Structural Health Monitoring and Damage Detection Using Neural Networks

In the bridge health monitoring and evaluation systems, the modal parameter can only access needed accuracy after times of experiments. The paper proposed a kind of bridge structure damage diagnosis method based on artificial neural network using the time domain vibration signals. Several statistical parameters are selected as characteristic features of the time-domain vibration signals. Monitoring data is collected during artificially induced damage conditions. The results indicate that the vibration monitoring data, with selected statistical parameters and particular network architecture, give good results to predict the undamaged and damaged condition of the bridge.