A novel framework for developing environmentally sustainable and cost-effective ultra-high-performance concrete (UHPC) using advanced machine learning and multi-objective optimization techniques
Bibliographic record
Abstract
This study aims to propose a novel framework for strength prediction and multi-objective optimization (MOO) of economical and environmentally sustainable ultra-high-performance concrete (UHPC) which aids in intelligent, sustainable, and resilient construction. Different tree- and boosting ensemble-based machine learning (ML) models are integrated to form an accurate and reliable prediction model for the uniaxial compressive strength of UHPC. The optimized models are integrated into a super learner model, resulting in a robust predictive model that is used as one of the objective functions in the MOO problem. A total of 19 objective functions are considered, including cost, uniaxial compressive strength, and 17 environmental impact categories that comprehensively evaluate the environmental sustainability of the UHPC mix. The resulting impacts from the mid-point indicators were calculated using the Eco-invent v3.7 Life Cycle Inventory database. The results showed that the super learner model accurately predicted the uniaxial compressive strength of UHPC. The MOO resulted in Pareto fronts, demonstrating the trade-off among the uniaxial compressive strength, cost, and environmental sustainability of the mix and a broad range of solutions that can be obtained for the 19 objectives. The study provides a useful tool for designers and decision-makers to select the optimal UHPC mixture that meets specific project requirements. Finally, for the practical application of the ML predictive model and MOO algorithm for UHPC, a graphical user interface-based software tool, FAI-OSUSCONCRET, was developed. This software tool offers fast, accurate, and intelligent predictions and multi-objective optimizations tailored to specific project requirements, thus resulting in a UHPC mixture that perfectly meets project needs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".