Volume 51 Issue 4
Nov.  2021
Turn off MathJax
Article Contents
Zhang J M, Yang W D, Li Y. Application of artificial intelligence in composite materials. Advances in Mechanics, 2021, 51(4): 865-900 doi: 10.6052/1000-0992-21-019
Citation: Zhang J M, Yang W D, Li Y. Application of artificial intelligence in composite materials. Advances in Mechanics, 2021, 51(4): 865-900 doi: 10.6052/1000-0992-21-019

Application of artificial intelligence in composite materials

doi: 10.6052/1000-0992-21-019
More Information
  • Corresponding author: 20501@tongji.edu.cn
  • Received Date: 2021-04-15
  • Accepted Date: 2021-07-20
  • Available Online: 2021-07-26
  • Publish Date: 2021-11-26
  • Composite materials have become the major materials of light-weight structure due to their light weight, high strength, high modulus, and strong designability. However, as the component, structure and requirements of capability become increasingly complex, traditional research methods based on experiment, theoretical modeling and numerical simulation meet lots of new problems in the properties prediction, design optimization, manufacturing and processing of composite materials. Insufficient experimental observation, lacking theoretical model, constrained numerical simulation and difficult conclusion validation have seriously restricted the development of advanced composite materials in the future-oriented engineering. Instead of the mathematical models used by mechanics, data-driven models are used in the Artificial Intelligence. It directly establishes the complex relationship between variables from high-dimensional and high-throughput data, then captures the laws that are difficult to be discovered by traditional mechanical method, shows natural advantages in simulation, prediction, optimization in complex systems. It has become the development trend in the field of composite materials to find new solutions to the problems faced by traditional methods through Artificial Intelligence. In this paper, the status of properties prediction, design optimization, manufacturing and health monitoring is introduced. The future development direction of this field is discussed.

     

  • loading
  • [1]
    杜善义, 关志东. 2008. 我国大型客机先进复合材料技术应对策略思考. 复合材料学报, 1: 1-10 (Du S Y, Guan Z D. 2008. Strategic considerations for development of advanced composite technology for large commercial aircraft in China. Acta Materiae Compositae Sinica, 1: 1-10). doi: 10.3321/j.issn:1000-3851.2008.01.001
    [2]
    宁莉, 杨绍昌, 冷悦, 任学明, 苏霞, 闫超. 2020. 先进复合材料在飞机上的应用及其制造技术发展概述. 复合材料科学与工程, 5: 123-128 (Ning L, Yang S C, Leng Y, Ren X M, Su X, Yan C. 2020. Overview of the application of advanced composite materials on aircraft and the development of its manufacturing technology. Composites Science and Engineering, 5: 123-128). doi: 10.3969/j.issn.1003-0999.2020.09.020
    [3]
    亓欣波, 陈国锋, 李勇, 程宣, 李长鹏. 2019. 将基于神经网络的机器学习方法应用于增材制造——应用现状、当前挑战和未来前景. 工程, 5: 275-294 (Qi X B, Chen G F, Li Y, Cheng X, Li C P. 2019. Applying neural-network-based machine learning to additive manufacturing: current applications, challenges, and future perspectives. Engineering, 5: 275-294).
    [4]
    吴陈铭, 戴澄恺, 王昌凌, 刘永进. 2019. 多自由度3D打印技术研究进展综述. 计算机学报, 42: 1918-1938 (Wu C M, Dai C K, Wang C L, Liu Y J. 2019. Recent Progress on Multi-DOF 3D Printing: A Survey. Chinese Journal of Computers, 42: 1918-1938). doi: 10.11897/SP.J.1016.2019.01918
    [5]
    杨乃宾. 2008. 新一代大型客机复合材料结构. 航空学报, 3: 596-604 (Yang N B. 2008. Composite structures for new generation large commercial jet. Acta Aeronautica ET Astronautica Sinica, 3: 596-604). doi: 10.3321/j.issn:1000-6893.2008.03.010
    [6]
    Addona D D, Teti R, Caprino G. 2012. Residual strength prediction of artificially damaged composite laminates based on neural networks. Journal of Intelligent & Fuzzy Systems, 23: 217-223.
