A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data
Rail breaks, which are crucial maintenance issues for the railways, require immediate inspection and maintenance as it can cause severe railway accidents. Though, it is still difficult to promptly detect rail breaks that occur during train operation even with the advances in maintenance and inspecti...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | IET Electrical Systems in Transportation |
| Online Access: | http://dx.doi.org/10.1049/2024/5574909 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825199979004690432 |
|---|---|
| author | Hye-Yeun Chun Jungtai Kim Dongkue Kim Ilmu Byun Kyeongjun Ko |
| author_facet | Hye-Yeun Chun Jungtai Kim Dongkue Kim Ilmu Byun Kyeongjun Ko |
| author_sort | Hye-Yeun Chun |
| collection | DOAJ |
| description | Rail breaks, which are crucial maintenance issues for the railways, require immediate inspection and maintenance as it can cause severe railway accidents. Though, it is still difficult to promptly detect rail breaks that occur during train operation even with the advances in maintenance and inspection technologies. In this research, as a preliminary study on rail break detection system, a deep learning-based discontinuous rail position classification method, which is using vibration data obtained from distributed acoustic sensing (DAS) system during train operation, is proposed. To analyze the vibration data, a preprocessing algorithm for determining train occupancy is applied first. After that, the data in the space–time domain occupied by the train is converted to the spectrogram which is in the frequency domain by using short-time Fourier transformation (STFT). In the third step, the spectrogram images are applied to the proposed 2D convolutional neural network (2D CNN) model and the network detects discontinuous rail positions along the track, which are geometrically distinct from continuous welded rails, such as rail breaks. In order to evaluate the superiority of the proposed network model, performance comparison tests with other existing models were conducted with data collected from an actual railway line. From the results, the proposed model could achieve 99.17%, 93.33%, 87.5%, 90.32% for accuracy, precision, recall, and F1 score, respectively, and the results show overwhelming detection performance compared to other models. |
| format | Article |
| id | doaj-art-bc1083cc10dd45fda49d44a7a06ae0f4 |
| institution | Kabale University |
| issn | 2042-9746 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Electrical Systems in Transportation |
| spelling | doaj-art-bc1083cc10dd45fda49d44a7a06ae0f42025-02-08T00:00:08ZengWileyIET Electrical Systems in Transportation2042-97462024-01-01202410.1049/2024/5574909A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing DataHye-Yeun Chun0Jungtai Kim1Dongkue Kim2Ilmu Byun3Kyeongjun Ko4Transportation System EngineeringSmart Electrical and Signaling DivisionSmart Electrical and Signaling DivisionSmart Electrical and Signaling DivisionDepartment of Computer EngineeringRail breaks, which are crucial maintenance issues for the railways, require immediate inspection and maintenance as it can cause severe railway accidents. Though, it is still difficult to promptly detect rail breaks that occur during train operation even with the advances in maintenance and inspection technologies. In this research, as a preliminary study on rail break detection system, a deep learning-based discontinuous rail position classification method, which is using vibration data obtained from distributed acoustic sensing (DAS) system during train operation, is proposed. To analyze the vibration data, a preprocessing algorithm for determining train occupancy is applied first. After that, the data in the space–time domain occupied by the train is converted to the spectrogram which is in the frequency domain by using short-time Fourier transformation (STFT). In the third step, the spectrogram images are applied to the proposed 2D convolutional neural network (2D CNN) model and the network detects discontinuous rail positions along the track, which are geometrically distinct from continuous welded rails, such as rail breaks. In order to evaluate the superiority of the proposed network model, performance comparison tests with other existing models were conducted with data collected from an actual railway line. From the results, the proposed model could achieve 99.17%, 93.33%, 87.5%, 90.32% for accuracy, precision, recall, and F1 score, respectively, and the results show overwhelming detection performance compared to other models.http://dx.doi.org/10.1049/2024/5574909 |
| spellingShingle | Hye-Yeun Chun Jungtai Kim Dongkue Kim Ilmu Byun Kyeongjun Ko A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data IET Electrical Systems in Transportation |
| title | A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data |
| title_full | A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data |
| title_fullStr | A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data |
| title_full_unstemmed | A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data |
| title_short | A Preliminary Study on 2D Convolutional Neural Network-Based Discontinuous Rail Position Classification for Detection on Rail Breaks Using Distributed Acoustic Sensing Data |
| title_sort | preliminary study on 2d convolutional neural network based discontinuous rail position classification for detection on rail breaks using distributed acoustic sensing data |
| url | http://dx.doi.org/10.1049/2024/5574909 |
| work_keys_str_mv | AT hyeyeunchun apreliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT jungtaikim apreliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT dongkuekim apreliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT ilmubyun apreliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT kyeongjunko apreliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT hyeyeunchun preliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT jungtaikim preliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT dongkuekim preliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT ilmubyun preliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata AT kyeongjunko preliminarystudyon2dconvolutionalneuralnetworkbaseddiscontinuousrailpositionclassificationfordetectiononrailbreaksusingdistributedacousticsensingdata |