Damage Assessment of Reinforced Concrete Bridge Decks Using TAM Network

Abstract

In order to establish a rational management program for bridge structures, it is necessary to evaluate the structural damage of existing bridges in a quantitative manner. However, it is difficult to avoid the subjectivity of inspectors when visual data are used for the evaluation of damage or deterioration. In this paper, an attempt is made to develop an optimal bridge maintenance system by using a health monitoring technique. The damage of Reinforced Concrete (RC) bridge decks is evaluated with the aid of digital photos and pattern recognition. So far, neural networks have been applied to judge the damage state of RC bridge decks. However, there are still some problems that learning data are not enough and recognition accuracy is not satisfactory. In order to solve these problems, TAM network is applied here, which is an optical system. Though the numerical examples using actual data, it is shown that the recognition rate is increased.