CoChat

Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends

Open access
Jia, Jing, Li, Ying · 2023 · Sensors

The DOI matches its Crossref record; 264 of the 271 references it cites were found in a registry or an index; 38 of the 105 sources its claims cite were checked for support.

Abstract

Environmental effects may lead to cracking, stiffness loss, brace damage, and other damages in bridges, frame structures, buildings, etc. Structural Health Monitoring (SHM) technology could prevent catastrophic events by detecting damage early. In recent years, Deep Learning (DL) has developed rapidly and has been applied to SHM to detect, localize, and evaluate diverse damages through efficient feature extraction. This paper analyzes 337 articles through a systematic literature review to investigate the application of DL for SHM in the operation and maintenance phase of facilities from three perspectives: data, DL algorithms, and applications. Firstly, the data types in SHM and the corresponding collection methods are summarized and analyzed. The most common data types are vibration signals and images, accounting for 80% of the literature studied. Secondly, the popular DL algorithm types and application areas are reviewed, of which CNN accounts for 60%. Then, this article carefully analyzes the specific functions of DL application for SHM based on the facility’s characteristics. The most scrutinized study focused on cracks, accounting for 30 percent of research papers. Finally, challenges and trends in applying DL for SHM are discussed. Among the trends, the Structural Health Monitoring Digital Twin (SHMDT) model framework is suggested in response to the trend of strong coupling between SHM technology and Digital Twin (DT), which can advance the digitalization, visualization, and intelligent management of SHM.

Overview

CoChat Summary

TL;DR

This systematic review analyzes 337 articles on deep learning (DL) for structural health monitoring (SHM), organizing the literature by data, algorithms, and applications. It finds CNN-dominated research, highlights cracks and bridges as major foci, and proposes a Structural Health Monitoring Digital Twin (SHMDT) framework as a future trend.

Key findings

  • The review covers 337 articles, including 23 review articles, retrieved from Web of Science for 1 January 2017–31 March 2023.
  • Vibration signals and images are the most common data types, together accounting for 80% of the studied literature; CNN accounts for 60% of DL algorithm studies.
  • Cracks are the most scrutinized application, accounting for 30% of research papers; bridges receive the highest proportion of application attention.
  • Only 15% of the research literature reaches the practical application stage, mainly for bridges; the paper suggests an SHMDT model framework to advance digitalization, visualization, and intelligent SHM management.

Methods

  • Systematic literature review using Web of Science with keywords combining SHM, DL, and CNN; 555 journal articles were retrieved, then manually screened to 337 articles, including 23 reviews.
  • The review analyzes the selected literature across three perspectives: data types and acquisition methods, DL algorithms, and application objects/functions.
  • Bibliometric and keyword co-occurrence analysis (VOSviewer) and summary tables/figures are used, followed by discussion of challenges and trends and proposal of the SHMDT framework.

Limitations

  • The paper states that it focuses more on CNNs, is retrieved only through the Web of Science platform, and covers three broad perspectives, so some detailed content is not discussed thoroughly.
  • Evident from the text: including CNN as a search keyword may bias the algorithm coverage toward CNN and underrepresent other DL methods.
  • Evident from the text: the search time frame is limited to 2017–31 March 2023, so earlier and later literature is excluded.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/s23218824

Cites

264 of 264 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Literature retrieval flow chart.
Figure 1 Literature retrieval flow chart.CC BY · PubMed Central
Figure 2 Number of DL and SHM-related articles from 2017 to 2023.
Figure 2 Number of DL and SHM-related articles from 2017 to 2023.CC BY · PubMed Central
Figure 3 Keyword co-occurrence graph.
Figure 3 Keyword co-occurrence graph.CC BY · PubMed Central
Figure 4 Data types summary diagram.
Figure 4 Data types summary diagram.CC BY · PubMed Central
Figure 5 Data types percentage diagram.
Figure 5 Data types percentage diagram.CC BY · PubMed Central
Figure 6 DL algorithm summary diagram.
Figure 6 DL algorithm summary diagram.CC BY · PubMed Central
Figure 7 CNN architecture diagram [160].
Figure 7 CNN architecture diagram [160].CC BY · PubMed Central
Figure 8 RNN architecture diagram [104].
Figure 8 RNN architecture diagram [104].CC BY · PubMed Central
Figure 9 Auto-encoder architecture diagram [104].
Figure 9 Auto-encoder architecture diagram [104].CC BY · PubMed Central
Figure 10 GAN architecture diagram [104].
Figure 10 GAN architecture diagram [104].CC BY · PubMed Central
Figure 11 DL algorithm types percentage graph.
Figure 11 DL algorithm types percentage graph.CC BY · PubMed Central
Figure 12 Application summary diagram of facility components.
Figure 12 Application summary diagram of facility components.CC BY · PubMed Central
Figure 13 Application summary diagram of facilities.
Figure 13 Application summary diagram of facilities.CC BY · PubMed Central
Figure 14 Other application functions summary diagram.
Figure 14 Other application functions summary diagram.CC BY · PubMed Central
Figure 15 Application summary diagram.
Figure 15 Application summary diagram.CC BY · PubMed Central
Figure 16 Trends (future direction and solution) summary diagram.
Figure 16 Trends (future direction and solution) summary diagram.CC BY · PubMed Central
Figure 17 SHMDT architecture diagram.
Figure 17 SHMDT architecture diagram.CC BY · PubMed Central

Verification

Claims the paper makes

25 Valid · 29 Not valid · 34 Not checked · 100 Own results and interpretations

49 more claims · 6 with their cited sources checked

Create a free account to see all 188 claims and to verify the 4 references still open.

See all claims — free account
  • Probably not a substantial claim. 106
  • It may state two separate claims as one. 84

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

2 of 2

Cited works that were retracted

Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.

1 of 1

Citations

Cites

1 retracted

Research works printed but not linked: 3

  1. Rytter, A. (1993). Vibrational Based Inspection of Civil Engineering Structures. [Ph.D. Thesis, Aalborg University].
  2. Hosoda, 2022, Prediction of maximum crack width by machine learning using concrete construction data in yamaguchi system, Int. J. Intell. Inform. Infrastruct. Data Sci. Pap., 3, 898
  3. Grieves, M., and Vickers, J. (2017). Transdisciplinary Perspectives on Complex Systems: New Findings and Approaches, Springer.

Cited by

See all 182

Metadata

Authors
Jia, J., & Li, Y.
Affiliations
Ocean University of China (CN)
Corresponding author
Jia, Jing
Venue
Sensors
Publisher
MDPI AG
Published
2023-10-30
Volume
23
Issue
21
Pages
8824
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4388018712
Cited by
182
References
271
Citations by year
2026: 97 · 2025: 64 · 2024: 20 · 2023: 1
FWCI
3.31
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (51908523)
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 › Civil and Structural Engineering › Structural Engineering and Materials Analysis
Keywords
structural health monitoring, deep learning, damage detection, crack detection, vibration signals, image-based damage detection, convolutional neural networks, digital twin, bridge structures, structural damage localization

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

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

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.