Application of categorical boosting to modelling the friction behaviour of DC05 steel sheets in strip drawing test

• Autorzy: Szewczyk Marek , Szwajka Krzysztof , Najm Sherwan Mohammed , Mohammed Salwa O.

Identyfikatory

DOI

10.7862/rm.2024.7

Warianty tytułu

PL

Zastosowanie wzbudzenia kategorycznego do modelowania zachowania tarciowego blach stalowych DC05 w teście ciągnienia pasa blachy

• Języki publikacji: EN

Abstrakty

EN

It is challenging to model the coefficient of friction, surface roughness, and related tribological processes during metal contact because of flattening, ploughing, and adhesion. It is important to choose the appropriate process parameters carefully when creating analytical models to overcome the challenges posed by complexity. This will ensure the production of sheet metal formed components that meets the required quality standards and is free from faults. This research analyses the impacts of nominal pressure, kinematic viscosity of lubricant, and lubricant pressure on the coefficient of friction and average roughness of DC05 deep-drawing steel sheets. The strip drawing test was used to determine the coefficient of friction. This work utilises the Categoric Boosting (CatBoost) machine learning algorithm created by Yandex to estimate the COF and surface roughness, intending to conduct a comprehensive investigation of process parameters. A Shapley decision plot exhibits the coefficient of friction prediction models via cumulative SHapley Additive exPlanations (SHAP) data. CatBoost has outstanding prediction accuracy, as seen by R2 values ranging from 0.955 to 0.894 for both the training and testing datasets for the COF, as well as 0.992 to 0.885 for surface roughness.

PL

Modelowanie współczynnika tarcia, chropowatości powierzchni i powiązanych procesów tribologicznych podczas kontaktu powierzchni blachy i narzędzi jest trudnym wyzwaniem ze względu na spłaszczanie, bruzdowanie i sczepianie nierówności powierzchni. Podczas tworzenia modeli analitycznych ważne jest, aby ostrożnie wybierać odpowiednie parametry procesu. Zapewni to produkcję elementów formowanych z blachy spełniających wymagane standardy jakościowe i pozbawione wad. W pracy analizowano wpływ ciśnienia nominalnego, lepkości kinematycznej smaru i ciśnienia smaru na współczynnik tarcia i średnią chropowatość powierzchni blach stalowych głęboko tłocznych DC05. Do wyznaczenia współczynnika tarcia wykorzystano test przeciągania pasa blachy. W pracy tej wykorzystano algorytm uczenia maszynowego CatBoost, stworzony przez firmę Yandex, w celu oszacowania wartości współczynnika tarcia ni chropowatości powierzchni. Przeprowadzono kompleksowe badania parametrów procesu tarcia. Modele przewidywania współczynnika tarcia na podstawie funkcji SHapley Additive exPlanations (SHAP)przedstawiono za pomocą wykresu decyzyjnego Shapleya. CatBoost charakteryzuje się wyjątkową dokładnością przewidywania potwierdzoną wartością R2 w zakresie od 0.955 do 0.894 zarówno w przypadku zbiorów danych uczących, jak i testowych dla współczynnika tarcia, a także od 0.992 do 0.885 w przypadku średniej chropowatości powierzchni.

Słowa kluczowe

EN

coefficient of friction; friction; sheet metal forming; steel sheet; surface roughness

PL

współczynnik tarcia; tarcie; kształtowanie blach; blacha stalowa; chropowatość powierzchni

• Wydawca: Oficyna Wydawnicza Politechniki Rzeszowskiej
• Czasopismo: Advances in Mechanical and Materials Engineering
• Rocznik: 2024
• Tom: Vol. 41, nr 1
• Strony: 69--78
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wykr.

