Toward Smart Railway Infrastructure Predictive and Optimised Maintenance Through Digital Twin (DT) System

Area of Science:

• Railway Engineering
• Cyber-Physical Systems
• Predictive Maintenance

Background:

• Digital Twin (DT) technology is emerging for optimizing railway maintenance.
• Current DT applications in railways are fragmented and lack systematic evaluation.
• A DT integrates physical assets, virtual models, and data exchange for real-time insights.

Purpose of the Study:

• To critically review DT-enabled systems for monitoring, analysis, and maintenance decision-support in railway engineering.
• To identify research gaps and future directions for DT applications in railways.
• To synthesize current DT implementations and highlight challenges for scalable frameworks.

Main Methods:

• Systematic review of 34 peer-reviewed studies (2020-2025) on DT in railway infrastructure and operations.
• In-depth analysis of 10 key studies focusing on technical implementation and data integration.
• Categorization of applications across track systems, rolling stock, bridges, and communication networks.

Main Results:

• DT approaches enhance fault detection and enable condition-based/predictive maintenance.
• DTs can reduce the need for manual inspections in railway systems.
• Most current studies are conceptual or pilot-scale with limited real-world validation.

Conclusions:

• Significant challenges hinder scalable DT implementation in railways, including standardization, interoperability, and real-time scalability.
• Data governance, cybersecurity, and integration of multi-source sensing/analytics require further attention.
• Addressing these gaps is crucial for reliable, integrated DT-driven railway maintenance frameworks.