By integrating a multi-scale simulation with the pseudo-cracking method, the remaining fatigue life of in-service reinforced concrete (RC) bridge decks can be estimated based upon their site-inspected crack patterns. But, it still takes time for computation. In order to achieve a quick deterioration-magnitude assessment of RC decks based upon their crack patterns, two evaluation methods are proposed. A predictive correlation between the remaining fatigue life and the cracks density (both cracks length and width) is presented as a fast judgment. For fair-detailed judgment, an artificial neural network (ANN) model is also introduced which is the basis of the machine learning. Both assessment methods are built commonly by thousands of artificial random crack patterns to cover all possible ranges since the variety of the real crack patterns on site is more or less limited. The built ANN performances are examined by k-fold cross-validation besides checking the prediction accuracy of real crack patterns of bridge RC decks. Finally, the hazard map of the deck’s bottom surface is introduced to indicate the location of higher risk cracking, which derives from the estimated weight of individual neuron in the built artificial neural network.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited