An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection
Railroads are a critical part of the United States’ transportation sector. Over 40 percent (by weight) of the nation’s freight is transported by rail, and according to the Bureau of Transportation statistics, railroads moved $186.5 billion of freight in 2021. A vital part of the freight network is r...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/3330 |
| _version_ | 1827747637114175488 |
|---|---|
| author | Omobolaji Lawal Shaik Althaf V. Shajihan Kirill Mechitov Billie F. Spencer |
| author_facet | Omobolaji Lawal Shaik Althaf V. Shajihan Kirill Mechitov Billie F. Spencer |
| author_sort | Omobolaji Lawal |
| collection | DOAJ |
| description | Railroads are a critical part of the United States’ transportation sector. Over 40 percent (by weight) of the nation’s freight is transported by rail, and according to the Bureau of Transportation statistics, railroads moved $186.5 billion of freight in 2021. A vital part of the freight network is railroad bridges, with a good number being low-clearance bridges that are prone to impacts from over-height vehicles; such impacts can cause damage to the bridge and lead to unwanted interruption in its usage. Therefore, the detection of impacts from over-height vehicles is critical for the safe operation and maintenance of railroad bridges. While some previous studies have been published regarding bridge impact detection, most approaches utilize more expensive wired sensors, as well as relying on simple threshold-based detection. The challenge is that the use of vibration thresholds may not accurately distinguish between impacts and other events, such as a common train crossing. In this paper, a machine learning approach is developed for accurate impact detection using event-triggered wireless sensors. The neural network is trained with key features which are extracted from event responses collected from two instrumented railroad bridges. The trained model classifies events as impacts, train crossings, or other events. An average classification accuracy of 98.67% is obtained from cross-validation, while the false positive rate is minimal. Finally, a framework for edge classification of events is also proposed and demonstrated using an edge device. |
| first_indexed | 2024-03-11T05:55:34Z |
| format | Article |
| id | doaj.art-aa6354ef5a974e75b478b121a009c3a3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:55:34Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-aa6354ef5a974e75b478b121a009c3a32023-11-17T13:49:11ZengMDPI AGSensors1424-82202023-03-01236333010.3390/s23063330An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact DetectionOmobolaji Lawal0Shaik Althaf V. Shajihan1Kirill Mechitov2Billie F. Spencer3Department of Civil and Environmental Engineering, University of Illinois, 205 N. Matthews Ave, Urbana, IL 61801, USADepartment of Civil and Environmental Engineering, University of Illinois, 205 N. Matthews Ave, Urbana, IL 61801, USADepartment of Civil and Environmental Engineering, University of Illinois, 205 N. Matthews Ave, Urbana, IL 61801, USADepartment of Civil and Environmental Engineering, University of Illinois, 205 N. Matthews Ave, Urbana, IL 61801, USARailroads are a critical part of the United States’ transportation sector. Over 40 percent (by weight) of the nation’s freight is transported by rail, and according to the Bureau of Transportation statistics, railroads moved $186.5 billion of freight in 2021. A vital part of the freight network is railroad bridges, with a good number being low-clearance bridges that are prone to impacts from over-height vehicles; such impacts can cause damage to the bridge and lead to unwanted interruption in its usage. Therefore, the detection of impacts from over-height vehicles is critical for the safe operation and maintenance of railroad bridges. While some previous studies have been published regarding bridge impact detection, most approaches utilize more expensive wired sensors, as well as relying on simple threshold-based detection. The challenge is that the use of vibration thresholds may not accurately distinguish between impacts and other events, such as a common train crossing. In this paper, a machine learning approach is developed for accurate impact detection using event-triggered wireless sensors. The neural network is trained with key features which are extracted from event responses collected from two instrumented railroad bridges. The trained model classifies events as impacts, train crossings, or other events. An average classification accuracy of 98.67% is obtained from cross-validation, while the false positive rate is minimal. Finally, a framework for edge classification of events is also proposed and demonstrated using an edge device.https://www.mdpi.com/1424-8220/23/6/3330impact detectionevent classificationrailroad bridgewireless sensorsartificial neural networks |
| spellingShingle | Omobolaji Lawal Shaik Althaf V. Shajihan Kirill Mechitov Billie F. Spencer An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection Sensors impact detection event classification railroad bridge wireless sensors artificial neural networks |
| title | An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection |
| title_full | An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection |
| title_fullStr | An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection |
| title_full_unstemmed | An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection |
| title_short | An Event-Classification Neural Network Approach for Rapid Railroad Bridge Impact Detection |
| title_sort | event classification neural network approach for rapid railroad bridge impact detection |
| topic | impact detection event classification railroad bridge wireless sensors artificial neural networks |
| url | https://www.mdpi.com/1424-8220/23/6/3330 |
| work_keys_str_mv | AT omobolajilawal aneventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT shaikalthafvshajihan aneventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT kirillmechitov aneventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT billiefspencer aneventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT omobolajilawal eventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT shaikalthafvshajihan eventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT kirillmechitov eventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection AT billiefspencer eventclassificationneuralnetworkapproachforrapidrailroadbridgeimpactdetection |