A review of prediction methods of process-induced distortions in thermoset composites based on artificial neural network

doi:10.19936/j.cnki.2096-8000.20221128.018

Abstract

Abstract: Thermosetting-matrix composites have become attractive in aerospace industry on account of their numerous advantages over conventional materials, such as their intriguing physical and mechanical properties, and their designable ability in terms of the design process and the subsequent manufacturing process. Despite these benefits, process-induced distortion is crucial issue since it cause assembly difficulties and residual stresses. This paper aimed at reporting the current research status of the process-induced distortion behavior of thermosetting-matrix composites, which was introduced during the hot forming process. The process-induced distortion mechanism, the related numerical simulation method, artificial neural network method and its application in the process-induced distortion were mainly introduced. An emphasis being placed on the state-of-art development of high-throughput prediction and inverse design of process-induced distortions based on artificial neural network. Finally, the future development directions of process-induced distortion and artificial neural network were briefly discussed.

Key words: composites, process-induced distortions, finite element method, machine learning, artificial neural network

CLC Number:

TB332

LUO Ling, TIAN Zhi-li, ZHANG Tao, LIU Lei-bo, LI Zhuo-da, LI Li-ying. A review of prediction methods of process-induced distortions in thermoset composites based on artificial neural network[J]. COMPOSITES SCIENCE AND ENGINEERING, 2022, 0(11): 120-127.

