Published Online:January 2025
Product Name:The IUP Journal of Structural Engineering
Product Type:Article
Product Code:IJSE020125
DOI:1111
Author Name:Daljit Singh, Arjun Sharma, Arghya Sharma and Vidushi Chadha
Availability:YES
Subject/Domain:Engineering
Download Format:PDF
Pages:43-57
Input factors and model parameters have a significant impact on the prediction of High-Performance Concrete Compressive Strength (HPCCS). The compressive strength is predicted using gradient booster. The paper proposes a machine learning (ML)- based method to predict HPCCS. Suitable variables are adopted to train the model. The database comprises 144 cube samples of size 150 mm 150 mm 150 mm of grade M60, M80 and M100 HPC. Five statistical indices—coefficient of determination (R2), mean-squared error (MSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean square error (RMSE)—of the models were used to determine which model was better for prediction. The findings imply that the suggested approach for estimating the compressive strength of HPC is reliable and efficient.
High performance concrete (HPC) is extensively used across various sectors of the construction industry due to its superior performance. Numerous engineering cases demonstrate that maintaining concrete quality is crucial for the long-term durability and safety of structures.