RESUMO
This study explores the integration of machine learning (ML) techniques to predict and optimize the compressive strength of alkali-activated materials (AAMs) sourced from four industrial waste streams: blast furnace slag, fly ash, reducing slag, and waste glass. Aimed at mitigating the labor-intensive trial-and-error method in AAM formulation, ML models can predict the compressive strength and then streamline the mixture compositions. By leveraging a dataset of only 42 samples, the Random Forest (RF) model underwent fivefold cross-validation to ensure reliability. Despite challenges posed by the limited datasets, meticulous data processing steps facilitated the identification of pivotal features that influence compressive strength. Substantial enhancement in predicting compressive strength was achieved with the RF model, improving the model accuracy from 0.05 to 0.62. Experimental validation further confirmed the ML model's efficacy, as the formulations ultimately achieved the desired strength threshold, with a significant 59.65% improvement over the initial experiments. Additionally, the fact that the recommended formulations using ML methods only required about 5 min underscores the transformative potential of ML in reshaping AAM design paradigms and expediting the development process.
RESUMO
Sorbents prepared from iron blast furnace slag (BFS) and hydrated lime (HL) through the hydration process have been studied with the aim to evaluate their reactivities toward SO2 under the conditions prevailing in dry or semidry flue gas desulfurization processes. The BFS/HL sorbents, having large surface areas and pore volumes due to the formation of products of hydration, were highly reactive toward SO2, as compared with hydrated lime alone (0.24 in Ca utilization). The sorbent reactivity increased as the slurrying temperature and time increased and as the particle size of BFS decreased; the effects of the liquid/solid ratio and the sorbent drying conditions were negligible. The structural properties and the reactivity of sorbent were markedly affected by the BFS/HL ratio; the sorbent with 30/70 ratio had the highest 1 h utilization of Ca, 0.70, and SO2 capture, 0.45 g SO2/g sorbent. The reactivity of a sorbent was related to its initial specific surface area (Sg0) and molar content of Ca (M(-1)); the 1 h utilization of Ca increased almost linearly with increasing Sg0/M. The results of this study are useful to the preparation of BFS/HL sorbents with high reactivity for use in the dry and semidry processes to remove SO2 from the flue gas.