Evaluating the Tensile Strength of Reinforced Concrete using Optimized Machine Learning Techniques

• Published in: Engineering fracture mechanics 2023-11, Vol.292, p.109677, Article 109677
• Main Authors: Albaijan, Ibrahim, Mahmoodzadeh, Arsalan, Flaih, Laith R., Hashim Ibrahim, Hawkar, Alashker, Yasser, Hussein Mohammed, Adil
• Format: Article
• Language: English
• Subjects: machine learning; manufactured-sand concrete; splitting tensile strength; stone nano-powder
• ISSN: 0013-7944; 1873-7315
• DOI: 10.1016/j.engfracmech.2023.109677

•Using manufactured-sand and natural pozzolana in the production of concrete.•Proposing ML models to facilitate the production of manufactured-sand concrete (MSC)•Employing a database containing 9 features effective on the tensile strength of MSC.•Study the effect of stone nano powder, water/cement, and curing age on the MSC.•Comparison of the ML models’ behavior with the laboratory tests. Many environmental issues have arisen as a result of the widespread usage of concrete, which has led to a reduction of river sand. The excessive extraction of river sand has led to various negative consequences, such as ecosystem disruption, groundwater depletion, coastal erosion, and biodiversity loss. Manufactured sand (MS) from waste deposits may be used in lieu of river sand to address this problem. In this study, to facilitate the production of manufactured sand concrete (MSC), the potential of twelve machine learning (ML)-based models was examined. These models were trained and tested on 248 and 62 laboratory datasets containing nine features effective on the mechanical properties of MSC. MSC's splitting tensile strength (STS) was considered the model's target. The influences that the water-to-cement (W/C) ratio, the stone nano-powder content (SNPC), and the curing age (CA) have on the STS of MSC were also analyzed. Detailed analysis of the results revealed that all the well-tuned ML models have acceptable potential for estimating the STS of MSC; however, the extra tree regressor (ETR) model was in the highest agreement with the laboratory results. Both the ML and laboratory findings showed that MSC with 10% SNPC benefits the long-term STS of MSC. A graphical user interface for the ML-based models was also developed to further aid in the estimation of STS for engineering challenges.The proposed models can be a suitable alternative to time-consuming, expensive, and complex laboratory methods to facilitate the MSC production.