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 stud...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 f1(x)and the maximum displacement to self-weight ratio as f2(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 f1(x)and f2(x).展开更多
An elastic gridshell is an efficient constructive typology for crossing large spans with little material.A flat elastic grid is built before buckling the structure into shape,in active and post-formed bending.The desi...An elastic gridshell is an efficient constructive typology for crossing large spans with little material.A flat elastic grid is built before buckling the structure into shape,in active and post-formed bending.The design and structural analysis of such a structure requires a stage of form finding that can mainly be done:(1)With a physical model:either by a suspended net method,or an active bending model;(2)With a numerical model performed by dynamic relaxation.All these solutions have various biases and assumptions that make them reflect more or less the reality.These three methods have been applied by Happold and Liddell[1]during the design of the Frei Otto’s Mannheim Gridshell which has allowed us to compare the results,and to highlight the significant differences between digital and physical models.Based on our own algorithm called ELASTICA[2],our study focuses on:(1)Comparing the results of the ELASTICA’s numerical models to load tests on physical models;(2)The identification of the various factors that can influence the results and explain the observed differences,some of which are then studied;(3)Applying the results to build a full-scale interlaced lattice elastic gridshell based on the Japanese Kagome pattern.展开更多
基金The research work was supported by the National Natural Science Foundation of China(Grant No.51978400)the National Key Research and Development Program of China(No.2021YFE0107800).The support is gratefully acknowledged.
文摘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 f1(x)and the maximum displacement to self-weight ratio as f2(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 f1(x)and f2(x).
文摘An elastic gridshell is an efficient constructive typology for crossing large spans with little material.A flat elastic grid is built before buckling the structure into shape,in active and post-formed bending.The design and structural analysis of such a structure requires a stage of form finding that can mainly be done:(1)With a physical model:either by a suspended net method,or an active bending model;(2)With a numerical model performed by dynamic relaxation.All these solutions have various biases and assumptions that make them reflect more or less the reality.These three methods have been applied by Happold and Liddell[1]during the design of the Frei Otto’s Mannheim Gridshell which has allowed us to compare the results,and to highlight the significant differences between digital and physical models.Based on our own algorithm called ELASTICA[2],our study focuses on:(1)Comparing the results of the ELASTICA’s numerical models to load tests on physical models;(2)The identification of the various factors that can influence the results and explain the observed differences,some of which are then studied;(3)Applying the results to build a full-scale interlaced lattice elastic gridshell based on the Japanese Kagome pattern.
