This research aimed to improve the interpretation of electrical resistivity (ER) results in concrete bridge decks by utilizing machine-learning algorithms developed using data from multiple nondestructive evaluation (NDE) techniques. To achieve this, a parametric study was first conducted using numerical simulations to investigate the effect of various parameters on ER measurements, such as the degree of saturation, corrosion length, delamination depth, concrete cover, and the moisture condition of delamination. A data set from this study was used to build a machine-learning algorithm based on the Random Forest methodology. Subsequently, this algorithm was applied to data collected from an actual bridge deck in the BEAST® facility, showcasing a significant advancement in ER measurement interpretation through the incorporation of information from other NDE technologies. Such strides are pivotal in advancing the reliability of assessments of structural elements for their durability and safety.
Keywords: bridge deck; concrete; corrosion; electrical resistivity; half-cell potential; impact echo; machine learning; multi-NDE; random forest.