Predictive maintenance in cyber-physical systems: a comprehensive review of applications, approaches, and challenges

The rapid proliferation of predictive maintenance (PdM) techniques has led to a fragmented research landscape, limiting knowledge consolidation and solution reuse across industrial contexts. Motivated by this issue, this study presents a systematic review of PdM approaches for cyber-physical systems, covering data-driven, statistical, stochastic, AI-based, knowledge-based, and hybrid methodologies. In the context of Industry 4.0 and the transition toward Industry 5.0, Prognostics and Health Management (PHM) has become a key enabler for reliable, adaptive, and human-centric industrial systems. While PdM benefits from increased data availability, connectivity, and advances in machine learning and artificial intelligence, its effectiveness remains highly dependent on application context, data quality, and evolving operating conditions. In complex cyber-physical systems, major challenges persist, including data heterogeneity and fusion, uncertainty management, model generalization, scalability, and deployment constraints. By analyzing these challenges across PdM paradigms and application domains, this review bridges methodological advances and practical deployment, identifies current limitations, and outlines future research directions for robust and trustworthy PdM.