Using neural networks to predict the low curves and processing maps of TNM-B1
Johan Andreas Stendal
, Aliakbar Emdadi
, Irina Sizova, Markus Bambach
Panta Rhei Gebäude, Konrad-Wachsmann-Allee 17, 03046 Cottbus, Germany.
DOI:
https://doi.org/10.7494/cmms.2018.4.0624
Abstract:
“The ability to predict the behavior of a material is vital in both science and engineering. Traditionally, this task has been carried out using physics-based mathematical modeling. However, material behavior is dependent on a wide range of interconnected phenomena, properties and conditions. During deformation processes, work hardening, softening, mi-crostructure evolution and generation of heat all occur simultaneously, and can either cooperate or compete. In addition, they can vary with the deformation temperature, applied force and process speed. As the complete picture of material be-havior from the macroscopic scale to the atomic scale is not yet fully understood, deformation processes such as hot forg-ing can be difficult to handle using physics-based modeling. Usually, modeling the high temperature deformation behav-ior of metals consists of extracting characteristic points from the experimental flow curve data, and use them to fit the model equations through regression analysis. This is called phenomenological modeling, as it is based on the observations of a phenomena rather than being derived from fundamental theory. Alternatively, the data obtained from experiments could be used for a data-driven or machine learning (ML) approach to model the material behavior. An ML model would require no knowledge of the underlying physical phenomena governing a deformation process, as it can learn a mapping function which connects input to output based purely on the experimental data. In this work, the application of machine learning to modeling the flow curves of two different states of the titanium aluminide (TiAl) TNM-B1 hot isostatically pressed (HIPed) and heat treated, is investigated. Neural networks were used to learn a mapping function which predicted flow stress based on the inputs temperature, strain and strain rate. In addition, strain rate sensitivity maps and processing maps based on the experimental and the predicted data are analysed and compared. The results revealed that the neural networks were able to produce realistic and accurate flow curves, which fitted to the underlying behavior of the experi-mental data rather than the noise. The strain rate sensitivity and processing maps showed conflicting results. Good corre-lation was found for the HIPed material state between the ones based on experimental data and the ones based on predict-ed values, while there was a significant difference for the heat treated state.”
Cite as:
Stendal, J., Emdadi, A., Sizova, I., Bambach , M. (2018). Using neural networks to predict the low curves and processing maps of TNM-B1. Computer Methods in Materials Science, 18(4), 134 – 142. https://doi.org/10.7494/cmms.2018.4.0624
Article (PDF):
Keywords:
Machine learning, Processing maps, Titanium aluminide, TNM-B1
References:
Anderson, J.A., 1995, An Introduction to Neural Networks, ABradford Book, The MIT Press.Bambach, M., Sizova, I., Bolz, S. et al., 2016, Devising StrainHardening Models Using Kocks–Mecking Plots—A Comparisonof Model Development for Titanium Aluminidesand Case Hardening Steel, Metals, 6, 204.
Cheng, L., Xue, X., Tang, B. et al., 2014, Flow characteristicsand constitutive modeling for elevated temperature deformationof a high Nb containing TiAl alloy, Intermetallics,49, 23–28.
Cingara, A., McQueen, H.J., 1992, New formula for calculatingflow curves from high temperature constitutive data for300 austenitic steels, Journal of Materials ProcessingTechnology, 36, 31–42.
Inui, H., Kishida, K., Misak, M. et al., 1995, Temperature dependenceof yield stress, tensile elongation and deformationstructures in polysynthetically twinned crystals ofTi-Al, Philosophical Magazine A, 72, 1609-1631.
Levenberg, K., 1944, A Method for the solution of certain nonlinearproblems in least squares, Quarterly of AppliedMathematics, 2, 164-168.
Lin, Y.C., Zhang, J., Zhong, J., 2008, Application of neuralnetworks to predict the elevated temperature flow behaviorof a low alloy steel, Computational Materials Science, 43,752-758.
Liu, B., Liu, Y., Qiu, C. et al., 2015, Design of low-cost titaniumaluminide intermetallics, Journal of Alloys and Compounds,650, 298-304.
Liu, Y., Zhao, T., Ju, W. et al., 2017, Materials discovery anddesign using machine learning, Computational MaterialsScience, 3, 159-177.
Marquardt, D., 1963, An algorithm for least-squares estimationof nonlinear parameters, SIAM Journal on Applied Mathematics,11, 431–441.
Masahashi, N., Mizuhara, Y., Matsuo, M. et al., 1991, Hightemperature behavior of titanium-aluminide based gammaplus beta microduplex alloy, ISIJ International, 31, 728-737.
Pilania, G., Wang, C., Jiang, X. et al., 2013, Accelerating materialsproperty predictions using machine learning, ScientificReports, 3.
Prasad, Y.V.R.K., Sasidhara, S., 1997, Hot working guide: acompendium of processing maps, ASM International, MaterialsPark.Prasad, Y.V.R.K., Seshacharyulu, T., 1998, Processing maps forhot working of titanium alloys, 243, 82-88.
Rojas, R., 1996, Neural Networks: A Systematic Introduction,Springer.Sheikh, H., Serajzadeh, S., 2008, Estimation of flow stressbehavior of AA5083 using artificial neural networks withregard to dynamic strain ageing effect, Journal of MaterialsProcessing Technology, 196, 115-119.
Schloffer, M., Iqbal, F., Gabrisch, H. et al., 2012, Microstructuredevelopment and hardness of a powder metallurgical multiphase γ-TiAl based alloy, Intermetallics, 22, 231-240.
Yu, W., Li, M.Q., Luo, J. et al., 2010, Prediction of the mechanicalproperties of the post-forged Ti–6Al–4V alloy usingfuzzy neural network, Materials & Design, 31, 3282-3288.
Zhu, Q., Abbod, M.F., Talamantes-Silva, J., Sellars, C.M. et al.,2003, Hybrid modelling of aluminium–magnesium alloysduring thermomechanical processing in terms of physically-based, neuro-fuzzy and finite element models, Acta Materialia,51, 5051-5062.