Deepwater drilling is conducted in structurally complex formations and harsh marine environments, which greatly intensifies the difficulty of maintaining well control. Reliable prediction of the shut-in pressure response in the wellbore is therefore essential for safe and efficient operations. In this work, published laboratory data are reanalyzed to derive empirical correlations that describe how drilling-fluid density changes with temperature and pressure. On this basis, the thermal expansion behavior of the drilling fluid is incorporated, and segmental temperature-field models are formulated for the seawater column, choke line, and formation intervals. A corresponding gas-expansion model and a shut-in wellhead-pressure prediction model suitable for deepwater conditions are then developed. Numerical examples are used to investigate the evolution of temperature, pressure, and fluid properties under different geothermal gradients. The simulations indicate that drilling-fluid density decreases exponentially with temperature and increases approximately linearly with pressure. In the choke line, the annular temperature continuously drops under the cooling effect of seawater, whereas in the formation interval it decreases in the upper part and increases toward the bottom, ultimately approaching the geothermal profile. When the thermal expansion of drilling fluids is taken into account, the geothermal gradient exerts a strong influence on the shut-in behavior: larger gradients enhance fluid expansion, leading to higher wellhead casing pressures and faster recovery of bottomhole pressure, which places stricter requirements on well-control design. The proposed method provides a useful theoretical reference for pressure prediction and safety evaluation during deepwater drilling shut-in.

While horizontal wells for gas hydrate exploitation allow for a larger effective contact area between the horizontal well and the reservoir, they also face severe wellbore stability problems. Two key issues are the dynamic drilling fluid safety density window and the limiting extension length of the horizontal section. This study established a horizontal well drilling model for hydrate reservoirs and a model for analyzing key parameters of the horizontal section based on the basic data of hydrate reservoirs at station SH2 in the South China Sea. The factors influencing the variation of the dynamic drilling fluid safety density window and the ultimate extension length of a horizontally drilled well section were analyzed using this model. The results showed that: The stress distribution in the surrounding rock of the well wall in the hydrate formation is dynamically changing due to changes in formation mechanical parameters resulting from hydrate decomposition after drilling fluid intrusion into the reservoir. This ultimately results in the safety density window for drilling fluids in horizontal wells drilled in marine hydrate reservoirs, which also changes dynamically over time. Drilling fluid physical properties play a vital role in limiting borehole extension length. As the drilling fluid injection temperature, rate and density increase, the ultimate extension length of the horizontal section decreases. Therefore, reducing the drilling fluid injection temperature, rate and density is an effective means to extend the borehole extension length and avoid wall stability problems. This study can provide theoretical and technical support for the safe and efficient drilling and extraction of natural gas hydrate in the future sea area.

Accurate prediction of water-based drilling fluid (water-based mud, WBM) density is of great significance for the precise calculation of hydraulic parameters and wellbore pressure, thereby ensuring drilling safety in deepwater high-temperature high-pressure (HTHP) wells. Based on actual WBM samples from a deepwater well in the South China Sea, experiments on the thermal expansion effects of WBM were conducted under conditions of 25–200 °C and 0.1–150 MPa. The variation trends of drilling fluid density with temperature and pressure were analyzed, and a characterization model for the thermal expansion effect of WBM was established. The model’s accuracy was verified using experimental data from Chen and McMordie. The relative error of the model-predicted drilling fluid density was less than 5

Deepwater oil and gas development is an important part of the oil and gas extraction field, among which open-circuit drilling technology (riserless drilling technology) is a widely used, safe and efficient deepwater shallow drilling technology. During this period, the problem of blowout caused by drilling shallow gas formations was particularly prominent. The shallow gas stored in the formation after a blowout will invade the wellbore and upwind under the drive of the pressure difference between the formation and the wellbore, and then spray into seawater to form a plume. In severe cases, it will migrate and spread to the vicinity of the platform, posing a serious threat to the safety of offshore drilling platform operations. Therefore, it is necessary to finely characterize the evolution patterns of the blowout plumes under different operating conditions. An experimental apparatus and method for the formation and evolution of plume after a deepwater open-circuit drilling blowout were designed based on similarity criteria, revealing the laws of plume formation and evolution after a blowout and clarifying the key influencing factors of plume movement after a blowout. The results indicate that after the fluid is ejected, it undergoes a process of turbulent jet entrainment bending convection diffusion, developing into a plume flow with a narrow bottom and a wide top. When the gas flow rate is 0.2 m/s, the offset angle range is 3.5–14.9° under weak cross flow conditions, and 9.4–20.8° under strong cross flow conditions; When the gas flow rate is 0.7 m/s, the offset angle range is 3.7–5.2° under weak cross flow conditions, and 4.3–14.5° under strong cross flow conditions. Overall, the initial offset angle of the plume is inversely proportional to the gas flow velocity and directly proportional to the nozzle diameter. The results of this study can lay the foundation for the study of the formation and evolution laws of blowout plumes.

