daohang fenxiangbox searchbox qikanlogonew daohangnew searchboxnew navrightzone footerzone paper
中
Home > Journals > Case Studies in Construction Materials
‹ Previous Article Next Article ›

Predictive modeling for depth of wear of concrete modified with fly ash: A comparative analysis of genetic programming-based algorithms AITranslate

Adil Khan; Majid Khan; Mohsin Ali; Murad Khan; Asad Ullah Khan; Muhammad Shakeel; Muhammad Fawad; Taoufik Najeh; Yaser Gamil;
University of Bradford; COMSATS University; Southeast University Nanjing; Tianjin University; COMSATS University; University of Engineering and Technology; Poland|Budapest University of Technology and Economics Hungary; Lulea University of Technology; Monash University Malaysia
AITranslate
Publisher: Elsevier
Share Citation Information Add to Favorites

    Scan to share on WeChat or Moments

Use WeChat scan.
Share with WeChat friends or Moments

Abstract AITranslate

There has been increasing growth in incorporating fly ash as a supplementary cementitious material in concrete mixtures due to its potential to enhance the durability and strength properties of concrete. However, there is a lack of research on predicting the depth of wear of fly ash-based concrete. The laboratory methods available for estimating the depth of wear often involve destructive and expensive tests. Therefore, to avoid costly and laborious tests, this study utilized two machine learning methods, including multi-expression programming (MEP) and gene expression programming (GEP), to predict the depth of wear of fly ash-modified concrete. A comprehensive dataset of 216 experimental records was compiled from published studies for model training and validation. This extensive dataset encompasses the depth of wear as the target variable, along with nine explanatory parameters, namely fly ash, cement content, fine and coarse aggregate, water content, plasticizer, age of concrete, air-entraining agent, and testing time. The models were trained with 70% of the data, and the remaining 30% of data was used for validating the models. The models were developed by a continuous trial-and-error process and iterative refinement of hyperparameters until optimal results were achieved. The efficacy of the models was assessed via multiple statistical indicators. Furthermore, the SHapley Additive exPlanation (SHAP) was utilized for the interpretability of the model prediction from both global and local perspectives. The GEP model exhibited excellent accuracy with a correlation coefficient (R) of 0.989 (training) and 0.992 (validation). Similarly, the MEP model provided prediction accuracy with R values of 0.965 and 0.968 for training and validation sets, respectively. In addition, the MEP and GEP models outperformed the traditional multi-linear regression model. The SHAP interpretation revealed that testing time and age have a higher contribution in determining the depth of wear. The findings of this study can assist practitioners and designers in avoiding costly and laborious tests for durability assessment and promoting sustainable use of fly ash in the construction sector.

KeyWords AITranslate

A Age Age AE Airentraining agent Airentraining agent ANN Artificial neural network Artificial neural network AR AdaBoost regressor AdaBoost regressor BR Bagging regressor Bagging regressor C Cement Cement CA Coarse aggregate Coarse aggregate CS Compressive strength Compressive strength DT Decision tree Decision tree DW Depth of wear Depth of wear ETs Expression trees Expression trees F Fly ash Fly ash FA Fine aggregate Fine aggregate GEP Gene expression programming Gene expression programming GP Genetic programming Genetic programming IQR Interquartile range Interquartile range LIME Local interpretable modelagnostic explanations Local interpretable modelagnostic explanations MAE Mean absolute error Mean absolute error MEP Multi expression programming Multi expression programming ML Machine learning Machine learning MLR Multi variable linear regression Multi variable linear regression M5P Model tree algorithm Model tree algorithm OF Objective function Objective function PC Portland cement Portland cement P Plasticizers Plasticizers ρ Performance index Performance index R Correlation coefficient Correlation coefficient RF Random forest Random forest RMSE Root mean square error Root mean square error RRMSE Relative root mean square error Relative root mean square error SCC Selfconsolidating concrete Selfconsolidating concrete SHAP SHapley Additive exPlanations SHapley Additive exPlanations T Time of testing Time of testing XAI Explainable artificial intelligence Explainable artificial intelligence Fly ash Abrasion resistance Gene expression programming Multiexpression programming SHAP
No data

Basic Information:

DOI：https://doi.org/10.1016/j.cscm.2023.e02744

Chinese Library Classification Number:

Citation Information:

