Digitalization in the rail industry: Localizing damaged cargo wagons using spatial operations and big data
(2021) In Student thesis series INES NGEM01 20211Dept of Physical Geography and Ecosystem Science
- Abstract
- Climate change and the sustainability challenges of the 21st century require the reduction of greenhouse gas emissions in all sectors. Accordingly, political objectives urge for a shift from road to rail in logistics. This drives innovation, increased efficiency, and customer friendliness in the rail industry. These advancements are strongly needed as investments have been neglected in the past and the technological development lags behind the standard in the road freight sector. The use of Global Navigation Satellite System (GNSS) wagon data to allow tracking, optimized fleet management and maintenance is one effort to compete with road freight. This thesis proposes an algorithm that can be used to gain information on the repair status of... (More)
- Climate change and the sustainability challenges of the 21st century require the reduction of greenhouse gas emissions in all sectors. Accordingly, political objectives urge for a shift from road to rail in logistics. This drives innovation, increased efficiency, and customer friendliness in the rail industry. These advancements are strongly needed as investments have been neglected in the past and the technological development lags behind the standard in the road freight sector. The use of Global Navigation Satellite System (GNSS) wagon data to allow tracking, optimized fleet management and maintenance is one effort to compete with road freight. This thesis proposes an algorithm that can be used to gain information on the repair status of a wagon while abroad. As cooperation and data exchange between railway companies are not well developed, delays in repair and disposition occur regularly. The created algorithm estimates the day a damaged wagon was back in operation, information that is not available today for most damage cases. In the process, geofences for cargo rail maintenance facilities in Europe are created automatedly. A methodology using existing address, infrastructure, and GNSS big data in combination with spatial analysis and clustering tools to identify insufficiently referenced geographic objects is proposed. Data from the largest rail operator in Europe, Deutsche Bahn AG, is used in the analysis.
The created algorithm computes the day a wagon was back in operation in over 86 % of damage cases. The result deviates on average four days from the actual day of the operations release. Although it was not possible to conclusively rate the quality of all geofences, the data and feedback from maintenance employees indicate that most of them are reliable. Faulty addresses, too small geofences, mobile maintenance, and damage protocol errors were the main reasons for unsuccessful operations release computations. (Less) - Popular Abstract
- Climate change and the sustainability challenges of the 21st century require the reduction of greenhouse gas emissions in all sectors. Accordingly, political objectives urge for a shift from road to rail in logistics. This drives innovation, increased efficiency, and customer friendliness in the rail industry. These advancements are strongly needed as investments have been neglected in the past and the technological development lags behind the standard in the road freight sector. Wagon location data derived e.g. via GPS can be used to allow tracking, optimize fleet management, and maintenance processes.
This thesis proposes an algorithm that can be used to gain information on the repair status of a wagon while abroad. As cooperation and... (More) - Climate change and the sustainability challenges of the 21st century require the reduction of greenhouse gas emissions in all sectors. Accordingly, political objectives urge for a shift from road to rail in logistics. This drives innovation, increased efficiency, and customer friendliness in the rail industry. These advancements are strongly needed as investments have been neglected in the past and the technological development lags behind the standard in the road freight sector. Wagon location data derived e.g. via GPS can be used to allow tracking, optimize fleet management, and maintenance processes.
This thesis proposes an algorithm that can be used to gain information on the repair status of a wagon while abroad. As cooperation and data exchange between railway companies are not well developed, delays in repair and disposition occur regularly. The created algorithm estimates the day a damaged wagon was back in operation, information that is not available today for most damage cases. In the process, virtual boundaries (geofences) for cargo rail maintenance facilities in Europe are created automatedly. A methodology using existing address, infrastructure, and wagon location big data (e.g. through GPS) in combination with various geospatial approaches is proposed. Data from the largest rail operator in Europe, Deutsche Bahn Cargo AG, is used in the analysis.
The created algorithm computes the day a wagon was back in operation in over 86 % of damage cases. This is a considerable increase compared to the data on damaged wagons available so far. The result is on average four days after the actual day of the operations release. This is caused by a prolonged stay of wagons at the repair location after the repair is concluded. The automatedly created geofences for maintenance facilities are useful to create alerts or notifications when a wagon enters or leaves a workshop. However, they are not as good as manually created boundaries around each maintenance facility. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9066961
- author
- Hellner, Julia LU
- supervisor
- organization
- alternative title
- A method to determine when damaged rail cargo wagons are being repaired
- course
- NGEM01 20211
- year
- 2021
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- physical geography and ecosystem analysis, big data, clustering, digitization, geofence, geomatics, GNSS, maintenance, rail, spatial analysis
- publication/series
- Student thesis series INES
- language
- English
- additional info
- External supervisors: Alexander Weiß, DB Cargo AG; Daniel Rost, DB Cargo AG
- id
- 9066961
- date added to LUP
- 2021-10-18 16:18:07
- date last changed
- 2021-10-18 16:18:07
@misc{9066961, abstract = {{Climate change and the sustainability challenges of the 21st century require the reduction of greenhouse gas emissions in all sectors. Accordingly, political objectives urge for a shift from road to rail in logistics. This drives innovation, increased efficiency, and customer friendliness in the rail industry. These advancements are strongly needed as investments have been neglected in the past and the technological development lags behind the standard in the road freight sector. The use of Global Navigation Satellite System (GNSS) wagon data to allow tracking, optimized fleet management and maintenance is one effort to compete with road freight. This thesis proposes an algorithm that can be used to gain information on the repair status of a wagon while abroad. As cooperation and data exchange between railway companies are not well developed, delays in repair and disposition occur regularly. The created algorithm estimates the day a damaged wagon was back in operation, information that is not available today for most damage cases. In the process, geofences for cargo rail maintenance facilities in Europe are created automatedly. A methodology using existing address, infrastructure, and GNSS big data in combination with spatial analysis and clustering tools to identify insufficiently referenced geographic objects is proposed. Data from the largest rail operator in Europe, Deutsche Bahn AG, is used in the analysis. The created algorithm computes the day a wagon was back in operation in over 86 % of damage cases. The result deviates on average four days from the actual day of the operations release. Although it was not possible to conclusively rate the quality of all geofences, the data and feedback from maintenance employees indicate that most of them are reliable. Faulty addresses, too small geofences, mobile maintenance, and damage protocol errors were the main reasons for unsuccessful operations release computations.}}, author = {{Hellner, Julia}}, language = {{eng}}, note = {{Student Paper}}, series = {{Student thesis series INES}}, title = {{Digitalization in the rail industry: Localizing damaged cargo wagons using spatial operations and big data}}, year = {{2021}}, }