Data-Driven Structural Health Monitoring Using Feature Fusion and Hybrid Deep Learning
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Smart structural health monitoring (SHM) for large-scale infrastructure is an intriguing subject for engineering communities thanks to its significant advantages such as timely damage detection, optimal maintenance strategy, and reduced resource requirement. Yet, it is a challenging topic as it requires handling a large amount of collected sensors data continuously, which is inevitably contaminated by random noises. Therefore, this study developed a practical end-to-end framework that makes use of physical features embedded in raw data and an elaborated hybrid deep learning model, namely 1-DCNN-LSTM, featuring two algorithms—convolutional neural network (CNN) and long-short term memory (LSTM). In order to extract relevant features from sensory data, the method combines various signal processing techniques such as the autoregressive model, discrete wavelet transform, and empirical mode decomposition. The hybrid deep learning 1-DCNN-LSTM is designed based on the CNN’s capacity of capturing local information and the LSTM network’s prominent ability to learn long-term dependencies. Through three case studies involving both experimental and synthetic data sets, it is demonstrated that the proposed approach achieves highly accurate damage detection, as accurate as the powerful 2-D CNN, but with a lower time and memory complexity, making it suitable for real-time SHM.Note to Practitioners—This article aims to develop a practical data-driven method for automatically monitoring the operational state of structures. In order to achieve consistently and highly accurate results in performing different tasks for diverse structures, we combine underlying features in both time and frequency domains extracted from measured signal vibration data. Three popular data featuring methods are combined to achieve the diversity gain which would not be possible with each individual method. As the vibration is usually measured by long time-series signals, the most efficient deep learning architecture for time-series signal, namely long-short term memory (LSTM), is considered for this work. Besides, each structure has its own dynamic properties, i.e., eigenfrequencies, around which the most relevant information is in the frequency domain, thus convolutional neural network specifically designed for capturing local information is used in combination with LSTM, forming a hybrid deep learning architecture. The applicability and effectiveness of the proposed approach are supported by three case studies with different types of structures, showing highly accurate damage detection with reduced resource requirements. These advantages can be valuable for developing a model for live monitoring of structural health in the future life-line infrastructures.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The problem of data temporal and spatial feature extraction can be solved using a combination of the CNN and RNN methods, such as CNN with GRU [64,109,123], CNN with LSTM [27,178,179,180,181,182], CNN with Auto-encoder and [183], CNN with echo state networks [113], etc.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [178]
In the citing paper
“Dang et al. [178] combined CNN with LSTM to process vibration signals, and they achieved high-accuracy bridge DD with reduced time and memory complexity.”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [178]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Here one adopted the ResNet18 classifier [21] owing to its competitive performance, and explicit feed-forward architecture and used the transfer learning technique to fine-tune the model for structural damage identification tasks.”
MethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“Indeed, there are methods using AR coefficients, which are able to address noisy data effectively, for example, the works in [30], [19] extracting modal characteristics of the structure from AR coefficients.”
BackgroundMethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“Specifically, the optimizer is Adam [27], the learning rate standing for the relative amount of DL model weights updated after each optimization iteration, is set to lr = 0.”
MethodInfluentialPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 3×
“The present hybrid deep learning algorithm is implemented with the help of the open-source machine learning library Pytorch [20].”
MethodHuang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., Yen, N.-C., Tung, C. C., & Liu, H. H. (1998) · Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.1998.0193 · Cited by 23,564 · cited 1×
“[17], introduced an adaptive method called Empirical Mode Decomposition, which can”
MethodPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“For further details of the transfer learning technique, refer to [22].”
BackgroundSciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.64134 · Cited by 10,460
1D convolutional neural networks and applications: A survey
Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.107398 · Cited by 2,835
Fastai: A Layered API for Deep Learning
Howard, J., & Gugger, S. (2020) · Information · doi:10.3390/info11020108 · Cited by 971 · cited 1×
“The 2DCNN is implemented with the help of the deep learning library Fastai [23].”
