Information-driven optimal experimental design with deep neural network surrogate model for composite materials

References

• H. Yang, and Y. Ren, Stacking design of uniaxial/biaxial braided composite tube under low-velocity impact load, Mech. Adv. Mater. Struct, vol. 0, no. 0, pp. 1–14, 2023. DOI: 10.1080/15376494.2023.2166169.
   Google Scholar
• R.S. Dhari, N.P. Patel, H. Wang, and P.J. Hazell, Progressive damage modeling and optimization of fibrous composites under ballistic impact loading, Mech. Adv. Mater. Struct., vol. 28, no. 12, pp. 1227–1244, 2021. DOI: 10.1080/15376494.2019.1655688.
   Web of Science ®Google Scholar
• E.I. Albak, Optimization design for circular multi-cell thinwalled tubes with discrete and continuous design variables, Mech. Adv. Mater. Struct., vol. 0, no. 0, pp. 1–15, 2022. DOI: 10.1080/15376494.2022.2111735.
   Google Scholar
• F. Fraternali, M.A. Porter, and C. Daraio, Optimal design of composite granular protectors, Mech. Adv. Mater. Struct., vol. 17, no. 1, pp. 1–19, 2009. DOI: 10.1080/15376490802710779.
   Web of Science ®Google Scholar
• K. Qiao, X. Xu, T.Q. Bui, T. Sun, and C. Zhang, Mechanical properties and macro–meso coupled damage behavior of threedimensional four-directional braided composites under bending loading, Mech. Adv. Mater. Struct., vol. 0, no. 0, pp. 1–15, 2023. DOI: 10.1080/15376494.2023.2185708.
   Google Scholar
• S. Mouloodi, H. Rahmanpanah, C. Burvill, S. Gohari, and H.M.S. Davies, Experimental, regression learner, numerical, and artificial neural network analyses on a complex composite structure subjected to compression loading, Mech. Adv. Mater. Struct.., vol. 29, no. 17, pp. 2437–2453, 2022. DOI: 10.1080/15376494.2020.1864071.
   Web of Science ®Google Scholar
• P. Zhan, X. Qin, Q. Zhang, and Y. Sun, Damage identification in beam-like structure using strain FRF-based damage index and artificial neural network, Mech. Adv. Mater. Struct.., vol. 0, no. 0, pp. 1–19, 2022. DOI: 10.1080/15376494.2022.2055241.
   Google Scholar
• A. Pagani, and M. Enea, Displacement and strain data-driven damage detection in multi-component and heterogeneous composite structures, Mech. Adv. Mater. Struct., vol. 0, no. 0, pp. 1–16, 2022. DOI: 10.1080/15376494.2022.2149907.
   Google Scholar
• D. Jia, F. Li, and Z. Liu, Design method and mechanical properties of a new pipe lattice structure, Mech. Adv. Mater. Struct., vol. 0, no. 0, pp. 1–17, 2022. DOI: 10.1080/15376494.2022.2058659.
   Google Scholar
• A. Singh, P.V. Katariya, and N. Karathanasopoulos, Composite sandwich plates with piezoelectric layers: structural design, modal attributes and electric potential, Mech. Adv. Mater. Struct., vol. 0, no. 0, pp. 1–15, 2023. DOI: 10.1080/15376494.2023.2198530.
   Google Scholar
• R. Yadav, and R. Ganguli, Reliability based and robust design optimization of truss and composite plate using particle swarm optimization, Mech. Adv. Mater. Struct., vol. 29, no. 13, pp. 1892–1902, 2022. DOI: 10.1080/15376494.2020.1843743.
   Web of Science ®Google Scholar
• K. Chaloner, and I. Verdinelli, Bayesian experimental design: a review, Statist. Sci., vol. 10, no. 3, pp. 273–304, 1995. DOI: 10.1214/ss/1177009939.
   Web of Science ®Google Scholar
• E.G. Ryan, C.C. Drovandi, J.M. McGree, and A.N. Pettitt, A review of modern computational algorithms for Bayesian optimal design, Int. Stat. Rev., vol. 84, no. 1, pp. 128–154, 2016. DOI: 10.1111/insr.12107.
