Estimates of Bridge Girder Conditions Based on Fuzzy Inspection Data

An effective bridge maintenance system requires an accurate bridge prediction model. Ordinary regression models have been extensively used to forecast future infrastructure conditions. However, data on current bridge conditions obtained from inspectors are inherently subjective and non-crisp; thus ordinary regression techniques are incapable of predicting bridge states when inspection data are fuzzy. This paper utilizes Chang´s fuzzy linear regression model for the estimation of bridge girder conditions. The model can deal with a mixture of fuzzy data and crisp data. An empirical case study is used to examine the variables contributing to deterioration of bridge girders. The results demonstrate the capability of the model.