Due to the complex and changing drilling conditions and the large scale of logging data, it is extremely difficult to process the data in real time and identify dangerous working conditions. Based on the multi-classification intelligent algorithm of Stacking model fusion, the 24 h actual working conditions of an XX well are classified and identified. The drilling conditions are divided into standpipe connection, tripping out, tripping in, Reaming, back Reaming, circulation, drilling, and other conditions. In the Stacking fusion model, the accuracy of the integrated model and the base learner is compared, and the confusion matrix of the drilling multi-condition recognition results is output, which verifies the effectiveness of the Stacking model fusion. Based on the variation in the parameter characteristics of different working conditions, a real-time working condition recognition diagram of the classification results is drawn, and the adaptation rules of the Stacking fusion model under different working conditions are summarized. The stacking model fusion method has a good recognition effect under the standpipe connection condition, tripping in condition, and drilling condition. These three conditions’ accuracy, recall rate, and F1 value are all above 90%. The stacking model fusion method has a relatively poor recognition effect on ‘other conditions‘, and the accuracy rate, recall rate, and F1 value reach less than 80%.

Annular pressure has been recognized as one of the most challenging problems in the petroleum industry, posing a series of threats to wellbore integrity. Annular pressure caused by thermal expansion during the cement hydration process is rarely studied by researchers. In light of the hydration heat generation process, a kinetics model for cement hydration under different curing temperatures is demonstrated in this paper. Considering interactions between temperature and cement hydration, a transient temperature prediction model during well cementing is built. On the basis of these assumptions, the prediction model of annular pressure is established, considering the change in cement temperature and the change in annulus volume. Using the models illustrated in this paper, a series of numerical simulations are performed. The changing roles of transient cement hydration degree and temperature in wellbores are analyzed thoroughly. The annular pressure during well cementing shows a rapid increase and then a decrease, which is similar to that of the temperature. In addition, a sensitive analysis of annular pressure is conducted. The analysis shows that the annular pressure increases with the geothermal gradient, the cement hydration heat, and the wellbore diameter. Suggestions and conclusions can provide safety guidance for the management of annular pressure during well cementing.

Underground Gas Storage (UGS) is transitioning from traditional fossil fuel peak-shaving facilities into comprehensive hubs for Terawatt-hour-scale Terawatt-hour (TWh) scale renewable energy storage. The unique physicochemical properties of diverse fluids, such as the negative Joule–Thomson coefficient of hydrogen (−0.03 K/bar), present complex engineering adaptability challenges. Since existing studies primarily focus on single mechanisms or specific geological types, this review integrates a unified engineering framework to evaluate the repurposing potential and retrofitting requirements of existing oil and gas assets. By compiling a property benchmarking matrix for methane, carbon dioxide, and hydrogen, the storage adaptability of various geological formations is summarized. Salt caverns exhibit strong adaptability to highly diffusive and reactive fluids due to their high salinity (exceeding 150 g/L) and mechanical stability, whereas porous media offer massive capacity (more than 10 times) but require overcoming severe biogeochemical obstacles. Based on thermo–hydro–mechanical–chemical–biological (THMCB) coupling mechanisms, an integrity evaluation system for artificial wellbore and natural geological barriers is systematically reviewed. Critical risks, including fatigue failure under high-frequency cyclic loading, material degradation, gas leakage, and indirect Global Warming Potential (GWP), are elucidated. A future evolution route integrating physical, digital, and policy dimensions is outlined. This roadmap emphasizes Hydrogen-Enriched Compressed Natural Gas (HCNG)synergistic storage, dynamic risk control utilizing digital twins and Artificial Intelligence (AI), and standardized Life Cycle Assessment mechanisms (LCA), providing a scientific basis for the sustainable transition of UGS facilities.