A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
According to the design and construction data of a cable-stayed highway bridge, damage-detection-oriented finite element model of the bridge is established, and BP neural networks is applied to identify bridge damaged. From the results of calculation and the analysis, following conclusions can be drawn. The optimized BP neural networks can effectively discern the position of the damage and the degree of the damage at the same time. For the training samples, BP neural networks can identify damaged locations with high accuracy. For the testing samples, the accuracy of damaged degree identification is also rather high. The displacement mode and curvature mode can be used as indices of damaged identification for cable-stayed bridge. Among them the susceptibility of the curvature modal index is higher than the that of the displacement modal index. The total accuracy rate of discernment to two and three damaged training samples is nearly up to 100 %. At the same time, they reflected very good discernment effect to the testing samples too. Above all, the method based on vibration modal analysis theory and BP neural networks can detect not only the location of the damage but also the degree of the damage.
According to the design and construction data of a cable-stayed highway bridge, damage-detection-oriented finite element model of the bridge is established, and BP neural networks is applied to identify bridge damaged. From the results of calculation and the analysis, following conclusions can be drawn. The optimized BP neural networks can effectively discern the position of the damage and the degree of the damage at the same time. For the training samples, BP neural networks can identify damaged locations with high accuracy. For the testing samples, the accuracy of damaged degree identification is also rather high. The displacement mode and curvature mode can be used as indices of damaged identification for cable-stayed bridge. Among them the susceptibility of the curvature modal index is higher than the that of the displacement modal index. The total accuracy rate of discernment to two and three damaged training samples is nearly up to 100 %. At the same time, they reflected very good discernment effect to the testing samples too. Above all, the method based on vibration modal analysis theory and BP neural networks can detect not only the location of the damage but also the degree of the damage.
Damage identification in cable-stayed bridge based on modal analysis and neural networks
Schadensidentifikation in Kabel verankerten Bücken auf der Grundlage der Modalanalyse und neuronaler Netze
2007
8 Seiten, 8 Bilder, 2 Tabellen, 5 Quellen
Conference paper
Storage medium
English
Modal Identification of Cable-Stayed Pedestrian Bridge.
| Online Contents | 1993
Modal Identification of a Cable-Stayed Bridge
| British Library Conference Proceedings | 1996
Modal Identification of Cable-Stayed Pedestrian Bridge
| British Library Online Contents | 1993
Modal Flexibility Analysis of Cable-Stayed Ting Kau Bridge for Damage Identification
| Online Contents | 2008