By comprehensively considering the influences of temperature and pressure on fluid density in high temperature and high pressure (HTHP) wells in deepwater fractured formations and the effects of formation fracture deformation on well shut-in afterflow, this study couples the shut-in temperature field model, fracture deformation model, and gas flow model to establish a wellbore pressure calculation model incorporating thermo-hydro-mechanical coupling effects. The research analyzes the governing patterns of geothermal gradient, bottomhole pressure difference, drilling fluid pit gain, and kick index on casing head pressure, and establishes a shut-in pressure determination chart for HPHT wells based on coupled model calculation results. The study results show: geothermal gradient, bottomhole pressure difference, and drilling fluid pit gain exhibit positive correlations with casing head pressure; higher kick indices accelerate pressure rising rates while maintaining a constant maximum casing pressure; validation against field case data demonstrates over 95% accuracy in predicting wellbore pressure recovery after shut-in, with the pressure determination chart achieving 97.2% accuracy in target casing head pressure prediction and 98.3% accuracy in target shut-in time. This method enables accurate acquisition of formation pressure after HPHT well shut-in, providing reliable technical support for subsequent well control measures and ensuring safe and efficient development of deepwater and deep hydrocarbon reservoirs.

In deepwater deep drilling, elevated geothermal gradients and narrow mud weight windows present significant challenges in maintaining wellbore stability and controlling wellbore pressure. We developed a novel computational model to determine mud weight windows in elastoplastic formations, considering thermo-mechanical coupling effects between the wellbore and formation systems. Validations through on-site measurements confirmed the model's reliability. Our research demonstrates that drilling fluid creates thermal effects that can disturb the formation temperature up to ten times the wellbore radius. These disturbances cause a 23.46 % increase in the vertical depth and a 13.33 % expansion in the lateral dimensions of shallow plastic zones in deepwater environments while simultaneously reducing the drilling operational mud weight window. In deepwater shallow formations, the mud weight window is positively correlated with the geothermal gradient and negatively correlated with the injection temperature and pump rate. In deep formations, the mud weight window is positively correlated with the injection temperature, and negatively correlated with the geothermal gradient and pump rate. In formations with narrow mud weight windows, temperature differentials exceeding 70 degrees C can induce over 50 % variation in the mud weight window, indicating substantial thermal impacts. To mitigate the impact of thermo-mechanical coupling effects on the mud weight window, distinct thermal management strategies were proposed. For deepwater shallow formations, minimizing the injection temperature and pump rate of the drilling fluid is advisable. In deep formations, increasing the injection temperature and minimizing the pump rate is recommended. These research findings provide theoretical support for precise mud weight window determination in deepwater deep drilling applications, addressing drilling safety and efficiency concerns in extreme downhole conditions.

