Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges
The PSC box girder bridge is a pre-stressed box girder bridge that accounts for a considerable part of large-scale bridges. However, when concrete is poured, even small mistakes might result in voids that appear during long-term maintenance. In this paper, we present a technique for detecting the vo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/3/1270 |
| _version_ | 1827661630866980864 |
|---|---|
| author | Da-In Lee Hyung Choi Jong-Dae Kim Chan-Young Park Yu-Seop Kim |
| author_facet | Da-In Lee Hyung Choi Jong-Dae Kim Chan-Young Park Yu-Seop Kim |
| author_sort | Da-In Lee |
| collection | DOAJ |
| description | The PSC box girder bridge is a pre-stressed box girder bridge that accounts for a considerable part of large-scale bridges. However, when concrete is poured, even small mistakes might result in voids that appear during long-term maintenance. In this paper, we present a technique for detecting the void in the duct inside the PSC box girder bridge. Data are acquired utilizing the non-destructive impact-echo (IE) approach to detect these voids. IE creates time-series data as signal data initially; however, we want to use a CNN auto-encoder (AE). A scalogram, which is a kind of wavelet transformation, is used to convert time series data into an image. An AE is a type of unsupervised learning that aims to minimize the difference between the input and output. By comparing histograms, the difference is calculated. To begin, we create scalogram images from all IE signal data, which were randomly sampled as 98% normal and 2% void. The CNN AE is then trained and evaluated utilizing all the data. Finally, we examine the input and output histogram similarity distributions. As a consequence, only 4% of the normal data had a similarity of less than two standard deviations from the mean, whereas 34.7% of the void data did. As a result, the existence of voids inside the PSC duct could be demonstrated to be predictive in the absence of annotated data. |
| first_indexed | 2024-03-10T00:13:55Z |
| format | Article |
| id | doaj.art-4ac592107e47443a85e282c272f21138 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:13:55Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4ac592107e47443a85e282c272f211382023-11-23T15:54:46ZengMDPI AGApplied Sciences2076-34172022-01-01123127010.3390/app12031270Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder BridgesDa-In Lee0Hyung Choi1Jong-Dae Kim2Chan-Young Park3Yu-Seop Kim4Department of Convergence Software, Hallym University, Chuncheon 24252, KoreaAI bridge Co., Ltd., Seoul 05117, KoreaDepartment of Convergence Software, Hallym University, Chuncheon 24252, KoreaDepartment of Convergence Software, Hallym University, Chuncheon 24252, KoreaDepartment of Convergence Software, Hallym University, Chuncheon 24252, KoreaThe PSC box girder bridge is a pre-stressed box girder bridge that accounts for a considerable part of large-scale bridges. However, when concrete is poured, even small mistakes might result in voids that appear during long-term maintenance. In this paper, we present a technique for detecting the void in the duct inside the PSC box girder bridge. Data are acquired utilizing the non-destructive impact-echo (IE) approach to detect these voids. IE creates time-series data as signal data initially; however, we want to use a CNN auto-encoder (AE). A scalogram, which is a kind of wavelet transformation, is used to convert time series data into an image. An AE is a type of unsupervised learning that aims to minimize the difference between the input and output. By comparing histograms, the difference is calculated. To begin, we create scalogram images from all IE signal data, which were randomly sampled as 98% normal and 2% void. The CNN AE is then trained and evaluated utilizing all the data. Finally, we examine the input and output histogram similarity distributions. As a consequence, only 4% of the normal data had a similarity of less than two standard deviations from the mean, whereas 34.7% of the void data did. As a result, the existence of voids inside the PSC duct could be demonstrated to be predictive in the absence of annotated data.https://www.mdpi.com/2076-3417/12/3/1270pre-stressed concrete (PSC)scalogram transformCNN auto-encoder (AE)histogram comparisonanomaly detection |
| spellingShingle | Da-In Lee Hyung Choi Jong-Dae Kim Chan-Young Park Yu-Seop Kim Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges Applied Sciences pre-stressed concrete (PSC) scalogram transform CNN auto-encoder (AE) histogram comparison anomaly detection |
| title | Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges |
| title_full | Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges |
| title_fullStr | Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges |
| title_full_unstemmed | Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges |
| title_short | Utilization of Unsupervised Machine Learning for Detection of Duct Voids inside PSC Box Girder Bridges |
| title_sort | utilization of unsupervised machine learning for detection of duct voids inside psc box girder bridges |
| topic | pre-stressed concrete (PSC) scalogram transform CNN auto-encoder (AE) histogram comparison anomaly detection |
| url | https://www.mdpi.com/2076-3417/12/3/1270 |
| work_keys_str_mv | AT dainlee utilizationofunsupervisedmachinelearningfordetectionofductvoidsinsidepscboxgirderbridges AT hyungchoi utilizationofunsupervisedmachinelearningfordetectionofductvoidsinsidepscboxgirderbridges AT jongdaekim utilizationofunsupervisedmachinelearningfordetectionofductvoidsinsidepscboxgirderbridges AT chanyoungpark utilizationofunsupervisedmachinelearningfordetectionofductvoidsinsidepscboxgirderbridges AT yuseopkim utilizationofunsupervisedmachinelearningfordetectionofductvoidsinsidepscboxgirderbridges |