Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection
ABSTRACT Wayside inspection of rolling stock has been around for some time and wheel impact load and fiber‐grating sensors are actively explored for getting high‐fidelity data. Visual inspection from wayside provides the opportunity to gain high‐resolution data, which can help in the early diagnosis...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.13027 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576644208918528 |
|---|---|
| author | Muhammad Zakir Shaikh Sanaullah Mehran Enrique Nava Baro Agata Manolova Mohammad Aslam Uqaili Tanweer Hussain Bhawani Shankar Chowdhry |
| author_facet | Muhammad Zakir Shaikh Sanaullah Mehran Enrique Nava Baro Agata Manolova Mohammad Aslam Uqaili Tanweer Hussain Bhawani Shankar Chowdhry |
| author_sort | Muhammad Zakir Shaikh |
| collection | DOAJ |
| description | ABSTRACT Wayside inspection of rolling stock has been around for some time and wheel impact load and fiber‐grating sensors are actively explored for getting high‐fidelity data. Visual inspection from wayside provides the opportunity to gain high‐resolution data, which can help in the early diagnosis of potential faults. It is rarely explored due to complexities associated with calibration, moving and rotating targets, and difficulties associated with data acquisition. This paper explores and presents an in‐depth design and development strategy for such systems. It presents the development steps, implementation, and results of a vision inspection system for regular and automated inspection of train wheels. First, various configurations for positioning of the cameras in a three‐dimensional setting are considered and discussed, followed by online data acquisition for establishing a data set. Later, a comprehensive comparative analysis was conducted on several object detection algorithms for wheel segmentation task. Different algorithms are evaluated using COCO evaluation metrics, and the best‐performing model, YOLOv9, achieves a mAP50 of 0.94 and a recall of 0.91. The developed system has produced satisfactory results in acquiring proper wheel tread images and segmenting the wheel. Further avenues for countering lighting issues and defect detection are provided. |
| format | Article |
| id | doaj-art-bfda4aa32f7d46b9a9673b1f73113bac |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-bfda4aa32f7d46b9a9673b1f73113bac2025-01-31T00:22:48ZengWileyEngineering Reports2577-81962025-01-0171n/an/a10.1002/eng2.13027Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel InspectionMuhammad Zakir Shaikh0Sanaullah Mehran1Enrique Nava Baro2Agata Manolova3Mohammad Aslam Uqaili4Tanweer Hussain5Bhawani Shankar Chowdhry6National Center for Robotics, Automation and Artificial Intelligence, Mehran University of Engineering and Technology (MUET) Jamshoro PakistanNCRA‐CMS Lab Mehran University of Engineering and Technology (MUET) Jamshoro PakistanDepartamento de Ingeniería de Comunicaciones Campus de Teatinos, Universidad de Malaga Málaga SpainFaculty of Telecommunications Technical University of Sofia Sofia BulgariaNCRA‐CMS Lab Mehran University of Engineering and Technology (MUET) Jamshoro PakistanNCRA‐CMS Lab Mehran University of Engineering and Technology (MUET) Jamshoro PakistanNational Center for Robotics, Automation and Artificial Intelligence, Mehran University of Engineering and Technology (MUET) Jamshoro PakistanABSTRACT Wayside inspection of rolling stock has been around for some time and wheel impact load and fiber‐grating sensors are actively explored for getting high‐fidelity data. Visual inspection from wayside provides the opportunity to gain high‐resolution data, which can help in the early diagnosis of potential faults. It is rarely explored due to complexities associated with calibration, moving and rotating targets, and difficulties associated with data acquisition. This paper explores and presents an in‐depth design and development strategy for such systems. It presents the development steps, implementation, and results of a vision inspection system for regular and automated inspection of train wheels. First, various configurations for positioning of the cameras in a three‐dimensional setting are considered and discussed, followed by online data acquisition for establishing a data set. Later, a comprehensive comparative analysis was conducted on several object detection algorithms for wheel segmentation task. Different algorithms are evaluated using COCO evaluation metrics, and the best‐performing model, YOLOv9, achieves a mAP50 of 0.94 and a recall of 0.91. The developed system has produced satisfactory results in acquiring proper wheel tread images and segmenting the wheel. Further avenues for countering lighting issues and defect detection are provided.https://doi.org/10.1002/eng2.13027automated inspection systemdeep learningonline data acquisitionYOLO |
| spellingShingle | Muhammad Zakir Shaikh Sanaullah Mehran Enrique Nava Baro Agata Manolova Mohammad Aslam Uqaili Tanweer Hussain Bhawani Shankar Chowdhry Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection Engineering Reports automated inspection system deep learning online data acquisition YOLO |
| title | Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection |
| title_full | Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection |
| title_fullStr | Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection |
| title_full_unstemmed | Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection |
| title_short | Design and Development of a Wayside AI‐Assisted Vision System for Online Train Wheel Inspection |
| title_sort | design and development of a wayside ai assisted vision system for online train wheel inspection |
| topic | automated inspection system deep learning online data acquisition YOLO |
| url | https://doi.org/10.1002/eng2.13027 |
| work_keys_str_mv | AT muhammadzakirshaikh designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT sanaullahmehran designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT enriquenavabaro designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT agatamanolova designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT mohammadaslamuqaili designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT tanweerhussain designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection AT bhawanishankarchowdhry designanddevelopmentofawaysideaiassistedvisionsystemforonlinetrainwheelinspection |