Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders
Tóm tắt
Due to the high computational cost of finite element analyses, particularly in optimization tasks, establishing a high-fidelity surrogate model is of immense importance to engineers. Analyses of fiber steering composite cylinders are costly and often involve high nonlinearity. Among different metamodeling approaches, machine learning techniques provide effective models that can capture high nonlinearity. Therefore, in this study, different machine learning techniques are employed to establish a relationship between the fiber angle and buckling capacity of the cylinders under bending-induced loads. The utilized data set contains a total of 11,000 cases, including seven attributes (i.e., fiber angles) for 11 different aspect ratios (
$$L/R$$
). The numerical results demonstrate that compared with the Random Forest Regressor, Decision Tree algorithm, and Multiple Linear Regression, the Deep Learning model obtains stable results with smaller errors and higher generalization.
Tài liệu tham khảo
Gürdal, Z., Tatting, B.F., Wu, C.K.: Variable stiffness composite panels: effects of stiffness variation on the in-plane and buckling response. Compos. A Appl. Sci. Manuf. 39(5), 911–922 (2008). https://doi.org/10.1016/j.compositesa.2007.11.015
Setoodeh, S., Abdalla, M.M., Ijsselmuiden, S.T., Gürdal, Z.: Design of variable-stiffness composite panels for maximum buckling load. Compos. Struct. 87(1), 109–117 (2009). https://doi.org/10.1016/j.compstruct.2008.01.008
Kaveh, A., Dadras Eslamlou, A., Geran Malek, N.: Buckling load of laminated composite plates using three variants of the biogeography-based optimization algorithm. Acta Mech. 229(4), 1551–1566 (2018). https://doi.org/10.1007/s00707-017-2068-0
Kaveh, A., Dadras Eslamlou, A., Geran Malek, N.: Optimum stacking sequence design of composite laminates for maximum buckling load capacity using parameter-less optimization algorithms. Eng. Comput. 35(3), 813–832 (2019). https://doi.org/10.1007/s00366-018-0634-2
Kaveh, A., Dadras Eslamlou, A., Geran Malek, N.: Robust design optimization of laminated plates under uncertain bounded buckling loads. Struct. Multidiscip. Optim. 59(3), 877–891 (2019). https://doi.org/10.1007/s00158-018-2106-0
Tatting, B.F.: Analysis and Design of Variable Stiffness Composite Cylinders. Virginia Tech, Tehran (1998)
Blom, A.W., Stickler, P.B., Gürdal, Z.: Optimization of a composite cylinder under bending by tailoring stiffness properties in circumferential direction. Compos. B Eng. 41(2), 157–165 (2010). https://doi.org/10.1016/j.compositesb.2009.10.004
Khani, A., Abdalla, M.M., Gürdal, Z.: Circumferential stiffness tailoring of general cross section cylinders for maximum buckling load with strength constraints. Compos. Struct. 94(9), 2851–2860 (2012). https://doi.org/10.1016/j.compstruct.2012.04.018
Sun, M., Hyer, M.W.: Use of material tailoring to improve buckling capacity of elliptical composite cylinders. AIAA J. 46(3), 770–782 (2008). https://doi.org/10.2514/1.32495
Rouhi, M., Ghayoor, H., Hoa, S.V., Hojjati, M., Weaver, P.M.: Stiffness tailoring of elliptical composite cylinders for axial buckling performance. Compos. Struct. 150, 115–123 (2016). https://doi.org/10.1016/j.compstruct.2016.05.007
Ghiasi, H., Fayazbakhsh, K., Pasini, D., Lessard, L.: Optimum stacking sequence design of composite materials part II: variable stiffness design. Compos. Struct. 93(1), 1–13 (2010). https://doi.org/10.1016/j.compstruct.2010.06.001
Heydarpour, Y., Aghdam, M.M.: A coupled integral–differential quadrature and B-spline-based multi-step technique for transient analysis of VSCL plates. Acta Mech. 228(9), 2965–2986 (2017). https://doi.org/10.1007/s00707-017-1850-3
Farsadi, T., Asadi, D., Kurtaran, H.: Nonlinear flutter response of a composite plate applying curvilinear fiber paths. Acta Mech. 231(2), 715–731 (2020). https://doi.org/10.1007/s00707-019-02564-y
Forrester, A.I.J., Sóbester, A., Keane, A.J.: Multi-fidelity optimization via surrogate modelling. Proc. R. Soc. A: Math., Phys. Eng. Sci. 463(2088), 3251–3269 (2007). https://doi.org/10.1098/rspa.2007.1900
Wang, G.G., Shan, S.: Review of metamodeling techniques in support of engineering design optimization. J. Mech. Des. 129(4), 370–380 (2007)
Younis, A., Dong, Z.: Trends, features, and tests of common and recently introduced global optimization methods. Eng. Optim. 42(8), 691–718 (2010). https://doi.org/10.1080/03052150903386674
Jin, R., Chen, W., Simpson, T.W.: Comparative studies of metamodelling techniques under multiple modelling criteria. Struct. Multidiscip. Optim. 23(1), 1–13 (2001). https://doi.org/10.1007/s00158-001-0160-4