In the process of shallow deepwater drilling, due to the narrow safety window of drilling fluid density and the frequent drilling in shallow gas, shallow flow, gas hydrate and other factors, the risk of drilling accidents increases, and kick and even blowouts are easy to occur, which seriously endangers the safety of operators. In the absence of risers and subsea blowout preventers, open-circuit drilling is usually used to drill deep water shallow drilling. In the process of open-circuit drilling, drilling fluid directly returns to the seabed, so it is impossible to shut in the well when kick or even blowout occurs, and it is difficult to obtain the shut-in vertical pressure and casing pressure through traditional methods, and it is difficult to calculate the bottomhole pressure, which cannot provide a basis for the selection of parameters such as density and displacement of subsequent kill fluid. Aiming at this problem, based on Fluent numerical simulation software, this paper simulated and studied the return form of drilling fluid at the bottom mud line of open-circuit drilling by solving the VOF model, and analyzed the influence of different ocean current velocity distribution, drilling fluid displacement, gas penetration on the return height of drilling fluid. It is found that ocean current velocity distribution has little influence on drilling fluid return height, and mainly affects the diffusion dilution degree of drilling fluid. Drilling fluid displacement, gas penetration and wellhead pressure have great influence on drilling fluid return displacement and height. On this basis, according to the principle of underwater jet, the relationship between drilling fluid return height and wellhead pressure is established. On the premise of known return height, the wellhead pressure can be calculated, and the bottomhole pressure can be retrieved from the wellhead pressure. This study reveals the regularities of drilling fluid return flow in open-circuit drilling, provides theoretical guidance for the prediction of bottomhole pressure when kick occurs and the well cannot be shut in, provides support for the effective implementation of subsequent well control measures, and ensures the operation safety of deep-water shallow open-circuit drilling.

High wellbore temperatures encountered during the drilling of horizontal sections can markedly affect the safety and efficiency of drilling operations. This study extends existing temperature prediction models by considering hydraulic power, rotational power, and bit power into the analysis. The paper also provides an analytical solution for the temperature distribution model of horizontal wellbores. The reliability of the model was confirmed through validation against field data from deep shale gas horizontal wells in the Southwest oil and gas fields, showing greater efficacy in analyzing wellbore temperature variations than the Hasan and Kabir model. A sensitivity analysis was conducted to evaluate the impact of various parameters on the temperature distribution within the wellbore annulus. The parameters under consideration included rotational speed, drilling fluid flow rate, density, circulating time, inlet temperature, length of the horizontal section, geothermal gradient, and the dimensions of the borehole and drill pipe. The analysis indicated that the influence of circulating time on bottom-hole temperature is limited, with diminishing effectiveness beyond a certain threshold. In contrast, the inlet temperature was identified as a significant factor affecting both bottom-hole and exit temperatures. Effective management of bottom-hole temperature can be achieved by reducing the rotational speed, which in turn lowers the rotational power and the associated heat generation from bit power. These findings provide valuable insights for optimizing drilling operations by highlighting the key factors that contribute to wellbore temperature control.

Unconventional tight oil and gas resources, including shale oil and gas, have become the main focus for increasing reserves and production. The safe and efficient development of unconventional oil and gas is a crucial demand for the energy development strategy. Deep tight oil and gas resource development generally adopts horizontal well drilling methods. During drilling, especially in long horizontal sections, the high temperature frequently causes failures of downhole drilling tools and rotary steering tools. The temperature rises sharply during rock breaking with the drill bit. Existing wellbore heat transfer models do not fully consider the impact of heat generated by the drill bit on the wellbore temperature field. This paper aims to experimentally study the temperature rise law of the cutting tooth of the bottom polycrystalline diamond compact (PDC) bit during rock breaking. A set of evaluation devices was developed to study the temperature field distribution characteristics at the bottom of the PDC bit during rock breaking under different experimental conditions. The results indicate that the flow rate of drilling fluid, bit rotation speed, and weight on bit (WOB) significantly affect the distribution of the temperature field at the well bottom. This experimental research on the temperature field distribution characteristics at the bottom of the PDC bit during rock breaking helps reveal the heat transfer characteristics of the long horizontal section wellbore, guide the optimization of drilling parameters, and develop temperature control methods. It is of great significance for the advancement of efficient development technologies for unconventional resources in long horizontal wells.

The advanced technology and tools of shale-gas horizontal well drilling are summarized. The challenges and development direction for shale-gas drilling technology are analyzed and proposed. The objectives of this chapter are to introduce (1) the horizontal well-drilling technology status for shale gas in China and internationally; (2) the primary technologies used in shale-gas drilling including engineering geological characteristics, drilling design, drilling fluids, cements, factory drilling, and underbalanced drilling; (3) engineering cases which reveal application effects of horizontal well-drilling technology for shale-gas; and (4) challenges and development directions for shale-gas drilling technology.

