JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Mahder, Ketemaw Abitew | |
| dc.date.accessioned | 2024-11-11T08:15:31Z | |
| dc.date.available | 2024-11-11T08:15:31Z | |
| dc.date.issued | 2024-03 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/16136 | |
| dc.description.abstract | The mechanical properties of concrete are the most important parameters in a design code and the strength of concrete is one of them. It mainly depends on factors such as cement consumption, water-cement ratio and nature of aggregates. Compressive strength ( �' c) is the most important mechanical property of concrete. These days to investigate the compressive strength of concrete using experimental and numerical analysis seems to get surpassed by machine learning (ML) approaches. Many Artificial intelligence technologies, particularly Machine learning algorithms, have been used and becoming vital in the construction industry. This study included collecting data from literatures and applying ML techniques to predict the �' cof concrete containing ash as a partial replacement of cement. The collected datasets include seven input parameters, namely sources of ash, ash (kg/m3), cement amount, coarse aggregate, fine aggregate, water and curing age in order to predict the model output (i.e., �' c). The main aim of this research is on the use of ML algorithms to predict �' c of concrete. Therefore, Artificial neural network (ANN), Decision tree (DT), Random forest (RF), Extreme gradient boosting (XGBoost) and Support vector regression (SVR) algorithms has been modeled and evaluated for their ability to predict �' c. The performance of the models was evaluated using coefficient of determination (R2), mean absolute error (MAE), and Root mean squared error (RMSE). Finally, best model has been identified for prediction of �' c. Based on the evaluation metrics, XGBoost model has shown an incredible prediction ability (R2 = 0.970) followed by Support vector regression model (R2 = 0.968). Moreover, XGBoost model also predicts that the optimum amount of ash to replace cement is 7.5– 12.4%. Key word: Cement, Ash, Concrete, Compressive strength, Machine learning | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | Civil and Water Resource Engineering | en_US |
| dc.title | Concrete Strength Prediction using Machine Learning Techniques: Effect of Ash as a Partial Replacement for Cement | en_US |
| dc.type | Thesis | en_US |
