A repeatability study of artificial neural network predictions in flow stress model development for a magnesium alloy

A repeatability study of artificial neural network predictions in flow stress model development for a magnesium alloy

Hubert Siewiór, Łukasz Madej

AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059, Krakow, Poland.

DOI:

https://doi.org/10.7494/cmms.2021.4.0769

Abstract:

This work is devoted to an evaluation of the capabilities of artificial neural networks (ANN) in terms of developing a flow stress model for magnesium ZE20. The learning procedure is based on experimental flow-stress data following inverse analysis. Two types of artificial neural networks are investigated: a simple feedforward version and a recursive one. Issues related to the quality of input data and the size of the training dataset are presented and discussed. The work confirms the general ability of feedforward neural networks in flow stress data predictions. It also highlights that slightly better quality predictions are obtained using recursive neural networks.

Cite as:

Siewiór, H., & Madej, Ł. (2021). A repeatability study of artificial neural network predictions in flow stress model development for a magnesium alloy. Computer Methods in Materials Science, 21(4), 209-218. https://doi.org/10.7494/cmms.2021.4.0769

Article (PDF):

Keywords:

Flow stress, Artificial neural networks, Feedforward, Recursive

References:

Baraniuk, R., Donoho, D., & Gavish, M. (2020). The science of deep learning. Proceedings of the National Academy of Sciences, 117(48), 30029–30032.

Curtarolo, S., Hart, G.L.W., Nardelli, M.B., Mingo, N., Sanvito, S., & Levy, O. (2013). The high-throughput highway to computational materials design. Nature Materials, 12, 191–201.

Deb, S. Muraleedharan, A., Immanuel, R.J., Panigrahi, S.K., Racineux, G., & Marya, S. (2022). 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, Theoretical and Applied Fracture Mechanics, 119, 103338.

El Naqa, I., & Murphy, M.J. (2015). What is machine learning? In I. El Naqa, L. Ruijiang, M.J. Murphy (Eds.), Machine Learning in Radiation Oncology (pp. 3–11), Springer, Cham.

Gondia, A., Siam, A., El-Dakhakhni, W., & Nassar, A.H. (2020). Machine learning algorithms for construction projects delay risk prediction, Journal of Construction Engineering and Management, 146(1).

Khnissi, K., Jabeur, C.B., & Seddik, H. (2020). A smart mobile robot commands predictor using recursive neural network. Robotics and Autonomous Systems, 131, 103593.

Kiang, M.Y. (2003). Neural networks. In H. Bidgoli (Ed.), Encyclopedia of Information Systems (pp. 303–315), Academic Press.

Kozuch, D.J., Stillinger, F.H., & Debenedetti, P.G. (2018). Combined molecular dynamics and neural network method for predicting protein antifreeze activity. Proceedings of the National Academy of Sciences, 115(52), 13252–13257.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.

Lee, S.-K., Lee, H., Back, J., An, K., Yoon, Y., Yum, K., Kim, S., & Hwang, S.-U. (2021). Prediction of tire pattern noise in early design stage based on convolutional neural network. Applied Acoustics, 172, 107617.

Lopez-Garcia, T.B., Coronado-Mendoza, A., & Domínguez-Navarro, J.A. (2020). Artificial neural networks in microgrids: A review. Engineering Applications of Artificial Intelligence, 95, 103894.

Mozaffar, M., Bostanabad, R., Chen, W., Ehmann, K., Cao, J., & Bessa, M.A. (2019). Deep learning predicts path-dependent plasticity. Proceedings of the National Academy of Sciences, 116(52), 26414–26420.

Pietrzyk, M., Madej, L., Rauch, L., & Szeliga, D. (2015). Computational Materials Engineering: Achieving High Accuracy and Efficiency in Metals Processing Simulations. Butterworth-Heinemann.

Pietrzyk, M., Kusiak, J., Szeliga, D., Rauch, L., Sztangret, L., & Górecki, G. (2016). Application of metamodels to identification of metallic materials models. Advances in Materials Science and Engineering, 2357534.

Plumeri, J.E., Madej, L., & Misiolek, W.Z. (2019). Constitutive modeling and inverse analysis of the flow stress evolution during high-temperature compression of a new ZE20 magnesium alloy for extrusion applications. Materials Science & Engineering: A, 740–741, 174–181.

Roucoules, C., Pietrzyk, M., & Hodgson, P.D. (2003). Analysis of work hardening and recrystalization during hot working of steel using a statistically based internal variable model. Materials Science and Engineering: A, 339(1–2), 1–9.

Shi, Z., Tsymbalov, E., Dao, M., Suresh, S., Shapeev, A., & Li, J. (2019). Deep elastic strain engineering of bandgap through machine learning. Proceedings of the National Academy of Sciences, 116(10), 4117–4122.

Stendal, J.A., Emdadi, A., Sizova, I., & Bambach, M. (2018). Using neural networks to predict the flow curves and processing maps of TNM-B1. Computer Methods in Materials Science, 18(4), 134–142.

Stendal, J.A., Bambach, M., Eisentraut, M., Sizova, I., & Weiß, S. (2019). Applying machine learning to the phenomenological flow stress modeling of TNM-B1. Metals, 9(2), 220.

Xiang, W., Yu, J., Yi, Z., Wang, C., Gao, Q., & Liao, Y. (2021). Coexistence of continuous attractors with different dimensions for neural networks. Neurocomputing, 429, 25–32.