Quantification of the out-of-plane loading fatigue response of bistable CFRP laminates using a machine learning approach

References

• M.W. Hyer, Some observations on the cured shape of thin unsymmetric laminates, J. Compos. Mater., vol. 15, no. 2, pp. 175–194, 3 1981. DOI: 10.1177/002199838101500207.
   Google Scholar
• M.W. Hyer, Calculations of the room-temperature shapes of unsymmetric laminates, J. Compos. Mater., vol. 15, no. 4, pp. 296–310, 7 1981. DOI: 10.1177/002199838101500401.
   Google Scholar
• M.W. Hyer, The room-temperature shapes of four-layer unsymmetric cross-ply laminates, J. Compos. Mater., vol. 16, no. 4, pp. 318–340, 1982. DOI: 10.1177/002199838201600406.
   Google Scholar
• V. Deshpande, S.A. Chowdhury, O. Myers, and S. Li, High-fidelity analytical modeling of asymmetric CFRP composites using Reissner–mindlin theory and hygroscopic degradation, Compos. Sci. Technol., vol. 236, pp. 109983, 5 2023. DOI: 10.1016/j.compscitech.2023.109983.
   Web of Science ®Google Scholar
• A.P. Vassilopoulos, and T. Keller, Fatigue of Fiber-Reinforced Composites. Springer, London, 2011.
   Google Scholar
• H. Mao, and S. Mahadevan, Fatigue damage modelling of composite materials, Compos. Struct., vol. 58, no. 4, pp. 405–410, 2002. DOI: 10.1016/S0263-8223(02)00126-5.
   Web of Science ®Google Scholar
• C. Nelon, O. Myers, and A. Hall, The intersection of damage evaluation of fiber-reinforced composite materials with machine learning: a review, J. Compos. Mater., vol. 56, no. 9, pp. 1417–1452, 2 2022. DOI: 10.1177/00219983211037048.
   Web of Science ®Google Scholar
• Z. Hashin, and A. Rotem, A fatigue failure criterion for fiber reinforced materials, J. Compos. Mater., vol. 7, no. 4, pp. 448–464, 1973. DOI: 10.1177/002199837300700404.
   Web of Science ®Google Scholar
• J. Degrieck, and W.V. Paepegem, Fatigue damage modeling of fibre-reinforced composite materials: review, Appl. Mech. Rev., vol. 54, pp. 279–300, 2001.
   Google Scholar
• F. Ellyin, and H. El-Kadi, A fatigue failure criterion for fiber reinforced composite laminae, Compos. Struct., vol. 15, no. 1, pp. 61–74, 1990. DOI: 10.1016/0263-8223(90)90081-O.
   Web of Science ®Google Scholar
• Z. Fawaz, and F. Ellyin, Fatigue failure model for fibre-reinforced materials under general loading conditions, J. Compos. Mater., vol. 28, no. 15, pp. 1432–1451, 1994. DOI: 10.1177/002199839402801503.
   Web of Science ®Google Scholar
• W. Hwang, and K. Han, Fatigue of composites—fatigue modulus concept and life prediction, J. Compos. Mater., vol. 20, no. 2, pp. 154–165, 1986. DOI: 10.1177/002199838602000203.
   Web of Science ®Google Scholar
• H.A. Whitworth, Cumulative damage in composites, J. Eng. Mater. Technol., vol. 112, no. 3, pp. 358–361, 7 1990. DOI: 10.1115/1.2903338.
   Web of Science ®Google Scholar
• F. Wu, and W. Yao, A fatigue damage model of composite materials, Int. J. Fatigue., vol. 32, no. 1, pp. 134–138, 2010. DOI: 10.1016/j.ijfatigue.2009.02.027.
   Web of Science ®Google Scholar
• S. Shiri, M. Yazdani, and M. Pourgol-Mohammad, A fatigue damage accumulation model based on stiffness degradation of composite materials, Mater. Des., vol. 88, pp. 1290–1295, 2015. DOI: 10.1016/j.matdes.2015.09.114.
   Web of Science ®Google Scholar
• H.W. Bergmann, and R. Prinz, Fatigue life estimation of graphite/epoxy laminates under consideration of delamination growth, Numer. Meth. Eng., vol. 27, no. 2, pp. 323–341, 9 1989. DOI: 10.1002/nme.1620270208.
   Web of Science ®Google Scholar
• R. Prinz, Damage Rates for Interlaminar Failure of Fatigued CFRP Laminates, Springer Netherlands, Netherlands, pp. 189–194, 1990.
