A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield
The timely detection of delamination is essential for preventing catastrophic failures and extending the service life of carbon fiber-reinforced polymers (CFRP). Full wavefields in CFRP encapsulate extensive information on the interaction between guided waves and structural damage, making them a wid...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4292 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850071097003737088 |
|---|---|
| author | Yitian Yan Kang Yang Yaxun Gou Zhifeng Tang Fuzai Lv Zhoumo Zeng Jian Li Yang Liu |
| author_facet | Yitian Yan Kang Yang Yaxun Gou Zhifeng Tang Fuzai Lv Zhoumo Zeng Jian Li Yang Liu |
| author_sort | Yitian Yan |
| collection | DOAJ |
| description | The timely detection of delamination is essential for preventing catastrophic failures and extending the service life of carbon fiber-reinforced polymers (CFRP). Full wavefields in CFRP encapsulate extensive information on the interaction between guided waves and structural damage, making them a widely utilized tool for damage mapping. However, due to the multimodal and dispersive nature of guided waves, interpreting full wavefields remains a significant challenge. This study proposes an end-to-end delamination imaging approach based on UNet++ using 2D frequency domain spectra (FDS) derived from full wavefield data. The proposed method is validated through a self-constructed simulation dataset, experimental data collected using Scanning Laser Doppler Vibrometry, and a publicly available dataset created by Kudela and Ijjeh. The results on the simulated data show that UNet++, trained with multi-frequency FDS, can accurately predict the location, shape, and size of delamination while effectively handling frequency offsets and noise interference in the input FDS. Experimental results further indicate that the model, trained exclusively on simulated data, can be directly applied to real-world scenarios, delivering artifact-free delamination imaging. |
| format | Article |
| id | doaj-art-d5679a5b29b54e2fa191114f758051fb |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-d5679a5b29b54e2fa191114f758051fb2025-08-20T02:47:22ZengMDPI AGSensors1424-82202025-07-012514429210.3390/s25144292A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full WavefieldYitian Yan0Kang Yang1Yaxun Gou2Zhifeng Tang3Fuzai Lv4Zhoumo Zeng5Jian Li6Yang Liu7State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaDepartment of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USAState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaInstitute of Modern Manufacturing Engineering, Zhejiang University, Hangzhou 310058, ChinaInstitute of Modern Manufacturing Engineering, Zhejiang University, Hangzhou 310058, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaState Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, ChinaThe timely detection of delamination is essential for preventing catastrophic failures and extending the service life of carbon fiber-reinforced polymers (CFRP). Full wavefields in CFRP encapsulate extensive information on the interaction between guided waves and structural damage, making them a widely utilized tool for damage mapping. However, due to the multimodal and dispersive nature of guided waves, interpreting full wavefields remains a significant challenge. This study proposes an end-to-end delamination imaging approach based on UNet++ using 2D frequency domain spectra (FDS) derived from full wavefield data. The proposed method is validated through a self-constructed simulation dataset, experimental data collected using Scanning Laser Doppler Vibrometry, and a publicly available dataset created by Kudela and Ijjeh. The results on the simulated data show that UNet++, trained with multi-frequency FDS, can accurately predict the location, shape, and size of delamination while effectively handling frequency offsets and noise interference in the input FDS. Experimental results further indicate that the model, trained exclusively on simulated data, can be directly applied to real-world scenarios, delivering artifact-free delamination imaging.https://www.mdpi.com/1424-8220/25/14/4292ultrasonic guided wavenon-destructive evaluationcarbon fiber-reinforced plasticdeep learningdelamination |
| spellingShingle | Yitian Yan Kang Yang Yaxun Gou Zhifeng Tang Fuzai Lv Zhoumo Zeng Jian Li Yang Liu A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield Sensors ultrasonic guided wave non-destructive evaluation carbon fiber-reinforced plastic deep learning delamination |
| title | A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield |
| title_full | A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield |
| title_fullStr | A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield |
| title_full_unstemmed | A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield |
| title_short | A UNet++-Based Approach for Delamination Imaging in CFRP Laminates Using Full Wavefield |
| title_sort | unet based approach for delamination imaging in cfrp laminates using full wavefield |
| topic | ultrasonic guided wave non-destructive evaluation carbon fiber-reinforced plastic deep learning delamination |
| url | https://www.mdpi.com/1424-8220/25/14/4292 |
| work_keys_str_mv | AT yitianyan aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT kangyang aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT yaxungou aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT zhifengtang aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT fuzailv aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT zhoumozeng aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT jianli aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT yangliu aunetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT yitianyan unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT kangyang unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT yaxungou unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT zhifengtang unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT fuzailv unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT zhoumozeng unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT jianli unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield AT yangliu unetbasedapproachfordelaminationimagingincfrplaminatesusingfullwavefield |