Ultra-high-performance concrete (UHPC) is a recently developed material which has attracted considerable attention in the field of civil engineering because of its outstanding characteristics. One of the key factors in concrete design is the compressive strength (CS) of UHPC. As one of the most potent tools in artificial intelligence (AI), machine learning (ML) can accurately predict concrete’s mechanical properties. Hyperparameter tuning is crucial in ensuring the prediction model’s reliability. However, it is a complex work. The purpose of this study is to optimize the CS prediction method for UHPC. Three ML methods, random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN), are selected to predict the CS of UHPC. Among them, the RF model demonstrates superior predictive accuracy, with the testing dataset R² of 0.8506. In addition, three meta-heuristic optimization algorithms, particle swarm optimization (PSO), beetle antenna search (BAS), and snake optimization (SO), are utilized to optimize the prediction model hyperparameters. The R² values for the testing dataset of SO-RF, PSO-RF, and BAS-RF are 0.9147, 0.8529, and 0.8607, respectively. The results indicate that SO-RF exhibits the highest predictive performance. Furthermore, the importance of input parameters is evaluated, and the findings prove the feasibility of the SO-RF model. This research enriches the prediction method of the CS of UHPC.

This study aims to explore the impact of different fibers on the explosive spalling resistance, residual compressive strength, residual flexural tensile strength, and mass loss of self-compacting concrete (SCC) after heating to elevated temperatures. The fiber types, fiber contents, and target temperatures are selected as the tested variables. Steel fibers (SF), polypropylene fibers (PF), and their combination are used to improve the fire resistance of SCC. Then, the specimens are tested after exposure to different target temperatures varying from 200 °C to 1000 °C and cooling down to room temperature naturally. The obtained results reveal that PF can effectively prevent explosive spalling in the SCC. Moreover, it was found that the temperature of 400 °C is a critical temperature for the residual compressive strength of fiber-reinforced SCC. Regarding the flexural tensile strength, the temperature of 200 °C was found to be a changing point of the SCC after heating to elevated temperatures. A sharp decrease in the compressive strength is observed when the target temperature exceeds 400 °C. For temperatures below 400 °C, the compressive strength is enhanced slightly with the increase of the target temperature. Moreover, incorporating a fiber cocktail is an effective way to improve the explosive spalling resistance and residual mechanical properties in the case of fire. Finally, the regression analysis was performed and the proposed correlations between the residual strengths and elevated temperatures are compared with equations in the literature. Good accuracy of the proposed correlation is achieved for fiber-reinforced SCC.