There has been increasing growth in incorporating fly ash as a supplementary cementitious material in concrete mixtures due to its potential to enhance the durability and strength properties of concrete. However, there is a lack of research on predicting the depth of wear of fly ash-based concrete. The laboratory methods available for estimating the depth of wear often involve destructive and expensive tests. Therefore, to avoid costly and laborious tests, this study utilized two machine learning methods, including multi-expression programming (MEP) and gene expression programming (GEP), to predict the depth of wear of fly ash-modified concrete. A comprehensive dataset of 216 experimental records was compiled from published studies for model training and validation. This extensive dataset encompasses the depth of wear as the target variable, along with nine explanatory parameters, namely fly ash, cement content, fine and coarse aggregate, water content, plasticizer, age of concrete, air-entraining agent, and testing time. The models were trained with 70% of the data, and the remaining 30% of data was used for validating the models. The models were developed by a continuous trial-and-error process and iterative refinement of hyperparameters until optimal results were achieved. The efficacy of the models was assessed via multiple statistical indicators. Furthermore, the SHapley Additive exPlanation (SHAP) was utilized for the interpretability of the model prediction from both global and local perspectives. The GEP model exhibited excellent accuracy with a correlation coefficient (R) of 0.989 (training) and 0.992 (validation). Similarly, the MEP model provided prediction accuracy with R values of 0.965 and 0.968 for training and validation sets, respectively. In addition, the MEP and GEP models outperformed the traditional multi-linear regression model. The SHAP interpretation revealed that testing time and age have a higher contribution in determining the depth of wear. The findings of this study can assist practitioners and designers in avoiding costly and laborious tests for durability assessment and promoting sustainable use of fly ash in the construction sector.

quote

GB/T 7714-2015 [1] Adil Khan, Majid Khan, Mohsin Ali, et al. Case Studies in Construction Materials, 2024(20). DOI:10.1016/j.cscm.2023.e02744.
MLA [1] Adil Khan, et al., Case Studies in Construction Materials, no. 20, 2024, https://doi.org/10.1016/j.cscm.2023.e02744.
APA [1] Adil Khan, Majid Khan, Mohsin Ali, Murad Khan, Asad Ullah Khan, Muhammad Shakeel, Muhammad Fawad, Taoufik Najeh, & Yaser Gamil. (2024). Case Studies in Construction Materials(20). https://doi.org/10.1016/j.cscm.2023.e02744
IEEE [1] Adil Khan, Majid Khan, Mohsin Ali, Murad Khan, Asad Ullah Khan, Muhammad Shakeel, Muhammad Fawad, Taoufik Najeh, and Yaser Gamil, Case Studies in Construction Materials, no. 20, 2024, doi: 10.1016/j.cscm.2023.e02744. keywords: {A Age;Age;AE Airentraining agent;Airentraining agent;ANN Artificial neural network;Artificial neural network;AR AdaBoost regressor;AdaBoost regressor;BR Bagging regressor;Bagging regressor;C Cement;Cement;CA Coarse aggregate;Coarse aggregate;CS Compressive strength;Compressive strength;DT Decision tree;Decision tree;DW Depth of wear;Depth of wear;ETs Expression trees;Expression trees;F Fly ash;Fly ash;FA Fine aggregate;Fine aggregate;GEP Gene expression programming;Gene expression programming;GP Genetic programming;Genetic programming;IQR Interquartile range;Interquartile range;LIME Local interpretable modelagnostic explanations;Local interpretable modelagnostic explanations;MAE Mean absolute error;Mean absolute error;MEP Multi expression programming;Multi expression programming;ML Machine learning;Machine learning;MLR Multi variable linear regression;Multi variable linear regression;M5P Model tree algorithm;Model tree algorithm;OF Objective function;Objective function;PC Portland cement;Portland cement;P Plasticizers;Plasticizers;ρ Performance index;Performance index;R Correlation coefficient;Correlation coefficient;RF Random forest;Random forest;RMSE Root mean square error;Root mean square error;RRMSE Relative root mean square error;Relative root mean square error;SCC Selfconsolidating concrete;Selfconsolidating concrete;SHAP SHapley Additive exPlanations;SHapley Additive exPlanations;T Time of testing;Time of testing;XAI Explainable artificial intelligence;Explainable artificial intelligence;Fly ash;Abrasion resistance;Gene expression programming;Multiexpression programming;SHAP}