DOI QR코드

DOI QR Code

Using Artificial Neural Network in the reverse design of a composite sandwich structure

  • Mortda M. Sahib (Faculty of Mechanical Engineering and Informatics, University of Miskolc) ;
  • Gyorgy Kovacs (Faculty of Mechanical Engineering and Informatics, University of Miskolc)
  • Received : 2022.09.06
  • Accepted : 2023.02.01
  • Published : 2023.03.10

Abstract

The design of honeycomb sandwich structures is often challenging because these structures can be tailored from a variety of possible cores and face sheets configurations, therefore, the design of sandwich structures is characterized as a time-consuming and complex task. A data-driven computational approach that integrates the analytical method and Artificial Neural Network (ANN) is developed by the authors to rapidly predict the design of sandwich structures for a targeted maximum structural deflection. The elaborated ANN reverse design approach is applied to obtain the thickness of the sandwich core, the thickness of the laminated face sheets, and safety factors for composite sandwich structure. The required data for building ANN model were obtained using the governing equations of sandwich components in conjunction with the Monte Carlo Method. Then, the functional relationship between the input and output features was created using the neural network Backpropagation (BP) algorithm. The input variables were the dimensions of the sandwich structure, the applied load, the core density, and the maximum deflection, which was the reverse input given by the designer. The outstanding performance of reverse ANN model revealed through a low value of mean square error (MSE) together with the coefficient of determination (R2) close to the unity. Furthermore, the output of the model was in good agreement with the analytical solution with a maximum error 4.7%. The combination of reverse concept and ANN may provide a potentially novel approach in designing of sandwich structures. The main added value of this study is the elaboration of a reverse ANN model, which provides a low computational technique as well as savestime in the design or redesign of sandwich structures compared to analytical and finite element approaches.

Keywords

Acknowledgement

The research was supported by the Hungarian National Research, Development, and Innovation Office-NKFIH under Project Number K 134358.

