Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model

Huanjia Hu; Xuebin Xu; Cheng Liu

doi:10.1109/ICSMD67131.2025.11365359

Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model

Huanjia Hu
, Xuebin Xu
, Cheng Liu^*

^*Corresponding author for this work

Department of Systems Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Advanced Structural Health Monitoring (SHM) systems are essential for aging aerospace infrastructure and Carbon Fiber Reinforced Polymer (CFRP) structures. Though Lamb wave-based Non-Destructive Testing (NDT) effectively monitors CFRP, traditional methods struggle with complex wave patterns, environmental variations, and large data volumes from continuous monitoring. This research overcomes these limitations by developing an AI system that integrates Lamb wave testing with Vision Transformer. The approach captures Lamb wave signals via actuators and sensors settled on CFRP structures, converting them into Continuous Wavelet Transform (CWT) inputs, and automates damage identification. This framework improves detection accuracy and reliability, enabling real-time assessment. © 2025 IEEE.

Original language	English
Title of host publication	2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD)
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	978-1-6654-7742-0
ISBN (Print)	978-1-6654-7745-1
DOIs	https://doi.org/10.1109/ICSMD67131.2025.11365359
Publication status	Published - Nov 2025
Event	6th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence (ICSMD 2025) - Guangzhou, China Duration: 21 Nov 2025 → 23 Nov 2025 https://icsmd2025.aconf.org/

Publication series

Name	ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence

Conference

Conference	6th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence (ICSMD 2025)
Abbreviated title	ICSMD2025
Place	China
City	Guangzhou
Period	21/11/25 → 23/11/25
Internet address	https://icsmd2025.aconf.org/

Research Keywords

Artificial Intelligence
CFRP Material
Continuous Wavelet Transform
EfficientNet Series
Non-Destructive Testing
Structural Health Monitoring
Vision Transformer

Access Output

10.1109/ICSMD67131.2025.11365359

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Hu, H., Xu, X., & Liu, C. (2025). Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model. In 2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) (ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence). IEEE. https://doi.org/10.1109/ICSMD67131.2025.11365359

Hu, Huanjia ; Xu, Xuebin ; Liu, Cheng. / Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model. 2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD). IEEE, 2025. (ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence).

@inproceedings{eea0f94c449a410b9d7ccb65ec4bcca1,

title = "Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model",

abstract = "Advanced Structural Health Monitoring (SHM) systems are essential for aging aerospace infrastructure and Carbon Fiber Reinforced Polymer (CFRP) structures. Though Lamb wave-based Non-Destructive Testing (NDT) effectively monitors CFRP, traditional methods struggle with complex wave patterns, environmental variations, and large data volumes from continuous monitoring. This research overcomes these limitations by developing an AI system that integrates Lamb wave testing with Vision Transformer. The approach captures Lamb wave signals via actuators and sensors settled on CFRP structures, converting them into Continuous Wavelet Transform (CWT) inputs, and automates damage identification. This framework improves detection accuracy and reliability, enabling real-time assessment. {\textcopyright} 2025 IEEE.",

keywords = "Artificial Intelligence, CFRP Material, Continuous Wavelet Transform, EfficientNet Series, Non-Destructive Testing, Structural Health Monitoring, Vision Transformer",

author = "Huanjia Hu and Xuebin Xu and Cheng Liu",

year = "2025",

month = nov,

doi = "10.1109/ICSMD67131.2025.11365359",

language = "English",

isbn = "978-1-6654-7745-1",

series = "ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence",

publisher = "IEEE",

booktitle = "2025 International Conference on Sensing, Measurement \& Data Analytics in the era of Artificial Intelligence (ICSMD)",

address = "United States",

note = "6th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence (ICSMD 2025), ICSMD2025 ; Conference date: 21-11-2025 Through 23-11-2025",

url = "https://icsmd2025.aconf.org/",

}

Hu, H, Xu, X & Liu, C 2025, Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model. in 2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD). ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, IEEE, 6th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence (ICSMD 2025), Guangzhou, China, 21/11/25. https://doi.org/10.1109/ICSMD67131.2025.11365359

Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model. / Hu, Huanjia; Xu, Xuebin ; Liu, Cheng.
2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD). IEEE, 2025. (ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model

AU - Hu, Huanjia

AU - Xu, Xuebin

AU - Liu, Cheng

PY - 2025/11

Y1 - 2025/11

N2 - Advanced Structural Health Monitoring (SHM) systems are essential for aging aerospace infrastructure and Carbon Fiber Reinforced Polymer (CFRP) structures. Though Lamb wave-based Non-Destructive Testing (NDT) effectively monitors CFRP, traditional methods struggle with complex wave patterns, environmental variations, and large data volumes from continuous monitoring. This research overcomes these limitations by developing an AI system that integrates Lamb wave testing with Vision Transformer. The approach captures Lamb wave signals via actuators and sensors settled on CFRP structures, converting them into Continuous Wavelet Transform (CWT) inputs, and automates damage identification. This framework improves detection accuracy and reliability, enabling real-time assessment. © 2025 IEEE.

AB - Advanced Structural Health Monitoring (SHM) systems are essential for aging aerospace infrastructure and Carbon Fiber Reinforced Polymer (CFRP) structures. Though Lamb wave-based Non-Destructive Testing (NDT) effectively monitors CFRP, traditional methods struggle with complex wave patterns, environmental variations, and large data volumes from continuous monitoring. This research overcomes these limitations by developing an AI system that integrates Lamb wave testing with Vision Transformer. The approach captures Lamb wave signals via actuators and sensors settled on CFRP structures, converting them into Continuous Wavelet Transform (CWT) inputs, and automates damage identification. This framework improves detection accuracy and reliability, enabling real-time assessment. © 2025 IEEE.

KW - Artificial Intelligence

KW - CFRP Material

KW - Continuous Wavelet Transform

KW - EfficientNet Series

KW - Non-Destructive Testing

KW - Structural Health Monitoring

KW - Vision Transformer

UR - https://www.scopus.com/pages/publications/105034872108

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105034872108&origin=recordpage

U2 - 10.1109/ICSMD67131.2025.11365359

DO - 10.1109/ICSMD67131.2025.11365359

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-6654-7745-1

T3 - ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence

BT - 2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD)

PB - IEEE

T2 - 6th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence (ICSMD 2025)

Y2 - 21 November 2025 through 23 November 2025

ER -

Hu H, Xu X , Liu C. Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model. In 2025 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD). IEEE. 2025. (ICSMD - International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence). doi: 10.1109/ICSMD67131.2025.11365359

Structural Health Monitoring of CFRP Composite Structures Using a Hybrid CNN-Vision Transformer Model

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this