Intelligent Damage Detection in Bridge Girders: Hybrid Approach

Abstract

This study is intended to facilitate damage detection in concrete bridge girders without the need for visual inspection while minimizing field measurements. Beams with different material and cracking parameters were modeled using ABAQUS finite-element analysis software to obtain stiffness values at specified nodes. The resulting database was then used to train an artificial neural network (ANN) model to inversely predict the most probable cracking pattern. The aim is to use the ANN approach to solve an inverse problem where a unique analytical solution is not attainable. Accordingly, simple span beams with three, five, seven, and nine stiffness nodes and a single crack were modeled in this work. To confirm that the ANN approach can characterize the logic within the databases, networks with geometric, material, and cracking parameters as inputs and stiffness values as outputs were created. These networks provided excellent prediction accuracy measures (R2 values>99%). For the inverse problem, the noted trend shows that better prediction accuracy measures are achieved when more stiffness nodes are used in the ANN modeling process. It was also observed that providing some outputs to the ANN as inputs, thus decreasing the number of required outputs, immensely improves the quality of predictions provided by the ANN. An experimental verification program will be conducted to qualify the effectiveness of the method proposed. This test program is described in details in the present paper.