[en] The manufacturing processes and design of metal and alloy products can be performed over a wide range of strain rates and temperatures. To design and optimize these processes using computational mechanics tools, the selection and calibration of the constitutive models is critical. In the case of hazardous and explosive impact loads, it is not always possible to test material properties. For this purpose, this paper assesses the efficiency and the accuracy of different architectures of ANNs for the identification of the Johnson-Cook material model parameters. The implemented computational tool of an ANN-based parameter identification strategy provides adequate results in a range of strain rates required for general manufacturing and product design applications. Four ANN architectures are studied to find the most suitable configuration for a reduced amount of experimental data, particularly for cases where high-impact testing is constrained. The different ANN structures are evaluated based on the model's predictive capability, revealing that the perceptron-based network of 66 inputs and one hidden layer of 30 neurons provides the highest prediction accuracy of the effective flow stress-strain behavior of Ti64 alloy and three virtual materials.
Disciplines :
Mechanical engineering
Author, co-author :
Tuninetti, Victor ; Université de Liège - ULiège > Département ArGEnCo ; Department of Mechanical Engineering, Universidad de La Frontera, Temuco 4811230, Chile
Forcael, Diego; Department of Mechanical Engineering, Universidad de La Frontera, Temuco 4811230, Chile
Valenzuela, Marian; Doctoral Program in Sciences of Natural Resources, Universidad de La Frontera, Temuco 4811230, Chile
Martínez, Alex; Department of Mechanical Engineering, Universidad de La Frontera, Temuco 4811230, Chile
Ávila, Andrés; Centro de Excelencia de Modelación y Computación Científica, Universidad de La Frontera, Temuco 4811322, Chile
Medina, Carlos ; Department of Mechanical Engineering, Faculty of Engineering, University of Concepción, Concepción 4070138, Chile
Pincheira, Gonzalo ; Department of Industrial Technologies, Faculty of Engineering, Universidad of Talca, Curicó 3340000, Chile
Salas, Alexis ; Department of Mechanical Engineering, Faculty of Engineering, University of Concepción, Concepción 4070138, Chile
Oñate, Angelo ; Department of Mechanical Engineering, Faculty of Engineering, Universidad del Bío-Bío, Concepción 4081112, Chile ; Department of Materials Engineering (DIMAT), Faculty of Engineering, Universidad de Concepcion, Concepción 4070138, Chile
Duchene, Laurent ; Université de Liège - ULiège > Département ArGEnCo > Analyse multi-échelles dans le domaine des matériaux et structures du génie civil
Language :
English
Title :
Assessing Feed-Forward Backpropagation Artificial Neural Networks for Strain-Rate-Sensitive Mechanical Modeling.
Serope K. Schmid S.R. Manufacturing Engineering and Technology 4th ed. Pearson Education, Inc. Upper Saddle River, NJ, USA 2006
Özel T. Karpat Y. Identification of constitutive material model parameters for high-strain rate metal cutting conditions using evolutionary computational algorithms Mater. Manuf. Process. 2007 22 659 667 10.1080/10426910701323631
Zhang H. Ding X. Guo H. Xu S. Li H. Nishiwaki S. Chen Y. Takezawa A. Multiscale topology optimization of biodegradable metal matrix composite structures for additive manufacturing Appl. Math. Model. 2023 114 799 822 10.1016/j.apm.2022.10.019
Jardin R.T. Tuninetti V. Tchuindjang J.T. Duchêne L. Hashemi N. Tran H.S. Carrus R. Mertens A. Habraken A.M. Optimizing laser power of directed energy deposition process for homogeneous AISI M4 steel microstructure Opt. Laser Technol. 2022 163 109426 10.1016/j.optlastec.2023.109426
Sepúlveda H. Valle R. Pincheira G. Prasad C.S. Salas A. Medina C. Tuninetti V. Dynamic numerical prediction of plasticity and damage in a turbofan blade containment test Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl. 2023 237 2251 2560 10.1177/14644207221136126
Cao Z. Fei Q. Jiang D. Kapania R.K. Wu S. Jin H. A sensitivity-based nonlinear finite element model updating method for nonlinear engineering structures Appl. Math. Model. 2021 100 632 655 10.1016/j.apm.2021.07.034
