Analyzing the compressive strength, eco-strength, and cost–strength ratio of agro-waste-derived concrete using advanced machine learning methods DOI Creative Commons
Muhammad Nasir Amin, Bawar Iftikhar,

Kaffayatullah Khan

и другие.

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2025, Номер 64(1)

Опубликована: Янв. 1, 2025

Abstract Agro-waste like eggshell powder (ESP) and date palm ash (DPA) are used as supplementary cementitious materials (SCMs) in concrete because of their pozzolanic attributes well environmental cost benefits. In addition, performing lab tests to optimize mixed proportions with different SCMs takes considerable time effort. Therefore, the creation estimation models for such purposes is vital. This study aimed create interpretable prediction compressive strength (CS), eco-strength (ECR), cost–strength ratio (CSR) DPA–ESP concrete. Gene expression programming (GEP) was employed model generation via hyperparameter optimization method. Also, importance input features determined SHapley Additive exPlanations (SHAP) analysis. The GEP accurately matched experimental results CS, ECR, CSR These can be future predictions, reducing need additional saving effort, time, costs. model’s accuracy confirmed by an R 2 value 0.94 high values 0.91 ECR 0.92 CSR, lower statistical checks. SHAP analysis suggested that test age most critical factor all outcomes.

Язык: Английский

Analyzing the compressive strength, eco-strength, and cost–strength ratio of agro-waste-derived concrete using advanced machine learning methods DOI Creative Commons
Muhammad Nasir Amin, Bawar Iftikhar,

Kaffayatullah Khan

и другие.

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2025, Номер 64(1)

Опубликована: Янв. 1, 2025

Abstract Agro-waste like eggshell powder (ESP) and date palm ash (DPA) are used as supplementary cementitious materials (SCMs) in concrete because of their pozzolanic attributes well environmental cost benefits. In addition, performing lab tests to optimize mixed proportions with different SCMs takes considerable time effort. Therefore, the creation estimation models for such purposes is vital. This study aimed create interpretable prediction compressive strength (CS), eco-strength (ECR), cost–strength ratio (CSR) DPA–ESP concrete. Gene expression programming (GEP) was employed model generation via hyperparameter optimization method. Also, importance input features determined SHapley Additive exPlanations (SHAP) analysis. The GEP accurately matched experimental results CS, ECR, CSR These can be future predictions, reducing need additional saving effort, time, costs. model’s accuracy confirmed by an R 2 value 0.94 high values 0.91 ECR 0.92 CSR, lower statistical checks. SHAP analysis suggested that test age most critical factor all outcomes.

Язык: Английский

Процитировано

0