With the exploration and development of oil and gas into the ultra-deep reservoir, hydraulic fracture propagation under the condition of high stress difference is prone to occur large curvature deflection, leading to wellhead overpressure, sand plugging and other problems occur frequently. It is of great significance to clarify the mechanism and main control factors of hydraulic fracture propagation and deflection near wellbore in ultra-deep and high stress difference reservoir for safe and efficient development. Under the constraint of the continuity framework of classical thermodynamics, the sharp fracture on the discrete interface is smoothly described as a continuous damage dispersion fracture, and the Lagrange Energy Functional is constructed based on Griffith energy balance relation and fracture variational principle, and then the phase field hydraulic fracturing model of perforated well in anisotropic reservoir is established based on the principle of energy minimization. The validity of the phase-field model presented in this paper is verified by comparing with the classical Griffith crack opening profile equation. It is found that the hydraulic fracture starts to crack along an approximate straight line between perforation and maximum horizontal principal stress, and then deflects to the maximum horizontal principal stress direction. The specific direction of crack initiation is affected by in-situ stress difference, displacement and perforation angle. The increase of the in-situ stress difference will promote the hydraulic fracture deflection propagation near the wellbore, make the deflection angle increase and the deflection radius decrease; increasing the displacement can weaken the hydraulic fracture deflection, and making the deflection angle decrease and the deflection radius increase; with the increase of perforation angle, the angle between perforation and the maximum horizontal principal stress increases, which will aggravate the deflection degree of crack propagation so that the flow friction of fracturing fluid increases and the risk of sand plugging increases; the anisotropy characteristics of the reservoir can also significantly affect the deflection and propagation process of hydraulic fractures. In the model, the critical energy release rate in different directions is taken as the anisotropic parameter of fracture resistance. The results show that fractures tend to propagate in the direction of low resistance. The stronger the anisotropy of fracture resistance, the greater the deflection degree of hydraulic fractures. The anisotropic characteristics of reservoir fractures significantly affect the turning behavior of fractures. The phase-field hydraulic fracturing model in this paper provides a convenient method to study the propagation and steering behavior of hydraulic fractures without any fracture criteria, which is helpful to improve the understanding of near-well fracture steering in ultra-deep and high stress difference reservoirs, help to understand the fracture mechanism and fracture deflection behavior under different geological environments and fracturing conditions, and provide reference and suggestions for fracturing technology design and perforation scheme optimization.

Considering that the current fiber optic signal interpretation models are based on vertical fractures, and the influence of natural fractures and bedding planes makes hydraulic fractures tilted during its propagation process. What’s more, its optical fiber monitoring signals will also differ from those produced by vertical fractures, rendering existing optical fiber signal interpretation models inapplicable. Therefore, a three-dimensional inclined fracture propagation model is established in this paper, considering the tensile and shear mechanical behaviors during crack extension, and solved by the finite element method. The model in this paper simulates the fiber optic signal characteristics under vertical crack extension conditions has good agreement with the discontinuous displacement method of Liu and Wu, which verifies the correctness of the numerical model in this paper.After that, we build the geometry model of inclined fractures, the effects of different inclination angles, tilt directions, fracture heights, fiber-optic monitoring distances, and in-situ stress states on fiber-optic strains and strain rates are investigated during the propagation of hydraulic fractures with inclination angles. Some conclusions can be drawn from the simulation results:red and blue bands appear on strain rate waterfall plots monitored by fiber optics in neighboring wells during inclined hydraulic fracture propagation. Symmetrical red and blue strain ellipses and strain rate bands appear when the hydraulic fracture inclination is at 30° to 55°. As the inclined hydraulic fracture continues to propagate, when the inclined fracture hits the fiber, multiple heartshaped zones appear on the strain rate waterfall map. The fiber-optic-monitored strain and strain-rate waterfall maps are also able to reflect the tilt direction of the hydraulic fracture. The width of the red bands of the strain rate waterfall plot increases with increasing hydraulic fracture height, which provides us with a way of interpreting the height of fractures based on the optical fiber monitoring. For hydraulic fractures of the same morphology and size, the optical fiber monitoring signals under different initial stress states exhibit significant differences, among which, the optical fiber monitoring signals under the normal fault stress state have the most distinct band characteristics. Under the simulation conditions of this paper, with each 100 m increase in fiber-optic monitoring distance, the intensity of the fiber-optic-monitored strain and strain-rate signals decreases by one order of magnitude. The research in this paper is of great significance in guiding the interpretation of hydraulic fracture morphology and size through neighboring well fiber-optic signals and guiding the placement of fiber optics in neighboring wells.

Wellbore stability is a key factor affecting safe and efficient drilling. At present, it is difficult to conduct real-time and accurate analysis of wellbore stability in related research. To address the current research shortcomings, this study proposes a real-time analysis model of wellbore stability integrating image recognition and an expert system, which mainly includes caving image segmentation and recognition, and a wellbore stability expert system. The caving image recognition proposes a new dynamic threshold segmentation method based on simple linear iterative clustering superpixel segmentation and visual geometry group 19-layer image classification. After completing the segmentation of the caving image, the geometric features of the caving are calculated, and the multi-source feature fusion GoogleNet model is established by integrating the geometric features with the convolution features extracted by GoogleNet to identify the caving types efficiently. After segmentation and recognition of caving images. The wellbore stability expert system uses the caving features to establish an expert system model to determine the mechanism of wellbore instability and provide reasonable solutions. Finally, the wellbore stability integrating image recognition and an expert system model was applied to a well in field production, accurately determining the mechanism of wellbore instability in real time and effectively solving the corresponding wellbore instability problem based on the measures provided by the model.

In regard to unconventional oil reservoirs, the transient dual-porosity and triple-porosity models have been adopted to describe the fluid flow in the complex fracture network. It has been proven to cause inaccurate production evaluations because of the absence of matrix–macrofracture communication. In addition, most of the existing models are solved analytically based on Laplace transform and numerical inversion. Hence, an approximate analytical solution is derived directly in real-time space considering variable matrix blocks and simultaneous matrix depletion.

To simplify the derivation, the simultaneous matrix depletion is divided into two parts: one part feeding the macrofractures and the other part feeding the microfractures. Then, a series of partial differential equations (PDEs) describing the transient flow and boundary conditions are constructed and solved analytically by integration. Finally, a relationship between oil rate and production time in real-time space is obtained.

The new model is verified against classical analytical models. When the microfracture system and matrix–macrofracture communication is neglected, the result of the new model agrees with those obtained with the dual-porosity and triple-porosity model, respectively. Certainly, the new model also has an excellent agreement with the numerical model. The model is then applied to two actual tight oil wells completed in western Canada sedimentary basin. After identifying the flow regime, the solution suitably matches the field production data, and the model parameters are determined. Through these output parameters, we can accurately forecast the production and even estimate the petrophysical properties.