   Google Scholar
• R. Aoki, R. Higuchi, and T. Yokozeki, Fatigue simulation for progressive damage in CFRP laminates using intra-laminar and inter-laminar fatigue damage models, Int. J. Fatigue., vol. 143, pp. 106015, 2 2021. DOI: 10.1016/j.ijfatigue.2020.106015.
   Web of Science ®Google Scholar
• S.A. Khan, S.S.R. Koloor, W.K. Jye, G. Siebert, and M.N. Tamin, A fatigue model to predict interlaminar damage of FRP composite laminates subjected to mode I load, Polymers (Basel)., vol. 15, no. 3, pp. 527, 1 2023. DOI: 10.3390/polym15030527.
   PubMed Web of Science ®Google Scholar
• G. Kemmann, and O. Myers, An experimental investigation of combined symmetric-asymmetric composite laminates, J. Compos. Sci., vol. 3, no. 3, pp. 71, 2019. DOI: 10.3390/jcs3030071.
   Google Scholar
• S. Phatak, O.J. Myers, S. Li, and G. Fadel, Defining relationships between geometry and behavior of bistable composite laminates, J. Compos. Mater., vol. 55, no. 22, pp. 3049–3059, 2021. DOI: 10.1177/00219983211005824.
   Web of Science ®Google Scholar
• H. Yu Meng, S. Jie Zhang, Y. Zhou, Y. Qing Hou, Q. Feng Chen, and J. Jun Jia, Snap behaviors of bistable unsymmetric cross-ply composite cylindrical shells with different thicknesses, Mech. Adv. Mater. Struct., vol. 29, no. 27, pp. 6557–6566, 2022. DOI: 10.1080/15376494.2021.1980929.
   Web of Science ®Google Scholar
• K. Yang, C. Li, and Y. Jiang, A bistable pure carbon fiber composite symmetric laminate and its preparation, modeling, and experimental verification, Mech. Adv. Mater. Struct., pp. 1–12, 2023. DOI: 10.1080/15376494.2023.2264847.
   Web of Science ®Google Scholar
• F. Mattioni, P. Weaver, and M. Friswell, Multistable composite plates with piecewise variation of lay-up in the planform, Int. J. Solids Struct., vol. 46, no. 1, pp. 151–164, 2009. DOI: 10.1016/j.ijsolstr.2008.08.023.
   Web of Science ®Google Scholar
• A. Algmuni, F. Xi, and H. Alighanbari, Design and analysis of a grid patch multi-stable composite, Compos. Struct., vol. 246, pp. 112378, 2020. DOI: 10.1016/j.compstruct.2020.112378.
   Web of Science ®Google Scholar
• F. Dai, H. Li, and S. Du, A multi-stable lattice structure and its snap-through behavior among multiple states, Compos. Struct., vol. 97, pp. 56–63, 2013. DOI: 10.1016/j.compstruct.2012.10.016.
   Web of Science ®Google Scholar
• K. Potter, Measurements of the snap-through behaviour and snap-through fatigue performance of bistable unsymmetric composite structures, 3rd International Conference on Composite Testing and Model Identification, Porto, Portugal, no. 4, pp. 1-2, 2003.
   Google Scholar
• S.A. Chowdhury, S. Li, and O.J. Myers, Fatigue analysis of bistable composite laminate, ASME 2022 Conference on Smart Materials, Adaptive Structures and Intelligent Systems, pp. 1–10, American Society of Mechanical Engineers, Dearborn, Michigan, pp. 1–10, 2022. DOI: 10.1115/SMASIS2022-90215.
   Google Scholar
• S.A. Chowdhury, S. Li, and O.J. Myers, Fatigue performance evaluation of bistable composites at different combinations of loading and environmental conditions, J. Compos. Mater., vol. 57, no. 27, pp. 4275–4289, 2023. DOI: 10.1177/00219983231207156.
   Web of Science ®Google Scholar
• H.R. Ashrafi, M. Jalal, and K. Garmsiri, Prediction of load–displacement curve of concrete reinforced by composite fibers (steel and polymeric) using artificial neural network, Expert Syst. Appl., vol. 37, no. 12, pp. 7663–7668, 2010. DOI: 10.1016/j.eswa.2010.04.076.
   Web of Science ®Google Scholar
• M.M. Kantor, V.V. Sudin, and K.A. Solntsev, Analysis of the relationship between the load-displacement curve and characteristics of fracture of low-alloy steel by neural networks, Inorg. Mater. Appl. Res., vol. 11, no. 4, pp. 893–902, 2020. DOI: 10.1134/S2075113320040176.
   Google Scholar
• M.-K. Kazi, F. Eljack, and E. Mahdi, Predictive ann models for varying filler content for cotton fiber/PVC composites based on experimental load displacement curves, Compos. Struct., vol. 254, pp. 112885, 2020. DOI: 10.1016/j.compstruct.2020.112885.