References

[1] SCHAPERY R A. Stress analysis of viscoelastic composite materials[J]. Journal of Composite Materials, 1967, 1(3): 228-267.
[2] WEITSMAN Y. Residual thermal stresses due to cool-down of epoxy-resin composites[J]. Journal of Applied Mechanics, 1979, 46(3): 563-567.
[3] BOGETTI T A, GILLESPIE J W. Process-induced stress and deformation in thick-section thermoset composite laminates[J]. Journal of Composite Materials, 1992, 26(5): 626-660.
[4] JOHNSTON A A. An integrated model of the development of process-induced deformation in autoclave processing of composite structures[D]. Ann Arbor: The University of British Columbia (Canada), 1998.
[5] JOHNSTON A A, VAZIRI R, POURSARTIP A. A plane strain model for process-induced deformation of laminated composite structures[J]. Jouranl of Composite Materials, 2001, 35(16): 1435-1469.
[6] DING A X, LI S X, WANG J H, et al. A new path-dependent constitutive model predicting cure-induced distortions in composite structures[J]. Composites Part A: Applied Science and Manufacturing, 2017, 95: 183-196.
[7] LANGE J, TOLL S, MANSON J E, et al. Residual stress build-up in thermoset films cured above their ultimate glass transition temperature[J]. Polymer, 1995, 36(16): 3135-3141.
[8] WISNOM M R, GIGLIOTTI M, ERSOY N, et al. Mechanisms generating residual stresses and distortion during manufacture of polymer-matrix composite structures[J]. Composites Part A: Applied Science and Manufacturing, 2006, 37(4): 522-529.
[9] HAHN H T, PAGANO N J. Curing stresses in composite laminates[J]. Journal of Composite Materials, 1975, 9(1): 91-106.
[10] LIU K, YE J R, TANG Z W, et al. Simulation and verification of machining deformation for composite materials[J]. The Journal of Wuhan University of Technology-Materials Science Edition, 2014, 29(5): 917-922.
[11] LIU K, ZHANG B M, XU X, et al. Simulation and analysis of process-induced distortions in hemispherical thermostamping for unidirectional thermoplastic composites[J]. Polymer Composites, 2018, 40(5): 1786-1800.
[12] 刘凯. 连续纤维增强复合材料热压工艺弹塑性变形机理与数值模拟[D]. 北京: 北京航空航天大学, 2018.
[13] 唐占文, 张博明. 复合材料设计制造一体化中的固化变形预报技术[J]. 航空制造技术, 2014, 15: 32-37.
[14] QI Z C, ZHANG N X, LIU Y, et al. Prediction of mechanical properties of carbon fiber based on cross-scale FEM and machine learning[J]. Composite Structures, 2019, 212: 199-206.
[15] YANG Z, GU X S, LIANG X Y, et al. Genetic algorithm-least squares support vector regression based predicting and optimizing model on carbon fiber composite integrated conductivity[J]. Materials & Design, 2010, 31(3): 1042-1049.
[16] FARHANA N I E, ABDUL MAJID M S, PAULRAJ M P, et al. A novel vibration based non-destructive testing for predicting glass fibre/matrix volume fraction in composites using a neural network model[J]. Composite Structures, 2016, 144: 96-107.
[17] BAYRAKTAR Ö, UZUN G, ÇAKIROĞLU R, et al. Experimental study on the 3d-printed plastic parts and predicting the mechanical properties using artificial neural networks[J]. Polymers for Advanced Technologies, 2016, 28(8): 1044-1051.
[18] SINGH A K, SIDDHARTHA, YADAV S. Investigation of sub-micron size cenosphere fillers and filler loading on the mechanical and tribological peculiarity of polyester composites[J]. Polymers for Advanced Technologies, 2017, 28(12): 1764-1777.
[19] YE L, SU Z Q, YANG C H, et al. Hierarchical development of training database for artificial neural network-based damage identification[J]. Composite Structures, 2006, 76(3): 224-233.
[20] NAIR A, CAI C S, KONG X. Acoustic emission pattern recognition in CFRP retrofitted RC beams for failure mode identification[J]. Composites Part B: Engineering, 2019, 161: 691-701.
[21] AL-ASSAF Y, KADI H E. Fatigue life prediction of composite materials using polynomial classifiers and recurrent neural networks[J]. Composite Structures, 2007, 77(4): 561-569.
[22] CARLONE P, ALEKSENDRIĆ D, ĆIROVIĆ V, et al. Meta-modeling of the curing process of thermoset matrix composites by means of a FEM-ANN approach[J]. Composites Part B: Engineering, 2014, 67: 441-448.
[23] LIN Y C, LIANG Y J, CHEN M S, et al. A comparative study on phenomenon and deep belief network models for hot deformation behavior of an Al-Zn-Mg-Cu alloy[J]. Applied Physics a-Materials Science & Processing, 2017, 123(1): 68.
[24] LIN Y C, LI J, CHEN M S, et al. A deep belief network to predict the hot deformation behavior of a Ni-based superalloy[J]. Neural Computing & Applications, 2018, 29(11): 1015-1023.
[25] RAI N, PITCHUMANI R. Rapid cure simulation using artificial neural networks[J]. Composites Part A: Applied Science and Manufacturing, 1997, 28A: 847-859.
[26] LUO L, ZHANG B M, ZHANG G W, et al. Rapid prediction of cured shape types of composite laminates using a FEM-ANN method[J]. Composite Structures, 2020, 238: 111980.
[27] LUO L, ZHANG B M, ZHANG G W, et al. Rapid prediction and inverse design of composite materials for desired distortion behaviours using artificial neural networks[J]. Polymer for Advanced Technologies, 2021, 32: 1049-1060.
[28] WANG Z L, ADACHI Y. Property prediction and properties-to-microstructure inverse analysis of steels by a machine-learning approach[J]. Materials Science and Engineering: A, 2019, 744: 661-670.
[29] ZHANG Z S, HONG Y, HOU B, et al. Accelerated discoveries of mechanical properties of graphene using machine learning and high-throughput computation[J]. Carbon, 2019, 148: 115-123.
[30] CHEN D D, LIN Y C, WU F. A design framework for optimizing forming processing parameters based on matrix cellular automaton and neural network-based model predictive control methods[J]. Applied Mathematical Modelling, 2019, 76: 918-937.
[31] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning internal representations by back-propagating errors[J]. Nature, 1986, 323(9): 533-536.
[32] 王晓霞. 热固性树脂基复合材料的固化变形数值模拟[D]. 济南: 山东大学, 2012.
[33] KIM Y K, WHITE S R. Viscoelastic analysis of processing-induced residual stresses in thick composite laminates[J]. Mechanics of Composite Materials and Structures, 1997, 4(4): 361-387.
[34] KIM Y K, WHITE S R. Stress relaxation behavior of 3501-6 epoxy resin during cure[J]. Polymer Engineering & Science, 1996, 36(23): 2852-2862.
[35] ZOCHER M A, GROVES S E, ALLEN D H. A three-dimensional finite element formulation for thermoviscoelastic orthotropic media[J]. International Journal for Numerical Methods in Engineering, 1997, 40(12): 2267-2288.
[36] SVANBERG J M, HOLMBERG J A. Prediction of shape distortions Part Ⅰ. FE-implementation of a path dependent constitutive model[J]. Composites Part A: Applied Science and Manufacturing, 2004, 35(6): 711-721.