    [7]
    Al-Assadi M, El Kadi H, Deiab I M. 2009. Predicting the fatigue life of different composite materials using artificial neural networks. Applied Composite Materials, 17: 1-14.
    [8]
    Al-Assadi M, El Kadi H A, Deiab I M. 2010. Using artificial neural networks to predict the fatigue life of different composite materials including the stress ratio effect. Applied Composite Materials, 18: 297-309.
    [9]
    Aleksendrić D, Carlone P, Ćirović V. 2016. Optimization of the temperature-time curve for the curing process of thermoset matrix composites. Applied Composite Materials, 23: 1047-1063. doi: 10.1007/s10443-016-9499-y
    [10]
    Alvarez-Montoya J, Carvajal-Castrillón A, Sierra-Pérez J. 2020. In-flight and wireless damage detection in a UAV composite wing using fiber optic sensors and strain field pattern recognition. Mechanical Systems and Signal Processing, 136: 106526. doi: 10.1016/j.ymssp.2019.106526
    [11]
    Antil S K, Antil P, Singh S, Kumar A, Pruncu C I. 2020. Artificial neural network and response surface methodology based analysis on solid particle erosion behavior of polymer matrix composites. Materials (Basel), 13: 1-13.
    [12]
    António C C. 2014. A memetic algorithm based on multiple learning procedures for global optimal design of composite structures. Memetic Computing, 6: 113-131. doi: 10.1007/s12293-014-0132-z
    [13]
    António C C, Davim J P, Lapa V. 2007. Artificial neural network based on genetic learning for machining of polyetheretherketone composite materials. The International Journal of Advanced Manufacturing Technology, 39: 1101-1110.
    [14]
    António C C, Hoffbauer L N. 2010. Uncertainty propagation in inverse reliability-based design of composite structures. International Journal of Mechanics and Materials in Design, 6: 89-102. doi: 10.1007/s10999-010-9123-5
    [15]
    António C C, Hoffbauer L N. 2013. Uncertainty assessment approach for composite structures based on global sensitivity indices. Composite Structures, 99: 202-212. doi: 10.1016/j.compstruct.2012.12.001
    [16]
    Apalak M K, Karaboga D, Akay B. 2013. The artificial bee colony algorithm in layer optimization for the maximum fundamental frequency of symmetrical laminated composite plates. Engineering Optimization, 46: 420-437.
    [17]
    Artero-Guerrero J A, Pernas-Sánchez J, Martín-Montal J, Varas D, López-Puente J. 2018. The influence of laminate stacking sequence on ballistic limit using a combined Experimental/FEM/Artificial Neural Networks (ANN) methodology. Composite Structures, 183: 299-308. doi: 10.1016/j.compstruct.2017.03.068
    [18]
    Aymerich F, Serra M. 1997. Prediction of fatigue strength of composite laminates by means of neural networks. Key Engineering Materials, 144: 231-242. doi: 10.4028/www.scientific.net/KEM.144.231
    [19]
    Babu U H, Sai N V, Sahu R K. 2020. Artificial intelligence system approach for optimization of drilling parameters of glass-carbon fiber/polymer composites. Silicon. https://doi.org/10.1007/s12633-020-00637-5
    [20]
    Bai G H, Meng S H, Zhang B M, Liu Y. 2008. Prediction on carbon/carbon composites ablative performance by artificial neutral net. Journal of Materials Science & Technology, 24: 945-952.
