Optimisation of material composition in functionally graded plates using a structure-tuned deep neural network

• Autorzy: Chiba Ryoichi , Kishida Takuya , Seki Ryoto , Sato Seiya

Identyfikatory

DOI

10.59441/ijame/192278

• Języki publikacji: EN

Abstrakty

EN

This study presents a neural network (NN)-based approach for optimising material composition in multi-layered functionally graded (FG) plates to minimise steady-state thermal stress. The focus is on the metal-ceramic composition across the thickness of heat-resistant FG plates, with the volume fractions of the ceramic constituent in each layer treated as design variables. A fully-connected NN, configured with an open-source Bayesian optimisation framework, is employed to predict the maximum in-plane thermal stress for various combinations of design variables. The optimal distribution of material composition is determined by applying a backpropagation algorithm to the NN. Numerical computations on ten- and twelve-layered FG plates demonstrate the usefulness of this approach in designing FG materials. NNs trained with 8000 samples enable the successful acquisition of valid optimal solutions within a practical timeframe.

Słowa kluczowe

EN

neural network; optimal design; functionally graded material; thermal stress; material design; multi-layered material

PL

sieć neuronowa; naprężenie cieplne; materiał wielowarstwowy

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mechanics and Engineering
• Rocznik: 2024
• Tom: Vol. 29, no. 4
• Strony: 78--95
• Opis fizyczny: Bibliogr. 41 poz., rys., wykr.

Twórcy

autor

Chiba Ryoichi

• Mechanical Engineering, Sanyo-Onoda City University, JAPAN

• https://orcid.org/0000-0002-2971-9049

autor

Kishida Takuya

• Mechanical Engineering, Sanyo-Onoda City University, JAPAN

autor

Seki Ryoto

• Mechanical Systems Engineering, National Institute of Technology, Asahikawa College, JAPAN

autor

Sato Seiya

• Mechanical Systems Engineering, National Institute of Technology, Asahikawa College, JAPAN

