Esteban Fraile-Garcia

Study of the Technical Feasibility of Increasing the Amount of Recycled Concrete Waste Used in Ready-Mix Concrete Production

The construction industry generates a considerable amount of waste. Faced with this undesirable situation, the ready-mix concrete sector, in particular, has invested energy and resources into reusing its own waste in its production process as it works towards the goal of more sustainable construction. This study examines the feasibility of incorporating two types of concrete waste, which currently end up in landfill, into the production process of ready-mix concrete: the waste generated during the initial production stage (ready-mix concrete waste), and waste created when demolition waste is treated to obtain artificial aggregate. The first phase of the study’s methodology corroborates the suitability of the recycled aggregate through characterization tests. After this phase, the impact of incorporating different percentages of recycled coarse aggregate is evaluated by examining the performance of the produced concrete. The replacement rate varied between 15% and 50%. The results indicate that recycled aggregates are, indeed, suitable to be incorporated into ready-mix concrete production. The impact on the final product’s performance is different for the two cases examined herein. Incorporating aggregates from generic concrete blocks led to a 20% decrease in the produced concrete’s strength performance. On the other hand, using recycled aggregates made from the demolition waste led to a smaller decrease in the concrete’s performance: about 8%. The results indicate that with adequate management and prior treatment, the waste from these plants can be re-incorporated into their production processes. If concrete waste is re-used, concrete production, in general, becomes more sustainable for two reasons: less waste ends up as landfill and the consumption of natural aggregates is also reduced.

Searching Parsimonious Solutions with GA-PARSIMONY and XGBoost in High-Dimensional Databases

EXtreme Gradient Boosting (XGBoost) has become one of the most successful techniques in machine learning competitions. It is computationally efficient and scalable, it supports a wide variety of objective functions and it includes different mechanisms to avoid over-fitting and improve accuracy. Having so many tuning parameters, soft computing (SC) is an alternative to search precise and robust models against classical hyper-tuning methods. In this context, we present a preliminary study in which a SC methodology, named GA-PARSIMONY, is used to find accurate and parsimonious XGBoost solutions. The methodology was designed to optimize the search of parsimonious models by feature selection, parameter tuning and model selection. In this work, different experiments are conducted with four complexity metrics in six high dimensional datasets. Although XGBoost performs well with high-dimensional databases, preliminary results indicated that GA-PARSIMONY with feature selection slightly improved the testing error. Therefore, the choice of solutions with fewer inputs, between those with similar cross-validation errors, can help to obtain more robust solutions with better generalization capabilities.

Acoustic Behavior of Hollow Blocks and Bricks Made of Concrete Doped with Waste-Tire Rubber

In this paper, we investigate the acoustic behaviour of building elements made of concrete doped with waste-tire rubber. Three different mixtures were created, with 0%, 10%, and 20% rubber in their composition. Bricks, lattice joists, and hollow blocks were manufactured with each mixture, and three different cells were built and tested against aerial and impact noise. The values of the global acoustic isolation and the reduction of the sound pressure level of impacts were measured. Results proved that highly doped elements are an excellent option to isolate low frequency sounds, whereas intermediate and standard elements constitute a most interesting option to block middle and high frequency sounds. In both cases, the considerable amount of waste-tire rubber recycled could justify the employment of the doped materials for the sake of the environment.