Abstract: A cement sheath sealing performance simulation method includes: establishing a three-dimensional deformable solid model of the borehole, dividing the model from inside to outside into a casing, cement sheath, a filter cake and a formation, performing mesh division, assigning material parameters to the casing, cement sheath and formation; establishing an element set for defining the filter cake material, assigning the element set to the meshes of the filter cake, obtaining material parameters of the filter cake based on Python code by considering the filter cake's heterogeneity, setting a boundary condition, simultaneously applying a load to the casing, inserting cohesive units for the interfaces between the casing and cement sheath, the cement sheath and the filter cake, and the filter cake and the formation respectively, performing linear damage evolution based on Maxs damage, and obtaining the equivalent plastic strain of the cement sheath and the micro-annulus size during the load application.

Abstract: A wellbore temperature optimization and predication method integrating numerical models and machine learning includes the following steps: establishing a wellbore-formation transient heat transfer model, obtaining an initial data set composed of relevant parameters, normalizing the initial data set, training a wellbore temperature prediction model by using a random forest algorithm, then optimizing the hyperparameters of the random forest algorithm by using a genetic algorithm, performing global optimization by using an annealing algorithm to obtain the optimized wellbore temperature and related parameters, calculating the wellbore temperature by substituting the optimized parameters into the wellbore-formation transient heat transfer model, and performing comparative verification on the optimized wellbore temperature and the calculated wellbore temperature.