    [21]
    Ball N R, Sargent P M, Ige D O. 1993. Genetic algorithm representations for laminate layups. Artificial Intelligence in Engineering, 8: 99-108. doi: 10.1016/0954-1810(93)90020-G
    [22]
    Barbosa A, Upadhyaya P, Iype E. 2020. Neural network for mechanical property estimation of multilayered laminate composite. Materials Today: Proceedings, 28: 982-985. doi: 10.1016/j.matpr.2019.12.336
    [23]
    Barry T J, Kesharaju M, Nagarajah C R, Palanisamy S. 2015. Defect characterisation in laminar composite structures using ultrasonic techniques and artificial neural networks. Journal of Composite Materials, 50: 861-871.
    [24]
    Bezerra E M, Ancelotti A C, Pardini L C, Rocco J A F F, Iha K, Ribeiro C H C. 2007. Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties. Materials Science and Engineering: A, 464: 177-185. doi: 10.1016/j.msea.2007.01.131
    [25]
    Bhoopal R S, Luyt A S, Sharma P K, Singh R. 2015. Prediction of the mechanical properties of copper powder-filled low-density polyethylene composites. a comparison between the ann and theoretical models. Composites: Mechanics, Computations, Applications: An International Journal, 6: 53-73. doi: 10.1615/CompMechComputApplIntJ.v6.i1.30
    [26]
    Bisagni C, Lanzi L. 2002. Post-buckling optimisation of composite stiffened panels using neural networks. Composite Structures, 58: 237-247. doi: 10.1016/S0263-8223(02)00053-3
    [27]
    Bobbili R, Madhu V. 2020. A machine learning approach in drilling of E-glass woven composites. Mechanics Based Design of Structures and Machines, 1-9.
    [28]
    Cacciola M, Lay-Ekuakille A, Megali G. 2013. Incremental Bayesian learning for in-service analysis of aeronautic composites. IET Science, Measurement & Technology, 7: 334-342.
    [29]
    Califano A, Chandarana N, Grassia L, D’Amore A, Soutis C. 2020. Damage detection in composites by artificial neural networks trained by using in situ distributed strains. Applied Composite Materials, 27: 657-671. doi: 10.1007/s10443-020-09829-z
    [30]
    Chakraborty D. 2005. Artificial neural network based delamination prediction in laminated composites. Materials & Design, 26: 1-7.
    [31]
    Chandrashekhara K, Okafor A C, Jiang Y P. 1998. Estimation of contact force on composite plates using impact-induced strain and neural networks. Composites Part B-Engineering, 29: 363-370.
    [32]
    Chen C T, Gu G X. 2020. Generative deep neural networks for inverse materials design using backpropagation and active learning. Adv Sci (Weinh), 7: 1902607. doi: 10.1002/advs.201902607
    [33]
    Chen R T Q, Rubanova Y, Bettencourt J, Duvenaud D. 2018. Neural ordinary differential equations. advances in neural information processing systems 31, La Jolla
    [34]
    Choi J H, Lee D G. 1995. Expert cure system for the carbon-fiber epoxy composite-materials. Journal of Composite Materials, 29: 1181-1200. doi: 10.1177/002199839502900903
    [35]
    Cupertino L F, Vilela Neto O P, Pacheco M A C, Vellasco M B R, d'Almeida J R M. 2011. Modeling the Young modulus of nanocomposites: a neural network approach// 2011 International Joint Conference on Neural Networks, San Jose, CA
    [36]
    Daghigh V, Lacy T E, Daghigh H, Gu G, Baghaei K T, Horstemeyer M F, Pittman C U. 2020. Machine learning predictions on fracture toughness of multiscale bio-nano-composites. Journal of Reinforced Plastics and Composites, 39: 587-598. doi: 10.1177/0731684420915984
    [37]
