A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data
The most important structural element of prestressed concrete (PSC) bridges is the prestressed tendon, and in order to ensure safety of such bridges, it is very important to determine whether the tendon is damaged. However, it is not easy to detect tendon damage in real time. This study proposes a n...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/7/1633 |
| _version_ | 1818000301204963328 |
|---|---|
| author | Kanghyeok Lee Seunghoo Jeong Sung-Han Sim Do Hyoung Shin |
| author_facet | Kanghyeok Lee Seunghoo Jeong Sung-Han Sim Do Hyoung Shin |
| author_sort | Kanghyeok Lee |
| collection | DOAJ |
| description | The most important structural element of prestressed concrete (PSC) bridges is the prestressed tendon, and in order to ensure safety of such bridges, it is very important to determine whether the tendon is damaged. However, it is not easy to detect tendon damage in real time. This study proposes a novelty detection approach for damage to the tendons of PSC bridges based on a convolutional autoencoder (CAE). The proposed method employs simulation data from nine accelerometers. The accuracies of CAEs for multi-vehicle are 79.5%–85.8% for 100% and 75% damage severities with all error levels and 50% damage severity without error. However, the accuracies for 50% damage severity with 5% and 10% error levels drop to 69.4%–73.3%. The accuracies of CAEs for single-vehicle ranges from 90.1%–95.1% for all damage severities and error levels that are satisfactory. The findings indicate that the CAE approach for multi-vehicle can be effective when the damages are severe, but not when moderate. Meanwhile, if acceleration data can be obtained for single-vehicle, then the CAE approach can provide a highly accurate and robust method of tendon damage detection in PSC bridges in use, even if the measurement errors are significant. |
| first_indexed | 2024-04-14T03:20:13Z |
| format | Article |
| id | doaj.art-a4c84d26bdcf4bc28553273008ca2e2b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T03:20:13Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a4c84d26bdcf4bc28553273008ca2e2b2022-12-22T02:15:20ZengMDPI AGSensors1424-82202019-04-01197163310.3390/s19071633s19071633A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration DataKanghyeok Lee0Seunghoo Jeong1Sung-Han Sim2Do Hyoung Shin3Department of Civil Engineering, Inha University, Incheon 22212, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 44919, KoreaSchool of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology, Ulsan 44919, KoreaDepartment of Civil Engineering, Inha University, Incheon 22212, KoreaThe most important structural element of prestressed concrete (PSC) bridges is the prestressed tendon, and in order to ensure safety of such bridges, it is very important to determine whether the tendon is damaged. However, it is not easy to detect tendon damage in real time. This study proposes a novelty detection approach for damage to the tendons of PSC bridges based on a convolutional autoencoder (CAE). The proposed method employs simulation data from nine accelerometers. The accuracies of CAEs for multi-vehicle are 79.5%–85.8% for 100% and 75% damage severities with all error levels and 50% damage severity without error. However, the accuracies for 50% damage severity with 5% and 10% error levels drop to 69.4%–73.3%. The accuracies of CAEs for single-vehicle ranges from 90.1%–95.1% for all damage severities and error levels that are satisfactory. The findings indicate that the CAE approach for multi-vehicle can be effective when the damages are severe, but not when moderate. Meanwhile, if acceleration data can be obtained for single-vehicle, then the CAE approach can provide a highly accurate and robust method of tendon damage detection in PSC bridges in use, even if the measurement errors are significant.https://www.mdpi.com/1424-8220/19/7/1633novelty detectionconvolutional autoencoderbridge damageprestress tendonsPSC bridge |
| spellingShingle | Kanghyeok Lee Seunghoo Jeong Sung-Han Sim Do Hyoung Shin A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data Sensors novelty detection convolutional autoencoder bridge damage prestress tendons PSC bridge |
| title | A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data |
| title_full | A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data |
| title_fullStr | A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data |
| title_full_unstemmed | A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data |
| title_short | A Novelty Detection Approach for Tendons of Prestressed Concrete Bridges Based on a Convolutional Autoencoder and Acceleration Data |
| title_sort | novelty detection approach for tendons of prestressed concrete bridges based on a convolutional autoencoder and acceleration data |
| topic | novelty detection convolutional autoencoder bridge damage prestress tendons PSC bridge |
| url | https://www.mdpi.com/1424-8220/19/7/1633 |
| work_keys_str_mv | AT kanghyeoklee anoveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT seunghoojeong anoveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT sunghansim anoveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT dohyoungshin anoveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT kanghyeoklee noveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT seunghoojeong noveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT sunghansim noveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata AT dohyoungshin noveltydetectionapproachfortendonsofprestressedconcretebridgesbasedonaconvolutionalautoencoderandaccelerationdata |