原文传递
Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls
| 题名： | Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls |
| 正文语种： | eng |
| 作者： | Feng, De-Cheng;Wang, Wen-Jie;Mangalathu, Sujith;Taciroglu, Ertugrul |
| 作者单位： | Southeast Univ Minist Educ Key Lab Concrete & Prestressed Concrete Struct Nanjing 211189 Peoples R China;Southeast Univ Sch Civil Engn Nanjing 211189 Peoples R China;Data Analyt Div Kollam 691507 Kerala India;Univ Calif Los Angeles Dept Civil & Environm Engn Los Angeles CA 90095 USA |
| 关键词： | Machine-learning (ML);Interpretation;eXtreme Gradient Boosting (XGBoost);Feature importance;SHapley Additive exPlanations (SHAP);Shear strength;Squat RC walls |
| 摘要： | RC shear walls are commonly used as lateral load-resisting elements in seismic regions, and the estimation of their shear strengths can become simultaneously design-critical and complex when they have so-called squat geometries, i.e., height-to-length ratios less than two. This paper presents a study on the training and interpretation of an advanced machine-learning model that strategically combines two algorithms for the said purpose. To train the model, a comprehensive shear strength database of 434 samples of squat RC walls is utilized. First, the eXtreme Gradient Boosting (XGBoost) algorithm is used to establish a predictive model for estimating the shear strength, wherein 70% and 30% of the data are respectively used for training and validation. This effort resulted in an approximately 97% validation accuracy, which well exceeds current mechanics-based/semiempirical models. Second, the SHapley Additive exPlanations (SHAP) algorithm is used to estimate the relative importance of the factors affecting XGBoost's shear strength estimates. This step thus enabled physical and quantitative interpretations of the input-output dependencies, which are nominally hidden in conventional machine-learning approaches. Through this setup, several squat wall attributes are identified as being critical in shear strength estimates. |
| 出版年： | 2021 |
| 期刊名称： | Journal of structural engineering |
| 卷： | 147 |
| 期： | 11 |
相关文献
- Peak Shear Strength of Flanged Reinforced Concrete Squat Walls
- Fragility and Economic Evaluations of High-Strength Reinforced Concrete Shear Walls in Nuclear Power Plants
- Prediction of the Lateral Load-Displacement Curves for Reinforced Concrete Squat Walls Failing in Shear
- Machine Learning–Based Failure Mode Recognition of Circular Reinforced Concrete Bridge Columns: Comparative Study
- Framework for Development and Comprehensive Comparison of Empirical Pavement Performance Models
- Probabilistic Machine-Learning Methods for Performance Prediction of Structure and Infrastructures through Natural Gradient Boosting
检索历史
应用推荐
