A novel compressive strength estimation approach for 3D printed fiber-reinforced concrete: integrating machine learning and gene expression programming

3D concrete printing (3DCP) is crucial in the construction because of the low labor cost, eco-friendly behavior; however, getting a proper mixture is always a challenge. This study focuses on predicting the compressive strength (CS) of fiber-reinforced concrete produced with 3DCP using eight machine learning (ML) algorithms to get optimized mixture. The ML models were trained and tested using a comprehensive database on CS collected from literature considering the various fiber-reinforced cementitious composites, comprising over 299 mixtures with 11 features. The results show that the trained ML models could predict CS with R² ranging from 0.927 to 0.990 and 0.914 to 0.988 for the training and testing dataset, respectively. Furthermore, supplementary experiments were conducted to create a new dataset to validate the predictive model's accuracy, with the extreme gradient boosting (XGB) and gene expression programming (GEP). Based on the GEP, a novel empirical equation was proposed and rigorously validated using experiments. The equation exhibits a high accuracy with the GEP algorithm (R² = 0.89), providing real-world field applications that might be improve decision-making and mixture optimization, which contributes to advancements, efficiency, and innovative solutions in 3D printing practical domains.