01 / OVERVIEW
A constrained prioritisation problem.
A regional maintenance team can inspect only a subset of its vehicle fleet each week. The project explored whether historical operational data could support a relative risk ranking that helps human reviewers decide where to look first.
Which vehicles should receive limited inspection capacity first?
Higher concentration of relevant cases in the top-ranked inspection set.
No verified physical-failure labels or component-level diagnostic truth.
Reviewers retain the final inspection and maintenance decision.
SUPPORTED CLAIMS
✓ Relative risk ranking✓ Inspection prioritisation✓ Capacity-aware decision support✓ Reproducible evaluation✓ Human reviewNOT SUPPORTED
— Exact component diagnosis— Physical-failure probability— Remaining useful life— Autonomous maintenance decisions— Guaranteed commercial savings02 / DECISION TRAIL
The choices that shaped the claim.
Define a ranking problem—not diagnosis
Vehicle-level labels and maintenance records did not support exact component diagnosis.
View linked evidenceOptimise capacity-aware utility
The operational question was which cases to inspect within a fixed weekly capacity.
View linked evidenceKeep commercial impact out of the claim
No production pilot or independently confirmed cost baseline was available.
View linked evidence03 / EVIDENCE GRAPH
Claims stay connected to their support.
04 / EVALUATION
Tested as a ranking workflow.
The ranking concentrated more relevant cases within each tested capacity band than the comparison baseline.
This supports prioritisation utility in the retrospective dataset. It does not establish production performance, physical failure, or savings.
05 / AI-USE DECLARATION
AI assistance, in context.
Used for code explanation, test-case ideation, documentation structure, and wording review.
Problem framing, feature acceptance, evaluation design, claim boundaries, and final evidence selection.
Generated code was inspected, adapted, executed, and checked against held-out data and documented assumptions.
Suggestions that implied failure probability or commercial impact were rejected as unsupported.
06 / LIMITATIONS
What this project does not demonstrate.
Clear boundaries are part of the evidence.
The work has not been deployed in an operational maintenance setting. It does not demonstrate causal reduction in downtime or costs, nor validate the ranking against confirmed physical failures. The next responsible step is a time-bounded, human-supervised operational pilot.
“The record makes a strong distinction between retrospective ranking performance and operational impact. The supported claim is appropriately bounded.”Dr Rana Khalid · Faculty reviewer · 27 March 2026