An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China
Tunnel lining defects are one of the most common problems that tunnels experience during operation, and they can pose severe safety risks. The most popular nondestructive testing method for detecting tunnel lining defects is ground penetrating radar (GPR), one of the basic geophysical applications....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/21/10234 |
| _version_ | 1797512774726713344 |
|---|---|
| author | Dongli Li Echuan Yan |
| author_facet | Dongli Li Echuan Yan |
| author_sort | Dongli Li |
| collection | DOAJ |
| description | Tunnel lining defects are one of the most common problems that tunnels experience during operation, and they can pose severe safety risks. The most popular nondestructive testing method for detecting tunnel lining defects is ground penetrating radar (GPR), one of the basic geophysical applications. However, detection responses might differ significantly from the real shape of tunnel lining defects, making it challenging to identify and interpret. When data quality is poor, interpretation and identification become more challenging, resulting in a high cost of tunnel repairs. The improved back projection (BP) imaging and robust principal component analysis (RPCA) are used in this work to offer a GPR data processing method. Even in the event of poor data quality, our method could recover GPR responses, allowing the shapes and locations of tunnel lining flaws to be clearly depicted. With BP imaging, this approach recovers the tunnel defects’ responses to better forms and positions, and with RPCA, it further isolates the target imaging from clutters. Several synthetic data demonstrate that the approach presented in this work may successfully repair and extract the positions and forms of lining defects, making them easier to identify and comprehend. Furthermore, our technique was used to GPR data gathered from the Qiyue Mountain Tunnel in China, yielding more accurate findings than the traditional method, which was validated by the actual scenario to illustrate the efficiency of our method on real data. |
| first_indexed | 2024-03-10T06:06:26Z |
| format | Article |
| id | doaj.art-50620e92f4c04bea8d247b7b51fa2c7e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:06:26Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-50620e92f4c04bea8d247b7b51fa2c7e2023-11-22T20:29:47ZengMDPI AGApplied Sciences2076-34172021-11-0111211023410.3390/app112110234An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, ChinaDongli Li0Echuan Yan1Faculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaFaculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaTunnel lining defects are one of the most common problems that tunnels experience during operation, and they can pose severe safety risks. The most popular nondestructive testing method for detecting tunnel lining defects is ground penetrating radar (GPR), one of the basic geophysical applications. However, detection responses might differ significantly from the real shape of tunnel lining defects, making it challenging to identify and interpret. When data quality is poor, interpretation and identification become more challenging, resulting in a high cost of tunnel repairs. The improved back projection (BP) imaging and robust principal component analysis (RPCA) are used in this work to offer a GPR data processing method. Even in the event of poor data quality, our method could recover GPR responses, allowing the shapes and locations of tunnel lining flaws to be clearly depicted. With BP imaging, this approach recovers the tunnel defects’ responses to better forms and positions, and with RPCA, it further isolates the target imaging from clutters. Several synthetic data demonstrate that the approach presented in this work may successfully repair and extract the positions and forms of lining defects, making them easier to identify and comprehend. Furthermore, our technique was used to GPR data gathered from the Qiyue Mountain Tunnel in China, yielding more accurate findings than the traditional method, which was validated by the actual scenario to illustrate the efficiency of our method on real data.https://www.mdpi.com/2076-3417/11/21/10234tunnel liningdetectionground penetrating radarback projection imagingrobust principal component analysis |
| spellingShingle | Dongli Li Echuan Yan An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China Applied Sciences tunnel lining detection ground penetrating radar back projection imaging robust principal component analysis |
| title | An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China |
| title_full | An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China |
| title_fullStr | An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China |
| title_full_unstemmed | An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China |
| title_short | An Improved GPR Method Based on BP and RPCA for Tunnel Lining Defects Detection and Its Application in Qiyue Mountain Tunnel, China |
| title_sort | improved gpr method based on bp and rpca for tunnel lining defects detection and its application in qiyue mountain tunnel china |
| topic | tunnel lining detection ground penetrating radar back projection imaging robust principal component analysis |
| url | https://www.mdpi.com/2076-3417/11/21/10234 |
| work_keys_str_mv | AT donglili animprovedgprmethodbasedonbpandrpcafortunnelliningdefectsdetectionanditsapplicationinqiyuemountaintunnelchina AT echuanyan animprovedgprmethodbasedonbpandrpcafortunnelliningdefectsdetectionanditsapplicationinqiyuemountaintunnelchina AT donglili improvedgprmethodbasedonbpandrpcafortunnelliningdefectsdetectionanditsapplicationinqiyuemountaintunnelchina AT echuanyan improvedgprmethodbasedonbpandrpcafortunnelliningdefectsdetectionanditsapplicationinqiyuemountaintunnelchina |