Machine learning assisted axial strength prediction models for concrete filled stainless steel tubular columns
Bibliographic record
Abstract
Concrete filled stainless steel tubular (CFSST) columns have gained popularity over conventional concrete filled steel tubular (CFST) columns owing to their higher axial capacity and excellent corrosion resistance of stainless steel (SS). Numerous experimental and numerical research have been performed to evaluate CFSST column response under different loading scenarios. Despite all these studies, inaccuracy still exists in predicting the axial strength of CFSST columns. Moreover, unique properties of SS do not allow using conventional code equations developed for CFST columns to be used for axial strength prediction of CFSST columns. To this end, this study aims to develop data-driven machine learning (ML) techniques for predicting the axial capacity of CFSST columns. A comprehensive dataset of 422 circular and rectangular CFSST columns are carefully gathered from literature, which is employed for developing the data-driven ML models. Model accuracy is assessed using various performance metrics such as coefficient of determination (R 2 ), root mean square error ( RMSE ), mean absolute error ( MAE) , Nash-Sutcliffe Model (NSE ) and Index of Agreement ( d ). Out of the ten ML algorithms considered in this study, CatBoost (CatB) turns out to be the most accurate one. SHapley Additive exPlanations (SHAP) analysis is performed to interpret the outcomes of the ML model and explain the importance of each input feature. The best performing CatB model is compared with six different design code equations to showcase its acceptance and superior performance. It is observed that the ML model provides a quick and accurate estimate of the axial capacity of CFSST columns by overcoming the limitations of existing design codes. For identifying the resistance factor for the CatB model, reliability analysis is also performed following AISC 360–16 provision. Finally, an interactive graphical user interface is developed for practicing engineers to enhance the accuracy of CFSST axial capacity prediction while promoting the use of interpretable ML models.
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 | 0.001 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".