ABSTRACT This paper introduces a PDC (Polycrystalline Diamond Compact) cutting rock model loaded by spring-mass-damping system by DEM (discrete element method), and this model allows force boundary conditions in the vertical and horizontal directions of the PDC cutter. Therefore, the model can simulate the rock-breaking of PDC cutter under vertical, horizontal, and composite impact load. The influence of the component and frequency of the impact on the rock-breaking performance and force of the PDC cutter was investigated. Lower amplitude composite impact load or only increasing vertical impact load may lead to increase of the fluctuation of PDC cutter contact force and peak force value; Increasing the amplitude of composite impact load both in horizontal and vertical directions, or only increasing the amplitude of horizontal impact load, has a significant effect on suppressing the vibration of cutting, and can improve the cutting depth, reduce the contact friction, and reduce the MSE (mechanical specific energy) of rock breaking. The simulated rock crushing state show that under the composite impact, increasing the amplitude of horizontal impact load is beneficial to increase number and length of transverse cracks, which promotes the large volume rock spalling, and the effect of high-frequency composite impact on suppressing PDC cutter vibration is more obvious. INTRODUCTION The polycrystalline diamond compact (PDC) bit has been widely used in oil and gas drilling industry since the 1980s (Feenstra, 1988). Many researchers have carried out a lot of research on indoor rock-breaking experiments and numerical simulation of PDC cutter and full-scale bit. The influence of rake angle, cutting depth, rock material and drilling parameters on rock cutting is investigated. With the development of bit processing technology, the impact load and temperature-pressure field are introduced into the research of cutting rock. In addition, a variety of non-planar structure cutters, such as conical cutter, axe cutter, stay cool multi-dimensional cutter, and Firestorm cutter are developed (Si et al., 2018). In terms of laboratory tests of PDC cutting rock, Black et al. (1986) compared the drilling and rock breaking characteristics of stepped PDC bit with positive displacement motor and turbodrill respectively through laboratory tests, and its economic benefits were evaluated. They established a functional relationship between the rate of penetration (ROP), bit torque and rotational speed, weight on bit (WOB) and drilling fluid flow rate. Glowka (1987) carried out a large number of tests of PDC single-cutter to investigate the effects of cutter size, wear degree, jet pressure and rock type on the rock-breaking performance and force of cutters. The cutting force model was established based on the assumption of the shape of the contact surface between the cutter and the rock. Then, the cutting contact model was extended to the full-scale bit, and a program was developed to predict the drilling performance and wear of the field test bit. Subsequently, Sinor and Warren (1987), Warren and Armagost (1988), Warren and Sinor (1989) and other scholars carried out a large number of experimental studies on topics such as drilling performance and wear prediction of different types of PDC bits. However, only some regular patterns were obtained because the experimental conclusions were based on the specific test bit. Detournay and Defourny (1992) performed the rock-cutting experiments of a PDC cutter with different wear degrees. The functional relationship between cutting force and vertical force was proposed by defining the geometric characteristics of cutters and rock-breaking specific energy. On this basis, the equation of the functional relationship between rock-breaking torque and bit weight of the full-size bit was established. The equation is often used as the boundary condition at the bit when modeling the drill string system now. The tests also studied the fracture pattern transition from plastic and brittle at different cutting depths, and the primary purpose of the investigations was to try to obtain the strength parameters of rock through scratch tests (Richard, 1999; Richard et al., 1998). T. Richard systematically studied the cutting and crushing process of rock, adopting a scratch test for the first time, which provided a reliable verification for the numerical model of subsequent studies.

Downhole vibrations caused by rock breaking when drilling through pebbled sandstone formations negatively affect the rate of penetration (ROP) and the safety of downhole tools. Therefore, it is of great significance to study the cutting characteristics of pebbled sandstone and find a method of reducing the drilling vibrations of pebbled sandstone formations. Based on the DEM (discrete element method), a simulation model of pebbled sandstone considering the random filling of high-strength gravels was established by using the random polygon distribution method. The influence of gravel content on the strength parameters and the breaking state of the pebbled sandstone samples was analyzed. Additionally, a DEM model of PDC cutting rocks loaded by a spring–mass system was established, and the Stribeck effect of contact friction between the PDC cutter and the rock was analyzed. The periodic vibration and the stick–slip phenomenon of the cutting system during the drilling process were presented by this model. The model was employed to simulate and explore the influence of composite impact load on stick–slip vibration during PDC cutting of pebbled sandstone. The simulation results showed that the composite impact load had a more obvious effect on mitigating the vibration of PDC cutting of pebbled sandstone under the condition of a higher horizontal impact amplitude coefficient (qh = 40%). Based on the simulation results, a composite impactor with a large impact angle α = 70° was selected to conduct the field tests in the pebbled sandstone formation of Well T1. The results showed that, compared to conventional drilling, the average WOB (weight on bit) of the section drilled with the composite impactor decreased by 57.13%, the standard deviation of the WOB decreased by 57.29%, and the average ROP increased by 98.31%. The employing of composite impactors in pebbled sandstone formations can significantly reduce drilling vibration, improve ROP, and protect bits and downhole instruments.

