Search

The creep behavior of Ultra-High-Performance Concrete (UHPC) was investigated by machine learning (ML) and SHapley Additive exPlanations (SHAP). Important features were selected by feature importance analysis, including water-to-binder ratio, aggregate-to-cement ratio, compressive strength at loading age, elastic modulus at loading age, loading duration, steel fiber volume content, and curing temperature. Four typical ML models—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting Machine (XGBoost), and Light Gradient Boosting Machine (LGBM)—were studied to predict the creep behavior of UHPC. Via Bayesian optimization and 5-fold cross-validation, the ML models were tuned to achieve high accuracy (R2 = 0.9847, 0.9627, 0.9898, and 0.9933 for RF, ANN, XGBoost, and LGBM, respectively). The contribution of different features to the creep behavior was ranked. Additionally, SHAP was utilized to interpret the predictions by the ML models, and four parameters stood out as the most influential for the creep coefficient: loading duration, curing temperature, compressive strength at loading age, and water-to-binder ratio. The SHAP results were consistent with theoretical understanding. Finally, the UHPC creep curves for three different cases were plotted based on the ML model developed, and the prediction by the ML model was more accurate than that by fib Model Code 2010. [ABSTRACT FROM AUTHOR]

Using oyster shell powder (OSP) to prepare magnesium phosphate cement (MPC) not only reduces the pollution caused by the wasted oyster shell disposal, but also benefits the development of more environmentally friendly cement. The effect of OSP on the hydration and strength development of MPC was studied. An axial compression experiment including 45 cuboid specimens was executed to investigate the compressive strength, failure mode, stress–strain relationship, and energy absorption of MPC mixing with different mass contents (0% to 12%) of OSP over the curing times of 7, 14, and 28 days. Scanning electron microscopy, X-ray diffraction and energy dispersive spectroscopy were utilized for measuring the variation of MPC microstructure and hydration products caused by OSP. Results indicated that a new reactant CaHPO4·2H2O was formed, which optimized matrix strength. The substitution of OSP could reduce the cost of MPC by 2–9% without decreasing the strength. Compared with MPC without OSP, the compressive strength of the specimen with 3% OSP is increased by 6%. However, with the continuous increase of OSP, the compressive strength gradually decreases. Similarly, the elastic modulus of MPC increases first and then decreases with the increase of OSP. [ABSTRACT FROM AUTHOR]

The rapid advancement of additive manufacturing technologies for concrete construction requires further understanding of material performance and its relationship with print parameters such as interlayer time-lapse and workability retention during the print. This study addresses the effects of the time delay between consecutive extruded layers on the mechanical performance of printed concrete using a mix designed by Quikrete. A series of specimens were prepared with printing delays of 10, 15, 30, and 60 min. This work correlates the change in fracture properties, mechanical performance, and workability retention with the interlayer time-lapse between two consecutive concrete layers. Interlayer time-lapse is defined as the time difference in printing of two consequent layers of concrete. It affects individual properties differently based on the loading direction and test types, but it is consistent in terms of interlayer performance. The understanding of the effect of interlayer time-lapse on the fracture properties between two consecutive printed layers fills the knowledge gaps in printed concrete research. Therefore, this study can help researchers perform required optimization and safely estimate the performance of printed concrete. [ABSTRACT FROM AUTHOR]