Bibliografia

• [1] Neubrand A. and Rödel J. (1997): Gradient materials: an overview of a novel concept.– Int. J. Materials Research, vol.88, No.5, pp.358-371, 10.3139/ijmr-1997-0066.
• [2] Nikbakht S., Kamarian S. and Shakeri M. (2019): A review on optimization of composite structures Part II:Functionally graded materials.– Composite Structures, vol.214, pp.83-102, 10.1016/j.compstruct.2019.01.105.
• [3] Nayak P. and Armani A. (2022): Optimal design of functionally graded parts.– Metals, vol.12, No.8, pp.1335,10.3390/met12081335.
• [4] Bobaru F. (2007): Designing optimal volume fractions for functionally graded materials with temperature-dependent material properties.– Trans. ASME J. Applied Mech., vol.74, No.5, pp.861-874, 10.1115/1.2712231.
• [5] Taheri A.H., Hassani B. and Moghaddam N.Z. (2014): Thermo-elastic optimization of material distribution of functionally graded structures by an isogeometrical approach.– Int. J. Solids Structures, vol.51, No.2, pp.416-429,10.1016/j.ijsolstr.2013.10.014.
• [6] Abdalla H.M.A., Casagrande D. and Moro L. (2020): Thermo-mechanical analysis and optimization of functionally graded rotating disks.– J. Strain Analysis Eng. Design, vol.55, No.5-6, pp.159-171, 10.1177/0309324720904793.
• [7] Roque C.M.C. and Martins P.A.L.S. (2015): Differential evolution for optimization of functionally graded beams.–Composite Structures, vol.133, pp.1191-1197, 10.1016/j.compstruct.2015.08.041.
• [8] Ootao Y., Kawamura R., Tanigawa Y. and Ishimaru O. (1998): Optimization of material composition of hollow circular cylinder of functionally graded material for thermal stress relaxation making use of genetic algorithm.–Trans. Japan Soc. Mech. Eng. Series A, vol.64, No.626, pp.2645-2652, 10.1299/kikaia.64.2645.
• [9] Shimojima K., Yamada Y., Mabuchi M., Saito N., Nakanishi M., Shigematsu I., Nakamura M., Asahina T. andIgarashi T. (1999): Optimization method of FGM compositional distribution profile design by genetic algorithm.–Materials Science Forum, vol.308-311, pp.1006-1011.
• [10] Ootao Y., Tanigawa Y. and Ishimaru O. (2000): Optimization of material composition of functionally graded plate for thermal stress relaxation using a genetic algorithm.– J. Thermal Stresses, vol.23, No.3, pp.257-271,10.1080/014957300280434.
• [11] Goupee A.J. and Vel S.S. (2006): Two-dimensional optimization of material composition of functionally graded materials using meshless analyses and a genetic algorithm.– Computer Methods Applied Mech. Eng., vol.195,No.44, pp.5926-5948, 10.1016/j.cma.2005.09.017.
• [12] Chiba R. and Sugano Y. (2012): Optimisation of material composition of functionally graded materials based on multiscale thermoelastic analysis.– Acta Mechanica, vol.223, No.5, pp.891-909, 10.1007/s00707-011-0610-z.
• [13] Fereidoon A., Sadri F. and Hemmatian H. (2012): Functionally graded materials optimization using particle swarm-based algorithms.– J. Thermal Stresses, vol.35, No.4, pp.377-392, 10.1080/01495739.2012.663688.
• [14] Xu Y., Zhang W., Chamoret D. and Domaszewski M. (2012): Minimizing thermal residual stresses in C/SiC functionally graded material coating of C/C composites by using particle swarm optimization algorithm.–Computational Materials Science, vol.61, pp.99-105, 10.1016/j.commatsci.2012.03.030.
• [15] Kou X.Y., Parks G.T. and Tan S.T. (2012): Optimal design of functionally graded materials using a procedural model and particle swarm optimization.– Computer-Aided Design, vol.44, No.4, pp.300-310,10.1016/j.cad.2011.10.007.
• [16] Eldeeb A., Shabana Y. and Elsawaf A. (2023): Thermoelastic stress mitigation and weight reduction of functionally graded multilayer nonuniform thickness disc.– J. Strain Analysis Eng. Design, vol.58, No.8, pp.661-671,10.1177/03093247231165091.
• [17] Eldeeb A.M., Shabana Y.M. and Elsawaf A. (2023): Particle swarm optimization for the thermoelastic behaviors of functionally graded rotating nonuniform thickness sandwich discs.– Arabian J. Science Eng., vol.48, No.3, pp.4067-4079, 10.1007/s13369-022-07351-x.
• [18] Kamgar R., Rahmani F. and Rahgozar R. (2024): Geometrical and material optimization of the functionally graded doubly-curved shell by metaheuristic optimization algorithms. Structures, vol.62, pp.106254,doi.org/10.1016/j.istruc.2024.106254.
• [19] Mozafari H., Ayob A. and Kamali F. (2012): Optimization of functional graded plates for buckling load by using imperialist competitive algorithm.– Procedia Technology, vol.1, pp.144-152, 10.1016/j.protcy.2012.02.028.
• [20] Cross S.R., Woollam R., Shademan S. and Schuh C.A. (2013): Computational design and optimization of multilayered and functionally graded corrosion coatings.– Corrosion Science, vol.77, pp.297-307,10.1016/j.corsci.2013.08.018.
• [21] Lieu Q.X. and Lee J. (2017): Modeling and optimization of functionally graded plates under thermo-mechanical load using isogeometric analysis and adaptive hybrid evolutionary firefly algorithm.– Composite Structures, vol.179, pp.89-106, 10.1016/j.compstruct.2017.07.016.
