Faculty of Engineering, Technology, Applied Design & FineArt (FETADFA)

Permanent URI for this collection

http://hdl.handle.net/20.500.12493/13

Browse

Browsing Faculty of Engineering, Technology, Applied Design & FineArt (FETADFA) by Author "Awoyera, Paul O."

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage
    (Scientific Reports, 2025) V. Vasic, Milica; Awoyera, Paul O.; Fadugba, Oladlu George; Barisic, Ivana; Nettinger Grubeša, Ivanka
    The firing stage is a critical phase in ceramic tile production, where the interplay of raw material composition and thermal treatment determines essential properties such as water absorption (WA) and bending strength (BS). This study employs advanced machine learning (ML) models to accurately predict these properties by capturing their complex nonlinear relationships. A robust dataset of 312 ceramic samples was analyzed, including variables such as particle size distribution, chemical and mineralogical composition, and firing temperatures ranging from 1000 to 1300 °C. Among the four ensemble ML models evaluated, CatBoost demonstrated the highest predictive performance. Model accuracy was assessed using multiple evaluation metrics, including the coefficient of determination (R²), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). To enhance interpretability, SHapley Additive exPlanations (SHAP) were used, revealing that clay mineral content and SiO₂ concentration were the most influential factors for WA, contributing approximately 40% and 30%, respectively. For BS, firing temperature (35%) and Al₂O₃ content (25%) were identified as the key predictors. Partial dependence plots further illustrated critical thresholds, such as a significant drop in WA above 62% SiO₂ and optimal BS values near 1200 °C, findings that align with known ceramic processing principles while offering new, data-driven formulation insights. These results demonstrate the value of explainable artificial intelligence (AI) in enabling real-time process optimization, enhancing product consistency, and supporting energy-efficient ceramic manufacturing. Future work will focus on extending the dataset to include a wider variety of clay compositions and investigating hybrid modeling approaches to further improve predictive performance.
  • Thumbnail Image
    ItemOpen Access
    Bamboo stem ash as a sustainable cement replacement in lightweight foam mortar enhancing mechanical thermal and microstructural properties.
    (Scientific Reports, 2025) Mydin, Md Azree Othuman; Azman, Nurul Zahirah Noor; Awoyera, Paul O.; Özkılıç, Yasin Onuralp; Fadugba, Olaolu George; Abdullah, Mohd Mustafa Al Bakri; Omar, Roshartini; Datta, Shuvo Dip
    This study presents a novel approach to enhancing the properties of lightweight foam mortar (LFM) by utilizing bamboo stem ash (BSA) as a partial cement replacement. Unlike traditional supplemental cementitious materials (SCMs) like fly ash or silica fume, BSA provides a special blend of lightweight properties and a high silica concentration. Thus, the effect of BSA (in proportions of 0–25% and steps of 5%) on the mortars’ fresh, hardened, microscale properties, such as workability, density, strength, durability, and microstructural characteristics, was explored. At 15% BSA replacement, the compressive strength reached 8.25 MPa at 28 days, 7% higher than the control mix (7.7 MPa). The study identifies 15% BSA as the optimal replacement level, striking a balance between mechanical strength, durability, and thermal insulation. Beyond 15%, increased porosity begins to reduce strength, while thermal resistance continues to improve. Thus, a 10–15% replacement range is recommended for applications requiring structural integrity and insulation. The density of the foam mortar decreased from 1000 kg/m3 for the control mix to 960 kg/m3 at 20% BSA replacement, improving the material’s lightweight characteristics. Also, the porosity increased from 24.8% (control) to 30.2% (25% BSA), positively influencing thermal insulation properties. Thermal conductivity measurements indicated a reduction from 0.25 W/mK (control) to 0.18 W/mK at 25% BSA replacement, demonstrating improved thermal resistance. BSA incorporation improves the pore structure and fosters stronger interfacial bonding within the matrix, especially at 15% replacement, according to microstructural investigation using SEM. The water absorption rate increased slightly from 18.2% (control) to 21.6% (25% BSA), still within reasonable bounds for lightweight construction applications. As demonstrated by the mortars’ notable performance, BSA may effectively replace OPC in LFM, improving its mechanical, thermal, and environmental qualities. With the results, BSA has shown potential for developing eco-friendly building materials and aiding in reducing carbon emissions in the built environment. These results show that BSA can be a green and practical substitute for OPC in lightweight building applications, especially for prefabricated panels, insulation layers, and non-load-bearing walls. Its ability to enhance mechanical strength while reducing thermal conductivity makes it a promising material for energy-efficient and sustainable building solutions.
  • Thumbnail Image
    ItemOpen Access
    Soft Computing Solutions for Reducing the Carbon Footprint of Fly Ash Based Concrete. Advances in Civil Engineering
    (John Wiley & Sons Ltd., 2025) Awoyera, Paul O.; Adetola, Joshua; Nayeemuddin, Mohammed; Mewada, Hiren; George Fadugba, Olaolu
    The construction industry significantly contributes to environmental degradation,with many structures exhibiting high carbon footprints throughout their construction processes and lifespans.Activities such as cement hydration and other commoncon-struction practices substantially influence environmental conditions overtime,necessitating a critical evaluation of material and design choices.This study reported the environmental impact of fly ash(FA),which is largely used to enhance concrete strength.A prediction of two end point indicators,that is,global warming potential(GWP)and CO2 emission using soft computing methods are presented,which are particularly effective for handling complex,non linear relationships in environmental data.To achieve this, two machine learning approaches,the random forest(RF)and decision tree(DT)models,are employed to assess the environ- mental impact of structural materials and designs.Two data sets were obtained from reputable databases,including ResearchGate, Science Direct, Semantic Scholar,and Mendeley Data.The models are trained to explore the potential for optimizing structural designs and material selection stominimize environmental impacts.Feature importance is analyzed using Shapley values,providing insights into the most influential factors affecting GWP and CO2 emission Model performance is evaluated using R2 and root mean square error(RMSE) metrics. Notably, the RF model achieved an R2 score of 91% for GWP and 97% for CO2 emission, demonstrating superior predictive accuracy compared to the DT approach.The findings demonstrate the effectiveness of these machine learning techniques in enhancing the sustainability of construction practices,offering a pathway for informed decision-making. This study highlights the urgent need for innovative approaches in the built environment to support sustainable development and mitigate the carbonfootprint associated with structural engineering.