References

  1. Avcar, M., Hadji, L. and Civalek, O. (2021), "Natural frequency analysis of sigmoid functionally graded sandwich beams in the framework of high order shear deformation theory", Compos. Struct, 276, 1-14. https://doi.org/10.1016/j.compstruct.2021.114564.
  2. Azizi, S., Awad M.M. and Ahmadloo, E. (2016), "Prediction of water holdup in vertical and inclined oil-water two-phase flow using artificial neural network", Int. J. Multiphas. Flow, 80, 181-187. ttps://doi.org/10.1016/j.ijmultiphaseflow.2015.12.010.
  3. Basheer, I.A. and Hajmeer, M. (2000), "Artificial neural networks: Fundamentals, computing, design, and application", J. Microbiol. Meth., 43(1), 3-31. https://doi.org/10.1016/S0167-7012(00)00201-3.
  4. Basu, J.K., Bhattacharyya, D. and Kim, T. (2010), "Use of artificial neural network in pattern recognition", Int. J. Softw. Eng. Appl., 4(2), 23-34.
  5. Baykasoglu, A. and Baykasoglu, C. (2017), "Multiple objective crashworthiness optimization of circular tubes with functionally graded thickness via artificial neural networks and genetic algorithms", Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., 231(11), 2005-2016. https://doi.org/10.1177/0954406215627181.
  6. Compton, B.G. and Lewis, J.A. (2014), "3D-printing of lightweight cellular composites", Adv. Mater., 26(34), 5930-5935. https://doi.org/10.1002/adma.201401804.
  7. Dababneh, O., Kipouros, T. and Whidborne, J.F. (2018), "Application of an efficient gradient-based optimization strategy for aircraft wing structures", Aerosp., 5(1), 1-27. https://doi.org/10.3390/aerospace5010003.
  8. Esmaeili, M., Osanloo, M., Rashidinejad, F., Aghajani B.A. and Taji, M. (2014), "Multiple regression, ANN and ANFIS models for prediction of backbreak in the open pit blasting", Eng. Comput., 30(4), 549-558. https://doi.org/10.1007/s00366-012-0298-2.
  9. Hadji, L. (2019), "An analytical solution for bending and free vibration responses of functionally graded beams with porosities: Effect of the micromechanical models", Struct. Eng. Mech., 69(2), 231-241. https://doi.org/10.12989/sem.2019.69.2.231.
  10. Hadji, L., Atmane, H.A., Tounsi, A., Mechab, I. and Adda Bedia, E.A. (2011), "Free vibration of functionally graded sandwich plates using four-variable refined plate theory", Appl. Math. Mech., 32(7), 925-942. https://doi.org/10.1007/s10483-011-1470-9.
  11. Hadji, L. and Avcar, M. (2021), "Free vibration analysis of FG porous sandwich plates under various boundary conditions", J. Appl. Comput. Mech., 7(2), 505-519. https://doi.org/10.22055/jacm.2020.35328.2628.
  12. Hadji, L., Khelifa, Z. and El Abbes, A.B. (2016), "A new higher order shear deformation model for functionally graded beams", KSCE J. Civil Eng., 20(5), 1835-1841. https://doi.org/10.1007/s12205-015-0252-0.
  13. Harizi, W., Anjoul, J., Acosta S.V.A., Aboura, Z. and Briand, V. (2022), "Mechanical behavior of carbon-reinforced thermoplastic sandwich composites with several core types during three-point bending tests", Compos. Struct., 262, 113590. 1-12. https://doi.org/10.1016/j.compstruct.2021.113590.
  14. HexCel Composites (2000), Honeycomb Sandwich Design Technology, HexWeb Honeycomb Sandw. Des. Technol., AGU 075b, 1-28.
  15. Kan, C.W. and Song, L.J. (2016), "An artificial neural network model for prediction of colour properties of knitted fabrics induced by laser engraving", Neur. Proc. Lett., 44(3), 639-650. https://doi.org/10.1007/s11063-015-9485-7.
  16. Kovacs, Gy. (2019), "Optimization of structural elements of transport vehicles in order to reduce weight and fuel consumption", Struct. Eng. Mech., 71(3), 283-290. https://doi.org/10.12989/sem.2019.71.3.283.
  17. Kumar, R., Aggarwal, R.K. and Sharma, J.D. (2015), "Comparison of regression and artificial neural network models for estimation of global solar radiations", Renew. Sustain. Energy Rev., 52, 1294-1299. https://doi.org/10.1016/j.rser.2015.08.021.
  18. Lan, X., Huang, Q., Zhou, T. and Feng, S. (2020), "Optimal design of a novel cylindrical sandwich panel with double arrow auxetic core under air blast loading", Def. Technol., 16(3), 617-626. https://doi.org/10.1016/j.dt.2019.09.010.
  19. Lanzi, L., Bisagni, C. and Ricci, S. (2004), "Neural network systems to reproduce crash behavior of structural components", Comput. Struct., 82(1), 93-108. https://doi.org/10.1016/j.compstruc.2003.06.001.
