Hardenability modelling and the performance of computational intelligence tools in research on structural alloy steels

• Autorzy: Sitek Wojciech , Trzaska J. , Iljkić D. , Smoljan B. , Batalha Gilmar Ferreira , Gemechu W. F.

Identyfikatory

DOI

10.5604/01.3001.0054.3226

• Języki publikacji: EN

Abstrakty

EN

The paper presents and discusses various computational tools for modelling hardenability, including multiple regression analysis, neural networks, fuzzy systems, and genetic programming. The research aims to demonstrate the application of these tools for understanding and predicting the hardenability of steel based on factors such as chemical composition and cooling properties. Design/methodology/approach The objectives of the research were achieved through the application of multiple regression analysis, neural networks, fuzzy systems, and genetic programming. The paper describes the preliminary results of genetic programming to calculate the maximum hardness based on carbon concentration. In addition, the study uses the cooling time from 800 to 500 °C (t8/5) as a relevant parameter for quenching and includes it in the mathematical models for steel hardening. The developed models, including neural networks and fuzzy logic, are used for simulation studies on the influence of alloying elements on the hardenability of steel. Findings The research results demonstrate the successful application of computational tools, including genetic programming, neural networks, and fuzzy systems, in modelling and predicting the hardenability of steel. The paper presents equations and models that enable the calculation of the Jominy curve for steel within certain chemical composition ranges. The results show promising results for predicting hardness distribution and structural transformations in quenched steel samples. Research limitations/implications While the study demonstrates the potential of computational tools for modelling hardenability, it also acknowledges limitations. The models presented are limited to specific mass concentrations of alloying elements, and further research is required to extend their applicability to a wider range of compositions. The limitations highlight opportunities for future research to refine and improve the proposed models. Practical implications The research findings bear practical significance in materials science as they provide tools for predicting hardness, structural transformations, and generating stresses and strains in steel alloys. The models developed particularly the easy-to-implement multiple regression model, can be widely used in industry. Practical applications include simulations of the effects of alloying elements on hardenability, which help optimise steel manufacturing processes. Originality/value The original value of the work lies in the comprehensive research and application of various computational tools for modelling the hardenability of steel alloys. Genetic programming, neural networks, and fuzzy systems provide novel approaches to understanding and predicting steel properties. The practical value extends to the industries involved in steel production and provides valuable tools for optimising processes and predicting material behaviour.

Słowa kluczowe

EN

hardenability modelling; steel alloys; genetic programming; neural networks; fuzzy systems

PL

modelowanie; hartowność; stopy metali; programowanie genetyczne; sieci neuronowe; systemy rozmyte

• Wydawca: International OCSCO World Press
• Czasopismo: Journal of Achievements in Materials and Manufacturing Engineering
• Rocznik: 2023
• Tom: Vol. 121, nr 2
• Strony: 275--288
• Opis fizyczny: Bibliogr. 25 poz., rys., tab., wykr.

Twórcy

autor

Sitek Wojciech

• Scientific and Didactic Laboratory of Nanotechnology and Materials Technologies, Silesian University of Technology, ul. Konarskiego 18a, 44-100 Gliwice, Poland

• https://orcid.org/0000-0002-6564-7177

autor

Trzaska J.

• Department of Engineering Materials and Biomaterials, Silesian University of Technology, ul. Konarskiego 18a, 44-100 Gliwice, Poland

autor

Iljkić D.

• Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 Rijeka, Croatia

autor

Smoljan B.

• University Center Koprivnica, University North, Trg dr. Žarka Dolinara 1, 48000 Koprivnica, Croatia

autor

Batalha Gilmar Ferreira

• University Center Koprivnica, University North, Trg dr. Žarka Dolinara 1, 48000 Koprivnica, Croatia

• https://orcid.org/0000-0001-8625-8499

autor

Gemechu W. F.

• Scientific and Didactic Laboratory of Nanotechnology and Materials Technologies, Silesian University of Technology, ul. Konarskiego 18a, 44-100 Gliwice, Poland

