Determining boride layer thicknesses formed on XC38 steel with artificial neural network
Boride layers result from surface treatments of materials, offering valuable mechanical and tribological aspects that extend the material's life expectancy and potential. They are achieved by a process known as boriding in which boron atoms are diffused into the material until saturation, where...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Engineering Society for Corrosion, Belgrade
2024-09-01
|
| Series: | Zaštita Materijala |
| Subjects: | |
| Online Access: | https://www.zastita-materijala.org/index.php/home/article/view/1221 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850232077041008640 |
|---|---|
| author | Yassine El Guerri Bendaoud Mebarek |
| author_facet | Yassine El Guerri Bendaoud Mebarek |
| author_sort | Yassine El Guerri |
| collection | DOAJ |
| description | Boride layers result from surface treatments of materials, offering valuable mechanical and tribological aspects that extend the material's life expectancy and potential. They are achieved by a process known as boriding in which boron atoms are diffused into the material until saturation, where a layer that may be mono or dual-phased begins to thicken over time depending on the period of treatment, the temperature held, the media applied, the composition of the material with its impurities, and more. Due to the difficulty of encompassing all those different parameters that influence the kinetic evolution of that boride layer, the idea was to start by training an artificial neural network to estimate its thickness with only two variables and inspect the results. Three experimental observations out of nine were used as validating data, while the rest were training data, along with others added. Depending on the reliability of the predictions given by the artificial neural network, further research can explore the possibilities of training it on different samples and environments through data mining. |
| format | Article |
| id | doaj-art-03ba5e37d8cb47459c7af3d3281dd490 |
| institution | OA Journals |
| issn | 0351-9465 2466-2585 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Engineering Society for Corrosion, Belgrade |
| record_format | Article |
| series | Zaštita Materijala |
| spelling | doaj-art-03ba5e37d8cb47459c7af3d3281dd4902025-08-20T02:03:18ZengEngineering Society for Corrosion, BelgradeZaštita Materijala0351-94652466-25852024-09-0165353454310.62638/ZasMat12211220Determining boride layer thicknesses formed on XC38 steel with artificial neural networkYassine El Guerri0https://orcid.org/0009-0008-9664-2361Bendaoud Mebarek1https://orcid.org/0000-0002-6838-3867Research Laboratory of Industrial Technologies, University of Tiaret, AlgeriaLaboratoire de Recherche en Intelligence Artificielle et Systèmes (LRIAS), University of Tiaret, AlgeriaBoride layers result from surface treatments of materials, offering valuable mechanical and tribological aspects that extend the material's life expectancy and potential. They are achieved by a process known as boriding in which boron atoms are diffused into the material until saturation, where a layer that may be mono or dual-phased begins to thicken over time depending on the period of treatment, the temperature held, the media applied, the composition of the material with its impurities, and more. Due to the difficulty of encompassing all those different parameters that influence the kinetic evolution of that boride layer, the idea was to start by training an artificial neural network to estimate its thickness with only two variables and inspect the results. Three experimental observations out of nine were used as validating data, while the rest were training data, along with others added. Depending on the reliability of the predictions given by the artificial neural network, further research can explore the possibilities of training it on different samples and environments through data mining.https://www.zastita-materijala.org/index.php/home/article/view/1221machine learning artificial neural network layer thicknessboride layersboriding |
| spellingShingle | Yassine El Guerri Bendaoud Mebarek Determining boride layer thicknesses formed on XC38 steel with artificial neural network Zaštita Materijala machine learning artificial neural network layer thickness boride layers boriding |
| title | Determining boride layer thicknesses formed on XC38 steel with artificial neural network |
| title_full | Determining boride layer thicknesses formed on XC38 steel with artificial neural network |
| title_fullStr | Determining boride layer thicknesses formed on XC38 steel with artificial neural network |
| title_full_unstemmed | Determining boride layer thicknesses formed on XC38 steel with artificial neural network |
| title_short | Determining boride layer thicknesses formed on XC38 steel with artificial neural network |
| title_sort | determining boride layer thicknesses formed on xc38 steel with artificial neural network |
| topic | machine learning artificial neural network layer thickness boride layers boriding |
| url | https://www.zastita-materijala.org/index.php/home/article/view/1221 |
| work_keys_str_mv | AT yassineelguerri determiningboridelayerthicknessesformedonxc38steelwithartificialneuralnetwork AT bendaoudmebarek determiningboridelayerthicknessesformedonxc38steelwithartificialneuralnetwork |