Selection of casting production parameters with the use of machine learning and data supplementation methods in order to obtain products with the assumed parameters

• Autorzy: Wilk-Kołodziejczyk Dorota , Pirowski Zenon , Bitka Adam , Wróbel Kamil , Śnieżyński Bartłomiej , Doroszewski Maciej , Jaśkowiec Krzysztof , Małysza Marcin

Identyfikatory

DOI

10.1007/s43452-022-00598-z

• Języki publikacji: EN

Abstrakty

EN

The main purpose of the research, presented in this publication, was to develop methodology for the construction of predictive models which allow the selection of material production parameters for the material-technological conversion process. The development of prototype modules based on information-decision system allows an initial assessment of the level of feasibility of undertaking this type of operation. Algorithms 1, 2, 3 presented in the article were used to complete the missing data. The result of the algorithm enabled the creation of a data table that specifies the operation of the predictive models indicated in chapter 3 of this article. Entire work is presented with regard to the background of the ADI cast iron production process to locate the requirement where to apply the developed methods in the field of predictive algorithms and data completion algorithms. On the basis of developed methods and predictive algorithms, trial castings were operated.

• Wydawca: Springer ; Wrocław University of Science and Technology
• Czasopismo: Archives of Civil and Mechanical Engineering
• Rocznik: 2023
• Tom: Vol. 23, no. 2
• Strony: art. no. e73, 2023
• Opis fizyczny: Bibliogr. 19 poz., rys., tab., wykr.

Twórcy

autor

Wilk-Kołodziejczyk Dorota

• AGH University of Science and Technology, Krakow, Poland
• Łukasiewicz Research Network-Krakow Institute of Technology, Krakow, Poland

• https://orcid.org/0000-0001-5590-0477

autor

Pirowski Zenon

• Łukasiewicz Research Network-Krakow Institute of Technology, Krakow, Poland

autor

Bitka Adam

• AGH University of Science and Technology, Krakow, Poland
• Łukasiewicz Research Network-Krakow Institute of Technology, Krakow, Poland

autor

Wróbel Kamil

• AGH University of Science and Technology, Krakow, Poland

autor

Śnieżyński Bartłomiej

• AGH University of Science and Technology, Krakow, Poland

autor

Doroszewski Maciej

• AGH University of Science and Technology, Krakow, Poland

autor

Jaśkowiec Krzysztof

• AGH University of Science and Technology, Krakow, Poland
• Łukasiewicz Research Network-Krakow Institute of Technology, Krakow, Poland

autor

Małysza Marcin

• AGH University of Science and Technology, Krakow, Poland
• Łukasiewicz Research Network-Krakow Institute of Technology, Krakow, Poland

Bibliografia

• 1. Olson D. Prediction of austenitic weld metal microstructure and properties. Weld J. 1985;64(10):281s-95s.
• 2. Kochanski A, Perzyk M, Klebczyk M. Knowledge in imperfect data. In: Advances in knowledge representation. London: IntechOpen; 2012. p. 181-209.
• 3. Arafeh L, Singh H, Putatunda SK. A neuro fuzzy logic approach to material processing. IEEE Trans Syst Man Cybern Part C (Appl Rev). 1999;29(3):362-70.
• 4. Yescas MA. Prediction of the Vickers hardness in austempered ductile irons using neural networks. Int J Cast Met Res. 2003;15(5):513-21.
• 5. Yescas M, Bhadeshia H, MacKay D. Estimation of the amount of retained austenite in austempered ductile irons using neural networks. Mater Sci Eng A. 2001;311(1):162-73.
• 6. PourAsiabi H, PourAsiabi H, AmirZadeh Z, BabaZadeh M. Development a multilayer perceptron artificial neural network model to estimate the Vickers hardness of Mn-Ni-Cu-Mo austempered ductile iron. Mater Des. 2012;35:782-9.
• 7. Savangouder RV, Patra JC, Bornand C. Artificial neural network-based modeling for prediction of hardness of austempered ductile iron. In: International conference on neural information processing. Cham: Springer; 2019. p. 405-413.
• 8. Savangouder RV, Patra JC, Bornand C. Prediction of hardness of austempered ductile iron using enhanced multilayer perceptron based on Chebyshev expansion. In: International conference on neural information processing. Cham: Springer; 2019. p. 414-422.
• 9. Russell SJ, Norvig P. Artificial intelligence: a modern approach. Financial Times Prentice Hall; 2019.
• 10. Sambridge M. Parallel tempering algorithm for probabilistic sampling and multimodal optimization. Geophys J Int. 2013;196(1):357-74.
• 11. Glover F. Tabu search: a tutorial. Interfaces. 1990;20:74-94.
• 12. Kumar A, Chakrabarti D, Chakraborti N. Data-driven pareto optimization for microalloyed steels using genetic algorithms. Steel Res Int. 2012;83(2):169-74.
• 13. Radiša R, Ducić N, Manasijević S, Marković N, Cojbašić Ž. Casting improvement based on metaheuristic optimization and numerical simulation. Facta Universitatis. 2017;15(3):397-411.
• 14. Norm: EN 1564:2012.
• 15. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32.
• 16. Breiman L. Bagging predictors. Mach Learn. 1996;24(2):123-40.
• 17. Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):1189-232.
• 18. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, ACM DIgital Library; 2016. p. 785-94.
• 19. Negnevitsky M. Artificial intelligence: a guide to intelligent systems. Pearson Education; 2005.