Use of pumice stone and silica fume as precursor material for the design of a geopolymer.

Background: Geopolymers are alternative materials to cement because they require less energy in their production process; hence, they contribute to the reduction in CO 2 emissions. This study aims to evaluate the possibility of using industrial residues such as silica fume (SF) to improve the physical and mechanical properties of a pumice stone (PS)-based geopolymer. Methods: Through an experimental methodology, the process starts with the extraction, grinding, and sieving of the raw material to carry out the physical and chemical characterization of the resulting material, followed by the dosage of the geopolymer mixture considering the factors that influence the resistance mechanical strength. Finally, the physical and mechanical properties of the geopolymer were characterized. This research was carried out in four stages: characterization of the pumice stone, design of the geopolymer through laboratory tests, application according to the dosage of the concrete, and analysis of the data through a multi-criteria analysis. Results: It was determined that the optimal percentage of SF replacement is 10%, which to improves the properties of the geopolymer allowing to reach a maximum resistance to compression and flexion of 14.10 MPa and 4.78 MPa respectively, showing that there is a direct relationship between the percentage of SF and the resistance. Conclusions: Geopolymer preparation involves the use of PS powder with a composition rich in silicon and aluminum. The factors influencing strength include the ratio of sodium silicate to sodium hydroxide, water content, temperature, curing time, molarity of sodium hydroxide, and binder ratio. The results showed an increase in the compression and flexural strength with 10% SF replacement. The geopolymer's maximum compressive strength indicates its non-structural use, but it can be improved by reducing the PS powder size.

Modeling the influence of lime on the unconfined compressive strength of reconstituted graded soil using advanced machine learning approaches for subgrade and liner applications.

In the field of soil mechanics, especially in transportation and environmental geotechnics, the use of machine learning (ML) techniques has emerged as a powerful tool for predicting and understanding the compressive strength behavior of soils especially graded ones. This is to overcome the sophisticated equipment, laboratory space and cost needs utilized in multiple experiments on the treatment of soils for environmental geotechnics systems. This present study explores the application of machine learning (ML) techniques, namely Genetic Programming (GP), Artificial Neural Networks (ANN), Evolutionary Polynomial Regression (EPR), and the Response Surface Methodology in predicting the unconfined compressive strength (UCS) of soil-lime mixtures. This was for purposes of subgrade and landfill liner design and construction. By utilizing input variables such as Gravel, Sand, Silt, Clay, and Lime contents (G, S, M, C, L), the models forecasted the strength values after 7 and 28 days of curing. The accuracy of the developed models was compared, revealing that both ANN and EPR achieved a similar level of accuracy for UCS after 7 days, while the GP model performed slightly lower. The complexity of the formula required for predicting UCS after 28 days resulted in decreased accuracy. The ANN and EPR models achieved accuracies of 85% and 82%, with R2 of 0.947 and 0.923, and average error of 0.15 and 0.18, respectively, while the GP model exhibited a lower accuracy of 66.0%. Conversely, the RSM produced models for the UCS with predicted R2 of more than 98% and 99%, for the 7- and 28- day curing regimes, respectively. The RSM also produced adequate precision in modelling UCS of more than 14% against the standard 7%. All input factors were found to have almost equal importance, except for the lime content (L), which had an average influence. This shows the importance of soil gradation in the design and construction of subgrade and landfill liners. This research further demonstrates the potential of ML techniques for predicting the strength of lime reconstituted G-S-M-C graded soils and provides valuable insights for engineering applications in exact and sustainable subgrade and liner designs, construction and performance monitoring and rehabilitation of the constructed civil engineering infrastructure.

Modeling the influence of bacteria concentration on the mechanical properties of self-healing concrete (SHC) for sustainable bio-concrete structures.

In this research paper, the intelligent learning abilities of the gray wolf optimization (GWO), multi-verse optimization (MVO), moth fly optimization, particle swarm optimization (PSO), and whale optimization algorithm (WOA) metaheuristic techniques and the response surface methodology (RSM) has been studied in the prediction of the mechanical properties of self-healing concrete. Bio-concrete technology stimulated by the concentration of bacteria has been utilized as a sustainable structural concrete for the future of the built environment. This is due to the recovery tendency of the concrete structures after noticeable structural failures. However, it requires a somewhat expensive exercise and technology to create the medium for the growth of the bacteria needed for this self-healing ability. The method of data gathering, analysis and intelligent prediction has been adopted to propose parametric relationships between the bacteria usage and the concrete performance in terms of strength and durability. This makes is cheaper to design self-healing concrete structures based on the optimized mathematical relationships and models proposed from this exercise. The performance of the models was tested by using the coefficient of determination (R2), root mean squared errors, mean absolute errors, mean squared errors, variance accounted for and the coefficient of error. At the end of the prediction protocol and model performance evaluation, it was found that the classified metaheuristic techniques outclassed the RSM due their ability to mimic human and animal genetics of mutation. Furthermore, it can be finally remarked that the GWO outclassed the other methods in predicting the concrete slump (Sl) with R2 of 0.998 and 0.989 for the train and test, respectively, the PSO outclassed the rest in predicting the flexural strength with R2 of 0.989 and 0.937 for train and test, respectively and the MVO outclassed the others in predicting the compressive strength with R2 of 0.998 and 0.958 for train and test, respectively.