Structural performance assessment of GFRP elastic gridshells by machine learning interpretability methods

被引:14
作者
Kookalani, Soheila [1 ]
Cheng, Bin [1 ]
Torres, Jose Luis Chavez [2 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Civil Engn, Shanghai 200240, Peoples R China
[2] Tech Univ Loja, Dept Civil Engn, Loja 110102, Ecuador
基金
中国国家自然科学基金;
关键词
machine learning; gridshell structure; regression; sensitivity analysis; interpretability methods; REGRESSION;
D O I
10.1007/s11709-022-0858-5
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The prediction of structural performance plays a significant role in damage assessment of glass fiber reinforcement polymer (GFRP) elastic gridshell structures. Machine learning (ML) approaches are implemented in this study, to predict maximum stress and displacement of GFRP elastic gridshell structures. Several ML algorithms, including linear regression (LR), ridge regression (RR), support vector regression (SVR), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), category boosting (CatBoost), and light gradient boosting machine (LightGBM), are implemented in this study. Output features of structural performance considered in this study are the maximum stress as f(1)(x) and the maximum displacement to self-weight ratio as f(2)(x). A comparative study is conducted and the Catboost model presents the highest prediction accuracy. Finally, interpretable ML approaches, including shapely additive explanations (SHAP), partial dependence plot (PDP), and accumulated local effects (ALE), are applied to explain the predictions. SHAP is employed to describe the importance of each variable to structural performance both locally and globally. The results of sensitivity analysis (SA), feature importance of the CatBoost model and SHAP approach indicate the same parameters as the most significant variables for f(1)(x) and f(2)(x).
引用
收藏
页码:1249 / 1266
页数:18
相关论文
共 50 条
[41]   ANALYSING MACHINE LEARNING METHODS AND CREDIT RISK ASSESSMENT [J].
Coelho, Felipe Fernandes ;
de Lima Amorim, Daniel Penido ;
de Camargos, Marcos Antonio .
REVISTA GESTAO & TECNOLOGIA-JOURNAL OF MANAGEMENT AND TECHNOLOGY, 2021, 21 (01) :89-116
[42]   Critical assessment of regression-based machine learning methods for polymer dielectrics [J].
Mannodi-Kanakkithodi, Arun ;
Pilania, Ghanshyam ;
Ramprasad, Rampi .
COMPUTATIONAL MATERIALS SCIENCE, 2016, 125 :123-135
[43]   A Review on Bayesian Methods for Uncertainty Quantification in Machine Learning Models Enhancing Predictive Accuracy and Model Interpretability [J].
Jiet, Moses Makuei ;
Verma, Prateek ;
Kamble, Aahash ;
Puri, Chetan .
2024 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT CYBER PHYSICAL SYSTEMS AND INTERNET OF THINGS, ICOICI 2024, 2024, :1671-1675
[44]   Estimation of the elastic modulus of basaltic rocks using machine learning methods [J].
Yesiloglu-Gultekin, Nurgul ;
Dogan, Ayhan .
EARTH SCIENCE INFORMATICS, 2024, 17 (06) :5941-5966
[45]   Performance Evaluation of Machine Learning Methods in Cultural Modeling [J].
Li, Xiao-Chen ;
Mao, Wen-Ji ;
Zeng, Daniel ;
Su, Peng ;
Wang, Fei-Yue .
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2009, 24 (06) :1010-1017
[46]   Quantifying performance of machine learning methods for neuroimaging data [J].
Jollans, Lee ;
Boyle, Rory ;
Artiges, Eric ;
Banaschewski, Tobias ;
Desrivieres, Sylvane ;
Grigis, Antoine ;
Martinot, Jean-Luc ;
Paus, Tomas ;
Smolka, Michael N. ;
Walter, Henrik ;
Schumann, Gunter ;
Garavan, Hugh ;
Whelan, Robert .
NEUROIMAGE, 2019, 199 :351-365
[47]   Performance Evaluation of Machine Learning Methods in Cultural Modeling [J].
李晓晨 ;
毛文吉 ;
曾大军 ;
苏鹏 ;
王飞跃 .
Journal of Computer Science & Technology, 2009, 24 (06) :1010-1017
[48]   Performance Evaluation of Machine Learning Methods in Cultural Modeling [J].
Xiao-Chen Li ;
Wen-Ji Mao ;
Daniel Zeng ;
Peng Su ;
Fei-Yue Wang .
Journal of Computer Science and Technology, 2009, 24 :1010-1017
[49]   Body Performance Analysis with Machine Learning and ANOVA Methods [J].
Sen, Huseyin Fatih ;
Taspinar, Yavuz Selim .
2024 21ST INTERNATIONAL CONFERENCE ON MECHATRONICS-MECHATRONIKA, ME 2024, 2024, :49-54
[50]   Performance optimization of a heat exchanger with coiled-wire turbulator insert by using various machine learning methods [J].
Celik, Nevin ;
Tasar, Beyda ;
Kapan, Sinan ;
Tanyildizi, Vedat .
INTERNATIONAL JOURNAL OF THERMAL SCIENCES, 2023, 192