Despite previous efforts to map the proportioning of a concrete to its strength, a robust knowledge-based model enabling accurate strength predictions is still lacking. As an alternative to physical or chemical-based models, data-driven machine learning methods offer a promising pathway to address this problem. Although machine learning can infer the complex, non-linear, non-additive relationship between concrete mixture proportions and strength, large datasets are needed to robustly train such models. This is a concern as reliable concrete strength data is rather limited, especially for realistic industrial concretes. Here, based on the analysis of a fairly large dataset (>10,000 observations) of measured compressive strengths from industrial concretes, we compare the ability of three selected machine learning algorithms (polynomial regression, artificial neural network, random forest) to reliably predict concrete strength as a function of the size of the training dataset. In addition, by adopting stratified sampling, we investigate the influence of the representativeness of the training datapoints on the learning capability of the models considered herein. Based on these results, we discuss the nature of the competition between how accurate a given model can eventually be (when trained on a large dataset) and how much data is actually required to train this model.
25 November 2023 in Construction and Building Materials
Foam concrete is a low-density controlled strength material that can potentially be used for accommodating different types of particles—recycled fine aggregate being an example. The paste matrix of this material has a cellular microstructure, and bulk performance is readily affected by the inclusion of fines. To study the effect of inclusion of fines on mechanical performance and foam structure of foam concrete, a group of 0.55 g/cm3 foam–sand composite mixtures with high-volume fly ash replacement are investigated. The elastic modulus is measured by a vibrational frequency test. The crushing mechanics are determined by the load-displacement response from a penetration test. The effect of particle inclusion on the foam concrete microstructure is characterized using micro computed tomography. The results indicate that use of fine-graded sand particles at a small dosage simultaneously reduces cement content and enhances the crushing performance, however poor material performance is observed for a high sand content. The cellular structure of the foam–sand composite, and thus its mechanical behavior, can be substantially diminished by larger sand particles, especially when the particle size is larger than the voids in foam.