The development of a predictive damage condition model of light structures on expansive soils using hybrid artificial intelligence techniques

Expansive soils have damage light structures due to movement of soil which was a common problem all around the world. Soils exhibiting expansive properties were common throughout Australia. The damage to light structures founded on expansive soils in Victoria occurred mainly in properties built on quaternary basaltic clays and Tertiary to Ordovician clays. A review of existing literature in the area of expansive soils showed a lack of a thorough scientific diagnostic of the damage to light structures founded on expansive soils. Very few studies had been performed on damage to light structures on expansive soils in Victoria. There were no models so far to predict damage condition to light structures. More over, most of the reports on damage to light structures on expansive soils in Victoria were poorly documented. The aim of this research project was to develop a model to predict the damage condition of light structure on expansive soils in Victoria. A hybrid Neural Network trained with Genetic Algorithm was adopted for the de-velopment of the Predictive Damage Condition model. The Neural Network and Genetic Algorithm toolboxes from MATLAB ® version 7.1 were used. The development of a Predictive Damage Condition model was driven by the shortage of defined quanti-tative studies and methods of selecting the factors that influenced the damage to light structure on expansive soils. The data used was based on information extracted from the Building Housing Commission which was recorded by different engineering companies based only on the tenants complain and site investigation of the properties. A series of factors that were believed to be dominant in influencing damage to light structures were chosen including: structural type, foundation, the presence of vegetation, soil type, age, and climate change. The model showed that it was able to resolve the problems facing light structures on expansive soils. First and foremost, the Predictive Damage Condition model was able to predict the damage condition or damage class using different combinations of fac-tors. It was also possible to identify the factors contributing to the damage of the struc-ture and to assess their relative importance in causing damage to light structures on expansive soil. It was found that the construction footing and vegetation were the most important among all the other input parameters. Change in Thornthwaite Moisture In-dex or climate was ranked second. Construction wall and age, were ranked third and fourth respectively while both region and geology were ranked fifth. In addition, Change in Thornthwaite Moisture Index was noted to have the strongest correlation with other input parameters.