daohang fenxiangbox searchbox qikanlogonew daohangnew searchboxnew navrightzone footerzone paper
English
Chinese 简体中文 English English
Home > Journals > Case Studies in Construction Materials
‹ Previous Article Next Article ›

Interpretable ensemble machine-learning models for strength activity index prediction of iron ore tailings AITranslate

Zhuxin Cheng; Yingchun Yang; Haoyou Zhang
Anhui Agricultural University; Anhui Agricultural University; Beijing University of Technology
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

When iron ore tailings (IOTs) are used as supplementary cementitious materials, their strength activity index is an important factor affecting the mechanical properties of IOTs-cement composites. In this study, four ensemble machine learning (ML) models, including Gradient Boosting Regression Tree (GBRT), EXtreme Gradient Boosting (XGBoost), Adaptive Boosting (Adaboost), and Categorical Boosting (Catboost), were used to predict the strength activity index of IOTs. Shapley additive explanations (SHAP) were also utilized to measure the impact of influencing elements in the strength activity index of IOTs. Results showed that the R2 values of all four models were above 0.83 on the testing set. Dosage, water-solid ratio, and D0.5 particle size were found to be the most important factors affecting the strength activity index of IOTs. For high-silica IOTs, the strength activity index increased with the increase of dosage when the dosage was less than 10%, while when the dosage was higher than 10%, the opposite situation occurred. However, for low-silica IOTs, the strength activity index decreased continuously with the increase of dosage. This research developed a new approach for predicting the strength activity index of IOTs and provided some suggestions for the application of IOTs in cement-based materials.

KeyWords AITranslate

IOTs Iron ore tailings Iron ore tailings SHAP SHapley Additive exPlanations SHapley Additive exPlanations D0.5 PS D0.5 particle size D0.5 particle size SAI strength activity index strength activity index WSR Watersolid ratio Watersolid ratio GBRT Gradient Boosting Regression Tree Gradient Boosting Regression Tree XGBoost EXtreme Gradient Boosting EXtreme Gradient Boosting Adaboost Adaptive Boosting Adaptive Boosting Catboost Categorical Boosting Categorical Boosting RF Random Forest Random Forest GBDT Gradient Boosting Decision Tree Gradient Boosting Decision Tree ANN Artificial Neural Network Artificial Neural Network LR Linear Regression Linear Regression GPR Gaussian Process Regression Gaussian Process Regression MLP MultiLayer Perceptron MultiLayer Perceptron DT Decision Tree Decision Tree LASSO Lasso Regressor Lasso Regressor SVM Support Vector Machine Support Vector Machine Iron ore tailings Strength activity index Ensemble model Machine learning (ML) Interpretation SHapley Additive exPlanations (SHAP)
No data

Basic Information:

DOI：https://doi.org/10.1016/j.cscm.2022.e01239

Chinese Library Classification Number:

Citation Information:

When iron ore tailings (IOTs) are used as supplementary cementitious materials, their strength activity index is an important factor affecting the mechanical properties of IOTs-cement composites. In this study, four ensemble machine learning (ML) models, including Gradient Boosting Regression Tree (GBRT), EXtreme Gradient Boosting (XGBoost), Adaptive Boosting (Adaboost), and Categorical Boosting (Catboost), were used to predict the strength activity index of IOTs. Shapley additive explanations (SHAP) were also utilized to measure the impact of influencing elements in the strength activity index of IOTs. Results showed that the R2 values of all four models were above 0.83 on the testing set. Dosage, water-solid ratio, and D0.5 particle size were found to be the most important factors affecting the strength activity index of IOTs. For high-silica IOTs, the strength activity index increased with the increase of dosage when the dosage was less than 10%, while when the dosage was higher than 10%, the opposite situation occurred. However, for low-silica IOTs, the strength activity index decreased continuously with the increase of dosage. This research developed a new approach for predicting the strength activity index of IOTs and provided some suggestions for the application of IOTs in cement-based materials.

quote

GB/T 7714-2015 [1] Zhuxin Cheng, Yingchun Yang, Haoyou Zhang. Case Studies in Construction Materials, 2022(17). DOI:10.1016/j.cscm.2022.e01239.
MLA [1] Zhuxin Cheng, et al., Case Studies in Construction Materials, no. 17, 2022, https://doi.org/10.1016/j.cscm.2022.e01239.
APA [1] Zhuxin Cheng, Yingchun Yang, & Haoyou Zhang. (2022). Case Studies in Construction Materials(17). https://doi.org/10.1016/j.cscm.2022.e01239
IEEE [1] Zhuxin Cheng, Yingchun Yang, and Haoyou Zhang, Case Studies in Construction Materials, no. 17, 2022, doi: 10.1016/j.cscm.2022.e01239. keywords: {IOTs Iron ore tailings;Iron ore tailings;SHAP SHapley Additive exPlanations;SHapley Additive exPlanations;D0.5 PS D0.5 particle size;D0.5 particle size;SAI strength activity index;strength activity index;WSR Watersolid ratio;Watersolid ratio;GBRT Gradient Boosting Regression Tree;Gradient Boosting Regression Tree;XGBoost EXtreme Gradient Boosting;EXtreme Gradient Boosting;Adaboost Adaptive Boosting;Adaptive Boosting;Catboost Categorical Boosting;Categorical Boosting;RF Random Forest;Random Forest;GBDT Gradient Boosting Decision Tree;Gradient Boosting Decision Tree;ANN Artificial Neural Network;Artificial Neural Network;LR Linear Regression;Linear Regression;GPR Gaussian Process Regression;Gaussian Process Regression;MLP MultiLayer Perceptron;MultiLayer Perceptron;DT Decision Tree;Decision Tree;LASSO Lasso Regressor;Lasso Regressor;SVM Support Vector Machine;Support Vector Machine;Iron ore tailings;Strength activity index;Ensemble model;Machine learning (ML);Interpretation;SHapley Additive exPlanations (SHAP)}