Ultra-high-performance concrete (UHPC) is a cementitious composite combining high-strength concrete matrix and fiber reinforcement. Standing out for its excellent mechanical properties and durability, this material has been widely recognized as a viable choice for highly complex engineering projects. This paper proposes (i) the review of the influence exerted by the constituent materials on the mechanical properties of compressive strength, flexural tensile strength, and elastic modulus of UHPC and (ii) the determination of optimal quantities of the constituent materials based on simplified statistical analyses of the developed database. The data search was restricted to papers that produced UHPC with straight steel fibers at a content of 2% by volume. UHPC mixture models were proposed based on graphical analyses of the relationship of constituent materials versus mechanical properties, aiming to optimize the material’s performance for each mechanical property. The results proved to be in accordance with the specifications present in the literature, characterized by high cement consumption, significant presence of fine materials, and low water-to-binder ratio. The divergences identified between the mixtures reflect how the constituent materials uniquely impact each mechanical property of the concrete. In general, fine materials were shown to play a significant role in increasing the compressive strength and flexural tensile strength of UHPC, while water and superplasticizers stood out for their influence on the material’s workability.

The artificial neural networks (ANNs)-based model has been used to predict the compressive strength of concrete, assisting in creating recycled aggregate concrete mixtures and reducing the environmental impact of the construction industry. Thus, the present study examines the effects of the training algorithm, topology, and activation function on the predictive accuracy of ANN when determining the compressive strength of recycled aggregate concrete. An experimental database of compressive strength with 721 samples was defined considering the literature. The database was used to train, validate, and test the ANN-based models. Altogether, 240 ANNs were trained, defined by combining three training algorithms, two activation functions, and topologies with a hidden layer containing 1–40 neurons. The ANN with a single hidden layer including 28 neurons, trained with the Levenberg–Marquardt algorithm and the hyperbolic tangent function, achieved the best level of accuracy, with a coefficient of determination equal to 0.909 and a mean absolute percentage error equal to 6.81%. Furthermore, the results show that it is crucial to avoid the use of overly complex models. Excessive neurons can lead to exceptional performance during training but poor predictive ability during testing.

Accurately predicting the fatigue life of concrete is crucial for ensuring the safety and durability of structural elements subjected to cyclic loading. Traditional empirical models often struggle to capture the complex interactions between mechanical properties and loading conditions, particularly the influence of frequency. This study introduces a hybrid machine learning model based on the stacking ensemble strategy, integrating Support Vector Regression (SVR), Random Forest (RF), and Artificial Neural Networks (ANNs) to enhance prediction accuracy. A dataset of 891 experimental results from the literature was utilized, incorporating four key input variables: compressive strength, stress ratio, maximum stress-to-strength ratio, and loading frequency. The hybrid model demonstrated superior performance (R² = 0.965, RMSE = 0.19), outperforming individual models and established predictive equations. SHAP analysis validated the model’s interpretability and emphasized the necessity of accounting for loading frequency. This study contributes a robust and generalizable tool for fatigue life prediction within the defined input domain, offering valuable insights for engineering design and structural assessment.

Ultra-high-performance concrete with steel fibers (UHPC) stands out for its exceptional mechanical properties and high ductility. The addition of steel fibers improves the tensile strength, allowing for its use in the design of structural elements subject to bending. The use of rice husk ash (RHA) as a natural mineral addition in the UHPC mixture offers significant advantages in terms of environmental impact and mechanical properties. Therefore, this work experimentally investigates the effect of RHA as a partial replacement for active silica fume on the flexural tensile strength and compressive behavior of UHPC. Additionally, a parametric study was conducted to examine the impact of varying prism geometries on the flexural tensile strength of UHPC with and without CCR in ABAQUS version 6.14. The experimental results made it possible to calibrate the UHPC parameters using RHA for numerical simulations of UHPC behavior based on the concrete damaged plasticity (CDP) model. The results indicated an increase of 4% in the compressive strength and 20% in the flexural tensile strength of UHPC with the addition of RHA. Furthermore, the numerical extrapolations of the flexural tensile strength test show that increasing the dimensions of the prisms reduces the strength by up to 30% of UHPC with RHA, evidencing the influence of geometry on the results.