    De Fenza A, Sorrentino A, Vitiello P. 2015. Application of Artificial Neural Networks and Probability Ellipse methods for damage detection using Lamb waves. Composite Structures, 133: 390-403. doi: 10.1016/j.compstruct.2015.07.089
    [38]
    Eder M A, Chen X. 2020. Fastigue: A computationally efficient approach for simulating discrete fatigue crack growth in large-scale structures. Engineering Fracture Mechanics, 233: 107075. doi: 10.1016/j.engfracmech.2020.107075
    [39]
    Ehsani A, Dalir H. 2019. Multi-objective optimization of composite angle grid plates for maximum buckling load and minimum weight using genetic algorithms and neural networks. Composite Structures, 229: 111450. doi: 10.1016/j.compstruct.2019.111450
    [40]
    El Kadi H. 2008. Predicting the crushing behavior of axially loaded elliptical composite tubes using artificial neural networks. Applied Composite Materials, 15: 273-285. doi: 10.1007/s10443-008-9074-2
    [41]
    Erdal O, Sonmez F O. 2005. Optimum design of composite laminates for maximum buckling load capacity using simulated annealing. Composite Structures, 71: 45-52. doi: 10.1016/j.compstruct.2004.09.008
    [42]
    Fernández-Fdz D, López-Puente J, Zaera R. 2008. Prediction of the behaviour of CFRPs against high-velocity impact of solids employing an artificial neural network methodology. Composites Part A: Applied Science and Manufacturing, 39: 989-996. doi: 10.1016/j.compositesa.2008.03.002
    [43]
    Freirejr R, Neto A, Deaquino E. 2007. Use of modular networks in the building of constant life diagrams. International Journal of Fatigue, 29: 389-396. doi: 10.1016/j.ijfatigue.2006.06.005
    [44]
    Fu T, Zhang Z, Liu Y, Leng J. 2015. Development of an artificial neural network for source localization using a fiber optic acoustic emission sensor array. Structural Health Monitoring: An International Journal, 14: 168-177. doi: 10.1177/1475921714568406
    [45]
    Fu X, Ricci S, Bisagni C. 2015. Minimum-weight design for three dimensional woven composite stiffened panels using neural networks and genetic algorithms. Composite Structures, 134: 708-715. doi: 10.1016/j.compstruct.2015.08.077
    [46]
    Gautam G D, Mishra D R. 2019. Firefly algorithm based optimization of kerf quality characteristics in pulsed Nd:YAG laser cutting of basalt fiber reinforced composite. Composites Part B: Engineering, 176: 107340. doi: 10.1016/j.compositesb.2019.107340
    [47]
    Geng X, Lu S, Jiang M, Sui Q, Lv S, Xiao H, Jia Y, Jia L. 2018. Research on FBG-based cfrp structural damage identification using bp neural network. Photonic Sensors, 8: 168-175. doi: 10.1007/s13320-018-0466-0
    [48]
    Gerrard D D, Fullwood D T, Halverson D M. 2014. Correlating structure topological metrics with bulk composite properties via neural network analysis. Computational Materials Science, 91: 20-27. doi: 10.1016/j.commatsci.2014.04.014
    [49]
    Ghaboussi J, Pecknold D A, Zhang M F, Haj-Ali R M. 1998. Autoprogressive training of neural network constitutive models. International Journal for Numerical Methods in Engineering, 42: 105-126. doi: 10.1002/(SICI)1097-0207(19980515)42:1<105::AID-NME356>3.0.CO;2-V
    [50]
    Ghanem R, Soize C, Mehrez L, Aitharaju V. 2020. Probabilistic learning and updating of a digital twin for composite material systems. International Journal for Numerical Methods in Engineering, doi:10.1002/nme.6430" target="_blank">10.1002/nme.6430">doi:10.1002/nme.6430
    [51]
    Graham D, Maas P, Donaldson G B, Carr C. 2004. Impact damage detection in carbon fibre composites using HTS SQUIDs and neural networks. NDT & E International, 37: 565-570.
