Drilling fluid loss is a common and complex downhole problem that occurs during drilling in deep fractured formations, which has a significant negative impact on the exploration and development of oil and gas resources. Establishing a drilling fluid loss model for the quantitative analysis of drilling fluid loss is the most effective method for the diagnosis of drilling fluid loss, which provides a favorable basis for the formulation of drilling fluid loss control measures, including the information on thief zone location, loss type, and the size of loss channels. The previous loss model assumes that the drilling fluid is driven by constant flow or pressure at the fracture inlet. However, drilling fluid loss is a complex physical process in the coupled wellbore circulation system. The lost drilling fluid is driven by dynamic bottomhole pressure (BHP) during the drilling process. The use of a single-phase model to describe drilling fluids ignores the influence of solid-phase particles in the drilling fluid system on its rheological properties. This paper aims to model drilling fluid loss in the coupled wellbore–-fracture system based on the two-phase flow model. It focuses on the effects of well depth, drilling pumping rate, drilling fluid density, viscosity, fracture geometric parameters, and their morphology on loss during the drilling fluid circulation process. Numerical discrete equations are derived using the finite volume method and the “upwind” scheme. The correctness of the model is verified by published literature data and experimental data. The results show that the loss model without considering the circulation of drilling fluid underestimates the extent of drilling fluid loss. The presence of annular pressure loss in the circulation of drilling fluid will lead to an increase in BHP, resulting in more serious loss.

Deep and ultra-deep drilling operations commonly encounter fractured and fracture-vuggy formations, where weak wellbore strength and well-developed fracture networks lead to frequent lost circulation, presenting a key challenge to safe and efficient drilling. Existing diagnostic practices mostly rely on drilling fluid loss dynamic models of single fractures or simplified discrete fractures to invert fracture geometry, which cannot capture the spatiotemporal evolution of loss in complex fracture networks, resulting in limited inversion accuracy and a lack of quantitative, fracture-network-based loss-dynamics support for bridge-plugging design. In this study, a geologically realistic wellbore–fracture-network coupled loss dynamic model is constructed to overcome the limitations of single- or simplified-fracture descriptions. Within a unified computational fluid dynamics (CFD) framework, solid–liquid two-phase flow and Herschel–Bulkley rheology are incorporated to quantitatively characterise fracture connectivity. This approach reveals how instantaneous and steady losses are controlled by key geometrical factors, thereby providing a computable physical basis for loss-zone inversion and bridge-plugging design. Validation against experiments shows a maximum relative error of 7.26% in pressure and loss rate, indicating that the model can reasonably reproduce actual loss behaviour. Different encounter positions and node types lead to systematic variations in loss intensity and flow partitioning. Compared with a single fracture, a fracture network significantly amplifies loss intensity through branch-induced capacity enhancement, superposition of shortest paths, and shortening of loss paths. In a typical network, the shortest path accounts for only about 20% of the total length, but contributes 40–55% of the total loss, while extending branch length from 300 mm to 1500 mm reduces the steady loss rate by 40–60%. Correlation analysis shows that the instantaneous loss rate is mainly controlled by the maximum width and height of fractures connected to the wellbore, whereas the steady loss rate has a correlation coefficient of about 0.7 with minimum width and effective path length, and decreases monotonically with the number of connected fractures under a fixed total width, indicating that the shortest path and bottleneck width are the key geometrical factors governing long-term loss in complex fracture networks. This work refines the understanding of fractured-loss dynamics and proposes the concept of coupling hydraulic deviation codes with deep learning to build a mapping model from mud-logging curves to fracture geometrical parameters, thereby providing support for lost-circulation diagnosis and bridge-plugging optimisation in complex fractured formations.

Irregular borehole enlargement alters annular flow structures and can create low-velocity regions that impair hole cleaning. However, conventional computational fluid dynamics (CFD) requires repeated geometric reconstruction and numerical simulations for each wellbore configuration, while existing physics-informed models have limited capability for cross-geometry extrapolation. This study develops transfer-learning-based parameterized physics-informed neural networks (TLP-PINNs) for the rapid three-dimensional prediction of Herschel–Bulkley drilling-fluid flow in locally enlarged irregular wellbores. A Gaussian enlargement ratio is introduced as an explicit geometric input, while mass and momentum conservation equations, boundary conditions, adaptive loss weighting, extrapolation-distance-driven physics-point allocation, and partial-layer transfer learning are integrated into a unified framework. The source model generally maintains good in-range interpolation accuracy for the velocity field within the 10–50% enlargement range, although the pressure error shows greater case-to-case variability for unseen intermediate geometries. For the unseen 80% enlargement case, transfer learning reduces the relative RMSEs of axial velocity, velocity magnitude, and pressure from 14.0%, 13.5%, and 3.5% to 9.42%, 9.50%, and 1.34%, respectively, with corresponding $R_p^2$ of 0.9668, 0.9663, and 0.9992. The transferred model also accurately captures the low-velocity zone within the enlarged section and the associated redistribution of the local pressure gradient, while reducing neural-network training time by 51.2% relative to full-domain retraining. These results demonstrate a practical cross-geometry framework for the rapid hydraulic assessment of irregular wellbores and provide detailed flow-field information for subsequent analyses of hole cleaning and particle transport.

Rockbursts are prevalent in underground excavation fields such as coal mining, underground crossings, dam engineering, and subsurface construction. However, within the petroleum engineering sector, phenomena resembling rockbursts—where rock abruptly fragments and erupts violently alongside natural gas during gas drilling—remain completely unreported in global literature. During nitrogen gas drilling operations at the Qionglai 1 well in the western Sichuan Basin in 2011, a severe blowout and deflagration event occurred, where the rockburst phenomenon within fractured tight sandstone gas reservoirs constituted a primary factor leading to this accident. The DN tight sandstone gas reservoir, belonging to deep coal-measure strata and situated within the Kuqa Depression of the Tarim Basin, contains thin coal seams, carbonaceous mudstone, and tight sandstone, with completion depths exceeding 5000 meters and encompassing high-stress tectonic zones. Utilizing nitrogen as the circulating medium during the drilling process results in minimal bottomhole pressure generated by the low-density gas. Upon penetrating high-yield gas layers, formation gas enters the wellbore at elevated velocities driven by the pressure differential, diminishing the stability of the surrounding rock and triggering rockburst phenomena. Taking bottomhole rockbursts as the primary research focus, this study applies conventional rockburst proneness evaluation indices to assess the tendency of the DN tight gas reservoir, and the evaluation results indicate that both the thin coal seams and the tight sandstone exhibit strong rockburst proneness. In addition, the gas monitoring while drilling and control system provides continuous real-time acquisition of drilling and return parameters, which supports rapid identification of abnormal downhole responses associated with bottomhole rockbursts. However, the present study does not establish a predictive threshold for impending rockbursts, and the monitoring results are therefore interpreted as an important basis for event recognition and for future early-warning research.