The prediction of damage condition for light structures with HybridArtificial Intelligence technique

摘要

A review of existing literature in the area of expansive soils showed a lack of a thorough scientificdiagnostic of the damage to light structures founded on them. A database of the records of damage tolight structures in Victoria, Australia was examined with a view to determining the factors whichmost influenced the cracking of the structures over time. This database recorded damage as andwhen it was reported by the occupants. The aim of this paper is to develop a model to predict thedamage condition of light structure on expansive soils in Victoria using a hybrid ArtificialIntelligence technique. The result from the analysis of the model is promising. It demonstrated that themodel is able to resolve the problems facing light structures on expansive soils. The model is able topredict the damage condition or damage class using different combinations of factors.