    [52]
    Gu G X, Chen C-T, Buehler M J. 2018a. De novo composite design based on machine learning algorithm. Extreme Mechanics Letters, 18: 19-28. doi: 10.1016/j.eml.2017.10.001
    [53]
    Gu G X, Chen C-T, Richmond D J, Buehler M J. 2018b. Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment. Materials Horizons, 5: 939-945. doi: 10.1039/C8MH00653A
    [54]
    Hanafi I, Khamlichi A, Cabrera F M, Nuñez López P J, Jabbouri A. 2012. Fuzzy rule based predictive model for cutting force in turning of reinforced PEEK composite. Measurement, 45: 1424-1435. doi: 10.1016/j.measurement.2012.03.022
    [55]
    Herencia J E, Weaver P M, Friswell M I. 2007. Optimization of long anisotropic laminated fiber composite panels with T-shaped stiffeners. Aiaa Journal, 45: 2497-2509. doi: 10.2514/1.26321
    [56]
    Hinton G E, Salakhutdinov R R. 2006. Reducing the dimensionality of data with neural networks. Science, 313: 504-507. doi: 10.1126/science.1127647
    [57]
    Hornik K. 1991. Approximation capabilities of multilayer feedforward networks. Neural Networks, 4: 251-257. doi: 10.1016/0893-6080(91)90009-T
    [58]
    Jac Fredo A R, Abilash R S, Femi R, Mythili A, Kumar C S. 2019. Classification of damages in composite images using Zernike moments and support vector machines. Composites Part B: Engineering, 168: 77-86. doi: 10.1016/j.compositesb.2018.12.064
    [59]
    Jayatheertha C, Webber J P H, Morton S K. 1996. Application of artificial neural networks for the optimum design of a laminated plate. Computers & Structures, 59: 831-845.
    [60]
    Jeon W S, Song J H. 2002. An expert system for estimation of fatigue properties of metallic materials. International Journal of Fatigue, 24: 685-698. doi: 10.1016/S0142-1123(01)00184-0
    [61]
    Jiang Z, Gyurova L A, Schlarb A K, Friedrich K, Zhang Z. 2008. Study on friction and wear behavior of polyphenylene sulfide composites reinforced by short carbon fibers and sub-micro TiO2 particles. Composites Science and Technology, 68: 734-742. doi: 10.1016/j.compscitech.2007.09.022
    [62]
    Jin Z, Zhang Z, Gu G X. 2019. Automated real-time detection and prediction of interlayer imperfections in additive manufacturing processes using artificial intelligence. Advanced Intelligent Systems, 2: 1900130.
    [63]
    Just-Agosto F, Serrano D, Shafiq B, Cecchini A. 2008. Neural network based nondestructive evaluation of sandwich composites. Composites Part B: Engineering, 39: 217-225. doi: 10.1016/j.compositesb.2007.02.023
    [64]
    Kalantari M, Dong C, Davies I J. 2017. Effect of matrix voids, fibre misalignment and thickness variation on multi-objective robust optimization of carbon/glass fibre-reinforced hybrid composites under flexural loading. Composites Part B: Engineering, 123: 136-147. doi: 10.1016/j.compositesb.2017.05.022
    [65]
    Kalita K, Mukhopadhyay T, Dey P, Haldar S. 2019. Genetic programming-assisted multi-scale optimization for multi-objective dynamic performance of laminated composites: The advantage of more elementary-level analyses. Neural Computing and Applications, 32: 7969-7993.
    [66]
    Kamarian S, Shakeri M, Yas M H. 2018. Natural frequency analysis and optimal design of CNT/fiber/polymer hybrid composites plates using mori-tanaka approach, GDQ technique, and firefly algorithm. Polymer Composites, 39: 1433-1446. doi: 10.1002/pc.24083
    [67]
    Kazi M K, Eljack F, Mahdi E. 2020. Optimal filler content for cotton fiber/PP composite based on mechanical properties using artificial neural network. Composite Structures, 251: 112654. doi: 10.1016/j.compstruct.2020.112654
    [68]
    Khan A, Kim H S. 2018. Assessment of delaminated smart composite laminates via system identification and supervised learning. Composite Structures, 206: 354-362. doi: 10.1016/j.com