All the available "Paris-like" models (analytical relationships between da/dN, crack growth rates, and ΔK, stress intensity factor amplitude) are not able to take into account the possible influence of all the parameters that influence the fatigue crack propagation process. Among them, the stress ratio R (e.g., K min /K max ) is one of the most investigated and, although in the last decades the influence of R on the different propagation mechanisms has been widely investigated (e.g., crack closure effect), this parameter is often considered as an independent variable in the "Paris-like" models. A different approach can be followed using the Artificial Neural Networks that are able to consider all the possible parameters, with the condition of a satisfactory training stage. In this work, an artificial Neural Networks based model is optimized considering the influence of the stress ratio on the fatigue crack propagation in a ferritic-pearlitic Ductile Cast Iron.
Fatigue crack propagation in Ductile Cast Irons: An Artificial Neural Networks based model / D'Agostino, L.; De Santis, A.; Di Cocco, V.; Iacoviello, D.; Iacoviello, F.. - In: PROCEDIA STRUCTURAL INTEGRITY. - ISSN 2452-3216. - 3:(2017), pp. 291-298. (Intervento presentato al convegno XXIV Italian Group of Fracture Conference tenutosi a Urbino; Italy) [10.1016/j.prostr.2017.04.048].
Fatigue crack propagation in Ductile Cast Irons: An Artificial Neural Networks based model
De Santis A.
;Iacoviello D.
;
2017
Abstract
All the available "Paris-like" models (analytical relationships between da/dN, crack growth rates, and ΔK, stress intensity factor amplitude) are not able to take into account the possible influence of all the parameters that influence the fatigue crack propagation process. Among them, the stress ratio R (e.g., K min /K max ) is one of the most investigated and, although in the last decades the influence of R on the different propagation mechanisms has been widely investigated (e.g., crack closure effect), this parameter is often considered as an independent variable in the "Paris-like" models. A different approach can be followed using the Artificial Neural Networks that are able to consider all the possible parameters, with the condition of a satisfactory training stage. In this work, an artificial Neural Networks based model is optimized considering the influence of the stress ratio on the fatigue crack propagation in a ferritic-pearlitic Ductile Cast Iron.File | Dimensione | Formato | |
---|---|---|---|
DAgostino_Fatigue-crack_2017.pdf
accesso aperto
Note: https://doi.org/10.1016/j.prostr.2017.04.048
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
1.59 MB
Formato
Adobe PDF
|
1.59 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.