Influence of modelling phase transformations with the use of LSTM network on the accuracy of computations of residual stresses for the hardening process

• Autorzy: Wróbel Joanna , Kulawik Adam

Identyfikatory

DOI

10.24425/bpasts.2023.145681

• Języki publikacji: EN

Abstrakty

EN

Replacing mathematical models with artificial intelligence tools can play an important role in numerical models. This paper analyses the modeling of the hardening process in terms of temperature, phase transformations in the solid state and stresses in the elastic-plastic range. Currently, the use of artificial intelligence tools is increasing, both to make greater generalizations and to reduce possible errors in the numerical simulation process. It is possible to replace the mathematical model of phase transformations in the solid state with an artificial neural network (ANN). Such a substitution requires an ANN network that converts time series (temperature curves) into shares of phase transformations with a small training error. With an insufficient training level of the network, significant differences in stress values will occur due to the existing couplings. Long-Short-Term Memory (LSTM) networks were chosen for the analysis. The paper compares the differences in stress levels with two coupled models using a macroscopic model based on CCT diagram analysis and using the Johnson-Mehl-Avrami-Kolmogorov (JMAK) and Koistinen-Marburger (KM) equations, against the model memorized by the LSTM network. In addition, two levels of network training accuracy were also compared. Considering the results obtained from the model based on LSTM networks, it can be concluded that it is possible to effectively replace the classical model in modeling the phenomena of the heat treatment process.

Słowa kluczowe

EN

hardening process; temperature; phase transformations in the solid state; effective stresses; numerical modelling; RNN; recurrent neural network

PL

proces hartowania; temperatura; przemiany fazowe w stanie stałym; modelowanie numeryczne; RNN; rekurencyjna sieć neuronowa; naprężenie efektywne

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2023
• Tom: Vol. 71, nr 4
• Strony: art. no. e145681
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Wróbel Joanna

• Department of Computer Science, Czestochowa University of Technology, Dabrowskiego 73, 42-201 Czestochowa, Poland

• https://orcid.org/0000-0002-4622-4013

autor

Kulawik Adam

• Department of Computer Science, Czestochowa University of Technology, Dabrowskiego 73, 42-201 Czestochowa, Poland

• https://orcid.org/0000-0002-6417-5606

Bibliografia

• [1] W. Chen, L. Xu, Y. Han, L. Zhao, and H. Jing, “Control of residual stress in metal addit. manuf. by low-temperature solid-state phase transformation: An experimental and numerical study,” Addit. Manuf., vol. 42, p. 102016, 2021, doi: 10.1016/j.addma.2021.102016.
• [2] B. Feujofack Kemda, N. Barka, M. Jahazi, and D. Osmani, “Modeling of phase transformation kinetics in resistance spot welding and investigation of effect of post weld heat treatment on weld microstructure,” Met. Mater. Int., vol. 27, pp. 1205–1223, 2021, doi: 10.1007/s12540-019-00486-x.
• [3] L. Borkowski, C. Sorini, and A. Chattopadhyay, “Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints,” Comput. Struct., vol. 258, p. 106678, 2022, doi: 10.1016/j.compstruc.2021.106678.
• [4] M. Lindroos, T. Pinomaa, A. Antikainen, J. Lagerbom, J. Reijonen, T. Lindroos, T. Andersson, and A. Laukkanen, “Micromechanical modeling approach to single track deformation, phase transformation and residual stress evolution during selective laser melting using crystal plasticity,” Addit. Manuf., vol. 38, p. 101819, 2021, doi: 10.1016/j.addma.2020.101819.
• [5] P. Taraphdar, R. Kumar, C. Pandey, and M. Mahapatra, “Significance of finite element models and solid-state phase transformation on the evaluation of weld induced residual stresses,” Met. Mater. Int., vol. 27, pp. 3478–3492, 2021, doi: 10.1007/s12540-020-00921-4.
• [6] K. Zhang, W. Dong, and S. Lu, “Transformation plasticity of af1410 steel and its influences on the welding residual stress and distortion: Experimental and numerical study,” Mater. Sci. Eng. A, vol. 821, p. 141628, 2021, doi: 10.1016/j.msea.2021.141628.
• [7] M. Avrami, “Kinetics of phase change. I general theory,” J. Chem. Phys., vol. 7, no. 12, pp. 1103–1112, 1939, doi: 10.1063/1.1750380.
• [8] W. Sun, F. Shan, N. Zong, H. Dong, and T. Jing, “A simulation and experiment study on phase transformations of ti-6al-4v in wire laser addit. manuf.” Mater. Des., vol. 207, p. 109843, 2021, doi: 10.1016/j.matdes.2021.109843.
• [9] S. Chen, K. Bandyopadhyay, S. Basak, B. Hwang, J. Shim, J. Lee, and M. Lee, “Predictive integrated numerical approach for modeling spatio-temporal microstructure evolutions and grain size dependent phase transformations in steels,” Int. J. Plast., vol. 139, p. 102952, 2021, doi: 10.1016/j.ijplas.2021.102952.
• [10] D. Koistinen and R. Marburger, “A general equation prescribing the extent of the autenite-martensite transformation in pure iron-carbon alloys and plain carbon steels,” Acta Metallurgica, vol. 7, no. 1, pp. 59–60, 1959, doi: 10.1016/0001-6160(59)90170-1.
• [11] Y. Li and S. Li, “Deep learning based phase transformation model for the prediction of microstructure and mechanical properties of hot-stamped parts,” Int. J. Mech. Sci., vol. 220, p. 107134, 2022, doi: 10.1016/j.ijmecsci.2022.107134.
• [12] J. Guo, X. Deng, H. Wang, L. Zhou, Y. Xu, and D. Ju, “Modeling and simulation of vacuum low pressure carburizing process in gear steel,” Coatings, vol. 11, p. 1003, 2021, doi: 10.3390/coatings11081003.
• [13] M. Yaakoubi, M. Kchaou, and F. Dammak, “Simulation of the thermomechanical and metallurgical behavior of steels by using abaqus software,” Comput. Mater. Sci., vol. 68, pp. 297–306, 2013, doi: 10.1016/j.commatsci.2012.10.001.
• [14] J. Wróbel and A. Kulawik, “Algorithm for determining time series of phase transformations in the solid state using long-short-term memory neural network,” Materials, vol. 15, p. 3792, 2022, doi: 10.3390/ma15113792.
• [15] C. Gür and A. Tekkaya, “Numerical investigation of non-homogeneous plastic deformation in quenching process,” Mater. Sci. Eng. A, vol. 319–321, pp. 164–169, 2001, doi: 10.1016/S0921-5093(01)01064-4.
• [16] A. Kulawik, “Modeling of thermomechanical phenomena of welding process of steel pipe,” Arch. Metall. Mater., vol. 57, no. 4, pp. 1229–1238, 2012, doi: 10.2478/V10172-012-0137-X.
• [17] A. Bokota and S. Iskierka, “Effect of phase transformation on stress states in surface layer of laser hardened carbon steel,” ISIJ Int., vol. 36, no. 11, pp. 1383–1391.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).