This paper systematically reviews the current technical framework and implementation approaches for drilling digital twin modeling, focusing on key challenges such as multi-source heterogeneous data fusion during wellbore drilling operations, the coupling of physics-based and data-driven models, and intelligent decision feedback mechanisms. First, targeting the objects and levels of drilling data fusion, the fusion mechanisms for multi-temporal and multi-spatial scale data and conflict resolution methods were explored. Second, a comprehensive digital twin architecture suitable for drilling operating conditions was established, and methods for implementing joint physics-based and data-driven modeling were summarized. Then, diagnostic methods for drilling anomaly data features were proposed, enabling the establishment of multi-perspective decision feedback mechanisms between the physical and digital entities. Finally, the application potential of wellbore digital twin technology was prospected in the areas of high spatiotemporal resolution cognition, edge deployment, and model credibility assurance. The research results can provide theoretical support and methodological guidance for achieving drilling state recognition and efficient control under complex operating conditions.

Severe downhole drill-string vibrations can accelerate fatigue damage, leading to substantial economic losses and increased non-productive time. Existing vibration monitoring approaches typically rely on multiple high-cost downhole sensors, which has hindered their widespread deployment in field operations. This work presents a real-time vibration monitoring approach based solely on acceleration measurements and machine-learning techniques. Radial and tangential acceleration signals are generated using a rotor dynamics model and transformed into time–frequency scalograms via continuous wavelet transform. Among various whirl modes, backward whirl is recognized as the most damaging to drilling tools and wellbore integrity. Accordingly, vibration events are classified into backward whirl and non-backward whirl categories, achieving classification accuracies exceeding 94% across different training–testing split ratios. For stick-slip identification, the proposed method distinguishes stick-slip from non-stick-slip conditions with 100% accuracy. Furthermore, based on the stick-slip index, stick-slip vibrations are subdivided into four severity levels—non-stick-slip, low, medium, and high—with classification accuracies exceeding 95% across all severity classes. The generalization capability of the proposed model is validated using independent acceleration data from ABAQUS simulations and field measurements, demonstrating robust performance beyond the training dataset. Backward whirl and stick-slip are accurately classified using single-point acceleration data alone, without requiring rotational speed measurements or symmetrically distributed accelerometers. This approach reduces sensor requirements, lowers operational costs, and facilitates practical real-time deployment.