Rouhi, M., Rais-Rohani, M., Najafi, A.: Probabilistic analysis and optimization of energy absorbing components made of nanofiber enhanced composite materials. Compos. Struct. 100, 144–153 (2013). https://doi.org/10.1016/j.compstruct.2012.12.037
Fang, H., Rais-Rohani, M., Liu, Z., Horstemeyer, M.F.: A comparative study of metamodeling methods for multiobjective crashworthiness optimization. Comput. Struct. 83(25), 2121–2136 (2005). https://doi.org/10.1016/j.compstruc.2005.02.025
Kaveh, A., Dadras Eslamlou, A., Geran Malek, N., Ansari, R.: An open-source computational framework for optimization of laminated composite plates. Acta Mech. 231(6), 2629–2650 (2020). https://doi.org/10.1007/s00707-020-02648-0
Kaveh, A., Geran Malek, N., Dadras Eslamlou, A., Azimi, M.: An open-source framework for the FE modelling and optimal design of fiber-steered variable-stiffness composite cylinders using water strider algorithm. Mechanics Based Design of Structures and Machines 1–18 (2020). (Accepted for publication)
Steuben, J., Michopoulos, J., Iliopoulos, A., Turner, C.: Inverse characterization of composite materials via surrogate modeling. Compos. Struct. 132, 694–708 (2015). https://doi.org/10.1016/j.compstruct.2015.05.029
Rikards, R., Abramovich, H., Auzins, J., Korjakins, A., Ozolinsh, O., Kalnins, K., Green, T.: Surrogate models for optimum design of stiffened composite shells. Compos. Struct. 63(2), 243–251 (2004). https://doi.org/10.1016/S0263-8223(03)00171-5
Haeri, A., Fadaee, M.J.: Efficient reliability analysis of laminated composites using advanced Kriging surrogate model. Compos. Struct. 149, 26–32 (2016). https://doi.org/10.1016/j.compstruct.2016.04.013
Lopes, P.A.M., Gomes, H.M., Awruch, A.M.: Reliability analysis of laminated composite structures using finite elements and neural networks. Compos. Struct. 92(7), 1603–1613 (2010). https://doi.org/10.1016/j.compstruct.2009.11.023
Arian Nik, M., Fayazbakhsh, K., Pasini, D., Lessard, L.: Surrogate-based multi-objective optimization of a composite laminate with curvilinear fibers. Compos. Struct. 94(8), 2306–2313 (2012). https://doi.org/10.1016/j.compstruct.2012.03.021
Rouhi, M., Ghayoor, H., Hoa, S.V., Hojjati, M.: Effect of structural parameters on design of variable-stiffness composite cylinders made by fiber steering. Compos. Struct. 118, 472–481 (2014). https://doi.org/10.1016/j.compstruct.2014.08.021
Rouhi, M., Ghayoor, H., Hoa, S.V., Hojjati, M.: Computational efficiency and accuracy of multi-step design optimization method for variable stiffness composite structures. Thin Walled Struct. 113, 136–143 (2017). https://doi.org/10.1016/j.tws.2017.01.019
Rouhi, M., Ghayoor, H., Hoa, S.V., Hojjati, M.: Multi-objective design optimization of variable stiffness composite cylinders. Compos. B Eng. 69, 249–255 (2015). https://doi.org/10.1016/j.compositesb.2014.10.011
Ghayoor, H., Rouhi, M., Hoa, S.V., Hojjati, M.: Use of curvilinear fibers for improved bending-induced buckling capacity of elliptical composite cylinders. Int. J. Solids Struct. 109, 112–122 (2017). https://doi.org/10.1016/j.ijsolstr.2017.01.012
Arian Nik, M., Fayazbakhsh, K., Pasini, D., Lessard, L.: A comparative study of metamodeling methods for the design optimization of variable stiffness composites. Compos. Struct. 107, 494–501 (2014). https://doi.org/10.1016/j.compstruct.2013.08.023
Luersen, M.A., Steeves, C.A., Nair, P.B.: Curved fiber paths optimization of a composite cylindrical shell via Kriging-based approach. J. Compos. Mater. 49(29), 3583–3597 (2015). https://doi.org/10.1177/0021998314568168
Ye, F., Wang, H., Li, G.: Variable stiffness composite material design by using support vector regression assisted efficient global optimization method. Struct. Multidiscip. Optim. 56(1), 203–219 (2017). https://doi.org/10.1007/s00158-017-1658-8
Systèmes, D.: Abaqus 6.10: Analysis User’s Manual. Dassault Systèmes Simulia Corp, Providence (2010)
McKay, M.D., Beckman, R.J., Conover, W.J.: A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 21(2), 239–245 (1979)
Iman, R.L., Conover, W.J.: A distribution-free approach to inducing rank correlation among input variables. Commun. Stat. Simul. Comput. 11(3), 311–334 (1982). https://doi.org/10.1080/03610918208812265
Stein, M.: Large sample properties of simulations using latin hypercube sampling. Technometrics 29(2), 143–151 (1987). https://doi.org/10.1080/00401706.1987.10488205
Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. CRC Press, Boca Raton (1984)
Breiman, L., Friedman, J., Olshen, R.: Classification and Regression Trees. Routledge, Abingdon (2017)
Yildiz, B., Bilbao, J.I., Sproul, A.B.: A review and analysis of regression and machine learning models on commercial building electricity load forecasting. Renew. Sustain. Energy Rev. 73, 1104–1122 (2017). https://doi.org/10.1016/j.rser.2017.02.023
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539