RESUMO
Construction industry is indirectly the largest source of CO2 emissions in the atmosphere, due to the use of cement in concrete. These emissions can be reduced by using industrial waste materials in place of cement. Self-Compacting Concrete (SCC) is a promising material to enhance the use of industrial wastes in concrete. However, there are very few methods available for accurate prediction of its strength, therefore, reliable models for estimating 28-day Compressive Strength (C-S) of SCC are developed in current study by using three Machine Learning (ML) algorithms including Multi Expression Programming (MEP), Extreme Gradient Boosting (XGB), and Random Forest (RF). The ML models were meticulously developed using a dataset of 231 points collected from internationally published literature considering seven most influential parameters including cement content, quantities of fly ash and silica fume, water content, coarse aggregate, fine aggregate, and superplasticizer dosage to predict C-S. The developed models were evaluated using different statistical errors including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2) etc. The results showed that the XGB model outperformed the MEP and RF model in terms of accuracy with a correlation R2 = 0.998 compared to 0.923 for MEP and 0.986 for RF. Similar trend was observed for other error metrices. Thus, XGB is the most accurate model for estimating C-S of SCC. However, it is pertinent to mention here that it does not give its output in the form of an empirical equation like MEP model. The construction of these empirical models will help to efficiently estimate C-S of SCC for practical purposes.
RESUMO
The utilization of phosphorite deposits as an industrial resource is of paramount importance, and its sustainability largely depends on ensuring safe and responsible practices. This study aims to evaluate the suitability of phosphorite deposits for industrial applications such as the production of phosphoric acid and phosphatic fertilizers. To achieve this goal, the study meticulously examines the geochemical characteristics of the deposits, investigates the distribution of natural Radioactivity within them, and assesses the potential radiological risk associated with their use. The phosphorites are massive and collected from different beds within the Duwi Formation at the Hamadat mining area. They are grain-supported and composed of phosphatic pellets, bioclasts (bones), non-phosphatic minerals, and cement. Geochemically, phosphorites contain high concentrations of P2O5 (23.59-28.36 wt.%) and CaO (40.85-44.35 wt.%), with low amounts of Al2O3 (0.23-0.51 wt.%), TiO2 (0.01-0.03 wt.%), Fe2O3 (1.14-2.28 wt.%), Na2O (0.37-1.19 wt.%), K2O (0.03-0.12 wt.%), and MnO (0.08-0.18 wt.%), suggesting the low contribution of the detrital material during their deposition. Moreover, they belong to contain enhanced U concentration (55-128 ppm). They are also enriched with Sr, Ba, Cr, V, and Zn and depleted in Th, Zr, and Rb, which strongly supports the low detrital input during the formation of the Hamadat phosphorites. The high Radioactivity of the studied phosphorites is probably due to the widespread occurrence of phosphatic components (e.g., apatite) that accommodate U in high concentrations. Gamma spectrometry based on NaI (Tl) crystal 3×3 has been used to measure occurring radionuclides in the phosphorite samples. The results indicate that the radioactive concentrations' average values of 226Ra, 232Th, and 40K are 184.18±9.19, 125.82±6.29, and 63.82±3.19 Bq Kg-1, respectively. Additionally, evaluations have been made of the radiological hazards. The calculated risk indicators exceeded the recommended national and world averages. The data obtained will serve as a reference for follow-up studies to evaluate the effectiveness of the Radioactivity of phosphatic materials collected from the Hamdat mine area.
