Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Performability Optimization Framework for Driverless and Unattended Mainline Systems
Luleå University of Technology, Department of Civil, Environmental and Natural Resources Engineering, Operation, Maintenance and Acoustics.ORCID iD: 0000-0001-8188-2372
Luleå University of Technology, Department of Social Sciences, Technology and Arts, Humans and Technology.ORCID iD: 0000-0003-3827-0295
Management of Technology, University of Moratuwa, Moratuwa, Sri Lanka.ORCID iD: 0000-0001-8693-3431
2025 (English)Conference paper (Refereed)
Abstract [en]

The present study highlights a novel concept for estimating the performability of automatic or unattended train operation. This need has been identified through supporting strategies concerning the implementation of Automatic Train Operation (ATO) atop diverse Grade of Automation (GoA). In addressing this challenge, the handling of delay logs supplied by train dispatchers remain a major concern as it can easily spread over the network. This task requires an integrated approach to detect, transmit and resolve difficulties caused by unplanned events. Therefore, we addressed the detectability aspects through the introduction a Joint Cognitive System (JCS) approach relying on a context-aware methodology with the aim to maximize the train driver interaction and resolution of performability issues with technical and safety competency. We proposed a Novelty Detection K-means algorithm for defining with sensory measurements, potential unplanned events and visual image processing for handling track related abnormalities on higher GoA levels. For transmission, we integrated the JCS concept in mainline railway and its context with satellite-based communication. This approach was incorporated into an optimization performability framework for mitigating uncertainty on critical dependability parameters. The validation strategy was exemplified by means of a model-based evaluation compliant with operational and regulatory authority demands.

Place, publisher, year, edition, pages
Luleå, 2025.
Keywords [en]
GNSS, novelty detection, context-aware, joint cognitive system, automatic train operation, grade of automation
National Category
Production Engineering, Human Work Science and Ergonomics
Research subject
Human Work Sciences; Operation and Maintenance Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-112112OAI: oai:DiVA.org:ltu-112112DiVA, id: diva2:1947068
Conference
International Congress and Workshop on Industrial AI and eMaintenance, May 13–15 2025, Luleå, Sweden
Available from: 2025-03-24 Created: 2025-03-24 Last updated: 2025-10-21

Open Access in DiVA

No full text in DiVA

Other links

Conference webpage

Authority records

Compierchio, AngeloTretten, Phillip

Search in DiVA

By author/editor
Compierchio, AngeloTretten, PhillipIllankoon, Prasanna
By organisation
Operation, Maintenance and AcousticsHumans and Technology
Production Engineering, Human Work Science and Ergonomics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 127 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf