The Influence of Materials on the Mechanical Properties of Ultra-High-Performance Concrete (UHPC): A Literature Review.

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.

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC's Compressive Strength.

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.