Topology-driven automated generation of geometric digital twins for railway overhead line equipment

Generating geometric digital twins (GDTs) of railway overhead line equipment (OLE) from point cloud data (PCD) using manual or semi-automated approaches is labour-intensive. This diminishes their practical benefits, with 74% of modelling effort spent converting PCD into GDTs. Automation reduces cost and effort, yet state-of-the-art methods struggle to deliver kilometre-scale GDTs without precision loss or manual intervention. This paper presents an automated method combining topology-aware segmentation, rule-based classification, and template-driven geometric reconstruction. Leveraging engineering rules and OLE spatial relationships, it enables modelling in cluttered, partially occluded scenes. OLE elements are segmented into labelled clusters, then aligned with parametric assemblies to generate industry foundation classes (IFC) models. Evaluation on 18.5 km of PCD achieved F1 scores of 98.3% for C sections, 89.8% for contact and 84.1% for catenary cables, with ±5.6 cm RMSE. Automation saved 98.6% of time versus manual workflows. This contributes a topology-informed strategy for scalable digital twin generation.

Authors

Institutions

Publication Details

Journal
Automation in Construction
Published
2026-11-16
DOI
https://doi.org/10.1016/j.autcon.2026.107371
Primary Topic
BIM and Construction Integration
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Topology-driven automated generation of geometric digital twins for railway overhead line equipment

M.R. Mahendrini Fernando Ariyachandra, Ioannis Brilakis
2 links
Automation in Construction
BIM and Construction Integration
article

Topology-driven automated generation of geometric digital twins for railway overhead line equipment

M.R. Mahendrini Fernando Ariyachandra, Ioannis Brilakis
article en

Abstract

Generating geometric digital twins (GDTs) of railway overhead line equipment (OLE) from point cloud data (PCD) using manual or semi-automated approaches is labour-intensive. This diminishes their practical benefits, with 74% of modelling effort spent converting PCD into GDTs. Automation reduces cost and effort, yet state-of-the-art methods struggle to deliver kilometre-scale GDTs without precision loss or manual intervention. This paper presents an automated method combining topology-aware segmentation, rule-based classification, and template-driven geometric reconstruction. Leveraging engineering rules and OLE spatial relationships, it enables modelling in cluttered, partially occluded scenes. OLE elements are segmented into labelled clusters, then aligned with parametric assemblies to generate industry foundation classes (IFC) models. Evaluation on 18.5 km of PCD achieved F1 scores of 98.3% for C sections, 89.8% for contact and 84.1% for catenary cables, with ±5.6 cm RMSE. Automation saved 98.6% of time versus manual workflows. This contributes a topology-informed strategy for scalable digital twin generation.

Automation in ConstructionVol. 193
University of Cambridge (GB), University College London (GB)
Cambridge Trust
Industry, innovation and infrastructure
BIM and Construction Integration
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon