Deep residual network framework for structural health monitoring
Convolutional neural networks have been widely employed for structural health monitoring and damage identification. The convolutional neural network is currently considered as the state-of-the-art method for structural damage identification due to its capabilities of efficient and robust feature lea...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
SAGE PUBLICATIONS LTD
2021
|
| Subjects: | |
| Online Access: | http://purl.org/au-research/grants/arc/FT190100801 http://hdl.handle.net/20.500.11937/90890 |
| _version_ | 1848765452536250368 |
|---|---|
| author | Wang, Ruhua Chencho, An, Senjian Li, Jun Li, Ling Hao, Hong Liu, Wan-Quan |
| author_facet | Wang, Ruhua Chencho, An, Senjian Li, Jun Li, Ling Hao, Hong Liu, Wan-Quan |
| author_sort | Wang, Ruhua |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Convolutional neural networks have been widely employed for structural health monitoring and damage identification. The convolutional neural network is currently considered as the state-of-the-art method for structural damage identification due to its capabilities of efficient and robust feature learning in a hierarchical manner. It is a tendency to develop a convolutional neural network with a deeper architecture to gain a better performance. However, when the depth of the network increases to a certain level, the performance will degrade due to the gradient vanishing issue. Residual neural networks can avoid the problem of vanishing gradients by utilizing skip connections, which allows the information flowing to the next layer through identity mappings. In this article, a deep residual network framework is proposed for structural health monitoring of civil engineering structures. This framework is composed of purely residual blocks which operate as feature extractors and a fully connected layer as a regressor. It learns the damage-related features from the vibration characteristics such as mode shapes and maps them into the damage index labels, for example, stiffness reductions of structures. To evaluate the efficacy and robustness of the proposed framework, an intensive evaluation is conducted with both numerical and experimental studies. The comparison between the proposed approach and the state-of-the-art models, including a sparse autoencoder neural network, a shallow convolutional neural network and a convolutional neural network with the same structure but without skip connections, is conducted. In the numerical studies, a 7-storey steel frame is investigated. Four scenarios with considering measurement noise and finite element modelling errors in the data sets are studied. The proposed framework consistently outperforms the state-of-the-art models in all the scenarios, especially for the most challenging scenario, which includes both measurement noise and uncertainties. Experimental studies on a prestressed concrete bridge in the laboratory are conducted. The proposed framework demonstrates consistent damage prediction results on this beam with the state-of-the-art models. |
| first_indexed | 2025-11-14T11:35:29Z |
| format | Journal Article |
| id | curtin-20.500.11937-90890 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T11:35:29Z |
| publishDate | 2021 |
| publisher | SAGE PUBLICATIONS LTD |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-908902023-05-05T05:56:09Z Deep residual network framework for structural health monitoring Wang, Ruhua Chencho, An, Senjian Li, Jun Li, Ling Hao, Hong Liu, Wan-Quan Science & Technology Technology Engineering, Multidisciplinary Instruments & Instrumentation Engineering Residual networks deep learning structural health monitoring damage identification uncertainties measurement noise DAMAGE IDENTIFICATION NEURAL-NETWORK Convolutional neural networks have been widely employed for structural health monitoring and damage identification. The convolutional neural network is currently considered as the state-of-the-art method for structural damage identification due to its capabilities of efficient and robust feature learning in a hierarchical manner. It is a tendency to develop a convolutional neural network with a deeper architecture to gain a better performance. However, when the depth of the network increases to a certain level, the performance will degrade due to the gradient vanishing issue. Residual neural networks can avoid the problem of vanishing gradients by utilizing skip connections, which allows the information flowing to the next layer through identity mappings. In this article, a deep residual network framework is proposed for structural health monitoring of civil engineering structures. This framework is composed of purely residual blocks which operate as feature extractors and a fully connected layer as a regressor. It learns the damage-related features from the vibration characteristics such as mode shapes and maps them into the damage index labels, for example, stiffness reductions of structures. To evaluate the efficacy and robustness of the proposed framework, an intensive evaluation is conducted with both numerical and experimental studies. The comparison between the proposed approach and the state-of-the-art models, including a sparse autoencoder neural network, a shallow convolutional neural network and a convolutional neural network with the same structure but without skip connections, is conducted. In the numerical studies, a 7-storey steel frame is investigated. Four scenarios with considering measurement noise and finite element modelling errors in the data sets are studied. The proposed framework consistently outperforms the state-of-the-art models in all the scenarios, especially for the most challenging scenario, which includes both measurement noise and uncertainties. Experimental studies on a prestressed concrete bridge in the laboratory are conducted. The proposed framework demonstrates consistent damage prediction results on this beam with the state-of-the-art models. 2021 Journal Article http://hdl.handle.net/20.500.11937/90890 10.1177/1475921720918378 English http://purl.org/au-research/grants/arc/FT190100801 SAGE PUBLICATIONS LTD unknown |
| spellingShingle | Science & Technology Technology Engineering, Multidisciplinary Instruments & Instrumentation Engineering Residual networks deep learning structural health monitoring damage identification uncertainties measurement noise DAMAGE IDENTIFICATION NEURAL-NETWORK Wang, Ruhua Chencho, An, Senjian Li, Jun Li, Ling Hao, Hong Liu, Wan-Quan Deep residual network framework for structural health monitoring |
| title | Deep residual network framework for structural health monitoring |
| title_full | Deep residual network framework for structural health monitoring |
| title_fullStr | Deep residual network framework for structural health monitoring |
| title_full_unstemmed | Deep residual network framework for structural health monitoring |
| title_short | Deep residual network framework for structural health monitoring |
| title_sort | deep residual network framework for structural health monitoring |
| topic | Science & Technology Technology Engineering, Multidisciplinary Instruments & Instrumentation Engineering Residual networks deep learning structural health monitoring damage identification uncertainties measurement noise DAMAGE IDENTIFICATION NEURAL-NETWORK |
| url | http://purl.org/au-research/grants/arc/FT190100801 http://hdl.handle.net/20.500.11937/90890 |