Abstract
Concrete structures have been long expected as permanent structures, and then they have been constructed without priory considering their maintenance. Recent year, however, they are suffered from severe damage. An artificial neural network is applied to assess deteriorating reinforced concrete structures using periodical inspection data for thermal power plants along the coast of Tokyo Bay. Using a completed training neural networks, a sensitivity analysis to determine the influence of a change in each variable such as maximum crack width, are of peeling-off of concrete surface, exposure of reinforcement, etc., on the damage level.
