2014
DOI: 10.2478/amm-2014-0021
|View full text |Cite
|
Sign up to set email alerts
|

The Prediction of Hardenability using Neural Networks

Abstract: The objective of the research that has been presented was to model the effect of differences in chemical composition within one steel grade on hardenability, with a very broad and heterogeneous database used for studying hardness predictions. This article presents the second part of research conducted with neural networks.In the previous article [1] the most influential parameters were defined along with their weights and on the basis of these results, an improved model for predicting hardenability was develop… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0

Year Published

2014
2014
2023
2023

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 11 publications
(10 citation statements)
references
References 9 publications
0
10
0
Order By: Relevance
“…Because of our experiences with even bigger data bases we decided to use MLP neuronal networks [17][18][19][20]. This method enable us to select most influential parameters at the beginning of the analysis and latter to find rules which can describe how they effect hydrogen content in steel melt.…”
Section: Our Experiences With Changes In Hydrogen Content In Other Stmentioning
confidence: 99%
“…Because of our experiences with even bigger data bases we decided to use MLP neuronal networks [17][18][19][20]. This method enable us to select most influential parameters at the beginning of the analysis and latter to find rules which can describe how they effect hydrogen content in steel melt.…”
Section: Our Experiences With Changes In Hydrogen Content In Other Stmentioning
confidence: 99%
“…Further similar works have been developed by Dobrazanski and Sitek on different constructional steels [32,33] and, more recently, by Knap et al on special microalloyed steel grades [34,35]. On the other hand, Pouraliakbar et al developed a study related to a particular class of pipeline steels by using as input of the NN both some elements of the chemical composition but also other mechanical properties, i.e.…”
Section: Data-driven Approaches To Forecast Steel Hardenabilitymentioning
confidence: 94%
“…The determination of elongation of the tested samples allows the graphs to be used for the identification of the elasticity modulus, and for developing a flow stress model for numerical simulations of the steel continuous casting process [10][11].…”
Section: Resultsmentioning
confidence: 99%