Proceedings of the 3rd International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2024)

<Previous Article In Volume
Next Article In Volume>

Efficient Anomaly Detection of Structural Health Monitoring Based on Improved MobileViTv3

Authors
Shuoting Zhao1, 2, Zhiyi Tang1, 2, *
1Faculty of Civil Engineering and Mechanics, Kunming University of Science and Technology, Kunming, 650500, China
2Intelligent Infrastructure Operation and Maintenance Technology Innovation Team of Yunnan Provincial, Department of Education, Kunming University of Science and Technology, Kunming, 650500, China
*Corresponding author. Email: tang@kust.edu.cn
Corresponding Author
Zhiyi Tang
Available Online 19 May 2025.
DOI
10.2991/978-94-6463-728-1_74How to use a DOI?
Keywords
Structural health monitoring; Data anomaly detection; MobileViTv3; Lightweight algorithm
Abstract

Actual structural health monitoring systems inevitably generate abnormal monitoring data, which affects the detection of structural damage. To improve the efficiency and accuracy of detecting various types of abnormal data in monitoring, this study proposes a structural health monitoring anomaly data diagnosis method based on an improved MobileViTv3 algorithm. This method aims to maintain high-precision monitoring while significantly reducing the model's weight and prediction time. To achieve this, two strategies are introduced: first, reducing the number of main network blocks to decrease the model's parameters; second, employing an increased expansion factor strategy to enhance the model's ability to capture features at different scales. These improvements allow the algorithm to better meet the needs of anomaly data detection. Additionally, a comparative analysis was conducted on a large bridge structural health monitoring system dataset against mainstream models such as VGG, ResNet, MobileNet, and EfficientNet. The study results show that the improved MobileViTv3 algorithm achieved the highest recognition accuracy of 96.8% in anomaly data detection tasks, reducing the model size to 1.4 MB, and also demonstrated significant advantages in training and prediction efficiency.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 3rd International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2024)
Series
Advances in Engineering Research
Publication Date
19 May 2025
ISBN
978-94-6463-728-1
ISSN
2352-5401
DOI
10.2991/978-94-6463-728-1_74How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Shuoting Zhao
AU  - Zhiyi Tang
PY  - 2025
DA  - 2025/05/19
TI  - Efficient Anomaly Detection of Structural Health Monitoring Based on Improved MobileViTv3
BT  - Proceedings of the 3rd International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2024)
PB  - Atlantis Press
SP  - 798
EP  - 810
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-728-1_74
DO  - 10.2991/978-94-6463-728-1_74
ID  - Zhao2025
ER  -