Development of Artificial Intelligent (AI)-based Model for Steel Alloys
Abstract
Alloy steel has many forms each having different properties due to the elements added to the steel. When treated with heat, these elements impart a wide range of physical properties incomparable to any metals/alloys. In the present work, the artificial intelligent (AI) technique namely, artificial neural networks (ANN) is utilized to model the true stress (τ) of ultra-strength Cr-Mn-Si-Ni ultra-strength alloyed steel in terms of holding time, heating rate, tensile temperature (Tts) and strain rate (γ). Neural networks are trained iteratively by adjusting the connections between nodes and the weight. A well-trained network can effectively predict the target. The developed ANN-based model is compared to the commonly employed multiple regression (MR) model in terms of statistical parameters. The coefficient of determination (R2) values for the ANN and MR models are 0.9948 and 0.2924 on the other hand average absolute relative error (AARE) are observed as 3.6%, and 56.16% respectively. The results thus obtained show that the ANN-based model has higher accuracy with greater generalization.
References
M.F. Carlson, B. V. Narasimha Rao, G. Thomas, The effect of austenitizing temperature upon the microstructure and mechanical properties of experimental Fe/Cr/C steels, Metall. Trans. A. 10(1979)1273–1284. https://doi.org/10.1007/BF02811983.
W.S. Lee, T.T. Su, Mechanical properties and microstructural features of AISI 4340 high-strength alloy steel under quenched and tempered conditions, J. Mater. Process. Technol. 87(1999)198-206. https://doi.org/10.1016/S0924-0136(98)00351-3.
N. Parveen, S. Zaidi, M. Danish, Artificial intelligence (AI)-based friction factor models for large piping networks, Chem. Eng. Commun. 207 (2019)213–230. https://doi.org/10.1080/00986445.2019.1578757.
N. Parveen, S. Zaidi, M. Danish, Development and Analyses of Artificial Intelligence (AI)-Based Models for the Flow Boiling Heat Transfer Coefficient of R600a in a Mini-Channel, ChemEngineering.2(2018)27. https://doi.org/10.3390/chemengineering2020027.
N. Parveen, S. Zaidi, M. Danish, Comparative analysis for the prediction of boiling heat transfer coefficient of R134a in micro/mini channels using artificial intelligence (AI)-based techniques, Int. J. Model.Simul.40(2020)114–129. https://doi.org/10.1080/02286203.2018.156480
S. Zaidi, Support Vector Regression (SVR) Model to Predict the Boiling/Non-boiling Length of the Heated Tube in a Vertical Tube Thermosiphon Reboiler, in: B.B. Singh, G.C. Mishra, S.K. Yadav (Eds.), 3rd Int. Conf. "Innovative Approach Appl. Phys. , Math. / Stat. , Chem. Sci. Emerg. Energy Technol. Sustain. Dev., “Social Welfare Foundation” In Association with “Krishi Sanskriti,” Jawaharlal Nehru University, New Delhi, India, 2014: pp. 1–139.
J.Y. Zhang, P. Jiang, Z. lin Zhu, Q. Chen, J. Zhou, Y. Meng, Tensile properties and strain hardening mechanism of Cr-Mn-Si-Ni alloyed ultra-strength steel at different temperatures and strain rates, J. Alloys Compd. 842 (2020) 155856. https://doi.org/10.1016/j.jallcom.2020.155856.
W.S. Mcculloch, W. Pitts, A Logical Calculus of the Ideas Immanent in Nervous Activity, Bull. Math. Biophys. 5 (1943) 115–133.
Ö.F. Ertuğrul, A novel type of activation function in artificial neural networks: Trained activation function, Neural Networks. 99 (2018) 148–157. https://doi.org/10.1016/j.neunet.2018.01.007.
J. Feng, S. Lu, Performance Analysis of Various Activation Functions in Artificial Neural Networks, J. Phys. Conf. Ser. 1237 (2019) 1237. https://doi.org/10.1088/1742-6596/1237/2/022030.
V. Devabhaktuni, M. Yagoub, Y. Fang, J. Xu, Q.-J. Zhang, Neural networks for microwave modeling: Model development issues and nonlinear modeling techniques, Int. J. RF Microw. Comput. Eng. 11 (2001) 4–21.
N. Parveen, S. Zaidi, M. Danish, Development and analyses of data-driven models for predicting the bed depth profile of solids flowing in a rotary kiln, Adv. Powder Technol. 31 (2020) 678–694.
N. Parveen, S. Zaidi, M. Danish, Support Vector Regression Prediction and Analysis of the Copper (II) Biosorption Efficiency, Indian Chem. Eng. 59 (2017) 295–311. https://doi.org/10.1080/00194506.2016.1270778.
N. Parveen, S. Zaidi, M. Danish, Development of SVR-based model and comparative analysis with MLR and ANN models for predicting the sorption capacity of Cr(VI), Process Saf. Environ. Prot. 107 (2017) 428–437. https://doi.org/10.1016/j.psep.2017.03.007.
M. Massinaei, Estimation of metallurgical parameters of flotation process from froth visual features, Int. J. Min. Geo-Eng. 49 (2015) 75–81.
S. Karsoliya, Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture, Int. J. Eng. Trends Technol. 3 (2012) 714–717.
H. Merdun, Ö. Çinar, Artificial neural network and regression techniques in modelling surface water quality, Environ. Prot. Eng. 36 (2010) 95–109.
S. Aber, a. R. Amani-Ghadim, V. Mirzajani, Removal of Cr(VI) from polluted solutions by electrocoagulation: Modeling of experimental results using artificial neural network, J. Hazard. Mater. 171 (2009) 484–490. https://doi.org/10.1016/j.jhazmat.2009.06.025.
A. Verikas, M. Bacauskiene, Using artificial neural networks for process and system modelling, Chemom. Intell. Lab. Syst. 67 (2003), 187–191. https://doi.org/10.1016/S0169-7439(03)00093-5.
