Szczegóły publikacji

Opis bibliograficzny

A system of analysis and prediction of the loss of forging tool material applying artificial neural networks / M. Hawryluk, B. MRZYGŁÓD // Journal of Mining and Metallurgy. Section: B, Metallurgy ; ISSN 1450-5339. — 2018 — vol. 54 iss. 3, s. 323–337. — Bibliogr. s. 336, Abstr.

Autorzy (2)

Słowa kluczowe

decision support systemloss of materialdurability of forging toolswearartificial neural network

Dane bibliometryczne

ID BaDAP119951
Data dodania do BaDAP2019-02-14
Tekst źródłowyURL
DOI10.2298/JMMB180417023H
Rok publikacji2018
Typ publikacjiartykuł w czasopiśmie
Otwarty dostęptak
Creative Commons
Czasopismo/seriaJournal of Mining and Metallurgy, Section: B, Metallurgy

Abstract

The article presents the use of artificial neural networks (ANN) to build a system of analysis and forecasting of the durability of forging tools and the process of acquiring the source knowledge necessary for the network learning process. In particular, the study focuses on the prediction of the geometrical loss of the tool material after different surface treatment variants.The methodology of developing neural network models and their quality parameters is also presented. The standard single-layer MLP networks were used here; their quality parameters are at a high level and the results presented with their participation give satisfactory results in line with technological practice. The data used in the learning process come from extensive comprehensive performance tests of forging tools operating under extreme operating conditions (cyclic mechanical and thermal loads). The parameterization of the factors important for the selected forging process was made and a database was developed, including 900 knowledge vectors, each of which provided information on the size of the geometrical loss of the tool material (explained variables). The value of wear was determined for the set values of explanatory variables such as: number of forgings, pressure, temperature on selected tool surfaces, friction path and the variant of the applied surface treatment. The results presented in the study, confirmed by expert technologists, have a clear applicational character, because based on the presented solutions, the optimal treatment can be chosen and the appropriate preventive measures applied, which will extend the service life. © 2018, Technical Faculty in Bor. U ovom članku je predstavljena upotreba veštačkih neuronskih mreža (ANN) da bi se napravio sistem za analizu i predvidanje izdržljivosti alata za kovanje, kao i sticanje izvora znanja neophodnih za proces proučavanja mreža. Ova studija je fokusirana na predvidanje geometrijskog gubitka materijala alata posle različitih varijanti tretiranja površina. Takode je predstavljena metodologija razvoja modela neuronskih mreža i njihovih parametara kvaliteta. Korišćene su standardne jednoslojne MLP mreže čiji su parametri kvaliteta bili na visokom nivou, i rezultati koji su dobijeni su zadovoljavajući i u skladu sa tehnološkom praksom. Podaci korišćeni u procesu učenja dolaze iz opsežnih ispitivanja performansi alata za kovanje u ekstremnim uslovima za rad (ciklična mehanička i termička opterećenja). Izvršena je parametrizacija faktora važnih za odabrane procese kovanja i razvijena je baza podataka, uključujući i 900 vektora znanja od kojih je svaki davao informaciju o veličini geometrijskog gubitka materijala alata (objašnjene varijable). Vrednost habanja odredena je za utvrdene vrednosti eksplanatornih varijabli kao što su: broj kovanja, pritisak, temperatura na odabranim površinama alata, linija trenja, kao i varijanta primenjenog tretiranja površine. Rezultati dati u ovoj studiji, potvrdeni od strane stručnjaka iz oblasti tehnologije, imaju jasno primenljiv karakter jer se na osnovu predstavljenih rešenja može odabrati optimalan postupak i mogu se primeniti odgovarajuće preventivne mere, što će produžiti radni vek alata. © 2018, Technical Faculty in Bor.

Publikacje, które mogą Cię zainteresować

artykuł
#127799Data dodania: 18.3.2020
Application of artificial neural networks in the analysis of mechanisms destroying forging tools / M. Hawryluk, B. MRZYGŁÓD, Z. Gronostajski, M. GŁOWACKI, I. OLEJARCZYK-WOŻEŃSKA // Archives of Metallurgy and Materials / Polish Academy of Sciences. Committee of Metallurgy. Institute of Metallurgy and Materials Science ; ISSN 1733-3490. — 2020 — vol. 65 iss. 1, s. 193–200. — Bibliogr. s. 200
fragment książki
#105978Data dodania: 1.7.2017
Sensitivity analysis of the artificial neural network inputs in a system to durability prediction of forging tools / MRZYGŁÓD Barbara, Hawryluk Marek, Polak Sławomir // W: Metal 2017 : 26th international conference on Metallurgy and materials : May 24th–26th 2017, Brno, Czech Republic, EU : abstracts. — Ostrava : TANGER Ltd., cop. 2017. — ISBN: 978-80-87294-73-4. — S. 110–111. — Pełny tekst na CD-ROMie. — S. 484–489. — Wymagania systemowe: Adobe Reader ; napęd CD-ROM. — Bibliogr. s. 488-489, Abstr. — ISBN 978-80-87294-79-6