Twórcy

autor

Szewczyk Marek

• Department of Integrated Design and Tribology Systems, Faculty of Mechanics and Technology, Rzeszow University of Technology

autor

Szwajka Krzysztof

• Department of Integrated Design and Tribology Systems, Faculty of Mechanics and Technology, Rzeszow University of Technology

autor

Najm Sherwan Mohammed

• Kirkuk Technical Institute, Northern Technical University, Kirkuk, Iraq
• Department of Manufacturing Science and Engineering, Budapest University of Technology and Economics, Budapest, Hungary

autor

Mohammed Salwa O.

• Kirkuk Technical Institute, Northern Technical University, Kirkuk, Iraq

Bibliografia

• 1. Bang, J., Park, N., Song, J., Kim, H. G., Bae, G., & Lee, M. G. (2021). Tool wear prediction in the forming of automotive DP980 steel sheet using statistical sensitivity analysis and accelerated U-bending based wear test. Metals, 11, 306. https://doi.org/10.3390/met11020306
• 2. Bay, N., Olsson, D. D., & Andreasen, J. L. (2008). Lubricant test methods for sheet metal forming. Tribology International, 41, 844–853. https://doi.org/10.1016/j.triboint.2007.11.017
• 3. Carcel, A. C., Palomares, D., Rodilla, E., & Pérez Puig, M. A. (2005). Evaluation of vegetable oils as pre-lube oils for stamping. Materials and Design, 26, 587–593. https://doi.org/10.1016/j.matdes.2004.08.010
• 4. Çavuşoğlu, O., Gürün, H. (2017). Statistical evaluation of the influence of temperature and surface roughness on aluminium sheet metal forming. Transactions Famena, 41, 57–64. https://doi.org/10.21278/TOF.41305
• 5. Daniel, D., Guiglionda, G., Litalien, P., & Shahani R. (2006). Overview of forming and formability issues for high volume aluminium car body panels. Materials Science Forum, 519-521, 795-802. https://doi.org/10.4028/www.scientific.net/MSF.519-521.795
• 6. Domitner, J., Silvayeh, Z., Shafiee Sabet, A., Öksüz, K. I., Pelcastre, L., & Hardell, J. (2021). Characterization of wear and friction between tool steel and aluminum alloys in sheet forming at room temperature. Journal of Manufacturing Processes, 64, 774-784. https://doi.org/10.1016/j.jmapro.2021.02.007
• 7. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: gradient boosting with categorical features support. http://arxiv.org/abs/1810.11363
• 8. Gali, O. A., Riahi, A. R., & Alpas, A. T. (2013). The tribological behaviour of AA5083 alloy plastically deformed at warm forming temperatures. Wear, 302, 1257-1267. https://doi.org/10.1016/j.wear.2012.12.048
• 9. Groche, P., & Christiany, M., & Wu, Y. (2019). Load-dependent wear in sheet metal forming. Wear, 422-423, 252-260. https://doi.org/10.1016/j.wear.2019.01.071
• 10. Guillon, O., Roizard, X., & Belliard, P. (2001). Experimental methodology to study tribological aspects of deep drawing Application to aluminium alloy sheets and tool coatings. Tribology International, 34, 757–766. https://doi.org/10.1016/S0301-679X(01)00069-X
• 11. Ibragimov, B., & Gusev, G. (2019, December 8-14). Minimal variance sampling in stochastic gradient boosting. Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, pp. 1-11.
• 12. Kim, H., Han, S., Yan, Q., & Altan, T. (2008). Evaluation of tool materials, coatings and lubricants in forming galvanized advanced high strength steels (AHSS). CIRP Annals, 57, 299–304. https://doi.org/10.1016/j.cirp.2008.03.029
• 13. Le, H. R., & Sutcliffe, M. P. F. (2002). Measurements of friction in strip drawing under thin film lubrication. Tribology International, 35, 123-128. https://doi.org/10.1016/S0301-679X(01)00104-9
