Railway infrastructure faces growing degradation risks from intensified operational loads and climate change, necessitating a paradigm shift from reactive repairs to digitalized predictive maintenance. This study explores the synergistic convergence of Artificial Intelligence (AI), Building Information Modeling (BIM), and Digital Twins (DT) to optimize asset management. A Systematic Literature Review was conducted, adhering to PRISMA guidelines and strictly selecting and analyzing 73 peer-reviewed articles from Web of Science and Scopus (2015–2026). The results reveal that while Supervised Learning remains the dominant paradigm for defect detection, Reinforcement Learning is emerging as a key tool for maintenance scheduling. However, a critical “Digital Twin Gap” is identified, where most systems function only as unidirectional digital representations rather than bidirectional, self-correcting twins. Furthermore, despite frequent sustainability claims, there is a marked absence of quantified environmental metrics in current research. Consequently, this paper concludes that future advancements must prioritize the development of “True Digital Twins” with autonomous actuation, ensure interoperability through Industry Foundation Classes (IFC), and integrate explicit “Green KPIs” to objectively validate the environmental benefits of digitalized maintenance strategies.
Mutlu et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: