ANN-Based LUBE Model for Interval Prediction of Compressive Strength of Concrete

This study uses ANN-based lower upper bound estimation (LUBE) method for construction of prediction intervals (PIs) at different confidence levels (CL) for the compressive strength of concrete for the first time. For the purpose of this study, an experimental study is done to prepare the required database from different mix designs of concrete. The results of this study demonstrate efficiency of the LUBE method for the three CLs considered of 85%, 90% and 95% in which the values of prediction interval coverage probability (PICP) are all greater or equal than CLs, which indicates that the ANN-based LUBE method can produce PIs with a reliable coverage probability. In addition, with average interval width index of 34.0% and the average failure distance index of 3.7% for three confidence levels, LUBE represents a more reliable and informative than exact point predictions for the compressive strength data in the test data set.