A novel data-driven machine learning techniques to predict compressive strength of fly ash and recycled coarse aggregates based self-compacting concrete

• Published in: Materials today communications 2024-06, Vol.39, p.109294, Article 109294
• Main Authors: Aggarwal, Somanshi, Singh, Rajwinder, Rathore, Ayush, Kapoor, Kanish, Patel, Mahesh
• Format: Article
• Language: English
• Subjects: Compressive strength; Fly ash; Graphical user interface; Machine learning; Recycled coarse aggregate
• ISSN: 2352-4928; 2352-4928
• DOI: 10.1016/j.mtcomm.2024.109294

Compressive strength (CS) of concrete is one of the most important factors in the construction industry and various time and effort-consuming tasks are required to measure it. To tackle such problems, the use of machine learning (ML), a branch of artificial intelligence, has recently resulted in a dramatic revolution in the construction sector, resulting in increased efficiency, accuracy, and creativity. Taking these factors into consideration, the current research was conducted on concrete manufactured with recycled coarse aggregate and fly ash generated as a byproduct of construction and demolition activities and thermal power plants. A large dataset consisting of 444 data points, along with ten input parameters, has been collected from the literature to forecast the CS of fly ash and recycled coarse aggregate-based self-compacting concrete. In this regard, ten advanced ML models, including K-Nearest Neighbors (KNN), Extra Tree Regressor (ETR), Bagging Regressor (BR), Adaboost Regressor (AR), Extreme Gradient Boosting (XGB), Linear Regression (LR), Random Forest (RF), Decision Tree Regression (DTR), Support Vector Regression (SVR) and Gradient Boosting Regression (GBR) have been considered. Furthermore, various data visualization plots and model’s performance matrices such as scatter plot, histograms, heatmaps, Shapley Additive Explanation (SHAP) Analysis, Regression Error Characteristics (REC), and errors have been utilized. In order to evaluate the most influential input parameter and depict the overall performance of ML models, sensitivity analysis and Taylor’s diagram are used. As a method of validation, the Kfold cross-validation approach has been implemented to justify the obtained output. Based on the outcome of the study, the BR model has displayed remarkable accuracy with insignificant errors and high R-squared values (R2 = 0.961), while XGB (R2 = 0.959), and DTR (R2 = 0.952) models also achieved commendable, as compared to other ML models. Additionally, water content, curing days, fly ash, and w/c ratio were found to be the most critical components that directly impact the CS of fly ash and RCA-based SCC. To cater to diverse and extensive practices, a graphical user interface has been developed to assist researchers and engineers in getting instant results of their fly ash and RCA-based SCC mixes prior to the execution of time- and resource-consuming laboratory work. [Display omitted]