Publication detail
Prediction of fracture toughness transition from tensile test data using artificial neural networks
AL KHADDOUR, S. STRATIL, L. VÁLKA, L. DLOUHÝ, I.
Czech title
Predikce tranzitního chování lomové houževnatosti z výsledků zkoušek tahem prostřednictvím neuronových sítí
English title
Prediction of fracture toughness transition from tensile test data using artificial neural networks
Type
conference paper
Language
en
Original abstract
The aim of this paper is develop prediction procedure for the fracture toughness transition from tensile test data using artificial neural networks. In total 29 experimental data sets from low alloy steels are applied to validate the model of reference temperature prediction. The tensile tests have been done at general yield temperature of circumferential notched tensile tests (purely brittle fracture temperature) and at room temperature (purely ductile fracture temperature). To build the model, all parameters of tensile test and hardness values were used as input variables. The study indicates that the reference temperature characterizing the fracture toughness transition behaviour in low alloy steels with predominantly ferritic structure is predictable on the basis of selected characteristics of tensile test.
Czech abstract
Cílem této práce je vyvinout postup pro predikci teplotní závislosti lomové houževnatoti na základě výsledků zkoušek tahem s využitím umělých neuronových sítí. Pro vytvoření a oveření modelu predikce referenční teploty je použito celkem 29 souborů experimentálních dat.
English abstract
The aim of this paper is develop prediction procedure for the fracture toughness transition from tensile test data using artificial neural networks. In total 29 experimental data sets from low alloy steels are applied to validate the model of reference temperature prediction. The tensile tests have been done at general yield temperature of circumferential notched tensile tests (purely brittle fracture temperature) and at room temperature (purely ductile fracture temperature). To build the model, all parameters of tensile test and hardness values were used as input variables. The study indicates that the reference temperature characterizing the fracture toughness transition behaviour in low alloy steels with predominantly ferritic structure is predictable on the basis of selected characteristics of tensile test.
Keywords in Czech
oceli; lomová houževnatost; zkouška tahem; umělé neuronové sítě; referenční teplota
Keywords in English
steels; fracture toughness; tensile test; artificial neural networks; reference temperature
Released
02.06.2016
Publisher
Brno University of Technology
Location
Brno
ISBN
978-80-214-5358-6
Book
MULTI-SCALE DESIGN OF ADVANCED MATERIALS - CONFERENCE PROCEEDINGS
Edition number
1
Pages from–to
79–86
Pages count
8
BIBTEX
@inproceedings{BUT126186,
author="Samer {Al Khaddour} and Luděk {Stratil} and Libor {Válka} and Ivo {Dlouhý},
title="Prediction of fracture toughness transition from tensile test data using artificial neural networks",
booktitle="MULTI-SCALE DESIGN OF ADVANCED MATERIALS - CONFERENCE PROCEEDINGS",
year="2016",
month="June",
pages="79--86",
publisher="Brno University of Technology",
address="Brno",
isbn="978-80-214-5358-6"
}