Hybrid intelligence framework for optimizing shear capacity of lightweight FRP-reinforced concrete beams
Bibliographic record
Abstract
This study rigorously assesses the shear capacity of Fiber Reinforced Polymer (FRP) reinforced concrete (RC) beams as a lightweight material alternative, scrutinizing the efficacy of the Eurocode and ACI design codes. Leveraging a dataset of 260 experimental FRP-RC beam cases, two distinct Artificial Neural Network (ANN) models were developed using the Levenberg-Marquardt algorithm. Beams with and without stirrups were considered, with parameters including beam width (), depth (), length (), concrete compressive strength (), FRP modulus of elasticity (, ) and FRP reinforcement ratios (, ). Multi-objective optimization was deployed to integrate Genetic Algorithms (GA) and fmincon to optimize beam parameters for maximizing the shear capacity, . Sensitivity analysis allowed to quantify the influence of each parameter, revealing that and significantly affect , with sensitivity scores of 0.39 and 0.35, respectively. The optimization process, highlighted by a 3D scatter plot, dynamically illustrated trade-offs among key design parameters (, , ), giving insights into the complex interplay in FRP beam design. The hybrid intelligence models reached superior predictive accuracy over traditional codes, achieving values of 0.89. Notably, for beams without stirrups, model predictions closely matched experimental data, with lower average ratio (1.02) compared to Eurocode (1.65) and ACI (1.58). Principal Component Analysis (PCA) unraveled complex variable relationships, enhancing the understanding of the structural behavior of FRP-RC beams. Integrating artificial intelligence, advanced optimization techniques, and rigorous statistical analyses coins a comprehensive framework for the structural analysis of FRP-RC beams, offering enhanced accuracy and insightful perspectives for future design optimization.
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 | 0.001 | 0.002 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".