A Numerical Simulation Study of Structural Damage Based on RBF Neural Network
It’s natural and direct to identify the structural stiffness based on the measurement of static displacement; In addition, considering that the lower frequencies of structures can be tested with high precision and can reflect the global dynamic properties of structures, static displacements at partial nodes and several low frequencies were used to constitute the input parameter vectors for neural networks. A damage numerical verification on an arch bridge model was carried out using a radical basis function (RBF) network. Identification results indicate that the neural network has an excellence capability to identify the location and extent of structural damage with the limited noises and incomplete measured data.
KeywordsDamage Location Quantification Result Damage Identification Hide Layer Node Identification Capability
Unable to display preview. Download preview PDF.
- 1.Wang, B.S., Ding, H.J.: Influence of modeling errors on structural damage identification using artificial neural networks [J]. China Civil Engineering Journal 33(1), 50–55 (2000)Google Scholar
- 8.Wen, X., Zhou, L.: Neural networks application design based on MATLAB [M], pp. 207–232. Science Publishing Company, Beijing (2000)Google Scholar