Data-driven vision-based inspection for reinforced concrete beams and slabs: Quantitative damage and load estimation

We show that computer-vision-based inspection can relate surface observations to quantitative damage and load level estimates in common reinforced concrete beams and slabs subjected to monotonic loading. This work is related to an earlier study focused on shear-critical beams and slabs (i.e., specimens lacking shear reinforcement), but here an expanded image database has been assembled to include specimens with both flexural and shear reinforcement such as would be found in practice. Using this expanded data set, a supervised machine learning algorithm builds cross-validated predictive models capable of estimating internal loads (i.e., shear and moment) and damage levels based on surface crack pattern images. The expanded data set contains a total of 127 specimens and 862 images captured in past studies across a range of load and damage levels. Textural and geometric attributes of surface crack patterns were used for feature engineering and tuning of predictive models. The expanded data set enables comparison of the estimation accuracy for shear-critical and shear-reinforced beams and slabs considered separately and in combined form. This includes the capability to categorize whether shear reinforcement is present or not. Estimation models based on surface observations for shear-reinforced elements are found to be comparable to those for shear-critical beams and slabs, with variability observed due to loading type range, member geometries, whether categorization is combined with regression, and the image feature sets used.