Artificial neural network method to evaluate bridge damage conditions

In view of the weakness of existing bridge evaluation methods, a neural network method was first introduced to evaluate the damage conditions of a bridge. The evaluation effects of several common artificial neural network (ANN) models were then compared. The ANN models were finally trained and tested based on the maintenance data of 1018 bridges on the national-grade roads in Guangdong province. It is found that the neural network method is effective in evaluating the bridge conditions, more than 60% of the bridge grade being correctly evaluated and the average evaluation error of each bridge being 0.25 grades.