The existence of gravels in the glutenite formations leads to the complex geometries of hydraulic fracturing propagation and difficult construction in fracturing engineering. To study the hydraulic fracturing propagation law of glutenite formations, this paper establishes a fracture propagation model for the heterogeneous glutenite formations based on discrete element method, and analyzes the effects of gravel content, particle size, distribution, horizontal stress difference, fracturing fluid viscosity and flow rate on hydraulic fracturing propagation behavior. Results show that the complex geometries of hydraulic fractures in glutenite formations can lead to the generation of branched fractures and fracture bifurcation. Small-sized gravels have little effect on the fracture propagation shape which leads to a single main fracture with a flat fracture surface, on the contrary, large-sized gravels may induce hydraulic fractures to deflect along the gravel interface and form branched fractures with distorted fracture surfaces. Hydraulic fractures can propagate around gravels under the condition of high stress difference, high viscosity and medium flow rate. Gravels can prevent the propagation of hydraulic fractures under low stress difference, low viscosity and small flow rate. Hydraulic fracture bifurcation can occur when encountering gravels under high stress difference and large displacement. Properly increasing the high viscosity of fracturing fluids can effectively promote the main hydraulic fracture propagation and reduce the fracture tortuosity, thereby avoiding sand up.

ABSTRACT Deep shale gas has become an important alternative resource for shale gas development in China, and the number of horizontal wells drilled is increasing year by year. However, the rate of penetration, bottom hole temperature and leakage in horizontal section are seriously restricted by the high mud weight. Firstly, an underbalanced drilling technology strategy and mud weight reduction implementation process in shale reservoir are proposed. Secondly, based on the identification of abnormal high pressure mechanism, the pore pressure prediction model is optimized, and the fluid-solid-thermal coupling collapse pressure prediction model of fractured shale reservoir is established according to the characteristics of shale bedding. Finally, combined with the three-dimensional geological model, the safety window distribution of mud weight is clarified, and the favorable area of underbalanced drilling operation is divided. The underbalanced drilling technology has been tested in 10 horizontal wells. Compared with the conventional drilling wells, the rate of penetration, temperature control and leakage control is obviously improved. When the mud weight is reduced by 0.2 ∼ 0.45g / cm3, the bottom hole circulation temperature is reduced by 3 ∼ 8 °C, the average rate of penetration is increased by 17 %, and the average leakage and loss time of single well are reduced by 239m3 and 207h respectively. INTRODUCTION The upper Ordovician Wufeng Formation-Lower Silurian Longmaxi Formation is the main strata in the favorable area of marine shale gas in southern Sichuan, China. The working area below 4500 m is 2.1 × 104 km2, and the shale gas resources are more than 10 × 1012 m3. Among them, the shale gas resources buried in 3500-4500 m are more than 8 × 1012 m3, accounting for 80 % nearly (He et al. 2021). Compared with the shallow shale gas buried below 3500 m, the deep shale gas buried in 3500-4500 m has undergone significant changes in reservoir temperature, pressure, ground stress and other aspects. The drilling and completion technology is in the exploratory stage. 94 horizontal wells were drilled in the deep shale gas area of southern Sichuan in 2020, of which the average drilling cycle of 215.9 mm well section was 56.7 days, the average rate of penetration (ROP)was 5.53 m/h, and the average number of trips was 10.6. One of the important factors that affect low rate of penetration and long drilling cycle is the high density of drilling fluid used in shale reservoir drilling. According to the geological design requirements, the density of oil-based drilling fluid in shale reservoir is usually in the range of 2.05-2.25 g/cm3. The high density of drilling fluid will induce serious pressure holding effect that can result in slow ROP of horizontal section. High density of drilling fluid will aggravate the increase of bottom hole circulation temperature during drilling (Keith et al., 2011). The bottom hole circulation temperature of horizontal section for deep shale gas well is between 135 °C and 155 °C, while conventional rotary steering tools and instruments cannot work normally for a long time under the temperature higher than 135 °C. The high density of drilling fluid will also aggravate the risk of well leakage. In 2020, 14 wells had lost circulation in the horizontal section that the cumulative leakage of oil-based drilling fluid is 981 m3 and the loss time is 149 days.