  20. Larbi, L.O., Hadji, L., Meziane, M.A.A. and Adda Bedia, E.A. (2018), "An analytical solution for free vibration of functionally graded beam using a simple first-order shear deformation theory", Wind Struct., 27(4), 247-254. https://doi.org/10.12989/was.2018.27.4.247.
  21. Panda, B.N., Bahubalendruni, M.V.A.R. and Biswal, B.B. (2015), "A general regression neural network approach for the evaluation of compressive strength of FDM prototypes", Neur. Comput. Appl., 26(5), 1129-1136. https://doi.org/10.1007/s00521-014-1788-5.
  22. Pandey, D.S., Das, S., Pan, I., Leahy, J.J. and Kwapinski, W. (2016), "Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor", Waste Manage., 58, 202-213. https://doi.org/10.1016/j.wasman.2016.08.023.
  23. Qiu, K., Zhang, W. and Zhu, J. (2009), "Bending and dynamic analyses of sandwich panels considering the size effect of sandwich core", Int. J. Simul. Multidisc. Des. Optim., 3(3), 370-383. https://doi.org/10.1051/ijsmdo/2009013.
  24. Ramirez, J.D.R., Castanie, B. and Bouvet, C. (2017), "Analysis of nonlinear behavior on honeycomb cores", 21st International Conference on Composite Materials (ICCM 21), August.
  25. Stocchi, A., Colabella, L., Cisilino, A. and Alvarez, V. (2014), "Manufacturing and testing of a sandwich panel honeycomb core reinforced with natural-fiber fabrics", Mater. Des., 55, 394-403. https://doi.org/10.1016/j.matdes.2013.09.054.
  26. Sun, G., Li, G., Stone, M. and Li, Q. (2010), "A two-stage multi-fidelity optimization procedure for honeycomb-type cellular materials", Comput. Mater. Sci., 49(3), 500-511. https://doi.org/10.1016/j.commatsci.2010.05.041.
  27. Sun, Y. and Li, Q.M. (2018), "Dynamic compressive behaviour of cellular materials: A review of phenomenon, mechanism and modelling", Int. J. Impact Eng., 112, 74-115. https://doi.org/10.1016/j.ijimpeng.2017.10.006.
  28. Sun, Z., Li, D., Zhang, W., Shi, S. and Guo, X. (2017), "Topological optimization of biomimetic sandwich structures with hybrid core and CFRP face sheets", Compos. Sci. Technol., 142, 79-90. https://doi.org/10.1016/j.compscitech.2017.01.029.
  29. Sutherland, L.S. (2018), "A review of impact testing on marine composite materials: Part I-Marine impacts on marine composites", Compos. Struct., 188, 197-208. https://doi.org/10.1016/j.compstruct.2017.12.073.
  30. Szava, R.I., Szava, I., Vlase, S. and Modrea, A. (2020), "Determination of young's moduli of the phases of composite materials reinforced with longitudinal fibers, by global measurements", Symmetry, 12(10), 1-13. https://doi.org/10.3390/sym12101607.
  31. Thai, H.T., Nguyen, T.K., Vo, T.P. and Lee, J. (2014). "Analysis of functionally graded sandwich plates using a new first-order shear deformation theory", Eur. J. Mech. A/Solid., 45, 211-225. https://doi.org/10.1016/j.euromechsol.2013.12.008.
  32. Todor, M.P., Kiss, I. and Cioata, V.G. (2020), "Development of fabric-reinforced polymer matrix composites using bio-based components from post-consumer textile waste", Mater. Today Proc., 45, 4150-4156. https://doi.org/10.1016/j.matpr.2020.11.927.
  33. Virag, Z. and Jarmai, K. (2020), "Optimum design of stiffened plates for static or dynamic loadings using different ribs", Struct. Eng. Mech., 74(2), 255-266. https://doi.org/10.12989/sem.2020.74.2.255.
  34. Vitale, J.P., Francucci, G., Xiong, J. and Stocchi, A. (2017), "Failure mode maps of natural and synthetic fiber reinforced composite sandwich panels", Compos. Part A Appl. Sci. Manuf., 94, 217-225. https://doi.org/10.1016/j.compositesa.2016.12.021.
  35. Wang, K., Xu, H., Qu, F., Wang, X. and Shi, Y. (2018), "A reliability analysis framework with Monte Carlo simulation for weld structure of crane's beam", AIP Conf. Proc., 1955(1), 030024. https://doi.org/10.1063/1.5033623.
  36. Yang, X.H., Yan, H.B., Wang, W.B., Jin, L.W., Lu, T.J. and Ichimiya, K. (2015), "Thermo-fluidic characteristics of natural convection in honeycombs: The role of chimney enhancement", Sci. China Technol. Sci., 58(8), 1318-1327. https://doi.org/10.1007/s11431-015-5869-1.
  37. Zenkert, D. (1995), An Introduction to Sandwich Construction, Engineering Materials Advisory Services (EMAS), London, Great Britain.
  38. Zhang, Q., Yang, X., Li, P., Huang, G., Feng, S., Shen, C., Han, B., Zhang, X., Jin, F., Xu, F. and Lu, T.J. (2015), "Bioinspired engineering of honeycomb structure-Using nature to inspire human innovation", Prog. Mater. Sci., 74, 332-400. https://doi.org/10.1016/j.pmatsci.2015.05.001.