   Web of Science ®Google Scholar
• R. Aggarwal, M. Demkowicz, and Y. Marzouk, Information-driven experimental design in materials science, Information Science for Materials Discovery and Design, Springer Ser. Mater. Sci. 225, pp. 13–44, 2016.
   Google Scholar
• A.M. Overstall, and D.C. Woods, Bayesian design of experiments using approximate coordinate exchange, Technometrics., vol. 59, no. 4, pp. 458–470, 2017. DOI: 10.1080/00401706.2016.1251495.
   Web of Science ®Google Scholar
• D.V. Lindley, Book Bayesian Statistics: A Review, ed., SIAM, Philadelphia, 1972.
   Google Scholar
• D.V. Lindley, and A.F. Smith, Bayes estimates for the linear model, J. R. Stat. Soc. B., vol. 34, no. 1, pp. 1–18, 1972. DOI: 10.1111/j.2517-6161.1972.tb00885.x.
   Google Scholar
• J. Stuckner, M. Piekenbrock, S.M. Arnold, and T.M. Ricks, Optimal experimental design with fast neural network surrogate models, Comput. Mater. Sci., vol. 200, pp. 110747, 2021. DOI: 10.1016/j.commatsci.2021.110747.
   Web of Science ®Google Scholar
• T.M. Cover, J.A. Thomas, Elements of Information Theory Elements of Information Theory (John Wiley & Sons, 2005, DOI: 10.1002/047174882X).
   Google Scholar
• K.J. Ryan, Estimating expected information gains for experimental designs with application to the random fatigue-limit model, J. Comput. Graphical Stat., vol. 12, no. 3, pp. 585–603, 2003. DOI: 10.1198/1061860032012.
   Web of Science ®Google Scholar
• S. Gao, G. Ver Steeg, and A. Galstyan, Efficient estimation of mutual information for strongly dependent variables. In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (AISTATS), pp:277–286, PMLR, 2015.
   Google Scholar
• W. Gao, S. Kannan, S. Oh, and P. Viswanath, Estimating mutual information for discrete-continuous mixtures, Adv. Neural Inform. Proc. Syst., vol. 30, 2017.
   Google Scholar
• A. Rahimzamani, and S. Kannan, Potential conditional mutual information: estimators and properties, in Proc. 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA, pp. 1228–1235, 2017. DOI: 10.1109/ALLERTON.2017.8262877.
   Google Scholar
• B. Póczos, and J. Schneider, Nonparametric estimation of conditional information and divergences. In: Artificial Intelligence and Statistics, pp. 914–923, 2012.
   Google Scholar
• A. Overstall, D. Woods, and M. Adamou, acebayes: An R package for Bayesian optimal design of experiments via approximate coordinate exchange, J. Stat. Softw. Vol. 95, no. 13, pp. 1–33, 2019.
   Google Scholar
• R.F. Gibson, Principles of Composite Material Mechanics, 4th ed, CRC press, 2016.
   Google Scholar
• K.A.-D. Bsisu, H.H. Hussein, and S.M. Sargand, The use of Hashin damage criteria, CFRP–concrete interface and concrete damage plasticity models in 3D finite element modeling of retrofitted reinforced concrete beams with CFRP sheets, Arab. J. Sci. Eng., vol. 42, no. 3, pp. 1171–1184, 2017. DOI: 10.1007/s13369-016-2356-3.
   Web of Science ®Google Scholar
• A. Géron, Hands-on machine learning with Scikit-Learn, Keras. In: and TensorFlow: concepts, tools, and techniques to build intelligent systems, O’Reilly Media, 2019.
   Google Scholar
• F.J.J. Joseph, S. Nonsiri, and A. Monsakul, Keras and TensorFlow: A hands-on experience. In Advanced Deep Learning for Engineers Scientists: A Practical Approach, Springer, pp. 85–111, 2021.
   Google Scholar