Durability analysis of forging tools after different variants of surface treatment using a decision-support system based on artificial neural networks

• Autorzy: Mrzygłód B. , Hawryluk M. , Gronostajski Z. , Opaliński A. , Kaszuba M. , Polak S. , Widomski P. , Ziemba J. , Zwierzchowski M.

Identyfikatory

DOI

10.1016/j.acme.2018.02.010

• Języki publikacji: EN

Abstrakty

EN

This article concerns a decision-support system based on artificial neural networks (ANN) enabling analysis and forecasting of the durability of forging tools used in the hot forging process of a cover forging – a sealing element of the driveshaft in road freight vehicles. The process of knowledge acquisition, adopted neural network architecture and parameters of the developed network are presented. In addition, 3 variants of a hybrid layer (gas nitrided layer GN + PVD coating) were applied to the selected tools (punches applied in the 2nd top forging operation): GN/AlCrTiN, GN/AlCrTiSiN, and GN/CrN, in order to improve durability, and the resultant tools were also compared to standard tools (with only gas nitriding) and regenerated tools (after repair welding regeneration). The indispensable knowledge about the durability of selected forging tools (after various surface engineering variants), required for the process of learning, testing and validation for various neural network architectures was obtained from comprehensive, multi-year studies. These studies covered, among other things: operational observation of the forging process, macroscopic analysis combined with scanning of tools’ working surfaces, microhardness measurements, microstructural analysis and numerical modeling of the forging process. The developed machine-learning dataset was a collection of approx. 900 knowledge records. The input (independent) variables were: number of forgings manufactures, pressing forces, temperature on selected tool surfaces, friction path and type of protective layer applied to tool. Meanwhile, output (dependent) variables were: geometrical loss of tool material and percentage share of the four main destructive mechanisms. Obtained results indicate the validity of employing ANN-based IT tools to build decision-support systems for the purpose of analyzing and forecasting the durability of forging tools.

Słowa kluczowe

EN

artificial neural network; decision support system; durability of forging tools; destructive mechanisms

PL

sztuczna sieć neuronowa; system wspomagania decyzji; kucie

• Wydawca: Springer ; Wrocław University of Science and Technology
• Czasopismo: Archives of Civil and Mechanical Engineering
• Rocznik: 2018
• Tom: Vol. 18, no. 4
• Strony: 1079--1091
• Opis fizyczny: Bibliogr. 40 poz., rys., tab., wykr.

Twórcy

autor

Mrzygłód B.

• AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Hawryluk M.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Gronostajski Z.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Opaliński A.

• AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Kaszuba M.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Polak S.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Widomski P.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Ziemba J.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

autor

Zwierzchowski M.

• Wroclaw University of Science and Technology, Department of Metal Forming and Metrology, Lukasiewicza Street 5, 50-370 Wrocław, Poland

