Structural health monitoring with statistical methods during progressive damage test of S101 Bridge

Döhler, Michael; Hille, Falk; Mevel, Laurent; Rücker, Werner

doi:10.1016/j.engstruct.2014.03.010

Cited by 124 publications

(77 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To this end, researchers have proposed various structural health monitoring (SHM) and structural damage detection (SDD) approaches. Examples are the vision‐based methods of Khuc and Catbas () and Barile, Casavola, Pappalettera, and Pappalettere (), Zaurin and Catbas (), and the vibration‐based SDD methods of Chang and Kim (), Döhler, Hille, Mevel, and Rücker (), Farahani and Penumadu (), and Kumar, Oshima, Yamazaki, Mikami, and Miyamouri ().…”

Section: Introductionmentioning

confidence: 99%

“…The subtle natural frequency changes induced by low-scale damages are easily smothered by environmental effects. Damage detection in changing environments has been discussed in several papers (Deraemaeker, Reynders, De Roeck, & Kullaa, 2008;Döhler et al, 2014;Reynders et al, 2014;Spiridonakos & Chatzi, 2014;Yan et al, 2005). As SDD indicators, natural frequencies lack information of the damage locations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vibration‐based structural state identification by a 1‐dimensional convolutional neural network

Zhang

Miyamori

Mikami

et al. 2019

Computer aided Civil Eng

209

View full text Add to dashboard Cite

Deep learning has ushered in many breakthroughs in vision‐based detection via convolutional neural networks (CNNs), but the vibration‐based structural damage detection by CNN remains being refined. Thus, this study proposes a simple one‐dimensional CNN that detects tiny local structural stiffness and mass changes, and validates the proposed CNN on actual structures. Three independent acceleration databases are established based on a T‐shaped steel beam, a short steel girder bridge (in test field), and a long steel girder bridge (in service). The raw acceleration data are not pre‐processed and are directly used as the training and validation data. The well‐trained CNN almost perfectly identifies the locations of small local changes in the structural mass and stiffness, demonstrating the high sensitivity of the proposed simple CNN to tiny structural state changes in actual structures. The convolutional kernels and outputs of the convolutional and max pooling layers are visualized and discussed as well.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vibration‐based structural state identification by a 1‐dimensional convolutional neural network

Zhang

Miyamori

Mikami

et al. 2019

Computer aided Civil Eng

209

View full text Add to dashboard Cite

show abstract

“…Since the applied damage detection framework already proved to be feasible for real civil structures in the field (see e.g. case studies [9,14,4]), the presented test robust to excitation changes should be of value for such applications, where the excitation is ambient and uncontrolled, and where the new test is thus expected to detect damage earlier and more reliably. The application of the new test to structures in the field is part of future work.…”

Section: Discussionmentioning

confidence: 99%

Subspace-Based Damage Detection on Steel Frame Structure Under Changing Excitation

Döhler

Hille

2014

Conference Proceedings of the Society for Experimental Mechanics Series

View full text Add to dashboard Cite

To cite this version:Michael Döhler, Falk Hille. Subspace-based damage detection on steel frame structure under changing excitation. AbstractDamage detection can be performed by detecting changes in the modal parameters between a reference state and the current (possibly damaged) state of a structure from measured output-only vibration data. Alternatively, a subspace-based damage detection test has been proposed and applied successfully, where changes in the modal parameters are detected, but the estimation of the modal parameters themselves is avoided. Like this, the test can run in an automated way directly on the vibration measurements. However, it was assumed that the unmeasured ambient excitation properties during measurements of the structure in the reference and possibly damaged condition stay constant, which is hardly satisfied by any application. A new version of the test has been derived recently that is robust to such changes in the ambient excitation. In this paper, the robust test is recalled and its performance is evaluated both on numerical simulations and a real application, where a steel frame structure is artificially damaged in the lab.

show abstract

“…An indicator sensitive to damage is a quantity extracted from the measured system's response that is able to indicate the presence of a structural change. Identifying features that can accurately distinguish a damaged structure from an undamaged one is the focus of most Structural Health Monitoring (SHM) techniques [3,4]. One of the most common methods of feature extraction comes from correlating observations of measured quantities with posterior observations of the degrading system.…”

Section: Introductionmentioning

confidence: 99%

Structural modification assessment using supervised learning methods applied to vibration data

Alves

Cury

Roitman

et al. 2015

Engineering Structures

View full text Add to dashboard Cite

Structural health monitoring with statistical methods during progressive damage test of S101 Bridge

Cited by 124 publications

References 28 publications

Vibration‐based structural state identification by a 1‐dimensional convolutional neural network

Vibration‐based structural state identification by a 1‐dimensional convolutional neural network

Subspace-Based Damage Detection on Steel Frame Structure Under Changing Excitation

Structural modification assessment using supervised learning methods applied to vibration data

Contact Info

Product

Resources

About