ABSTRACT Deep shale gas with a burial depth of 3500–5000m became an important area for shale gas development in China. The characteristics of the rock's mechanics and the in situ stress have a significant impact on the drilling and fracturing effects of horizontal wells. Finite element simulation is used to build an accurate in situ stress model from the data of acoustic logging, diagnostic fracturing injection test, FMI imaging logging, and stress measurement. The results show that Young's modulus and Poisson's ratio in the Luzhou block change vertically with the deposition time. The Longmaxi reservoir has an abnormally high pore pressure gradient which ranges from 16.7 kPa/m to 21.7 kPa/m. The stress regime of the Luzhou block is primarily strike-slip type, with an overburden pressure gradient of 25.5kPa/m, and a minimum horizontal stress gradient range of 18.8 to 24.5kPa/m. According to wellbore breakouts and acoustic emission experiments of cores, the ratio between σhmax and σhmin is 1.165. The horizontal principal stress of the reservoir increases with the increase of Young's modulus and pore pressure. The conclusion is that high-precision geomechanical models can effectively serve to improve the efficiency of drilling operations, improve the production of single wells and benefit development. INTRODUCTION As an important unconventional energy source, shale gas has become a global hotspot for resource development. Shale gas deposits are abundant in China and are predominantly concentrated in the southern Sichuan Basin (Zou, et al. 2022; Ma, et al. 2021; Zhao, et al. 2020). Currently, deep shale gas deposits with a burial depth of 3500–5000 m have recently achieved a strategic breakthrough and have become an important area for shale gas development in China. However, deep shale gas development still faces numerous geological and engineering problems, though, as a result of the short exploration period, complex geological conditions, and inadequate engineering technology adaptability (He, et al. 2021). Shale is a typical "artificial gas reservoir" with nanoscale pore space and Nadasi grade permeability, and has no natural production capacity, therefore, commercial development of shale gas needs the use of horizontal wells drilling and large-scale volume fracturing technologies (Jiang, et al. 2017). The effectiveness of horizontal well drilling and large-scale volume fracturing is significantly influenced by reservoir characteristics and in situ stress conditions. During the drilling stage, high shear stress and pore pressure can lead to wellbore stability problems. Loss of circulation and sticking caused by the unreasonable design of drilling fluid density will negatively impact the drilling cycle (Mehrabian, et al. 2017). At the completion stage, casing deformation is a significant obstacle to shale gas production (Chen, et al. 2016).

ABSTRACT: Machine Learning (ML) studies are carried on in the hydrocarbon exploration and production. The Rate of penetration (ROP) is one of the investigations related to ML. Previous studies could not fit the ultra-deep well and most of machine learning ROP prediction are black box models lacking of enough explanation. ML ROP prediction need more accurate ROP models. In this paper a new and reliable calculation method of ROP prediction for well drilling is proposed by Extreme Gradient Boosting (XGBoost) algorithm. It is compared with Random Forest Regression algorithm on ROP prediction models. According to the importance ranking, rotating torque is the most impacted factor in this dataset. The conclusion is that ROP prediction model based on XGBoost has smaller prediction mean square error and shows higher efficiency than Random Forest, showing the superiority of the XGBoost. Considering the SHAP value ranking, torque and RPM are the most important features and they are positively impacted ROP in well drilling ROP model established by XGBoost machine learning method can make reasonable use of drilling parameters and provide reference for well drilling optimization. ROP model optimization derived from XGBoost can extremely reduce the expenses by reducing the drilling time. 1. INTRODUCTION Hydrocarbons, including oil and gas, are often stored in sedimentary rocks in deep formations (Yang et al. 2017). wells are drilled both onshore and offshore with more drilling cost (Ma, Ping, and Jian 2016). One of the most important factors is the Rate of Penetration (ROP) which affect the drilling efficiency and cost (Eskandarian, Bahrami, and Kazemi 2017). It is difficult to enhance ROP for ultra-deep well drilling as the well depth is increased. Increasing ROP is an approach of drilling optimization and cutting costs by reducing the drilling time. Existing ML models considering less parameters and data points cannot meet current ultra-deep well developing demands. In order to cut costs and increase the amount of drilling operations, finding out the relationship between the ROP and parameters is very important. Make it clear that variables and their relationships with ROP are the main factors which is helpful to promote ROP. Traditionally instantaneous ROP refers to the drilling footage in time unit, like the data used in this work. And some researchers want to estabilish some models of ROP using drilling parameters. These models can be used to make real time drilling optimization by equipment design guidance and drilling parameters selection.