Bibliografia

• [1] N. Kobasko, Optimal hardenability steel for any size and form of machine components to increase their service life and decrease alloy elements in material, International Journal of Current Research 10/02 (2018) 65867-65878.
• [2] W. Sitek, J. Trzaska, W.F. Gemechu, Modelling and Analysis of the Synergistic Alloying Elements Effect on Hardenability of Steel, Archives of Foundry Engineering 4 (2022) 102-108. DOI: https://doi.org/10.24425/afe.2022.143957
• [3] B. Smoljan, Numerical simulation of steel quenching, Journal of Materials Engineering and Performance 11 (2002) 75-79. DOI: https://doi.org/10.1007/s11665-002-0011-5
• [4] A. Rose, F. Wever, Atlas on the heat treatment of steels I, 2; Max Planck Institute for Iron Research, Verlag Stahleisen m.b.H, Düsseldorf, 1954 (in German).
• [5] R.A. Grange, C.R. Hribal, L.F. Porter, Hardness of tempered martensite in carbon and low-alloy steels, Metallurgical Transactions A 8 (1977) 1775-1785. DOI: https://doi.org/10.1007/bf02646882
• [6] E.C. Bain, H.W. Paxton, Alloying Elements in Steel, 2 nd Edition, ASM, Metals Park, Ohio, 1961.
• [7] W.E. Jominy, A.L. Boegehold, A hardenability test for carburizing steel. Transactions of the Metallurgical Society of AIME 26 (1938) 574-599.
• [8] M.A. Grossmann, Hardenability calculated from chemical composition, The American Institute of Mining, Metallurgical, and Petroleum Engineers 150 (1942) 227-255.
• [9] J. Trzaska, W. Sitek, A hybrid method for calculating the chemical composition of steel with the required hardness after cooling from the austenitizing temperature, Materials 17/1 (2024) 97. DOI: https://doi.org/10.3390/ma17010097
• [10] L.A. Dobrzański, W. Sitek, Comparison of hardenability calculation methods of the heat-treatable constructional steels, Journal of Materials Processing Technology 64/1-3 (1997) 117-126. DOI: https://doi.org/10.1016/s0924-0136(96)02559-9
• [11] L.A. Dobrzański, W. Sitek, Designing of the chemical composition of constructional alloy steels, Journal of Materials Processing Technology 89-90 (1999) 467-472. DOI: https://doi.org/10.1016/s0924-0136(99)00140-5
• [12] L.A. Dobrzański, W. Sitek, The modelling of hardenability using neural networks, Journal of Materials Processing Technology 92-93 (1999) 8-14. DOI: https://doi.org/10.1016/s0924-0136(99)00174-0
• [13] W. Sitek, J. Trzaska, L.A. Dobrzański, Modified Tartagli method for calculation of Jominy hardenability curve, Proceedings of the 5th International Conference Physical and Numerical Simulation of Material Processing “ICPNS 07”, Zhengzhou, China, 2007, 892-897.
• [14] W. Sitek, J. Trzaska, Practical Aspects of the Design and Use of the Artificial Neural Networks in Materials Engineering, Metals 11/11 (2021) 1832. DOI: https://doi.org/10.3390/met11111832
• [15] S. Smokvina Hanza, T. Marohnić, D. Iljkić, R. Basan, Artificial neural networks-based prediction of hardness of low-alloy steels using specific Jominy distance, Metals 11/5 (2021) 714. DOI: https://doi.org/10.3390/met11050714
• [16] S. Smokvina Hanza, B. Smoljan, L. Štic, K. Hajdek, Prediction of microstructure constituents’ hardness after the isothermal decomposition of austenite, Metals 11/2 (2021) 180. DOI: https://doi.org/10.3390/met11020180
• [17] E. Just, New Formulas for Calcultaing Hardenability, Metal Progress 96 (1969) 87-88.
• [18] A. Moser, A. Legat, Calculating hardenability from chemical composition, HTM Hardening Shop Technical Information 24 (1969) 100-104 (in German).
• [19] R.J. Mostert, G.T. van Rooyen, Interaction of carbon and the major alloying elements on austenite decomposition, and a proposed hardenability-calculation system that allows for this effect, Metallurgical Transactions A 15 (1984).
• [20] ASTM A225, Standard Method for End-Quench Test for Hardenability of Steel, ASTM, 2010.
• [21] W. Sitek, A. Irla, The use of fuzzy systems for forecasting the hardenability of steel, Archives of Metallurgy and Materials 61/2 (2016) 797-802. DOI: https://doi.org/10.1515/amm-2016-0134
• [22] J. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection; The MIT Press, Cambridge, MA, 1992.
• [23] D.E. Goldberg, Genetic algorithms in search, optimization, and machine learning, Addison-Wesley Longman, Massachusetts, 1989.
• [24] B. Smoljan, Numerical simulation of as-quenched hardness in a steel specimen of complex form, Communications in Numerical Methods in Engineering 14/3 (1998) 277-285. DOI: https://doi.org/10.1002/(sici)1099-0887(199803)14:3<277::aid-cnm148>3.0.co;2-q
• [25] B. Smoljan, D. Iljkic, S.S. Hanza, M. Jokic, L. Stic, A. Boric, Mathematical Modeling and Computer Simulation of Steel Quenching, Materials Performance and Characterization 8/2 (2019) 17-36. DOI: https://doi.org/10.1520/mpc20180040