Hydraulic fracturing is a crucial technique for the extraction of geothermal energy from hot dry rock reservoirs. However, the development of such reservoirs faces significant challenges due to the high in-situ stress and strong elastic-plastic behavior of these rocks, which often result in simplified fracture geometries and subsequent low heat extraction efficiency. To address this issue, a novel reservoir treatment method based on thermal expansion and contraction principles is proposed. By applying alternating heating-cooling treatments to the reservoir, cyclic thermal stress is generated within the rock to enhance the complexity of post-fracturing fracture networks. To investigate the resultant hydraulic fracture propagation under alternate-temperature loading, a custom-developed thick-walled cylinder expansion fracturing device was employed to study the fracture propagation mechanisms in hot dry rock samples under cyclic thermal loading. The fracture network complexity was characterized by the fractal dimension method. Experimental results demonstrated that alternate thermal load cycling significantly enhances the fracture network complexity compared to conventional single-phase heat treatment. The maximum improvement in fractal dimension (3.86% increase) was observed at 500 ℃. Under alternating temperature loads, the upper surface fractures predominantly exhibited bilateral symmetric structures. At 600 ℃, a substantial increase in branched fractures and rock debris near boreholes occurred, indicating that alternating temperature loads significantly enhance the complexity of engineered fracture networks in hot dry rock. These findings suggest that incorporating thermal cycling into hydraulic fracturing processes can significantly improve the fracture network complexity, thereby enhancing the efficiency of heat extraction from hot dry rock reservoirs.

The digital twin, as the decision center of the automated drilling system, incorporates physical or data-driven models to predict the system response (rate of penetration, down-hole circulating pressure, drilling torques, etc.). Real-time drilling torque prediction aids in drilling parameter optimization, drill string stabilization, and comparing the discrepancy between observed signal and theoretical trend to detect down-hole anomalies. Due to their inability to handle huge amounts of time series data, current machine learning techniques are unsuitable for the online prediction of drilling torque. Therefore, a new way, the just-in-time learning (JITL) framework and local machine learning model, are proposed to solve the problem. The steps in this method are: (1) a specific metric is designed to measure the similarity between time series drilling data and scenarios to be predicted ahead of bit; (2) parts of drilling data are selected to train a local model for a specific prediction scenario separately; (3) the local machine learning model is used to predict drilling torque ahead of bit. Both the model data test results and the field data application results certify the advantages of the method over the traditional sliding window methods. Moreover, the proposed method has been proven to be effective in drilling parameter optimization and pipe sticking trend detection. Finally, we offer suggestions for the selection of local machine learning algorithms and real-time prediction with this approach based on the test results.

The difference in microstructure leads to the diversity of shale mechanical properties and bedding fractures distribution patterns. In this paper, the microstructure and mechanical properties of Longmaxi marine shale and Qingshankou continental shale were studied by X-ray diffractometer (XRD), field emission scanning electron microscope (FE-SEM) with mineral analysis system, and nanoindentation. Additionally, the typical bedding layers area was properly stratified using Focused Ion Beam (FIB), and the effects of microstructure and mechanical properties on the distribution patterns of bedding fractures were analyzed. The results show that the Longmaxi marine shale sample contains more clay mineral grains, while the Qingshankou continental shale sample contains more hard brittle mineral grains such as feldspar. For Longmaxi marine shale sample, hard brittle minerals with grain sizes larger than 20 μm is 18.24% and those with grain sizes smaller than 20 μm is 16.22%. For Qingshankou continental shale sample, hard brittle minerals with grain sizes larger than 20 μm is 40.7% and those with grain sizes smaller than 20 μm is 11.82%. In comparison to the Qingshankou continental shale sample, the Longmaxi marine shale sample has a lower modulus, hardness, and heterogeneity. Laminated shales are formed by alternating coarse-grained and fine-grained layers during deposition. The average single-layer thickness of Longmaxi marine shale sample is greater than Qingshankou continental shale sample. The two types of shale have similar bedding fractures distribution patterns and fractures tend to occur in the transition zone from coarse-grained to fine-grained deposition. The orientation of the fracture is usually parallel to the bedding plane and detour occurs in the presence of hard brittle grains. The fracture distribution density of the Longmaxi marine shale sample is lower than that of the Qingshankou continental shale sample due to the strong heterogeneity of the Qingshankou continental shale. The current research provides guidelines for the effective development of shale reservoirs in various sedimentary environments.

The perforating phase leads to complex and diverse hydraulic fracture propagation behaviors in laminated shale formations. In this paper, a 2D high-speed imaging scheme which can capture the interaction between perforating phase and natural shale bedding planes was proposed. The phase field method was used to simulate the same conditions as in the experiment for verification and hydraulic fracture propagation mechanism under the competition of perforating phase and bedding planes was discussed. The results indicate that the bedding planes appear to be no influence on fracture propagation while the perforating phase is perpendicular to the bedding planes, and the fracture propagates along the perforating phase without deflection. When the perforating phase algins with the bedding planes, the fracture initiation pressure reserves the lowest value, and no deflection occurs during fracture propagation. When the perforating phase is the angle 45°, 60° and 75° of bedding planes, the bedding planes begin to play a key role on the fracture deflection. The maximum deflection degree is reached at the perforating phase of 75°. Numerical simulation provides evidence that the existence of shale bedding planes is not exactly equivalent to anisotropy for fracture propagation and the difference of mechanical properties between different shale layers is the fundamental reason for fracture deflection. The findings help to understand the intrinsic characteristics of shale and provide a theoretical basis for the optimization design of field perforation parameters.