A physics-regularized machine learning approach for predicting time-temperature-transformation curves in alloys: application to uranium-based alloys
Sunidhi Garg, Jishnu Bhattacharyya, Vineet V Joshi, Sean R Agnew, Prasanna V Balachandran · 2026
Read A physics-regularized machine learning approach for predicting time-temperature-transformation curves in alloys: application to uranium-based alloys by Sunidhi Garg, Jishnu Bhattacharyya, Vineet V Joshi, Sean R Agnew, Prasanna V Balachandran (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13507102.txt.
Description
Sunidhi Garg and colleagues develop, in 2026 work, a machine learning method that predicts phase change charts for uranium alloys while respecting physical shape rules. The charts, called time-temperature-transformation diagrams, show how fast a solid phase changes at each heat level. Lab mapping of each alloy is slow and costly, which limits alloy search.
They tested four training goals, from plain error fitting to versions that enforce the classic C-curve bend and nucleation physics. Shape-aware models gave realistic curves that matched lab data well. The best model flagged five uranium mixes with molybdenum plus a third metal as more stable than the base mix. Faster screening could focus costly lab work.
Catalog record
| CREATOR | Sunidhi Garg, Jishnu Bhattacharyya, Vineet V Joshi, Sean R Agnew, Prasanna V Balachandran |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68586 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |