Materials Science Forum Vol. 1162

Abstract: Geopolymerization has emerged as a promising technology in the pursuit of sustainable and environmentally friendly construction practices. This process involves synthesizing inorganic polymers from natural and industrial by-products such as metakaolin, fly ash, slag, mine tailings, and other aluminosilicate materials using an alkaline hardener solution. Unlike traditional cement production, which involves high-energy consumption and significant carbon emissions, geopolymerization offers a promising avenue towards a cleaner environment by significantly reducing energy consumption, greenhouse gas emissions, industrial waste, and conserving natural resources. This review explores the principle of geopolymerization, its environmental benefits, and its potential applications as a cleaner alternative to traditional cement-based materials, fostering sustainable development and combating climate change thereby addressing the ecological impact of construction activities. The use of geopolymers not only diverts waste from landfills but also mitigates the need for the exploration of virgin raw materials, thus reducing the overall carbon footprint of infrastructural developments.

Abstract: Accurately predicting the water-binder ratio (W/B ratio) is crucial for achieving rice husk ash supplemented concrete structures' desired strength and durability. This study introduces an innovative approach for W/B ratio prediction, utilizing cutting-edge machine learning algorithms in combination with Explainable Artificial Intelligence (XAI) techniques. The research employs hybrid ensemble learning models, including Random Forest (RF), CATBoost (CB), Whale Optimization Algorithm-optimized RF (RF-WOA), and Moth Flame Optimization-optimized CB (CB-MFOA). The results indicate that these hybridized models significantly outperform the standalone models (RF and CATBoost) and traditional empirical methods (feret’s law, Abram’s law and bolomey’s method), with the CB-MFOA model achieving the highest accuracy, demonstrated by an R-value of 0.9984 during the calibration phase. In the verification phase, the CB model excelled with an R-value of 0.966. In addition to model performance, the study integrates XAI methods to explain the predictions and identify the key factors influencing the w/b ratio. Cement was found to be the most critical variable, enhancing the accuracy of the CB-MFOA model. The findings confirm that the proposed method improves prediction precision and provides engineers with a reliable tool to optimize concrete mix designs, thereby improving the durability and sustainability of concrete. This research contributes to the broader field of concrete technology by advancing the application of AI-based solutions in civil engineering and related fields.

Abstract: This study is undertaken to provide a viable alternative to destructive test assessment which is prohibitively costly and makes it difficult to fully capture the bending strength distribution of timber. The bending strength of glued laminated Nigerian wood specie which from previous research have clearly not been sufficiently studied were carefully evaluated under controlled conditions. Five wood species—Afara (Terminalia superba), Akomu (Pycnanthus angolensis), Melina (Gmelina arborea), Iroko (Milicia excelsa), and Omo cedar (Stereospermum accuminatissmum)—were tested for physical and mechanical properties at a mean moisture content level of 13%. Using standard procedures, density was determined for the wood species and found to be within low and medium densities. The glulam beams were produced using Phenol resorcinol formaldehyde, Urea formaldehyde, and Polyurethane adhesives. Furthermore, the bending strength of the beams was assessed parallel and perpendicular to the glue line using central point loading. Based on the strength assessment, four variables were evaluated as determinants for bending strength. These were wood density, wood species, adhesive type, and load direction. Analysis of variance was conducted to evaluate the significance of these variables as bending strength determinants in the beams. Furthermore, a stepwise regression method was used to develop the models, from which three models emerged with density, wood species, and load direction as predictors. Finally, these models were validated using an in-sample technique by splitting the data into a validation group and a training group in a ratio of 20% to 80%, respectively. The Pearson correlation between the predicted and experimental data was 0.847, 0.917, and 0.916 in the validation group and 0.824, 0.875, and 0.877 in the training group for models 1, 2, and 3, respectively. Higher correlation with the experimental data was found in the validation group than in the training group, thereby validating the models. These models are recommended for use because of the simplicity and efficiency of prediction.