ABSTRACT: Drilling string vibration data is a high-density ancillary data and it has the advantages of low-latency and low-cost which can be acquired in real time. In this study, vibration dataset is used as signal source, and the original vibration signal is filtered by Butterworth (BHPF). vibration time-frequency characteristics are extracted into time frequency images with the application of short-time Fourier transform (STFT). This paper develops lithology classification models using new data sources based on convolutional neural network (CNN) combining with Mobilenet and ResNet. This model is used for complex formation lithology including fine gravel sandstone, fine sandstone and mudstone. In order to improve the trustworthiness of decision-making results, the gradient-weighted class-activated thermal localization map is applied to interpret the results of the model. The final vertification test shows that the single-sample decision time of the model is 10ms, the test macro precision rate is 90.0%, and the macro recall rate is 89.3%. The lithology classification model is more efficiency and accessible. In conclusion, The CNN model using drill string vibration supplies a superior method of lithology classification. This study provides low-latency and low-cost lithology judgment methods to ensure safe and rapid drilling. 1. INTRODUCTION Lithology classification of underground formation is of great importance in the field of oil & gas exploration engineering as lithology represents the reservoir petrophysical characterization.(Buryakovsky et al. 2012). Vibration data of drill string can also be used to make real time lithology classification considering different formation characteristics. (Esmaeili et al. 2012b) Some researchers made logging-based lithology prediction by using artificial neural networks. It is demonstrated that lithofacies information from images could be used for lithology classification based on ANN.(Ivchenko et al. 2018) Random Forest is always applied to make underground formation lithology compared with other machine learning algorithms such as GTB, GBM and AdaBoost.(J. Sun et al. 2019) Baraboshkin applied convolutional neural networks on rock description based on color distribution and feature extraction by using different neural network architectures. GoogleNet make a better performance than other algorithms.(Baraboshkin et al. 2020) Ahemd used three machined learning models to predict the lithology changes and formation tops in real-time while drilling including ANN, ANNFIS and FNN, the results shows ANN model shows better performance.

ABSTRACT: Longmaxi S1l11 layer is main shale gas reservoir formation in southern Sichuan Basin, the difference of sublayer post-fracture response is significant. In this paper, we make triaxial tests with Longmaxi shale samples from southern Sichuan Basin layers to study damage character during hydraulic fracturing. Cohesive unit numerical simulation method is used to study the characteristics of hydraulic fracture (HF) propagation considering shale damage. The results show that in Longmaxi shale compression damage is divided into three stages: compaction, linear damage and rock failure. Reservoir shale damage due to HF concentrated in the linear damage stage. The degree of S1I13, S1I14 shale damage is greater than that of S1I11, S1I12 shale with the same strain. Fracture propagate straight into S1I12 layer after S1I11 layer fracture initiation, most fractures propagate into S1I11 layer, and few fractures propagate into S1I13 layer after S1I12 layer fracture initiation, which is the similar HF in S1I13 layer. The fracture propagation of S1I11 and S1I12 layers is highly sensitive to the liquid injection displacement. With the increase of liquid injection displacement, the total length of the fracture increases significantly and the number of damage and failure units increases significantly. During HF propagation, more plane bedding and natural weak surfaces can be better connected and opened to form more branch fractures; The fracture propagations of S1I13 and S1I14 sublayers are highly sensitive to the liquid injection displacement. With the increase of liquid injection displacement, the total length of fractures and the number of damage and failure units are significantly reduced. During the fracture propagation of S1I13 and S1I14 sublayers, the fracture shape is relatively straight, and only a small amount of plane bedding and natural weak surfaces in the formation are connected and opened, forming a small number of inconspicuous branch fractures.

