., Kocak, Y. and Gulbandilar, E. (2017), "Estimation of compressive strength of BFS and WTRP blended cement mortars with machine learning models", Comput. Concrete, 19(3), 275-282. https://doi.org/10.12989/cac.2017.19.3.275
  18. Papadopoulos, L. and Kassapoglou, C. (2007), "Shear buckling of rectangular composites plates composed of concentric layups", Compos. Part A., 38(5), 1425-1430. https://doi.org/10.1016/j.compositesa.2006.05.008
  19. Park, C.H., Lee, W.I., Han, W.S. and Vautrin, A. (2008), "Improved genetic algorithm for multidisciplinary optimization of composites laminates", Comput. Struct., 86(19-20), 1894-1903. https://doi.org/10.1016/j.compstruc.2008.03.001
  20. Pohlak, M., Majak, J., Karjust, K. and Kuttner, R. (2010), "Multicriteria optimization of large composite parts", Compos. Struct., 92(9), 2146-2152. https://doi.org/10.1016/j.compstruct.2009.09.039
  21. Samui, P. (2011a), "Least square support vector machine and relevance vector machine for evaluating seismic liquefaction potential using SPT", Nat. Hazard., 59(2), 811-822. https://doi.org/10.1007/s11069-011-9797-5
  22. Samui, P. (2011b), "Prediction of pile bearing capacity using support vector machine", Int. J. Geotech. Eng., 5(1), 95-102. https://doi.org/10.3328/IJGE.2011.05.01.95-102
  23. Serban, A. (2016), "Fast and robust Matlab-based finite element model used in the layup optimization of composite laminates", Proceedings of the 7th International Conference on Advanced Concepts in Mechanical Engineering, Iasi, Romania, June.
  24. Sharma, D.S., Patel, N.P. and Trivedi, R.R. (2014), "Optimum design of laminates containing an elliptical hole", Int. J. Mech. Sci., 85, 76-87. https://doi.org/10.1016/j.ijmecsci.2014.04.019
  25. Sliseris, J. and Rocens, K. (2013), "Optimal design of composite plates with discrete variable thickness", Compos. Struct., 98, 15-23. https://doi.org/10.1016/j.compstruct.2012.11.015
  26. Topal, U. (2013), "Pareto optimum design of laminated composite truncated circular conical shells", Steel Compos. Struct., 14(4), 397-408. https://doi.org/10.12989/scs.2013.14.4.397
  27. Yong, M., Falzon, B.G. and Iannucci, L. (2008), "On the application of genetic algorithms for optimizing composites against impact loading", Int. J. Impact Eng., 35, 1293-1302. https://doi.org/10.1016/j.ijimpeng.2007.10.004
  28. Yong, M., Iannucci, L. and Falzon, B.G. (2010), "Efficient modelling and optimization of hybrid multilayered plates subject to ballistic impact", Int. J. Impact Eng., 37(6), 605-624. https://doi.org/10.1016/j.ijimpeng.2009.07.004