EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Data-Driven Operations-Intelligence Framework for Lifecycle-Aware Maintenance Decision-Making Across Tramway Superstructure Variants

Vivien Révész-Jóvér, Szabolcs Fischer

Journal of Operations Intelligence · 17.07.2026 · 4 (1) · 42-64

DOI: 10.31181/jopi41202673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Operations Intelligence, online erschienen am 17.07.2026. Verfasst von Vivien Révész-Jóvér und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban-rail operators must convert routine track-geometry inspections into operational maintenance decisions across heterogeneous superstructures, yet age-based schedules and per-rail mean defects obscure the underlying deterioration mechanism. This paper develops an operations-intelligence framework that turns repeated geometric measurements into an explainable, data-driven ranking of sections by maintenance urgency. The framework is applied to 374,610 measurement points from 18 Budapest tramway sections, sampled 6 to 8 times over 2.3 years. Six analytical layers combine descriptive statistics; both-rail unified metrics including the EN 13848 track twist; an EN 13848-style Track Quality Index; hierarchical mixed-effects models; bootstrap (B = 10,000) and Theil–Sen confidence intervals; and AIC-based linear-versus-exponential model selection. Degradation proceeds mainly through twist generation – right- and left-rail slopes correlate strongly negatively (r = −0.864, p < 0.0001, n = 18). Concrete-slab gauge depends strongly on age (R² = 0.72, n = 24); mixed-effects models attribute 60.3% of gauge variance to between-section identity; the linear model is selected in 94% of fits; and a 3.0 mm threshold flags four sections for intervention within ten years. The pipeline feeds directly into operational decision-making and maintenance management systems and is transferable across sectors, relying on periodic condition monitoring.

Zitieren

APA

Révész-Jóvér, V., & Fischer, S. (2026). A Data-Driven Operations-Intelligence Framework for Lifecycle-Aware Maintenance Decision-Making Across Tramway Superstructure Variants. Journal of Operations Intelligence, 4(1), 42-64. https://doi.org/10.31181/jopi41202673

Vancouver

Révész-Jóvér V, Fischer S. A Data-Driven Operations-Intelligence Framework for Lifecycle-Aware Maintenance Decision-Making Across Tramway Superstructure Variants. Journal of Operations Intelligence. 2026;4(1):42-64. doi:10.31181/jopi41202673

BibTeX
@article{RvszJvr2026,
  author = {Révész-Jóvér, Vivien and Fischer, Szabolcs},
  title = {A Data-Driven Operations-Intelligence Framework for Lifecycle-Aware Maintenance Decision-Making Across Tramway Superstructure Variants},
  journal = {Journal of Operations Intelligence},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {42--64},
  doi = {10.31181/jopi41202673}
}
Kostenlos starten →