四川盆地不同埋深龙马溪页岩储层地质特征及应力状态不同,水力裂缝缝高形态及其延伸规律差异显著.本文基于石柱县中深层与武隆县深层龙马溪页岩露头的真三轴试验结果,总结不同埋深页岩水力裂缝的缝高延伸形态及差异,明确主控因素;在此基础上,建立水力裂缝与层理面交叉作用的三维有限元模型,定量表征层理强度与地应力两大主控因素对缝高扩展的影响,揭示不同埋深页岩水力裂缝纵向穿层扩展规律.研究结果表明,根据水力裂缝与层理面作用方式不同,得到5种近井筒水力裂缝起裂及扩展模式:①垂直于层理起裂和扩展;②沿层理起裂和扩展;③垂直于层理起裂和扩展,并在局部沟通层理面;④沿层理起裂并扩展一定距离后,转向沿垂直层理面方向扩展;⑤多条裂缝同时起裂和扩展.随着埋深增加,页岩缝高形态逐渐由瘦高型过渡为矮胖型,石柱县中深层页岩缝网类型呈以横切缝为主缝的鱼骨刺状裂缝网络;武隆县深层页岩缝网类型呈以层理缝为主缝的多侧向台阶状裂缝网络.层理强度与垂向应力差异系数大小决定水力裂缝与层理的交叉方式,是不同埋深页岩储层缝高形态差异的主控因素.研究结果可为认识川南页岩气压裂缝高形态与指导压裂施工提供依据.

ABSTRACT: Lost circulation is a technical problem in drilling engineering, resulting in increased drilling cost and extended drilling cycle. Reservoir rocks in Block A of Shale Gas have the characteristics of low porosity and low permeability, strong heterogeneity and fault fracture development. Lost circulation is mainly caused by fracture. Seismic fracture prediction to assess lost circulation risk has limitations. Therefore, it is necessary to study more effective methods of lost circulation risk assessment. In this paper, based on the analysis of lost circulation, seismic prediction on fractures and rock mechanics parameters in block A, a comprehensive evaluation method of lost circulation index is formed by using seismic prediction of the relative degree of fracture development, fracture apparent length and the combination of Young’s modulus and Poisson’s ratio in 3D attribute modeling, and the classification evaluation standard is established. The method is used to evaluate the lost circulation risk of completion drilling in shale gas well of Block A, and the evaluation results are consistent with the well drilling data. Lost circulation index evaluation method can effectively evaluate the risk of lost circulation in shale formation with low porosity and low permeability, strong heterogeneity and fracture development, which can promote the efficient development of shale gas. 1. INTRODUCTION With reservoir exploration and development, it is more difficult for conventional oil and gas resources to increase reserves and production. Unconventional oil and gas resources are of strategic importance. As an important unconventional energy source, shale gas has become a hotspot in global resource development. Shale gas development can effectively alleviate the energy crisis, reduce the pressure on natural gas gaps, improve the energy structure, and ensure national energy security. In recent years, with the continuous development and improvement of the basic theory and technology development of shale gas in China, Fuling, Sichuan Changning-Weiyuan and Zhaotong national shale gas demonstration areas have been established. Shale gas production in southern Sichuan basin reaches 128×108m3 in 2021. Horizontal well drilling technology is the key to the shale gas resources development. With continuous research and exploration, PetroChina has made remarkable progress in unconventional oil and gas horizontal well drilling and completion technology through the introduction of advanced oil and gas engineering technology from North America. The average length of the horizontal section of shale gas horizontal wells in 2021 has reached 1760 meters, and the average drilling cycle is controlled within 80 days(Jun et al.2018). However, the complex geological conditions of China’s shale gas lead to drilling accident. According to statistics, the average well accident time of shale gas horizontal wells in 2021 is 7.25 days, mainly for lost circulation time. Lost circulation is still the main factor restricting the drilling cycle and drilling efficiency of shale gas horizontal wells.