Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage
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 predi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Scientific Reports
2025
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12493/2952 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1856816788439826432 |
|---|---|
| author | V. Vasic, Milica Awoyera, Paul O. Fadugba, Oladlu George Barisic, Ivana Nettinger Grubeša, Ivanka |
| author_facet | V. Vasic, Milica Awoyera, Paul O. Fadugba, Oladlu George Barisic, Ivana Nettinger Grubeša, Ivanka |
| author_sort | V. Vasic, Milica |
| collection | KAB-DR |
| description | 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. |
| format | Article |
| id | oai:idr.kab.ac.ug:20.500.12493-2952 |
| institution | KAB-DR |
| language | English |
| publishDate | 2025 |
| publisher | Scientific Reports |
| record_format | dspace |
| spelling | oai:idr.kab.ac.ug:20.500.12493-29522025-10-01T00:00:34Z Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage V. Vasic, Milica Awoyera, Paul O. Fadugba, Oladlu George Barisic, Ivana Nettinger Grubeša, Ivanka Ceramic tiles Firing stage Machine learning Water absorption Bending strength SHAP analysis Process optimization 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. 2025-09-30T17:14:39Z 2025-09-30T17:14:39Z 2025 Article Vasić, Milica V., et al. "Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage." Scientific Reports 15.1 (2025): 31397. https://doi.org/10.1038/s41598-025-12011-9 http://hdl.handle.net/20.500.12493/2952 en Attribution-NonCommercial-NoDerivs 3.0 United States http://creativecommons.org/licenses/by-nc-nd/3.0/us/ application/pdf Scientific Reports |
| spellingShingle | Ceramic tiles Firing stage Machine learning Water absorption Bending strength SHAP analysis Process optimization V. Vasic, Milica Awoyera, Paul O. Fadugba, Oladlu George Barisic, Ivana Nettinger Grubeša, Ivanka Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title | Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title_full | Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title_fullStr | Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title_full_unstemmed | Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title_short | Advanced machine learning models for the prediction of ceramic tiles’ properties during the firing stage |
| title_sort | advanced machine learning models for the prediction of ceramic tiles properties during the firing stage |
| topic | Ceramic tiles Firing stage Machine learning Water absorption Bending strength SHAP analysis Process optimization |
| url | http://hdl.handle.net/20.500.12493/2952 |
| work_keys_str_mv | AT vvasicmilica advancedmachinelearningmodelsforthepredictionofceramictilespropertiesduringthefiringstage AT awoyerapaulo advancedmachinelearningmodelsforthepredictionofceramictilespropertiesduringthefiringstage AT fadugbaoladlugeorge advancedmachinelearningmodelsforthepredictionofceramictilespropertiesduringthefiringstage AT barisicivana advancedmachinelearningmodelsforthepredictionofceramictilespropertiesduringthefiringstage AT nettingergrubesaivanka advancedmachinelearningmodelsforthepredictionofceramictilespropertiesduringthefiringstage |