• [22] Cho J.R. and Shin S.W. (2004): Material composition optimization for heat-resisting FGMs by artificial neural network.– Composites Part A, vol.35, No.5, pp.585-594, 10.1016/j.compositesa.2003.12.003.
• [23] Yas M.H., Kamarian S. and Pourasghar A. (2014): Application of imperialist competitive algorithm and neural networks to optimise the volume fraction of three-parameter functionally graded beams.– J. Experimental Theoretical Artificial Intelligence, vol.26, No.1, pp.1-12, 10.1080/0952813X.2013.782346.
• [24] Do D.T.T., Lee D. and Lee J. (2019): Material optimization of functionally graded plates using deep neural network and modified symbiotic organisms search for eigenvalue problems.– Composites Part B, vol.159, pp.300-326,10.1016/j.compositesb.2018.09.087.
• [25] Truong T.T., Lee S. and Lee J. (2020): An artificial neural network-differential evolution approach for optimization of bidirectional functionally graded beams.– Composite Structures, vol.233, pp.111517,10.1016/j.compstruct.2019.111517.
• [26] Do D.T.T., Nguyen-Xuan H. and Lee J. (2020): Material optimization of tri-directional functionally graded plates by using deep neural network and isogeometric multimesh design approach.– Applied Mathematical Modelling,vol.87, pp.501-533, 10.1016/j.apm.2020.06.002.
• [27] Truong T.T., Lee J. and Nguyen-Thoi T. (2021): Multi-objective optimization of multi-directional functionally graded beams using an effective deep feed forward neural network-SMPSO algorithm.– Structural Multidisciplinary Optimization, vol.63, No.6, pp.2889-2918, 10.1007/s00158-021-02852-z.
• [28] Ootao Y., Kawamura R., Tanigawa Y. and Nakamura, T. (1998): Neural network optimization of material composition of a functionally graded material plate at arbitrary temperature range and temperature rise.– Archiveof Applied Mechanics, vol.68, No.10, pp.662-676, 10.1007/s004190050195.
• [29] Ootao Y., Tanigawa Y. and Nakamura T. (1999): Optimization of material composition of FGM hollow circular cylinder under thermal loading: a neural network approach.– Composites Part B, vol.30, No.4, pp.415-422,10.1016/S1359-8368(99)00003-7.
• [30] Ootao Y., Kawamura R., Tanigawa Y. and Imamura R. (1999): Optimization of material composition of nonhomogeneous hollow sphere for thermal stress relaxation making use of neural network.– Computer Methods Applied Mech. Eng., vol.180, No.1, pp.185-201, 10.1016/S0045-7825(99)00055-9.
• [31] Ootao Y., Kawamura R., Tanigawa Y. and Imamura R. (1999): Optimization of material composition of nonhomogeneous hollow circular cylinder for thermal stress relaxation making use of neural network.– J. Thermal Stresses, vol.22, No.1, pp.1-22, 10.1080/014957399281020.
• [32] Eldeeb A., Shabana Y. and Elsawaf A. (2021): Thermo-elastoplastic behavior of a rotating sandwich disc made of temperature-dependent functionally graded materials.– J. Sandwich Structures Materials, vol.23, No.5, pp.1761-1783, 10.1177/1099636220904970.
• [33] Fathi R., Wei H., Saleh B., Radhika N., Jiang J., Ma A., Ahmed M.H., Li Q. and Ostrikov K.K. (2022): Past andpresent of functionally graded coatings: Advancements and future challenges.– Applied Materials Today, vol.26,pp.101373, 10.1016/j.apmt.2022.101373.
• [34] Cho J.R. and Ha D.Y. (2002): Volume fraction optimization for minimizing thermal stress in Ni–Al2O3 functionally graded materials.– Materials Science Eng. A, vol.334, No.1, pp.147-155, 10.1016/S0921-5093(01)01791-9.
• [35] Sugano Y. (1987): An expression for transient thermal stress in a nonhomogeneous plate with temperature variation through thickness.– Ing. Arch., vol.57, No.2, pp.147-156, 10.1007/BF00541388.
• [36] Bergstra J., Bardenet R., Bengio Y. and Kégl B. (2011): Algorithms for hyper-parameter optimization.– In the 24thInt. Conf. Neural Information Processing Systems. (NY, USA: Curran Assosiates Inc.), pp.2546-2554.
• [37] Akiba T., Sano S., Yanase T., Ohta T. and Koyama, M. (2019): Optuna: a next-generation hyperparameter optimization framework.– In the 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining. (Anchorage,USA), pp.2623-2631.
• [38] Tanaka M., Hanahara K. and Seguchi, Y. (1992): Configuration control of the truss-type parallel manipulator by the modular neural network model.– JSME Int. J. Series 3, vol.35, No.1, pp.89-95, 10.1299/jsmec1988.35.89.
• [39] Cho J.R. and Ha D.Y. (2001): Averaging and finite-element discretization approaches in the numerical analysis of functionally graded materials.– Materials Science Eng. A, vol.302, No.2, pp.187-196, 10.1016/S0921-5093(00)01835-9.
• [40] Zhang X.C., Xu B.S., Wang H.D., Jiang Y. and Wu Y.X. (2006): Modeling of thermal residual stresses in multilayer coatings with graded properties and compositions.– Thin Solid Films, vol.497, No.1-2, pp.223-231,10.1016/j.tsf.2005.09.184.
• [41] Awaji H., Takenaka H., Honda S. and Nishikawa T. (2001): Temperature/stress distributions in a stress-relief-type plate of functionally graded materials under thermal shock.– JSME Int. J. Series A, vol.44, No.1, pp.37-44,10.1299/jsmea.44.37.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025)