   Web of Science ®Google Scholar
• S. Mouloodi, H. Rahmanpanah, C. Burvill, and H.M. Davies, Prediction of load in a long bone using an artificial neural network prediction algorithm, J. Mech. Behav. Biomed. Mater., vol. 102, pp. 103527–103527, 2020. DOI: 10.1016/j.jmbbm.2019.103527.
   PubMed Web of Science ®Google Scholar
• H. Rahmanpanah, S. Mouloodi, C. Burvill, S. Gohari, and H.M. Davies, Prediction of load-displacement curve in a complex structure using artificial neural networks: a study on a long bone, Int. J. Eng. Sci., vol. 154, pp. 103319, 2020. DOI: 10.1016/j.ijengsci.2020.103319.
   Web of Science ®Google Scholar
• S. Zambal, C. Eitzinger, M. Clarke, J. Klintworth, and P.-Y. Mechin, A digital twin for composite parts manufacturing: effects of defects analysis based on manufacturing data, 2018 IEEE 16th International Conference on Industrial Informatics (INDIN), Porto, Portugal, pp. 803–808, 2018. DOI: 10.1109/INDIN.2018.8472014.
   Google Scholar
• C. González, and J. Fernández-León, A machine learning model to detect flow disturbances during manufacturing of composites by liquid moulding, J. Compos. Sci., vol. 4, no. 2, pp. 71, 6 2020. DOI: 10.3390/jcs4020071.
   Google Scholar
• S. Stieber, N. Schröter, A. Schiendorfer, A. Hoffmann, and W. Reif, FlowFrontNet: Improving Carbon Composite Manufacturing with CNNs, Springer, Berlin, Germany, pp. 411–426, 2021.
   Google Scholar
• Z. Jiang, L. Gyurova, Z. Zhang, K. Friedrich, and A.K. Schlarb, Neural network based prediction on mechanical and wear properties of short fibers reinforced polyamide composites, Mater. Des., vol. 29, no. 3, pp. 628–637, 2008. DOI: 10.1016/j.matdes.2007.02.008.
   Web of Science ®Google Scholar
• H.T. Fan, and H. Wang, Predicting the open-hole tensile strength of composite plates based on probabilistic neural network, Appl. Compos. Mater., vol. 21, no. 6, pp. 827–840, 2014. DOI: 10.1007/s10443-014-9387-2.
   Web of Science ®Google Scholar
• C. Hu, W.N.J. Hau, W. Chen, and Q.-H. Qin, The fabrication of long carbon fiber reinforced polylactic acid composites via fused deposition modelling: experimental analysis and machine learning, J. Compos. Mater., vol. 55, no. 11, pp. 1459–1472, 2021. DOI: 10.1177/0021998320972172.
   Web of Science ®Google Scholar
• T.-T. Le, Prediction of tensile strength of polymer carbon nanotube composites using practical machine learning method, J. Compos. Mater., vol. 55, no. 6, pp. 787–811, 2021. DOI: 10.1177/0021998320953540.
   Web of Science ®Google Scholar
• W. Sai, G.B. Chai, and N. Srikanth, Fatigue life prediction of glare composites using regression tree ensemble‐based machine learning model, Advcd. Theory and Sims., vol. 3, no. 6, pp. 1–11, 2020. DOI: 10.1002/adts.202000048.
   Web of Science ®Google Scholar
• F. Aymerich, and M. Serra, Prediction of fatigue strength of composite laminates by means of neural networks, KEM., vol. 144, pp. 231–242, 1997. DOI: 10.4028/www.scientific.net/KEM.144.231.
   Google Scholar
• J.A. Lee, D.P. Almond, and B. Harris, Use of neural networks for the prediction of fatigue lives of composite materials, Compos. A Appl. Sci. Manufact., vol. 30, no. 10, pp. 1159–1169, 1999. DOI: 10.1016/S1359-835X(99)00027-5.
   Web of Science ®Google Scholar
• H.E. Kadi, and Y. Al-Assaf, Prediction of the fatigue life of unidirectional glass fiber/epoxy composite laminae using different neural network paradigms, Compos. Struct., vol. 55, no. 2, pp. 239–246, 2002. DOI: 10.1016/S0263-8223(01)00152-0.
   Web of Science ®Google Scholar
• H.E. Kadi, and Y. Al-Assaf, Energy-based fatigue life prediction of fiberglass/epoxy composites using modular neural networks, Compos. Struct., vol. 57, no. 1–4, pp. 85–89, 2002. DOI: 10.1016/S0263-8223(02)00071-5.
