Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods
Highlights Innovative ML models were integrated to predict the chloride resistance of RAC. Model interpretability was improved by SRC and partial dependence analysis. A mixture design method and a service life prediction approach were proposed.
Abstract This study investigates the feasibility of introducing machine learning algorithms to predict the diffusion resistance to chloride penetration of recycled aggregate concrete (RAC). A total of 226 samples collated from published literature were used to train and test the developed machine learning framework, which integrated four standalone models and two ensemble models. The hyperparameters involved were fine-tuned by grid search and 10-fold cross-validation. Results showed that all the models had good performance in predicting the chloride penetration resistance of RAC and among them, the gradient boosting model outperformed the others. The water content was identified as the most critical factor affecting the chloride ion permeability of RAC based on the standardized regression coefficient analysis. The model’s interpretability was greatly improved through a two-way partial dependence analysis. Finally, based on the proposed machine learning models, a performance-based mixture design method and a service life prediction approach for RAC were developed, thereby offering novel and robust design tools for achieving more durable and resilient development goals in procuring sustainable concrete.
Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods
Highlights Innovative ML models were integrated to predict the chloride resistance of RAC. Model interpretability was improved by SRC and partial dependence analysis. A mixture design method and a service life prediction approach were proposed.
Abstract This study investigates the feasibility of introducing machine learning algorithms to predict the diffusion resistance to chloride penetration of recycled aggregate concrete (RAC). A total of 226 samples collated from published literature were used to train and test the developed machine learning framework, which integrated four standalone models and two ensemble models. The hyperparameters involved were fine-tuned by grid search and 10-fold cross-validation. Results showed that all the models had good performance in predicting the chloride penetration resistance of RAC and among them, the gradient boosting model outperformed the others. The water content was identified as the most critical factor affecting the chloride ion permeability of RAC based on the standardized regression coefficient analysis. The model’s interpretability was greatly improved through a two-way partial dependence analysis. Finally, based on the proposed machine learning models, a performance-based mixture design method and a service life prediction approach for RAC were developed, thereby offering novel and robust design tools for achieving more durable and resilient development goals in procuring sustainable concrete.
Innovative modeling framework of chloride resistance of recycled aggregate concrete using ensemble-machine-learning methods
Liu, Kai-Hua (Autor:in) / Zheng, Jia-Kai (Autor:in) / Pacheco-Torgal, Fernando (Autor:in) / Zhao, Xin-Yu (Autor:in)
20.04.2022
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
NA , natural aggregates , RA , recycled aggregates , RAC , recycled aggregate concrete , NAC , natural aggregate concrete , ML , machine learning , ANN , artificial neural network , GPR , Gaussian process regression , SVR , support vector regression , CART , classification and regression tree , RF , random forest , GBDT , gradient boosting decision trees , CEF , coulomb passed electric charge , RCM , rapid chloride ions migration coefficient , RMSE , root mean square error , SI , scattering index , MAPE , mean absolute percentage error , VIF , variance inflation factor , SRC , standardized regression coefficient , CSH , calcium silicate hydrate , Recycled aggregate concrete , Chloride penetration , Machine learning , Model interpretability , Mixture , Service life prediction
| DOAJ | 2023
Chloride Resistance of Recycled Aggregate Concrete under Wetting-Drying Cycles
| Trans Tech Publications | 2016