Bridge Damage Detection Research Articles

Constructing input vectors to neural networks for structural damage identification

This paper addresses construction of appropriate input vectors (input patterns) toneural networks for hierarchical identification of structural damage locationand extent from measured modal properties. Hierarchical use of neuralnetworks is feasible for damage detection of large-scale civil structures such ascable-supported bridges and tall buildings. The neural network is first trainedusing one-level damage samples to locate the position of damage. After thedamage location is determined, the network is re-trained by an incremental weightupdate method using additional samples corresponding to different damagedegrees but only at the identified location. The re-trained network offers anaccurate evaluation of the damage extent. The input vectors have been designedto meet two requirements: (i) most parameters of the input vectors are arguablyindependent of damage extent and only depend on damage location; (ii) allparameters of the input vectors can be computed from several natural frequenciesand a few incomplete modal vectors. The damage detection capacity of suchconstructed networks is experimentally verified on a steel frame withextent-unknown damage inflicted at its connections, and the applicability of thehierarchical identification strategy to cable-supported bridges is discussed.

Nondestructive Damage Detection of Bridges: A Status Review

The recent advances in detecting and locating damage in bridges by different kinds of non-destructive testing and evaluation (NDT&E) methods are reviewed. From the application point of view, classifications for general bridge components and their damage types are presented. The relationships between damage, bridge components, and NDT&E techniques are summarized. Many useful WEB sources of NDT&E techniques in bridge damage detection are given. It is concluded that: (1) vibration-based damage detection methods are successful to a certain extent, especially when the overall damage is significant and, low frequency vibration can identify those areas where more detailed local inspection should be concentrated; (2) robust identification techniques that are able to locate damage based on realistic measured data sets still seem a long way from reality, and, basic research is still necessary in the mean time; (3) the rapid development of computer technology and digital signal processing (DSP) techniques greatly impacts upon the conventional NDT techniques, especially in control data processing and data displaying, as well as in simulation and modeling; (4) most of the NDT&E techniques introduced in this paper have their own practical commercial systems, but the effort required for combining the theoretical, experimental and engineering achievements, is still a challenging task when establishing the relationship between the unknown quantities and the measured signal parameters and specialised instruments have shown great advantages for doing some things more effectively than general ones; (5) in bridge damage detection, a problem usually requires the application of different NDT&E techniques; two or more independent techniques are needed to enable confidence in the results.

Time-delay neural networks in damage detection of railway bridges

The recent developments in multilayer perceptron using the backpropagation algorithm, has opened up new possibilities in structural identification. Limitation of traditional neural networks (TNN) in dealing with patterns that may vary in time domain has given birth to time-delay neural networks (TDNN). In the present paper the TNN and the TDNN have been implemented in detecting the damage in bridge structure using vibration signature analysis. A comparative study has been carried out for the various cases of complete as well as incomplete measurement data. It has been observed that TDNNs have performed better than TNNs in this application.