Automation of Requirement Governance in Railway Communication Systems: AI-assisted Workflow for System Migration from GSM-R to FRMCS
K. Kapllani (TU Delft - Technology, Policy and Management)
Aaron Ding – Mentor (TU Delft - Technology, Policy and Management)
I. Nikolic – Graduation committee member (TU Delft - Technology, Policy and Management)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Requirements governance in complex system migrations remains fragmented, manual, and dependent on implicit knowledge spread across heterogeneous documents and stakeholders. This thesis investigates how a document-grounded, AI-assisted workflow can support requirements governance while keeping humans in control of consequential decisions, using the railway sector's GSM-R to FRMCS transition as its case. Following Design Science Research, seven design requirements were derived and operationalised in a staged three-agent prototype with role-differentiated human checkpoints. Evaluation on official FRMCS specifications showed five requirements fully met and two partially met, while exposing how a normalisation error propagated into a spurious conflict flag. The contribution is a set of explicit workflow design requirements with documented rationale, redistributing human effort from repetitive comparison toward targeted verification and authorisation.
Repository in GitHub to perform the work in n8n: https://github.com/kristikapllani/frmcs-requirements-governance-workflow