Implementation of Elman neural networks for enhancing reliability of integrated bridge deterioration model

Probabilistic modelling is one of the most prominent techniques in bridge deterioration forecast. It can be classified into two types, namely, state- and time-based models. Reliability of both modelling techniques in forecasting long-term performance rely heavily on sufficient amount of bridge condition rating data being available together with well-distributed deterioration pattern over the age of bridge. However, it can be problematic when the available condition rating records are insufficient. In order to overcome this problem, an integrated deterioration method incorporating both the state- and time-based models has recently been developed. Despite such development and advancement, certain issues still remain with some cases of given condition data that cannot be used to produce reliable long-term performance curve. Aiming to achieve enhanced prediction performance, an Elman neural networks (ENN) technique is incorporated in the integrated method to replace the third-order polynomial regression function, the latter being the core component for long-term prediction in the state-based model. In the present study, the ENN are able to generate more reliable deterioration patterns than a typical deterministic method. The results demonstrate that the integrated method incorporating ENN are more effective in handling various situations of condition data quantities and distributions for generating long-term performance curves. © Institution of Engineers Australia, 2014