   Web of Science ®Google Scholar
• M. Al-Assadi, H.A.E. Kadi, and I.M. Deiab, Using artificial neural networks to predict the fatigue life of different composite materials including the stress ratio effect, Appl. Compos. Mater., vol. 18, no. 4, pp. 297–309, 2011. DOI: 10.1007/s10443-010-9158-7.
   Web of Science ®Google Scholar
• S.A. Tawfik, D.S. Dancila, and E. Armanios, Planform effects upon the bistable response of cross-ply composite shells, Compos. A Appl. Sci. Manufact., vol. 42, no. 7, pp. 825–833, 2011. DOI: 10.1016/j.compositesa.2011.03.012.
   Web of Science ®Google Scholar
• F. Mattioni, P.M. Weaver, K.D. Potter, and M.I. Friswell, Analysis of thermally induced multistable composites, Int. J. Solids Struct., vol. 45, no. 2, pp. 657–675, 2008. DOI: 10.1016/j.ijsolstr.2007.08.031.
   Web of Science ®Google Scholar
• S. Tawfik, X. Tan, S. Ozbay, and E. Armanios, Anticlastic stability modeling for cross-ply composites, J. Compos. Mater., vol. 41, no. 11, pp. 1325–1338, 2007. DOI: 10.1177/0021998306068073.
   Web of Science ®Google Scholar
• M. Cantera, J. Romera, I. Adarraga, and F. Mujika, Modelling and testing of the snap-through process of bi-stable cross-ply composites, Compos. Struct., vol. 120, pp. 41–52, 2015. DOI: 10.1016/j.compstruct.2014.09.064.
   Web of Science ®Google Scholar
• M. Kuhn, and K. Johnson, Applied Predictive Modeling, Springer New York, New York, NY, 2013.
   Google Scholar
• E. Alpaydın, and F. Bach, Introduction to Machine Learning, 3rd ed., MIT Press, Cambridge, MA, 2014.
   Google Scholar
• G. Bonaccorso, Machine Learning Algorithms, 2nd ed., Packt Publishing, Birmingham, 2018.
   Google Scholar
• F. Pedregosa, et al., Scikit-learn: machine learning in python, J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
   Web of Science ®Google Scholar
• J.H. Friedman, Greedy function approximation: a gradient boosting machine, Ann. Statist., vol. 29, no. 5, pp. 1189–1232, 2001. DOI: 10.1214/aos/1013203451.
   Web of Science ®Google Scholar
• J.H. Friedman, Stochastic gradient boosting, Comput. Stat. Data Anal., vol. 38, no. 4, pp. 367–378, 2002. DOI: 10.1016/S0167-9473(01)00065-2.
   Web of Science ®Google Scholar
• G.E. Batista, and D.F. Silva, How k-nearest neighbor parameters affect its performance, Argentine Symposium on Artificial Intelligence, Mar Del Plata, Argentina, pp. 1–12, 2009.
   Google Scholar
• M. Heath, Scientific Computing: An Introductory Survey, 2nd ed., McGraw Hill, New York, NY, 2002.
   Google Scholar
• J. Nocedal, Updating quasi-newton matrices with limited storage, Math. Comp., vol. 35, no. 151, pp. 773–782, 1980. DOI: 10.2307/2006193.
   Web of Science ®Google Scholar
• A.J. Shepherd, Second-Order Methods for Neural Networks., 1st ed., Springer, Berlin, Germany, 1997.
   Google Scholar
• R.C. Schweitzer, and J.B. Morris, A tutorial on neural networks using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) training algorithm and molecular descriptors with application to the prediction of dielectric constants through the development of quantitative structure property relationships (qsprs), 1999.
   Google Scholar
• D. Byatt, I.D. Coope, and C.J. Price, Effect of limited precision on the BFGS quasi-newton algorithm, ANZIAMJ., vol. 45, pp. 283–285, 2004. DOI: 10.21914/anziamj.v45i0.888.
   Google Scholar
• H. Pakdel, and B. Mohammadi, Stiffness degradation of composite laminates due to matrix cracking and induced delamination during tension-tension fatigue, Eng. Fract. Mech., vol. 216, pp. 106489, 7 2019. DOI: 10.1016/j.engfracmech.2019.106489.
   Web of Science ®Google Scholar
• H.A.E. Kadi, and Y. Al-Assaf, The use of neural networks in the prediction of the fatigue life of different composite materials, 16th International Conference on Composite Materials, ICCM-16, pp. 7–13. International Committee on Composite Materials, Kyoto, Japan, vol. 7, 2007.
   Google Scholar