Scrutinizing the Performances of Hybrid ANN Models for Forecasting Condition of Bridges

Abstract Bridges all over the world are vulnerable to severe deterioration agents meanwhile their maintenance budgets being tightened. This state of affairs necessitates establishment an autonomous model predict performance condition bridges. research paper explores implementation a set intelligent data driven models analyze future ratings bridge decks. These comprise support vector machines, Gaussian process regression, regression tree, back propagation artificial neural network, Elman recurrent cascade forward long short‐term memory network and deep convolutional network. The comparison is carried out using five evaluation metrics root mean squared percentage error, absolute error relative error. herein developed validated structural information retrieved from National Bridge Inventory (NBI). It can be argued that could implemented by departments transportation monitor behavior components useful lifetime.