Gaussian Process for Machine Learning-Based Fatigue Life Prediction Model under Multiaxial Stress-Strain Conditions.
CuZn37 brass
fatigue life prediction
machine learning
Journal
Materials (Basel, Switzerland)
ISSN: 1996-1944
Titre abrégé: Materials (Basel)
Pays: Switzerland
ID NLM: 101555929
Informations de publication
Date de publication:
04 Nov 2022
04 Nov 2022
Historique:
received:
12
10
2022
revised:
24
10
2022
accepted:
03
11
2022
entrez:
11
11
2022
pubmed:
12
11
2022
medline:
12
11
2022
Statut:
epublish
Résumé
In this paper, a new method for fatigue life prediction under multiaxial stress-strain conditions is developed. The method applies machine learning with the Gaussian process for regression to build a fatigue model. The fatigue failure mechanisms are reflected in the model by the application of the physics-based stress and strain invariants as input quantities. The application of the machine learning algorithm solved the problem of assigning an adequate parametric fatigue model to given material and loading conditions. The model was verified using the experimental data on the CuZn37 brass subjected to various cyclic loadings, including non-proportional multiaxial strain paths. The performance of the machine learning-based fatigue life prediction model is higher than the performance of the well-known parametric models.
Identifiants
pubmed: 36363388
pii: ma15217797
doi: 10.3390/ma15217797
pmc: PMC9659309
pii:
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : National Science Center
ID : 2021/41/B/ST8/00257
Déclaration de conflit d'intérêts
The authors declare no conflict of interest.
Références
Philos Trans A Math Phys Eng Sci. 2015 Mar 28;373(2038):
pubmed: 25713457
Materials (Basel). 2017 Aug 09;10(8):
pubmed: 28792487
Materials (Basel). 2019 May 10;12(9):
pubmed: 31083468
Materials (Basel). 2021 Jan 04;14(1):
pubmed: 33406668