Abstract
Optimization of tool steel properties and corresponding heat treatment is mainly based on trial and error approach, which requires tremendous experimental work and resources. Therefore, there is a huge need for tools allowing prediction of mechanical properties of tool steels as a function of composition and heat treatment process variables. The aim of the present work was to explore the potential and possibilities of artificial neural network-based modeling to select and optimize vacuum heat treatment conditions depending on the hot work tool steel composition and required properties. In the current case training of the feedforward neural network with error backpropagation training scheme and four layers of neurons (8-20-20-2) scheme was based on the experimentally obtained tempering diagrams for ten different hot work tool steel compositions and at least two austenitizing temperatures. Results show that this type of modeling can be successfully used for detailed and multifunctional analysis of different influential parameters as well as to optimize heat treatment process of hot work tool steels depending on the composition. In terms of composition, V was found as the most beneficial alloying element increasing hardness and fracture toughness of hot work tool steel; Si, Mn, and Cr increase hardness but lead to reduced fracture toughness, while Mo has the opposite effect. Optimum concentration providing high KIc/HRC ratios would include 0.75 pct Si, 0.4 pct Mn, 5.1 pct Cr, 1.5 pct Mo, and 0.5 pct V, with the optimum heat treatment performed at lower austenitizing and intermediate tempering temperatures.
Similar content being viewed by others
References
[1] J. Galán, L. Samek, P. Verleysen, K. Verbeken and Y. Houbaert: Revista de Metalurgia, 2012, Vol 48, pp. 118-131.
[2] N. Baluch, Z.M. Udin and C.S. Abdullah: Engineering, Technology & Applied Science Research, 2014, Vol. 4, pp. 686-689.
[3] P. Groche and M. Christiany: Wear, 2013, Vol. 302, pp. 1279-1285.
[4] Jing-Yuan Li, Yu-Lai Chen and Jian-Hua Huo: Materials Science and Engineering: A, 2015, Vol. 640, pp. 16–23.
[5] D. Mellouli, N. Haddar, A. Köster and H.F. Ayedi: Engineering Failure Analysis, 2014, Vol. 45, pp. 85–95.
[6] R. Ebara: Int. J. Fatigue, 2010, Vol. 32, pp. 830-840.
[7] B. Podgornik and V. Leskovšek: Metall. Mater. Trans. A, 2013, Vol. 44, pp. 5694-5702.
[8] Xu Liujie, Xing Jiandong, Wei Shizhong, Zhang Yongzhen and Long Rui: Materials and Design, 2007, Vol. 28, pp. 1425–1432.
[9] M. Col, H.M. Ertunc and M. Yilmaz: Materials and Design, 2007, Vol. 28, pp. 488–495.
[10] V. Leskovšek, B. Šuštaršič and G. Jutriša: J. Mater. Process. Technol., 2006, Vol. 178, pp. 328-334.
[11] P. Michaud, D. Delagnes, P. Lamesle, M.H. Mathon and C. Levaillant: Acta Mater., 2007, Vol. 55, pp. 4877-4889.
P.M. Novotny and M.K. Banerjee: Mater. Sci. Mater. Eng., 2016. DOI:10.1016/B978-0-12-803581-8.02534-0
[13] S. Kheirandish and A. Noorian: Journal of Iron and Steel Research, International, 2008, Vol. 15, pp. 61-66.
[14] A. Eser, C. Broeckmann and C. Simsir: Computational Materials Science, 2016, Vol. 113, pp. 280–291.
[15] Xie Hao-jie, Wu Xiao-chun and Min Yeng-an: Journal of Iron and Steel Research, International, 2008, Vol. 15, pp. 56-61.
[16] R.A. Mesquita and H.-J. Kestenbach: Materials Science and Engineering: A, 2012, Vol. 556, pp. 970-973.
[17] R.A. Mesquita, C.A. Barbosa, E.V. Morales and H.-J. Kestenbach: Metall. Mater. Trans. A, 2011, Vol. 42A, pp. 461-472.
[18] Z. Guo, N. Saunders, J.P. Schille and A.P. Miodownik: Materials Science and Engineering: A, 2009, Vol. 499, pp. 7-13.
[19] A. Powar and P. Date: Materials Science and Engineering: A, 2015, Vol. 628, pp. 89–97.
[20] C.J. Small and N. Saunders: MRS Bulletin, 1999, Vol. 24, pp. 22-26.
[21] C. Simsir and C.H. Gür: Computational Materials Science, 2008, Vol. 44, pp. 588–600.
[22] A. Eser, C. Broeckmann and C. Simsir: Computational Materials Science, 2016, Vol. 113, pp. 292-300.
[23] W. Paszkowicz: Materials and Manufacturing Processes, 2009, Vol. 24, pp. 174-197.
[24] W. Paszkowicz: Materials and Manufacturing Processes, 2013, Vol. 28, pp. 708-725.
[25] R.S. Khabbaz, B.D. Manshadi, A. Abedeian and R. Mahmudi: Materials&Design, 2009, Vol. 30, pp. 687-697.
S.S. Shivathaya: Material design in steel making utilising mathematical modelling, knowledge-based and fuzzy logic approaches, PhD Thesis, University of Wollongong, Wollongong, 1997.
[27] A.P. Ihom and A. Offiong: European Journal of Engineering and Technology, 2015, Vol. 3, pp. 40-54.
