Back Propagation Artificial Neural Network Approach to Predict the Flow Stress in Isothermal Tensile Test of Medium Carbon Steel Material

Abstract:

Isothermal tensile test of medium carbon steel material was conducted on a computer controlled servo-hydraulic testing machine at the deformation temperatures (923 to 1223 K) and the strain rates (0.05 to 1.0 s^-1). Using the experimental data, the artificial neural network (ANN) model with a back-propagation (BP) algorithm was proposed to predict the hot deformation behavior of medium carbon steel material. For the model training and testing purpose, deformation temperature, strain rate and strain data were considered as inputs and in addition, the flow stress data were used a targets. Before running the neural network, the test data were normalized to effectively run the problem and after solving the problem, the obtained results were again converted in order to achieve the actual data. According to the predicted results, the coefficient of determination (R²) and the average absolute relative error between the predicted flow stress and the experimental data were determined as 0.997 and 0.913%, respectively. In addition, by evaluating each test conditions, it was found that the average absolute relative error based on an ANN model varied from 0.55% to 1.36% and moreover, the results showed the better predictability compared with the measured data. Overall, the trained BP-ANN model is found to be much more efficient and accurate by means of flow stress prediction with respect to the experimental data for an entire tested conditions.

• Periodical: Materials Science Forum (Volume 977)
• Pages: 163-168
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.977.163
• Online since: February 2020
• Authors: Mohanraj Murugesan, Dong Won Jung*
• Keywords: BP Artificial Neural Network, Flow Stress, Hot Deformation Behavior, Isothermal Tensile Test, Medium Carbon Steel

References

[1] Changqing Huang, Xiaodong Jia, Zhiwu Zhang, Modified Back Propagation Artificial Neural Network Model Based on Genetic Algorithm to Predict the Flow Behavior of 5754 Aluminum Alloy, Materials, 11, 855, (2018).

DOI: 10.3390/ma11050855

[2] Johan A. Stendal, Markus Bambach, Mark Eisentraut, Irina Sizova, Sabine Weib, Applying Machine Learning to the Phenomenological Flow Stress Modeling of TNM-B1, Metals, 9, 220, (2019).

DOI: 10.3390/met9020220

[3] Zhubin He, Zhibiao Wang, Yanli Lin and Xiaobo Fan, Hot Deformation Behavior of a 2024 Aluminum Alloy Sheet and its Modeling by Fields-Backofen Model Considering Strain Rate Evolution, Metals, 9, 243, (2019).

DOI: 10.3390/met9020243

[4] Mohanraj Murugesan, Dong Won Jung, Johnson Cook Material and Failure Model Parameters Estimation of AISI-1045 Medium Carbon Steel for Metal Forming Applications, Materials, 12, 609, (2019).

DOI: 10.3390/ma12040609

[5] Mohanraj Murugesan, Dong Won Jung, Two flow stress models for describing hot deformation behavior of AISI-1045 medium carbon steel at elevated temperatures, Heliyon 5 (2019) e01347.

DOI: 10.1016/j.heliyon.2019.e01347

[6] H.R. Rezaei Ashtiani, P. Shahsavari, A comparative study on the phenomenological and artificial neural network models to predict hot deformation behavior of AlCuMgPb alloy, Journal of Alloys and Compounds 687 (2016) 263-273.

DOI: 10.1016/j.jallcom.2016.04.300

[7] Yanchun Zhu, Weidong Zeng, Yu Sun, Fei Feng, Yigang Zhou, Artificial neural network approach to predict the flow stress in the isothermal compression of as-cast TC21 titanium alloy, Computational Materials Science 50 (2011) 1785–1790.

DOI: 10.1016/j.commatsci.2011.01.015

[8] Guoliang Ji, Fuguo Li, Qinghua Li, Huiqu Li, Zhi Li, comparative study on Arrhenius-type constitutive model and artificial neural network model to predict high-temperature deformation behavior in Aermet100 steel, Materials Science and Engineering A 528 (2011) 4774–4782.

DOI: 10.1016/j.msea.2011.03.017