The hot rolling mills of steel plants are in the process of transformation from manual operation to artificial intelligence (AI) based automatic operations. Most of the mill input parameters required by the automation system are recorded from different sensors installed in the mill except the flow stress of rolled material. Generally a semi-empirical equation is used that correlate flow stress with strain, strain rate and temperature during rolling. The coefficients and exponents of the empirical equations are calculated from experimental data with parameter estimation techniques. This paper discusses the application of artificial neural network (ANN) for calculation of flow stress of material from experimental data. Experiments were conducted in a dynamic thermo-mechanical simulator to measure flow stress of steel at different strain, strain rate and temperature. The experimental data was used to calculate coefficients of empirical equations using multivariable optimization techniques. The data was also used to formulate an ANN model using feed forward network. The ANN model was trained with backpropagation algorithm. The ANN method is found to be more accurate than the semi-empirical equations for correlating the flow stress with strain, strain rate and temperature.
| Published in | American Journal of Neural Networks and Applications (Volume 3, Issue 3) |
| DOI | 10.11648/j.ajnna.20170303.12 |
| Page(s) | 36-39 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2017. Published by Science Publishing Group |
Flow Stress, Steel, Artificial Neural Network, Semi-Empirical Equations
| [1] | Lenard, J. G., Pietrzyk, M. and Cser, L., “Mathematical and physical simulation of the properties of hot rolled products”, ELSEVIER, 1999. |
| [2] | Shida, S. “Effect of carbon content, temperature and strain rate on compressive flow stress of carbon steel”, Hitachi Research Lab Report, pp. 1-9, 1974. |
| [3] | Hatta, N, Kakao, J, Kikuchi, S. and Takuda H, “Modelling of flow stress of plain carbon steel at elevated temperature”, Steel Research, Vo. 56, pp. 572-582, 1985. |
| [4] | Y. V. Konovalov, A. L. Ostapenko, V. E. Ponomarev, “Расчет Параметров Листовой Прокатки”, Москва Металлурия (Calculation of Sheet Rolling Parameters, Moscow Metallurgy), 1986, pp. 8-27. |
| [5] | Kuesta, J. L. & Mize, J. H., “Optimization techniques with FORTRAN”, McGraw Hill Book Company, 1973. |
| [6] | Belegundu, A. D. and Chandruptla, T. R., “Optimization concepts and application in Engineering”, Pearson Education, 2002. |
| [7] | Deb, K. “Optimization of Engineering Design: Algorithm and Examples”, Prentice-Hall of India, 1995. |
| [8] | Yagnarayana, B., “Artificial Neural Networks”, Prentice-Hall of India, 2004. |
| [9] | Kriti Priya Gupta, Madhu Jain. Performance Analysis of Cellular Radio System Using Artificial Neural Networks. American Journal of Neural Networks and Applications. Vol. 3, No. 1, 2017, pp. 5-13. doi: 10.11648/j.ajnna.20170301.12. |
| [10] | S. Rath, A. P. Singh, U. Bhaskar, B. Krishna, B. K. Santra, D. Rai and N. Neogi, “Artificial Neural Network Modeling for Prediction of Roll Force During Plate Rolling Process”, International journal of Materials and Manufacturing Processes, T&F, Volume 25, Issue 1–3, January 2010, pp. 149–153. |
| [11] | Guo-zheng Quan, Tong Wang, Yong-le Li, Zong-yang Zhan, Yu-feng Xia, “Artificial Neural Network Modeling to Evaluate the Dynamic Flow Stress of 7050 Aluminum Alloy”, J. of Materi Eng and Perform (2016) 25: 553. https://doi.org/10.1007/s11665-016-1884-z. |
APA Style
Sushant Rath, Pinaki Talukdar, Arujun Prasad Singh. (2017). Application of Artificial Neural Network for Flow Stress Modelling of Steel. American Journal of Neural Networks and Applications, 3(3), 36-39. https://doi.org/10.11648/j.ajnna.20170303.12
ACS Style
Sushant Rath; Pinaki Talukdar; Arujun Prasad Singh. Application of Artificial Neural Network for Flow Stress Modelling of Steel. Am. J. Neural Netw. Appl. 2017, 3(3), 36-39. doi: 10.11648/j.ajnna.20170303.12
AMA Style
Sushant Rath, Pinaki Talukdar, Arujun Prasad Singh. Application of Artificial Neural Network for Flow Stress Modelling of Steel. Am J Neural Netw Appl. 2017;3(3):36-39. doi: 10.11648/j.ajnna.20170303.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnna.20170303.12,
author = {Sushant Rath and Pinaki Talukdar and Arujun Prasad Singh},
title = {Application of Artificial Neural Network for Flow Stress Modelling of Steel},
journal = {American Journal of Neural Networks and Applications},
volume = {3},
number = {3},
pages = {36-39},
doi = {10.11648/j.ajnna.20170303.12},
url = {https://doi.org/10.11648/j.ajnna.20170303.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20170303.12},
abstract = {The hot rolling mills of steel plants are in the process of transformation from manual operation to artificial intelligence (AI) based automatic operations. Most of the mill input parameters required by the automation system are recorded from different sensors installed in the mill except the flow stress of rolled material. Generally a semi-empirical equation is used that correlate flow stress with strain, strain rate and temperature during rolling. The coefficients and exponents of the empirical equations are calculated from experimental data with parameter estimation techniques. This paper discusses the application of artificial neural network (ANN) for calculation of flow stress of material from experimental data. Experiments were conducted in a dynamic thermo-mechanical simulator to measure flow stress of steel at different strain, strain rate and temperature. The experimental data was used to calculate coefficients of empirical equations using multivariable optimization techniques. The data was also used to formulate an ANN model using feed forward network. The ANN model was trained with backpropagation algorithm. The ANN method is found to be more accurate than the semi-empirical equations for correlating the flow stress with strain, strain rate and temperature.},
year = {2017}
}
TY - JOUR T1 - Application of Artificial Neural Network for Flow Stress Modelling of Steel AU - Sushant Rath AU - Pinaki Talukdar AU - Arujun Prasad Singh Y1 - 2017/12/14 PY - 2017 N1 - https://doi.org/10.11648/j.ajnna.20170303.12 DO - 10.11648/j.ajnna.20170303.12 T2 - American Journal of Neural Networks and Applications JF - American Journal of Neural Networks and Applications JO - American Journal of Neural Networks and Applications SP - 36 EP - 39 PB - Science Publishing Group SN - 2469-7419 UR - https://doi.org/10.11648/j.ajnna.20170303.12 AB - The hot rolling mills of steel plants are in the process of transformation from manual operation to artificial intelligence (AI) based automatic operations. Most of the mill input parameters required by the automation system are recorded from different sensors installed in the mill except the flow stress of rolled material. Generally a semi-empirical equation is used that correlate flow stress with strain, strain rate and temperature during rolling. The coefficients and exponents of the empirical equations are calculated from experimental data with parameter estimation techniques. This paper discusses the application of artificial neural network (ANN) for calculation of flow stress of material from experimental data. Experiments were conducted in a dynamic thermo-mechanical simulator to measure flow stress of steel at different strain, strain rate and temperature. The experimental data was used to calculate coefficients of empirical equations using multivariable optimization techniques. The data was also used to formulate an ANN model using feed forward network. The ANN model was trained with backpropagation algorithm. The ANN method is found to be more accurate than the semi-empirical equations for correlating the flow stress with strain, strain rate and temperature. VL - 3 IS - 3 ER -
Information
Email: