Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound
Voids behind tunnel linings are critical factors affecting tunnels’ safety and durability. For automatic, rapid, and accurate detection of void defects behind tunnel linings, this paper proposes an intelligent recognition method of void detection based on deep learning (DL) and percussion method. Ex...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2023-12-01
|
| Series: | Journal of Intelligent Construction |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/JIC.2023.9180029 |
| _version_ | 1797354878588157952 |
|---|---|
| author | Xiaolei Zhang Xin Lin Wei Zhang Yong Feng Wei Lan Yuewu Da Kan Hu |
| author_facet | Xiaolei Zhang Xin Lin Wei Zhang Yong Feng Wei Lan Yuewu Da Kan Hu |
| author_sort | Xiaolei Zhang |
| collection | DOAJ |
| description | Voids behind tunnel linings are critical factors affecting tunnels’ safety and durability. For automatic, rapid, and accurate detection of void defects behind tunnel linings, this paper proposes an intelligent recognition method of void detection based on deep learning (DL) and percussion method. Extensive indoor percussion experiments were first conducted to obtain a total of 77,925 percussion signals. Afterward, the mel-frequency cepstrum coefficients (MFCCs) are utilized for signal feature extraction, based on which a convolutional neural network (CNN) is developed for automatic void defect diagnosis. The void automated diagnosis tests are subsequently performed, and the impact of three key factors on the recognition results is investigated. The results show that the proposed CNN can accurately identify voids ranging from 0.10 to 0.30 m, with an average accuracy of 94.96% and an F1 score of 72.29%. The exploration of the slab thickness indicates that the proposed method is capable of detecting voids with an average accuracy of 94.37% and an F1 score of 74.55%, with the slab thicknesses ranging from 0.10 to 0.30 m. Furthermore, the boundary effects of concrete slabs are analyzed. Finally, an on-site validation is carried out, and the good agreements between the developed method and ultrasonic detection method indicate that the CNN-aided percussion method is feasible in practical tunnel lining void inspection tasks. |
| first_indexed | 2024-03-08T13:56:10Z |
| format | Article |
| id | doaj.art-76c4cb4c2c5a497cb2c83ff7a11a296f |
| institution | Directory Open Access Journal |
| issn | 2958-3861 2958-2652 |
| language | English |
| last_indexed | 2024-03-08T13:56:10Z |
| publishDate | 2023-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Journal of Intelligent Construction |
| spelling | doaj.art-76c4cb4c2c5a497cb2c83ff7a11a296f2024-01-15T14:38:24ZengTsinghua University PressJournal of Intelligent Construction2958-38612958-26522023-12-01149180029918002910.26599/JIC.2023.9180029Intelligent recognition of voids behind tunnel linings using deep learning and percussion soundXiaolei Zhang0Xin Lin1Wei Zhang2Yong Feng3Wei Lan4Yuewu Da5Kan Hu6Key Laboratory of Geotechnical and Underground Engineering of the Ministry of Education, Department of Geotechnical Engineering, Tongji University, Shanghai 200092, ChinaKey Laboratory of Geotechnical and Underground Engineering of the Ministry of Education, Department of Geotechnical Engineering, Tongji University, Shanghai 200092, ChinaWuxi Water Group Co., Ltd., Wuxi 214031, ChinaUrban Mobility Institute, Tongji University, Shanghai 201804, ChinaShanghai Shenyuan Geotechnical Engineering Co., Ltd., Shanghai 200040, ChinaWuxi Water Group Co., Ltd., Wuxi 214031, ChinaWuxi Water Group Co., Ltd., Wuxi 214031, ChinaVoids behind tunnel linings are critical factors affecting tunnels’ safety and durability. For automatic, rapid, and accurate detection of void defects behind tunnel linings, this paper proposes an intelligent recognition method of void detection based on deep learning (DL) and percussion method. Extensive indoor percussion experiments were first conducted to obtain a total of 77,925 percussion signals. Afterward, the mel-frequency cepstrum coefficients (MFCCs) are utilized for signal feature extraction, based on which a convolutional neural network (CNN) is developed for automatic void defect diagnosis. The void automated diagnosis tests are subsequently performed, and the impact of three key factors on the recognition results is investigated. The results show that the proposed CNN can accurately identify voids ranging from 0.10 to 0.30 m, with an average accuracy of 94.96% and an F1 score of 72.29%. The exploration of the slab thickness indicates that the proposed method is capable of detecting voids with an average accuracy of 94.37% and an F1 score of 74.55%, with the slab thicknesses ranging from 0.10 to 0.30 m. Furthermore, the boundary effects of concrete slabs are analyzed. Finally, an on-site validation is carried out, and the good agreements between the developed method and ultrasonic detection method indicate that the CNN-aided percussion method is feasible in practical tunnel lining void inspection tasks.https://www.sciopen.com/article/10.26599/JIC.2023.9180029tunnelvoid defectdeep learningpercussion methodmfccs |
| spellingShingle | Xiaolei Zhang Xin Lin Wei Zhang Yong Feng Wei Lan Yuewu Da Kan Hu Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound Journal of Intelligent Construction tunnel void defect deep learning percussion method mfccs |
| title | Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| title_full | Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| title_fullStr | Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| title_full_unstemmed | Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| title_short | Intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| title_sort | intelligent recognition of voids behind tunnel linings using deep learning and percussion sound |
| topic | tunnel void defect deep learning percussion method mfccs |
| url | https://www.sciopen.com/article/10.26599/JIC.2023.9180029 |
| work_keys_str_mv | AT xiaoleizhang intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT xinlin intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT weizhang intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT yongfeng intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT weilan intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT yuewuda intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound AT kanhu intelligentrecognitionofvoidsbehindtunnelliningsusingdeeplearningandpercussionsound |