• 14. Lee, B. H., Keum, Y. T., & Wagoner, R. H. (2002). Modeling of the friction caused by lubrication and surface roughness in sheet metal forming. Journal of Materials Processing Technology, 130-131, 60-63. https://doi.org/10.1016/S0924-0136(02)00784-7
• 15. Masters L.G., Williams D. K., & Roy R. (2013). Friction behaviour in strip draw test of pre-stretched high strength automotive aluminium alloys. International Journal of Machine Tools and Manufacture, 73, 17–24, https://doi.org/10.1016/j.ijmachtools.2013.05.002
• 16. Nabipour, M., & Keshavarz, P. (2017). Modeling surface tension of pure refrigerants using feed forward backpropagation neural networks. International journal of refrigeration, 75, 217–227. https://doi.org/10.1016/j.ijrefrig.2016.12.011
• 17. Najm, S.M., & Paniti, I. (2023). Investigation and machine learning-based prediction of parametric effects of single point incremental forming on pillow effect and wall profile of AlMn1Mg1 aluminum alloy sheets. Journal of Intelligent Manufacturing, 34, 331–367. https://doi.org/10.1007/s10845-022-02026-8
• 18. Severo, V., Vilhena, L., Silva, P. N., Dias, J. P., Becker, D., Wagner, S., & Cavaleiro, A. (2009). Tribological behaviour of W–Ti–N coatings in semi-industrial strip-drawing tests. Journal of Materials Processing Technology, 209, 4662–4667. https://doi.org/10.1016/j.jmatprotec.2008.11.040
• 19. Shisode, M., Hazrati, J., Mishra, T., Rooij, M., Horn, C., Beck, J., & Boogaard, T. (2021). Modelling boundary friction of coated sheets in sheet metal forming. Tribology International, 153, 106554. https://doi.org/10.1016/j.triboint.2020.106554
• 20. Sigvant, M., Pilthammar, J., Hol, J., Wiebenga, J. H., Chezan, T., Carleer, B., & van den Boogaard, T. (2019). Fiction in sheet metal forming: influence of surface roughness and strain rate on sheet metal forming simulation results. Procedia Manufacturing, 29, 512-519. https://doi.org/10.1016/j.promfg.2019.02.169
• 21. Szewczyk, M., & Szwajka, K. (2022). Analysis of the friction mechanisms of DC04 steel sheets in the flat strip drawing test. Advances in Mechanical and Materials Engineering, 94, 51-61. https://doi.org/10.7862/rm.2022.4
• 22. Spišák, E., Majerníková, J., Duľová Spišáková, E., & Kaščák, Ľ. (2016). Analysis of plastic deformation of double reduced sheets. Acta Mechanica et Automatica, 10(4), 271-274. https://doi.org/10.1515/ama-2016-0041
• 23. Trzepieciński, T., Szewczyk, M., & Szwajka, K. (2022). The use of non-edible green oils to lubricate DC04 steel sheets in sheet metal forming process. Lubricants, 10, 210. https://doi.org/10.3390/lubricants10090210
• 24. Venema, J, Matthews, D. T. A., Hazrati, J., Wörmann, J. & Van den Boogaard, A. H. (2017). Friction and wear mechanisms during hot stamping of AlSi coated press hardening steel. Wear, 380-381, 137-145. https://doi.org/10.1016/j.wear.2017.03.014
• 25. Wang, C., Ma, R., Zhao, J., & Zhao, J. (2017). Calculation method and experimental study of coulomb friction coefficient in sheet metal forming. Journal of Manufacturing Processes, 27, 126–137. https://doi.org/10.1016/j.jmapro.2017.02.016
• 26. Żaba, K., Kuczek, Ł., Puchlerska, S., Wiewióra, M., Góral, M., & Trzepieciński, T. (2023). Analysis of tribological performance of new stamping die composite inserts using strip drawing test. Advances in Mechanical and Materials Engineering, 40, 55–62. https://doi.org/10.7862/rm.2023.7
• 27. Żaba, K., Puchlerska, S., Pieja, T., & Pyzik, J. (2020). Process design for superalloys sheet rotary forming. Materials Science Forum, 985, 91-96. https://doi.org/10.4028/www.scientific.net/MSF.985.91

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).