MethodAutomated Crack Detection on Concrete Bridges
Prasanna, P., Dana, K. J., Gucunski, N., Basily, B. B., La, H. M., Lim, R. S., & Parvardeh, H. (2016) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2014.2354314 · Cited by 474 · cited 1×
“Here a common value K = 10 is selected [26], meaning the training process will be iterated ten times, each time one different portion is used for validation, whereas the remaining serves for training as illustrated in Fig.”
Method
Cited by
Digital Twins: A Survey on Enabling Technologies, Challenges, Trends and Future Prospects
Mihai, S., Yaqoob, M., Hung, D. V., Davis, W., Towakel, P., Raza, M., Karamanoglu, M., Barn, B., Shetve, D., Prasad, R. V., et al. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2022.3208773 · Cited by 1,049
“Thus, a highly modular architecture has been devised, allowing switching different DL algorithms and combining data from different sensors in a straightforward way [181].”
MethodSelf-citationIoT in smart cities: A survey of technologies, practices and challenges
Syed, A. S., Sierra-Sosa, D., Kumar, A., & Elmaghraby, A. (2021) · Smart Cities · doi:10.3390/smartcities4020024 · Cited by 527
“In [196–198], accelerometer signals have been used where as [199] have used piezo electric transducers for performing structural health monitoring of bridges formulated as a classifi-cation problem between different damaged states of a bridge.”
BackgroundCloud-Based Digital Twinning for Structural Health Monitoring Using Deep Learning
Dang, H., Tatipamula, M., & Nguyen, H. X. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3115119 · Cited by 270
Self-citationJia, J., & Li, Y. (2023) · Sensors · doi:10.3390/s23218824 · Cited by 182
“Dang et al. [178] combined CNN with LSTM to process vibration signals, and they achieved high-accuracy bridge DD with reduced time and memory complexity.”
BackgroundMethodMardanshahi, A., Sreekumar, A., Yang, X. P. O., Barman, S. K., & Chronopoulos, D. (2025) · Sensors · doi:10.3390/s25051424 · Cited by 233
Metadata
- Authors
- Dang, H. V., Tran-Ngoc, H., Nguyen, T. V., Bui-Tien, T., De Roeck, G., & Nguyen, H. X.
- Affiliations
- Ghent University (BE)
- Schlumberger (France) (FR)
- University of Transport and Communications (VN)
- Middlesex University London (GB)
- Venue
- IEEE Transactions on Automation Science and Engineering
- Published
- 2021-10
- Volume
- 18
- Issue
- 4
- Pages
- 2087-2103
- ISSN
- 1545-5955 (ISSN-L)
- 1558-3783
- OpenAlex
- W3100090196
- Cited by
- 170
- References
- 33
- Citations by year
- 2026: 28 · 2025: 37 · 2024: 40 · 2023: 35 · 2022: 20 · 2021: 9
- FWCI
- 9.50
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Automation Science and Engineering (publishedVersion)
- Middlesex University Research Repository (Middlesex University Of London) (acceptedVersion)
- Funders
- Institutional Links Grant, under the Newton Program Vietnam partnership (429715093)
- U.K. Department of Business, Energy and Industrial Strategy (BEIS) and delivered by the British Council
- Topics
- Physical Sciences › Engineering › Civil and Structural Engineering › Structural Health Monitoring Techniques
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Keywords
- structural health monitoring, damage detection, vibration signal analysis, CNN-LSTM hybrid model, feature fusion, discrete wavelet transform, empirical mode decomposition, autoregressive models, time-frequency feature extraction, real-time monitoring, sensor noise robustness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Data-Driven Structural Health Monitoring Using Feature Fusion and Hybrid Deep Learning. https://app.cochat.ai/papers/10.1109/tase.2020.3034401
- The paper
- Dang, H. V., Tran-Ngoc, H., Nguyen, T. V., Bui-Tien, T., De Roeck, G., & Nguyen, H. X. (2021). Data-Driven Structural Health Monitoring Using Feature Fusion and Hybrid Deep Learning. IEEE Transactions on Automation Science and Engineering. https://doi.org/10.1109/tase.2020.3034401
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.