Bustos F. Hinojosa J. Tuninetti V. Computational Comparison of Performance of Different Steel Plate Shear Yielding Dampers Buildings 2023 13 793 10.3390/buildings13030793
Fylstra D. Lasdon L. Watson J. Waren A. Design and use of the Microsoft Excel Solver Interfaces 1998 28 29 55 10.1287/inte.28.5.29
Lasdon L. Fox R. Ratner M. Nonlinear optimization using the generalized Inform. Rech. Opérationn 1974 3 73 103
Bergs T. Hardt M. Schraknepper D. Determination of Johnson-Cook material model parameters for AISI 1045 from orthogonal cutting tests using the Downhill-Simplex algorithm Procedia Manuf. 2020 48 541 552 10.1016/j.promfg.2020.05.081
Tuninetti V. Alternative experimental method for characterizing the deformation behavior of Ti6Al4V at constant strain rates over the full elastoplastic range Int. J. Mater. Form. 2019 preprint
Rojas-Ulloa C. Bouffioux C. Jaramillo A.F. García-Herrera C.M. Hussain T. Duchêne L. Riu G. Josep Roa J. Flores P. Marie Habraken A. et al. Nanomechanical Characterization of the Deformation Response of Orthotropic Ti–6Al–4V Adv. Eng. Mater. 2021 23 2001341 10.1002/adem.202001341
Tuninetti V. Gilles G. Flores P. Pincheira G. Duchêne L. Habraken A.-M. Impact of distortional hardening and the strength differential effect on the prediction of large deformation behavior of the Ti6Al4V alloy Meccanica 2019 54 1823 1840 10.1007/s11012-019-01051-x
Rojas-Ulloa C. Valenzuela M. Tuninetti V. Habraken A.M. Identification and validation of an extended Stewart-Cazacu micromechanics damage model applied to Ti–6Al–4V specimens exhibiting positive stress triaxialities Proc. Inst. Mech. Eng. Part L J. Mater. Des. Appl. 2021 235 1248 1261 10.1177/14644207211009933
Lee H. Huen W.Y. Vimonsatit V. Mendis P. An Investigation of Nanomechanical Properties of Materials using Nanoindentation and Artificial Neural Network Sci. Rep. 2019 9 13189 10.1038/s41598-019-49780-z 31515524
Uz M.M. Hazar Yoruç A.B. Cokgunlu O. Aydoğan C.S. Yapici G.G. A comparative study on phenomenological and artificial neural network models for high temperature flow behavior prediction in Ti6Al4V alloy Mater. Today Commun. 2022 33 104933 10.1016/j.mtcomm.2022.104933
Kalina K.A. Linden L. Brummund J. Metsch P. Kästner M. Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks Comput. Mech. 2022 69 213 232 10.1007/s00466-021-02090-6
Zhang A. Mohr D. Using neural networks to represent von Mises plasticity with isotropic hardening Int. J. Plast. 2020 132 102732 10.1016/j.ijplas.2020.102732
Marouani H. Aguir H. Identification of material parameters of the Gurson-Tvergaard-Needleman damage law by combined experimental, numerical sheet metal blanking techniques and artificial neural networks approach Int. J. Mater. Form. 2012 5 147 155 10.1007/s12289-011-1035-x
Sun Y. Zeng W.D. Zhao Y.Q. Han Y.F. Ma X. Intelligent method to develop constitutive relationship of Ti-6Al-2Zr-1Mo-1V alloy Trans. Nonferrous Met. Soc. China Engl. Ed. 2012 22 1457 1461 10.1016/S1003-6326(11)61341-1
Xie G. Jia H. Li H. Zhong Y. Du W. A life prediction method of mechanical structures based on the phase field method and neural network Appl. Math. Model. 2023 119 782 802 10.1016/j.apm.2023.03.022
Gorji M.B. Mozaffar M. Heidenreich J.N. Cao J. Mohr D. On the potential of recurrent neural networks for modeling path dependent plasticity J. Mech. Phys. Solids 2020 143 103972 10.1016/j.jmps.2020.103972
Li L.F. Chen C.Q. Equilibrium-based convolution neural networks for constitutive modeling of hyperelastic materials J. Mech. Phys. Solids 2022 164 104931 10.1016/j.jmps.2022.104931
Lecarme L. Viscoplasticity, Damage, and Fracture of Ti-6Al-4V Ph.D. Thesis Université Catholique de Louvain Ottignies-Louvain-la-Neuve, Belgium 2013
Tuninetti V. Experimental and Numerical Study of the Quasi-Static Behavior of Ti–6Al–4v Ph.D. Thesis Univertisé de Liège Liège, Belgium 2014
Peirs J. Experimental Charcterisation and Modelling of the Dynamic Behaviour of the Titanium Alloy Ti6Al4V Ph.D. Thesis Ghent University Gent, Belgium 2012
Tuninetti V. Flores P. Valenzuela M. Pincheira G. Medina C. Duchêne L. Habraken A.M. Experimental characterization of the compressive mechanical behaviour of Ti6Al4V alloy at constant strain rates over the full elastoplastic range Int. J. Mater. Form. 2020 13 709 724 10.1007/s12289-020-01543-2