[28] L.A. Dobrzanski, J. Trzaska and A.D. Dobrzanska-Danikiewicz: Reference Module in Materials Science and Materials Engineering: Comprehensive Materials Processing, 2014, Vol. 2, pp. 161–198, DOI:10.1016/B978-0-08-096532-1.00215-6
[29] N.S. Reddy, J. Krishnaiah, Seong-Gu Hong and Jae Sang Lee: Materials Science and Engineering: A, 2009, Vol. 508, pp. 93-105
[30] B. Lotfi and P. Beiss: Materials and Design, 2013, Vol. 50, pp. 440–445.
[31] W. Sha and K.L. Edwards: Materials & Design, Vol. 28, 2007, pp. 1747-1752
[32] I. Belič, Neural networks and static modelling, in: M. Elhevnawi, M. Mysara (Eds.), Recurrent neural networks and soft computing, InTech, Rijeka, 2012, pp. 3-22.
[33] Liujie Xua, Jiandong Xing, Shizhong Wei, Yongzhen Zhang and Rui Long: Materials Science and Engineering: A, 2006, Vol. 433, pp. 251–256.
[34] T. Bhattacharyy, S.B. Singh, S. Sikdar(Dey), S. Bhattacharyy, W. Bleck and D. Bhattacharjee: Materials Science and Engineering: A, 2013, Vol. 565, pp. 148–157.
[35] Z. Sterjovski, D. Nolan, K.R. Carpenter, D.P. Dunne and J. Norrish: Journal of Materials Processing Technology, 2005, Vol. 170, pp. 536–544.
[36] G. Bloch and T. Denoeux: ISA Transactions, 2003, Vol. 42, pp. 39-51
[37] W. Sitek and J. Trzaska: Journal of Achievements in Materials and Manufacturing Engineering, 2011, Vol. 45, pp. 71-78.
[38] N.S. Reddy, B.B. Panigrahi, C.M. Ho, J.H. Kim and C.S. Lee: Computational Materials Science, 2015, Vol. 107, pp. 175-183.
[39] J. Kusiak and R. Kuziak: Journal of Materials Processing Technology, 2002, Vol. 127, pp. 115-121.
[40] S. Krajewski and J. Nowacki: Archives of Civil and Mechanical Engineering, 2014, Vol. 14, pp. 278-286.
[41] S.M.K. Hosseini, A. Zarei-Hanzaki, M.J. Yazdan Panah and S. Yue: Materials Science and Engineering: A, 2004, Vol. 374, pp. 122-128.
[42] R. Esmaeili and M.R. Dashtbayazi: Expert Systems With Applications, 2014, Vol. 41, pp. 5817-5831.
[43] I. Holzer and E. Kozeschnik: Materials Science and Engineering: A, 2010, Vol. 527, pp. 3546-3551.
[44] Z. Guo and W. Sha: Computational Materials Science, 2004, Vol. 29, pp. 12-28.
[45] J. Zhao, H. Ding, W. Zhao, M. Huang, D. Wei and Z. Jiang: Computational Materials Science, 2014, Vol. 92, pp. 47-56.
[46] S. Malinov and W. Sha: Materials Science and Engineering: A: 2004, Vol. 365, pp. 202-211
[47] O. Palavar, D. Ozyurek and A. Kalyon: Materials & Design, 2015, Vol. 82, pp. 164-172.
[48] Shen Wei, Zhao Tingshi, Gao Daxing, Liu Dunkang, Li Poliang and Qui Xiaoyun: Engineering Fracture Mechanics, 1982, Vol. 16, pp. 69–82.
[49] B. Ule, V. Leskovšek and B. Tuma: Engineering Fracture Mechanics, 2000. Vol. 65, pp. 559–572.
[50] B. Podgornik, V. Leskovšek and B. Žužek: Materials Performance and Characterization, 2014, Vol. 3, pp. 87-103.
https://www.cheshireeng.com/Neuralyst/; accessed July 2016
B. Podgornik, B. Žužek, F. Kafexhiu and V. Leskovšek: Tribol. Lett., 2016. DOI:10.1007/s11249-016-0695-6.
[53] R.A. Mesquita and H.-J. Kestenbach: Materials Science and Engineering: A, 2011, Vol. 528, pp. 4856-4859.
[54] You Fa Yin and Roy G Faulkner: Materials Science and Engineering: A, 2003, Vol. 344, pp. 92–102.
[55] B. Podgornik, V. Leskovsek, F. Tehovnik and J. Burja: Surface and Coatings Technology, 2015, Vol. 261, pp. 253-261.
[56] D.T. Llewellyn and R.C. Hudd: Steels – Metallurgy & Applications, 3rd edition, Butterworth-Heinemann, Oxford, 1998
Acknowledgment
Research in this work was conducted within the Slovenian Research Agency research group P2-0050 (fracture toughness measurement) and P2-0056 (ANN modeling).
Author information
Authors and Affiliations
Corresponding author
Additional information
Manuscript submitted May 2, 2016.
Rights and permissions
About this article
Cite this article
Podgornik, B., Belič, I., Leskovšek, V. et al. Tool Steel Heat Treatment Optimization Using Neural Network Modeling. Metall Mater Trans A 47, 5650–5659 (2016). https://doi.org/10.1007/s11661-016-3723-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11661-016-3723-0