Pregled bibliografske jedinice broj: 882189
New insights into estimation of cyclic behaviour of steels based on their monotonic properties using artificial neural networks
New insights into estimation of cyclic behaviour of steels based on their monotonic properties using artificial neural networks // Proceedings of the 5th Symposium on Structural Durability in Darmstadt / Vormwald, Michael ; Beier, Heinz Thomas ; Breidenbach, Kerstin (ur.).
Darmstadt: Technische Universitat Darmstadt - Institut fur Stahlbau und Werkstoffmechanik, 2017. str. 223-230 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 882189 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
New insights into estimation of cyclic behaviour of steels based on their monotonic properties using artificial neural networks
Autori
Marohnić, Tea
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 5th Symposium on Structural Durability in Darmstadt
/ Vormwald, Michael ; Beier, Heinz Thomas ; Breidenbach, Kerstin - Darmstadt : Technische Universitat Darmstadt - Institut fur Stahlbau und Werkstoffmechanik, 2017, 223-230
ISBN
978-3-939195-55-9
Skup
Symposium on Structural Durability in Darmstadt SoSDiD 2017
Mjesto i datum
Darmstadt, Njemačka, 17.05.2017. - 18.05.2017
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
steels ; cyclic stress–strain parameters ; statistical analysis ; artificial neural networks
Sažetak
Within the framework of this research, a new methodology was proposed for estimation of cyclic Ramberg–Osgood parameters i.e. cyclic behaviour of steels based on their monotonic properties using artificial neural networks. A large number of experimental data for steels were collected from relevant literature and divided into unalloyed, low-alloy and high-alloy steels, since previous research confirmed that statistically significant differences exist among cyclic parameters of different groups of steels. Detailed statistical analysis was performed by means of forward selection and monotonic properties relevant for estimation of each cyclic parameter of each group of steels were determined. Based on results of performed statistical analyses, artificial neural networks were developed, separately for each parameter and each steel subgroup, using only monotonic properties that proved to be relevant for estimation of particular parameter. Neural networks have been evaluated on an independent set of data, in comparison with experimental values and values obtained by existing empirical estimation methods. The new approach proved to be more successful than empirical methods for estimation of most of the cyclic properties and behaviour of different steel subgroups.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
