In recent years, there has been significant research and practical application of machine learning methods for predicting reservoir pore pressure. However, these studies frequently concentrate solely on reservoir blocks exhibiting normal-pressure conditions. Currently, there exists a scarcity of research addressing the prediction of pore pressure within reservoir blocks characterized by abnormally high pressures. In light of this, the present paper introduces a machine learning-based approach to predict pore pressure within reservoir blocks exhibiting abnormally high pressures. The methodology is demonstrated using the X block as a case study. Initially, the combination of the density–sonic velocity crossplot and the Bowers method is favored for elucidating the overpressure-to-compact mechanism within the X block. The elevated pressure within the lower reservoir is primarily attributed to the pressure generated during hydrocarbon formation. The Bowers method has been chosen to forecast the pore pressure in well X-1. Upon comparison with real pore pressure data, the prediction error is found to be under 5%, thus establishing it as a representative measure of the reservoir’s pore pressure. Intelligent prediction models for pore pressure were developed using the KNN, Extra Trees, Random Forest, and LightGBM algorithms. The models utilized five categories of well logging data, sonic time difference (DT), gamma ray (GR), density (ZDEN), neutron porosity (CNCF), and well diameter (CAL), as input. After training and comparison, the results demonstrate that the LightGBM model exhibits significantly superior performance compared to the other models. Specifically, it achieves R² values of 0.935 and 0.647 on the training and test sets, respectively. The LightGBM model is employed to predict the pore pressure of two wells neighboring well X-1. Subsequently, the predicted data are juxtaposed with the actual pore pressure measurements to conduct error analysis. The achieved prediction accuracy exceeds 90%. This study delivers a comprehensive analysis of pore pressure prediction within sections exhibiting anomalously high pressure, consequently furnishing scientific insights to facilitate both secure and efficient drilling operations within the X block.

Small-spacing twin-well (SSTW) salt caverns have an extensive application prospect in thin or bedded rock salt formations due to their good performance, while they are rarely used in ultra-deep formations. The target strata depth of Pingdingshan salt mine is over 1700 m, and it is planned to apply an SSTW cavern to construct the underground gas storage (UGS). A 3D geomechanical model considering the viscoelastic plasticity of the rock mass is introduced into Flac^3D to numerically study the influence of internal gas pressure, cavern upper shape and well spacing on the stability of an SSTW salt cavern for Pingdingshan UGS. A set of assessment indices is summarized for the stability of gas storage. The results show that the minimum internal gas pressure is no less than 14 MPa, and the cavern should not be operated under constant low gas pressure for a long time. The cavern with an upper height of 70 m is recommended for Pingdingshan gas storage based on the safety evaluation and maximum volume. The well spacing has a limited influence on the stability of the salt cavern in view of the volume shrinkage and safety factor. Among the values of 10 m, 20 m and 30 m, the well spacing of 20 m is recommended for Pingdingshan gas storage. In addition, when the cavern groups are constructed, the pillar width on the short axis should be larger than that on the long axis due to its greater deformation in this direction. This study provides a design reference for the construction of salt cavern gas storage in ultra-deep formations with the technology of SSTW.

Salt cavern gas storage has become the key project of current and future underground gas storage (UGS) facilities construction due to their efficient peak-shaving and supply assurance capacities. The Sanshui Basin in Guangdong Province, China, is rich in salt resources and has high-purity salt rock, which is a potential area for the construction of salt cavern underground gas storage. To speed up the large-scale construction of underground gas storage in China and promote the sustainable development of the natural gas market, it is very necessary to analyze the geomechanics of the target salt layer and study the feasibility of gas storage construction. Based on comprehensive experiments of rock mechanics and thermodynamics, the strength, creep and temperature-sensitive mechanical properties of the target rock in Sanshui Basin were studied. Then, according to the geological conditions of Sanshui salt formation, a three-dimensional geological model was established to analyze the stability of salt cavern gas storage under the injection-production operation. The results show that the average tensile strength and uniaxial compressive strength of salt rock are 1.51 MPa and 26.04 MPa, respectively, showing lower strength. However, under triaxial compression, the compressive strength of salt rock increases significantly, and there is no obvious shear failure phenomenon observed. Moreover, after the peak strength, the salt rock still has a large bearing capacity. In addition, under the confining pressure of 30 MPa, the strength of salt rock decreases by 8.3% at a temperature of 60 °C compared with that at room temperature, indicating that the temperature has a low, modest effect on the mechanical properties of salt rock. The stability analysis shows that, under an injection-production operating pressure of 10–23 MPa, the displacement, plastic zone range and volume convergence rate of single cavity and cavity group are small, and the cavity shows good stability. Overall, the target salt formation in Sanshui Basin, Guangdong Province, presents a good geomechanical condition suitable for the construction of underground salt cavern gas storage. This study can provide a reference for the development and design of salt cavern UGS.

The bottom hole fluctuating pressure has a large influence on the wellbore instability. To address this problem, firstly, according to the principle of seepage mechanics, we established a calculation model of the change in pore pressure around the wellbore radius under fluctuating pressure; then, through laboratory rock mechanics test and rock damage mechanics theory analysis, the change law of formation strength under the action of static hydration and dynamic damage are determined; finally, based on the theory of rock mechanics in porous media, a quantitative evaluation method for the risk of wellbore instability under fluctuating pressure is established and the changing pattern of wellbore instability risk is analyzed. The results show that the pore pressure around the well shows a trend of fluctuation increase under fluctuating pressure, and there is a certain lag in the fluctuation of pore pressure inside the formation; the longer the muddy shale is immersed in drilling fluid, the greater the reduction in strength; the reduction is greater in the early stage of immersion, and the reduction in strength in water-based drilling fluid is greater than that in oil-based drilling fluid. At the beginning of the pressure cycle, the formation damage variable and compressive strength gradually increase and decrease with the increase of the pressure cycle number; after several cycles, the magnitude of change gradually decreases with the increase of the cycle number. When the bottom hole pressure fluctuates at a certain period, the greater the fluctuation, the shorter the period of wellbore stability; when the bottom hole pressure fluctuates at a certain range, the smaller the fluctuation period, the faster the borehole enters the high-risk period, while the shortest period of wellbore stability occurs when the fluctuation period is smallest; and when the wave cycle is in the middle, the wellbore stability period is the longest.