Abstract
Data on the effects of the environmental conditions, structure, and properties of concrete onto the degree of damage caused by chloride-induced steel corrosion have been gathered on three concrete structures in an Adriatic marine environment. The damages were classified into six categories based on the type of remedial work necessary. An artificial neural network for feature categorization was used as a tool for classification of the degree of damage. The model was successfully trained and validated for the range of data from investigated bridges. The interactions and sensitivities of the principal parameters were investigated. The model indicates that the exposure and microclimate conditions are rated higher than the porosity, strength, water–cement ratio, cement content, and cement type. The model could be useful for planning the maintenance of investigated structures and design of remedial works.