AI-Driven Digital Twin Frameworks for Predictive Maintenance and Closed-Loop Remote Control in Smart Factories: A Structured Review

Abstract

The increasing connectivity of industrial machines has changed maintenance from a largely schedule-driven activity into a continuous, data-driven process. Digital Twin (DT) technology supports this transition by providing a dynamic virtual representation of a physical asset that is continually updated using operational data. When artificial intelligence (AI) is embedded within the twin, the resulting system can move beyond visualization to support fault identification, anomaly detection, degradation assessment, Remaining Useful Life (RUL) estimation, and maintenance decision-making. This paper presents a structured review of AI-enabled digital twin approaches for predictive maintenance in smart manufacturing, examined end-to-end across physical sensing, data acquisition, communication, twin synchronization, intelligent analytics, maintenance decision-making, and remote corrective control. Machine learning, deep learning, unsupervised anomaly detection, hybrid and physics-informed models, edge intelligence, federated learning, and generative AI (GenAI) are discussed with respect to their industrial suitability and their bearing on the accessibility of digital-twin maintenance for resource-constrained manufacturers. Particular attention is given to a limitation that remains evident throughout the literature: most reported systems detect or predict abnormal behavior but stop short of converting those predictions into safe, closed-loop actions. The review classifies systems by their progression from monitoring and diagnosis to prediction, prescription, and autonomous control, and introduces a GenAI-Augmented Digital Twin Maturity Evaluation (GADT-ME) framework that scores a system jointly on functional maturity and generative-AI capability. Challenges relating to scarce failure data, latency, cybersecurity, synchronization, explainability, interoperability, computational cost, and deployment cost for small and medium enterprises (SMEs) are also examined. The review concludes that future research should prioritize hybrid edge–cloud intelligence, secure actuation, multi-sensor fusion, interpretable