Interpretable machine learning with Bayesian optimization for bond strength prediction of steel reinforcement in geopolymer concrete
Viet Hung Tran, Viet Hai Hoang, Quang Minh Tran · 2026
Read Interpretable machine learning with Bayesian optimization for bond strength prediction of steel reinforcement in geopolymer concrete by Viet Hung Tran, Viet Hai Hoang, Quang Minh Tran (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/plos-pone-0352645.txt.
Description
Tran, Hoang, and Tran built a learning system to predict how well steel bars grip eco-friendly concrete in a 2026 study. The concrete uses industrial byproducts instead of cement, but its grip on steel is hard to estimate with old formulas. A database of nearly two hundred forty published tests with twenty input factors fed six learning methods.
All methods predicted grip strength well after automated tuning of their settings. The best tuned model also allowed interpretation of which factors drive grip. Reliable prediction supports safe design of greener structures, where engineers cannot lean on decades of cement-based experience.
Catalog record
| CREATOR | Viet Hung Tran, Viet Hai Hoang, Quang Minh Tran |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 85550 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |