Prediction of concrete mixing proportions using deep learning

초록

This study aims to build a deep learning model that can predict the value of concrete mixing properties according to a given concrete strength value. In results, in the case of 'curing temperature', which had a narrow range of values in the existing data set, showed the lowest error rate with less than 1% error based on MAE, and the highest error rate with an error of 12 to 14% for fly and bfs.