Bibliografia

• [1] P. Anders, S. Hogmark, J. Bergström, Simulation and evaluation of thermal fatigue cracking of hot work tool steels, Int. J. Fatigue 10 (2004) 1095–1107.
• [2] A. Azari, M. Poursina, D. Poursina, Radial forging force prediction through MR, ANN and ANFIS models, Neural Comput. Appl. 25 (3–4) (2014) 849–858.
• [3] G.A. Berti, M. Monti, Thermo-mechanical fatigue life assessment of hot forging die steel, Fatigue Fract. Eng. Mater. Struct. 28 (11) (2005) 1025–1034.
• [4] Ch. Choi, A. Groseclose, T. Altan, Estimation of plastic deformation and abrasive wear in warm forging dies, J. Mater. Process. Technol. 212 (8) (2012) 1742–1752.
• [5] T. Gangopadhyay, D. Kumar, I. Pratihar, Expert system to predict forging load and axial stress, Appl. Soft. Comput. 11 (1) (2014) 744–753.
• [6] Z. Gronostajski, et al., Application of a measuring arm with an integrated laser scanner in the analysis of the shape changes of forging instrumentation during production, Eksploatacja i Niezawodnosc (Maintenance Reliab.), 18 (2) (2016) 194–200.
• [7] Z. Gronostajski, M. Hawryluk, et al., The expert system supporting the assessment of the durability of forging tools, Int. J. Adv. Manuf. Technol. 82 (9) (2015) 1973–1991.
• [8] Z. Gronostajski, M. Hawryluk, The main aspects of precision forging, Arch. Civil Mech. Eng. 8 (2) (2008) 39–57.
• [9] Z. Gronostajski, M. Kaszuba, M. Hawryluk, M. Zwierzchowski, A review of the degradation mechanisms of the hot forging tools, Arch. Civil Mech. Eng. 4 (14) (2001) 528–539.
• [10] Z. Gronostajski, et al., The failure mechanisms of hot forging dies, Mater. Sci. Eng. A 657 (2016) 147–160.
• [11] M. Hawryluk, Metody analizy oraz zwiększania trwałości narzędzi kuźniczych stosowanych w procesach kucia matrycowego na gorąco, ISBN 978-83-7789-410-1, Radom, in: Monograficzna seria wydawnicza Problemy Eksploatacji i Budowy M aszyn, 2016.
• [12] M. Hawryluk, et al., Analysis of the wear of forging tools surface layer after hybrid surface treatment, Int. J. Mach. Tools Manuf. 114 (2017) 60–71.
• [13] M. Hawryluk, et al., Application of selected surface engineering methods to improve the durability of tools used in precision forging, Int. J. Adv. Manuf. Technol. (2017) (in press).
• [14] M. Hawryluk, B. Mrzygłód, A durability analysis of forging tools for different operating conditions with application of a decision support system based on artificial neural networks (ANN), Eksploatacja i Niezawodnosc (Maintenance Reliab.), 19 (3) (2017) 338–348.
• [15] M. Hawryluk, Review of selected methods of increasing the life of forging tools in hot die forging processes, Arch. Civil Mech. Eng. 16 (2016) 845–866. http://dx.doi.org/10.1016/j. acme.2016.06.001.
• [16] M. Hawryluk, B. Mrzygłód, Application of adaptive neuro-fuzzy inference system (ANFIS) to predict the wear of forging tools, in: METAL 2016: 25th International Conference on Metallurgy and Materials, 2016, 384–385.
• [17] D. Heinemeyer, Gensekschäden und Einflussgrössen der Standmenge, Industrieanzeiger 100 (73) (1978).
• [18] T. Katayama, M. Akamatsu, Y. Tanaka, Construction of PC based expert system for cold forging process design, J Mater. Process. Technol. 155–156 (2004) 1583–1589.
• [19] A. Katunin, The conception of the fatigue model for layered composites considering thermal effects, Arch. Civil Mech. Eng. 11 (2) (2011) 333–342.
• [20] D.H. Kima, H.C. Leeb, B.M. Kimc, K.H. Kimd, Estimation of die service life against plastic deformation and wear during hot forging processes, J. Mater. Process. Technol. 212 (2012) 1742–1752.
• [21] S. Kluska-Nawarecka, D. Wilk-Kolodziejczyk, K. Regulski, Practical aspects of knowledge integration using attribute tables generated from relational databases, semantic methods for knowledge management and communication, Book Series: Stud. Comput. Intell. 381 (2011) 13–22.
• [22] K. Lange, L. Cser, M. Geiger, J.A.G. Kals, Tool life and tool quality in bulk metal forming, Proc. Inst. Mech. Engrs. Part B: J. Eng. Manuf. 207 (1993) 223–239.
• [23] R. Lapovok, S. Smirnov, V. Shveykin, Damage mechanics for the fracture prediction of metal forming tools, Int. J. Fract. 103 (2) (2000) 111–126.
• [24] M. Li, X. Liu, A. Xiong, Prediction of the mechanical properties of forged TC11 titanium alloy by ANN, J. Mater. Process. Technol. 121 (1) (2012) 1–4.
• [25] B. Lu, H. Ou, H. Long, Die shape optimisation for net-shape accuracy in metal forming using direct search and localised response surface methods, Struct. Multidisc. Optim. 44 (2011) 529–545.
• [26] D. Mazurkiewicz, Maintenance of belt conveyors using an expert system based on fuzzy logic, Arch. Civil Mech. Eng. 15 (2) (2015) 412–418. http://dx.doi.org/10.1016/j.acme.2014.12.009.
• [27] A. Meller, S. Legutko, J. Smolik, Badanie wpływu warstw hybrydowych na trwałość matryc do kucia na gorąco, Archiwum Technologii Maszyn i Automatyzacji 30 (4) (2010) 199–211.
• [28] F. Meng, K. Tagashira, R. Azuma, H. Sohma, Role of eta-carbide precipitations in the wear resistance improvements of Fe 12Cr-Mo-V 1.4C tool steel by cryogenic treatment, ISIJ Int. 34 (2) (1994) 205–210.
• [29] Y. Min, X. Wu, Influence of different surface treatments of H13 hot work die steel on its thermal fatigue behaviors, J. Shanghai Univ. 5 (4) (2001) 326–330.
• [30] E. Nawarecki, S. Kluska-Nawarecka, K. Regulski, Multi-aspect character of the man-computer relationship in a diagnostic-advisory system, in: Z.S. Hippe, J.L. Kulikowski, T. Mroczek (Eds.), Human – Computer Systems Interaction: Backgrounds and Applications, 2, Springer-Verlag, Berlin; Heidelberg, 2012.
• [31] A. Persson, S. Hogmarkb, J. Bergstroma, Thermal fatigue cracking of surface engineered hot work tool steels, Surf. Coat. Technol. 191 (2005) 216–227.
• [32] L. Rauch, A. Chmura, Z. Gronostajski, M. Pietrzyk, M. Zwierzchowski, Cellular automata model for prediction of crack initiation and propagation in hot forging tools, Arch. Civil Mech. Eng. 16 (3) (2016) 437–447.
• [33] C. Starlinga, J. Brancob, Thermal fatigue of hot work tool steel with hard coatings, Thin Solid Films 308 (309) (1997) 436–442.
• [34] A.V. Subba Rao, D.K. Pratihar, Fuzzy logic-based expert system to predict the results of finite element analysis, Knowl.-Based Syst. 20 (2007) 37–50.
• [35] Y. Sun, L. Hu, Modelling optimisation of hot processing parameters of Ti-6Al-4V alloy using artificial neural network and genetic algorithm, Mater. Res. Innov. 18 (2014) 1052–1056.
• [36] R. Tadeusiewicz, Neural networks in mining sciences – general overview and some representative examples, Arch. Min. Sci. 60 (4) (2015) 971–984.
• [37] A. Taylan, N. Gracious, S. Gangshu, Cold and hot forging fundamentals and application, ASM Int. ASM Metals Handb. 14 (2005) 337–338.
• [38] A. Tompos, J.L. Margitfalvi, E. Tfirst, K. Héberger, Predictive performance of 'highly complex' artificial neural networks, Appl. Catal. Gen. 324 (2007) 90–93.
• [39] J. Turek, Trwałość matryc kuźniczych z wykrojami napawanymi, Politechnika Krakowska, 2010.
• [40] M. Yong-an, W. Xiao-chun, X. Luo-ping, T. Wen-jun, Influence of different surface treatments of H13 hot work die steel on its thermal fatigue behaviors, J. Shanghai Univ. 5 (4) (2001) 326–330.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019)