Under the condition of heavy oil thermal recovery, the cement sheath is easy to crack in the high temperature environment, resulting in the decrease of cement paste strength, which may further cause sealing failure and oil and gas production safety accidents. In this paper, the influence of graphite on the mechanical properties of cement paste under the simulated thermal recovery of heavy oil was studied, and its mechanism is explored by testing and analyzing the microstructure. The phase composition and microstructure of graphite-cement composites were determined by X-ray diffraction analysis (XRD) and scanning electron microscope (SEM), and the thermogravimetric analyzer (TG/DTG) was used to analyze the heat resistance of the graphite-cement composites. The results show that the addition of graphite significantly improved the strength and deformation resistance of the Class G oil well cement at high temperature (300, 400, and 500 °C) and low temperature (50 °C), and the optimal addition amount is 0.07%. The microscopic analysis shows that the incorporation of graphite promoted the formation of hydration products, and played a role in filling pores and reducing microcracks in cement pastes. At the same time, due to the better thermal conductivity of graphite, it can balance the internal thermal stress of the cement pastes and inhibit the strength decline of cement pastes under high temperature environments. The integrity of cement pastes was guaranteed through the mechanism of "crack deflection" and "crack bridging". The research results of this paper have presented a certain theoretical basis and new ideas for the development of cementing slurry systems in heavy oil thermal recovery wells.

In order to resolve the technical problem of cementing when drilling super high-pressure gas layers or saltwater layers of Guandu structure in Chishui region, Guizhou province, an ultra-heavy slurry was developed by optimizing weighting materials and designing particles, and applied to well Guanshen1 for liner cementing. According to the needs of preparing ultra-heavy slurry, the weighting additive MicroMAX in spherical particles was selected and combination of weight additives—reduced iron powder, iron powder, MicroMAX—was chosen for optimization. The particle size-distribution of the slurry was designed on the basis of the theory of tight packing, and the actual particle size-distribution is close to the ideal condition of tight packing. The ultra-heavy slurry with a density of 2.70-3.00 g/cm³ was designed, which is good in basic performance, flow ability and stability. In the simulated mixing test on the ground, a slurry with an average density of 2.71 g/cm³ was prepared by using conventional one-time cementing process. In the liner cementing of well Guanshen 1, the slurry with a density of 2.80 g/cm³ was used to successfully seal the super high-pressure saltwater layer: the average density of the slurry pumped into well was 2.78 g/cm³ and the maximum density was 2.82 g/cm³; amplitude log showed that the cementing quality was good; the well bore kept stable in follow-up drilling when the density of drilling fluid was reduced from 2.77 g/cm³ to 2.00 g/cm³.

Conventional fluid loss additives have difficultly controlling the water loss of cement–metakaolin slurry with semi-saturated brine cement slurry and limiting it to less than 50 mL (30 min)⁻¹. This paper describes the development of an anti-salt fluid loss additive for metakaolin–cement systems. This study adopted the aqueous solution polymerization method; selected four kinds of monomers, namely 2-Acrylamido-2-methylpropane sulfonic acid (AMPS), N,N-Dimethylacrylamide (DMAA), acrylamide (AM), and methyl acrylate (MA); and performed a single-factor experiment on the proportion of monomer, reaction temperature, initiator dosage, and developed fluid loss additive, which has a high salt tolerance and temperature tolerance. This fluid loss additive can resist salt until saturation, and it can control fluid loss in 24 mL·(30 min)⁻¹ when its dosage is 2%. The fluid loss additive can achieve the effect of fluid loss reduction by increasing the filtrate viscosity, forming a flexible elastic adsorption layer via adsorption, and blocking mud cake pores.

To investigate the effects of graded equal amplitude cyclic loading on rock deformation and failure, this study examines the influence of confining pressure and upper limit cyclic stress on the deformation parameters, stress–strain hysteresis curves, and macroscopic failure characteristics of sandstone during cyclic loading and unloading processes. Through a series of three-stage cyclic loading and unloading tests conducted under varying confining pressures, the findings indicate the following. With the increase of confining pressure and upper limit stress, the axial hysteretic loop of cyclic loading and unloading shows a tendency of expansion, and the hysteresis loop gradually changes from dense to sparse. However, the change of the hoop hysteresis loop is only related to the confining pressure, and the ability to resist the hoop deformation is the best under the confining pressure of 10 MPa. Compared to conventional triaxial tests, the peak strength, axial peak strain, and elastic modulus of sandstone decrease under cyclic loading and unloading conditions, whereas the peak axial strain increases. The Poisson’s ratio initially decreases and then increases with increasing confining pressure. Cyclic loading and unloading deteriorates the strength of rock mass, and the damage stress is greater than that of conventional triaxial specimens. With the increase of confining pressure, the growth effect on the crack initiation stress gradually weakens compared with conventional triaxial tests. In both test conditions, the rock samples exhibit distinct brittle failure characteristics, with macroscopic failure modes predominantly manifesting as shear failure. However, cyclic loading and unloading inhibit microcrack formation. These findings elucidate the deformation and failure mechanisms of sandstone under graded constant-amplitude cyclic loading, providing valuable insights for stability assessment and hazard mitigation in open-pit mine slopes.

Cement bond quality is critical to ensuring the long-term safety and structural integrity of oil and gas wells. However, due to the complex interdependencies among geological conditions, operational parameters, and fluid properties, accurately predicting cement bond quality remains a considerable challenge. To improve the accuracy and practical applicability of cement bond prediction, this study develops an intelligent prediction model. A Wide and Deep neural network architecture is adopted, into which two key parameters of the cement slurry’s power-law rheological model—the consistency coefficient and the flow behavior index—are embedded. A temperature correction mechanism is incorporated by integrating the correction equations directly into the network structure, allowing for a more realistic representation of the cement slurry’s behavior under downhole conditions. The proposed model is designed to simultaneously predict the bonding quality at both the casing–cement sheath and cement sheath–formation interfaces. It is trained on a field dataset comprising 30,000 samples from eight wells in an oilfield in western China. On the test set, the model achieved prediction accuracies of 87.29% and 87.49% at the two interfaces, respectively. Furthermore, field testing conducted during a third-stage cementing operation of a well demonstrated a prediction accuracy of approximately 90%, indicating strong adaptability to real-world engineering conditions. The results demonstrate that the temperature-corrected neural network effectively captures the flow characteristics of the cement slurry. The proposed model meets engineering application requirements and serves as a reliable, data-driven tool for optimizing cementing operations and enhancing well integrity.