SHAP-based prediction and optimization of compressive strength in M30 concrete with dry sewage sludge as fine aggregate replacement

Abstract

This study explores the feasibility of using dry sewage sludge (DSS), as a partial replacement for fine aggregates in concrete. Once dried, DSS becomes a sand-like material with potential as a sustainable construction alternative. However, concerns exist regarding environmental and Health risks, such as pathogen presence And Heavy metal leaching. Proper treatment of sludge significantly reduces the organic content And microbial contaminants. The concrete mixtures were developed with DSS replacing 3–12% of the fine aggregates by weight. Workability was measured via the slump test, And mechanical properties, including compressive, split tensile, And flexural strengths, were evaluated at 7, 14, And 28 days. At 3% replacement (DSS3), the slump was 85 mm, which was close to that of the control mixture (95 mm). The compressive strength at 28 days reached 37 MPa, whereas it reached 39 MPa for the control. DSS3 also achieved a split tensile strength of 6.3 MPa And flexural strength of 7.2 MPa, indicating minimal performance loss. Higher DSS levels negatively affected both workability and strength. To enhance prediction and optimization, the machine learning models multilayer perceptron (MLP), random forest (RF), and decision tree (DT) were applied. The random forest model outperformed the other models, with An RMSE of 2.35, An MAE of 1.75, and an R² of 0.96. SHAP Analysis revealed that the curing time, cement content, And water-to-cement ratio are key factors influencing strength. Overall, 3% DSS replacement offers a viable sustainable alternative, although further research is needed on long-term durability and environmental performance.