Neural network analysis of oxygen in weld metals
Source abstract
Abstract
The fine acicular ferrite microstructure in the weld metal that results in both good strength and toughness is the result of various oxides that form during solidification. The intent of this paper is to develop a neural networks for the Vickers hardness number as a function of composition and cooling time from 800 to 500°C. The predictive capability of the neural network will then be used to examine the effect of oxygen and its oxides and nitrogen and its nitrides on the Vickers hardness number.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Non-Destructive Testing Techniques · Advanced machining processes and optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Eamweld LLC, Alexandria, VA, 22308, USA
Colorado School of Mines, Golden, CO, 80401, USA
Osaka University, 11-1 Mihogaoka, Ibaraki, Osaka, 567 0047, Japan
References (12)
Show source-provided references
1. Honeycombe R. W. K., and Bhadeshia H. K. D. H. ‘Steels microstructure and properties’, 2nd ed, Chapter 7; 1995, London, Edward Arnold.
2. Yurioka N., Fujii H., and Ichikawa K. ‘A Baysian neural network analysis of tensile strength, FATT, and hardness of large-heat- input saw welds, Report II – effect of Al/O on toughness’, IIW Doc. IX–1962–00.
3. Yurioka N. ‘Prediction of strength of weld metal (Report I), IIW Doc. IX–1992–01.
4. Yurioka N. ‘Prediction of strength of weld metal (Report II), IIW Doc. IX–2026–02.
5. 10.1162/neco.1992.4.3.44810.1162/neco.1992.4.3.448 ↗
6. 10.2355/isijinternational.39.96610.2355/isijinternational.39.966 ↗
7. 10.1179/13621710010153813710.1179/136217100101538137 ↗
8. 10.1179/13621710010153814610.1179/136217100101538146 ↗
9. 10.1179/13621710110153862210.1179/136217101101538622 ↗
10. 10.1179/stw.2001.6.6.36810.1179/stw.2001.6.6.368 ↗
11. McKay D. J. C.: in ‘Mathematical modelling of weld phenomena 3’, (ed. H. Cerjak), 359–389; 1997, London, The Institute of Materials.
12. 10.1016/0001-6160(85)90238-X10.1016/0001-6160(85)90238-X ↗