Tuninetti V. Gilles G. Sepúlveda H. Pincheira G. Flores P. Duchêne L. Habraken A.M. Direct and Inverse Characterization of the Asymmetric Hardening Behavior of Bulk Ti64 Alloy Phys. Sci. Forum 2022 4 2 10.3390/psf2022004002
Kara F. Aslantaş K. Çiçek A. Prediction of cutting temperature in orthogonal machining of AISI 316L using artificial neural network Appl. Soft Comput. J. 2016 38 64 74 10.1016/j.asoc.2015.09.034
Cheng P. Wang D. Zhou J. Zuo S. Zhang P. Comparison of the Warm Deformation Constitutive Model of GH4169 Alloy Based on Neural Network and the Arrhenius Model Metals 2022 12 1429 10.3390/met12091429
Titu N.A. Baucum M. No T. Trotsky M. Karandikar J. Schmitz T.L. Khojandi A. Estimating Johnson-Cook material parameters using neural networks Procedia Manuf. 2021 53 680 689 10.1016/j.promfg.2021.06.082
Deb S. Muraleedharan A. Immanuel R.J. Panigrahi S.K. Racineux G. Marya S. Establishing flow stress behaviour of Ti-6Al-4V alloy and development of constitutive models using Johnson-Cook method and Artificial Neural Network for quasi-static and dynamic loading Theor. Appl. Fract. Mech. 2022 119 103338 10.1016/j.tafmec.2022.103338
Yousfi W. Darnis P. Cahuc O. Laheurte R. Calamaz M. 3D modeling of strain fields and strain rate in the cutting area: Application to milling Int. J. Adv. Manuf. Technol. 2016 84 2207 2218 10.1007/s00170-015-7848-x
Golasiński K. Pieczyska E. Maj M. Staszczak M. Świec P. Furuta T. Kuramoto S. Investigation of strain rate sensitivity of Gum Metal under tension using digital image correlation Arch. Civ. Mech. Eng. 2020 20 53 10.1007/s43452-020-00055-9
Afrasiabi M. Klippel H. Roethlin M. Wegener K. An improved thermal model for SPH metal cutting simulations on GPU Appl. Math. Model. 2021 100 728 750 10.1016/j.apm.2021.08.010
Ning J. Liang S.Y. Inverse identification of Johnson-Cook material constants based on modified chip formation model and iterative gradient search using temperature and force measurements Int. J. Adv. Manuf. Technol. 2019 102 2865 2876 10.1007/s00170-019-03286-0
He Z. Guo X. Xuan H. Shan X. Fan X. Chen C. Hong W. Characteristics and mechanisms of turboshaft engine axial compressor casing containment Chin. J. Aeronaut. 2021 34 171 180 10.1016/j.cja.2020.08.050
Rai R. Kumar G. Dagar S. Somashekar V. Ahmed C. Numerical simulation of ballistic impact on aluminium 5083-H116 plate with Johnson cook plasticity model Mater. Today Proc. 2021 46 10619 10627 10.1016/j.matpr.2021.01.373
Chen J.-Y. Feng D.-L. Lien F.-S. Yee E. Deng S.-X. Gao F. Peng C. Numerical modelling of interaction between aluminium structure and explosion in soil Appl. Math. Model. 2021 99 760 784 10.1016/j.apm.2021.07.010
Tuninetti V. Habraken A.M. Impact of anisotropy and viscosity to model the mechanical behavior of Ti-6Al-4V alloy Mater. Sci. Eng. A 2014 605 39 50 10.1016/j.msea.2014.03.009
Rosenblatt F. The perceptron: A probabilistic model for information storage and organization in the brain Psychol. Rev. 1958 65 386 408 10.1037/h0042519 13602029
Harris C.R. Millman K.J. van der Walt S.J. Gommers R. Virtanen P. Cournapeau D. Wieser E. Taylor J. Berg S. Smith N.J. et al. Array programming with NumPy Nature 2020 585 357 362 10.1038/s41586-020-2649-2 32939066
Hunt J. Working with Excel Files Advanced Guide to Python 3 Programming Springer International Publishing Cham, Switzerland 2019 249 255 978-3-030-25943-3
Sim K.H. Ri Y.C. Jo C.H. Kim O.J. Kim R.S. Pak H. Modified Zerilli-Armstrong and Khan-Huang-Liang constitutive models to predict hot deformation behavior in a powder metallurgy Ti-22Al-25Nb alloy Vacuum 2023 210 111749 10.1016/j.vacuum.2022.111749
Stoffel M. Bamer F. Markert B. Neural network based constitutive modeling of nonlinear viscoplastic structural response Mech. Res. Commun. 2019 95 85 88 10.1016/j.mechrescom.2019.01.004
Linka K. Hillgärtner M. Abdolazizi K.P. Aydin R.C. Itskov M. Cyron C.J. Constitutive artificial neural networks: A fast and general approach to predictive data-driven constitutive modeling by deep learning J. Comput. Phys. 2021 429 110010 10.1016/j.jcp.2020.110010
