A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data
Many machine learning (ML)-based detection methods for interpreting ground-penetrating radar (GPR) data of concrete tunnels require extensive labeled damage-state data for model training, limiting their practical use in concealed damage detection of in-service tunnels. This study presents a probabil...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/14/11/3662 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846154023135084544 |
|---|---|
| author | Junfang Wang Heng Chen Jianfu Lin Xiangxiong Li |
| author_facet | Junfang Wang Heng Chen Jianfu Lin Xiangxiong Li |
| author_sort | Junfang Wang |
| collection | DOAJ |
| description | Many machine learning (ML)-based detection methods for interpreting ground-penetrating radar (GPR) data of concrete tunnels require extensive labeled damage-state data for model training, limiting their practical use in concealed damage detection of in-service tunnels. This study presents a probabilistic, data-driven method for GPR-based damage detection, which exempts the requirement in the training process of supervised ML models. The approach involves extracting a radar feature vector (RFV), building a Bayesian baseline model with healthy data, and quantifying damage severity with the Bayes factor. The RFV is a complex vector obtained by radargram data fusion. Bayesian regression is applied to build a model for the relationship between real and imaginary parts of the RFV. The Bayes factor is employed for defect identification and severity assessment, by quantifying the difference between the RFV built with new observations and the baseline RFV predicted by the baseline model with new input. The probability of damage is calculated to reflect the influence of uncertainties on the detection result. The effectiveness of the proposed method is validated through simulated data with random noise and physical model tests. This method facilitates GPR-based hidden damage detection of in-service tunnels when lacking labeled damage-state data in the model training process. |
| format | Article |
| id | doaj-art-5d0a280234444d148adc5ecad0c900fe |
| institution | Kabale University |
| issn | 2075-5309 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-5d0a280234444d148adc5ecad0c900fe2024-11-26T17:56:31ZengMDPI AGBuildings2075-53092024-11-011411366210.3390/buildings14113662A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar DataJunfang Wang0Heng Chen1Jianfu Lin2Xiangxiong Li3National Key Laboratory of Green and Long-Life Road Engineering in Extreme Environment, College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, ChinaNational Key Laboratory of Green and Long-Life Road Engineering in Extreme Environment, College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, ChinaCenter of Safety Monitoring of Engineering Structures, Shenzhen Academy of Disaster Prevention and Reduction, China Earthquake Administration, Shenzhen 518003, ChinaShenzhen Research Institute of The Hong Kong Polytechnic University, Shenzhen 518057, ChinaMany machine learning (ML)-based detection methods for interpreting ground-penetrating radar (GPR) data of concrete tunnels require extensive labeled damage-state data for model training, limiting their practical use in concealed damage detection of in-service tunnels. This study presents a probabilistic, data-driven method for GPR-based damage detection, which exempts the requirement in the training process of supervised ML models. The approach involves extracting a radar feature vector (RFV), building a Bayesian baseline model with healthy data, and quantifying damage severity with the Bayes factor. The RFV is a complex vector obtained by radargram data fusion. Bayesian regression is applied to build a model for the relationship between real and imaginary parts of the RFV. The Bayes factor is employed for defect identification and severity assessment, by quantifying the difference between the RFV built with new observations and the baseline RFV predicted by the baseline model with new input. The probability of damage is calculated to reflect the influence of uncertainties on the detection result. The effectiveness of the proposed method is validated through simulated data with random noise and physical model tests. This method facilitates GPR-based hidden damage detection of in-service tunnels when lacking labeled damage-state data in the model training process.https://www.mdpi.com/2075-5309/14/11/3662ground-penetrating radarconcealed damage detectionBayesian learningquantitative assessmentradar feature vector |
| spellingShingle | Junfang Wang Heng Chen Jianfu Lin Xiangxiong Li A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data Buildings ground-penetrating radar concealed damage detection Bayesian learning quantitative assessment radar feature vector |
| title | A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data |
| title_full | A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data |
| title_fullStr | A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data |
| title_full_unstemmed | A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data |
| title_short | A Method to Detect Concealed Damage in Concrete Tunnels Using a Radar Feature Vector and Bayesian Analysis of Ground-Penetrating Radar Data |
| title_sort | method to detect concealed damage in concrete tunnels using a radar feature vector and bayesian analysis of ground penetrating radar data |
| topic | ground-penetrating radar concealed damage detection Bayesian learning quantitative assessment radar feature vector |
| url | https://www.mdpi.com/2075-5309/14/11/3662 |
| work_keys_str_mv | AT junfangwang amethodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT hengchen amethodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT jianfulin amethodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT xiangxiongli amethodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT junfangwang methodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT hengchen methodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT jianfulin methodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata AT xiangxiongli methodtodetectconcealeddamageinconcretetunnelsusingaradarfeaturevectorandbayesiananalysisofgroundpenetratingradardata |