Uncertainty Analysis of the Residual Strength of Non-Uniformly Loaded Casingsin Deep Wells

An uncertainty analysis method is proposed for the assessment of the residual strength of a casing subjected to wear and non-uniform load in a deep well.The influence of casing residual stress,out-of-roundness and non-uniform load is considered.The distribution of multi-source parameters related to the residual anti extrusion strength and residual anti internal pressure strength of the casing after wear are determined using the probability theory.Considering the technical casing of X101 well in Xinjiang Oilfield as an example,it is shown that the randomness of casing wear depth,formation elastic modulus and formation Poisson’s ratio are the main factors that affect the uncertainty of residual strength.The wider the confidence interval is,the greater the uncertainty range is.Compared with the calculations resulting from the proposed uncertainty analysis method,the residual strength obtained by means of traditional single value calculation method is either larger or smaller,which leads to the conclusion that the residual strength should be considered in terms of a range of probabilities rather than a single value.

Study on Deep Well Dewatering Optimization Design in Deep Foundation Pit and Engineering Application

Based on analyses of the theories of groundwater unsteady flow in deep well dewatering in the deep foundation pit, Theis equations are chosen to calculate and analyze the relationship between water level drawdown of confined aquifer and dewatering duration. In order to reduce engineering cost and diminish detrimental effect on ambient surrounding, optimization design target function based on the control of confined water drawdown and four restriction requisitions based on the control of safe water level, resistance to throwing up from the bottom of foundation pit, avoiding excessively great subsidence and unequal surface subsidence are proposed. A deep well dewatering project in the deep foundation pit is optimally designed. The calculated results including confined water level drawdown and surface subsidence are in close agreement with the measured results, and the optimization design can effectively control both surface subsidence outside foundation pit and unequal subsidence as a result of dewatering.

Characteristics of helical flow in slim holes and calculation of hydraulics for ultra-deep wells

Due to the slim hole at the lower part of the ultra-deep and deep wells, the eccentricity and rotation of drill string and drilling fluid properties have great effects on the annular pressure drop. This leads to the fact that conventional computational models for predicting circulating pressure drop are inapplicable to hydraulics design of deep wells. With the adoption of helical flow theory and H-B rheological model, a computational model of velocity and pressure drop of non-Newtonian fluid flow in the eccentric annulus was established for the cases where the drill string rotates. The effects of eccentricity, rotation of the drill string and the dimensions of annulus on pressure drop in the annulus were analyzed. Drilling hydraulics was given for an ultra-deep well. The results show that the annular pressure drop decreases with an increase in eccentricity and rotary speed, and increases with a decrease in annular flow area. There is a great difference between static mud density and equivalent circulating density during deep well drilling.

CAN-based Control System Design on Minor-caliber Deep Well Rescue Robot

By introdming a small-caliber deep well rescue robot, a hold-hug pattern rescue mechanism was brought forward. In order to reduce the volmne, the trader-well rescue imclmnism is modularizing designed. At the same tirae, the audio and video systyems, the illumination system and the ventilation system are expatiated. The rescuing robot can rescue the falling person in the deep well, it can save much manateral resources and time. It＇s really an ideal rescue device for the small-caliber fall.

Research on Temperature Distribution in Wellbore of Deep Well Drilling

The wellbore temperature has an important effect on design and drilling of deep well. Based on energy conservation equations and actual drilling data of one deep well, the wellbore temperature distribution was simulated and the influence of different parameters on the wellbore temperature was revealed using the software of Hydraulics Analysis System. The results show that, while drilling, the mud temperature in wellbore gradually decreases from the formation temperature to the stable temperature, and it is higher than the mud inlet temperature on ground, the annular temperature is higher than the temperature in drill string, and the bottom hole temperature is higher than the ground temperature. The effect of geothermal gradient on wellbore temperature is great, while the mud density is negligible. The bottom hole temperature increases with the increase of mud inlet temperature, geothermal gradient, mud thermal conductivity and decrease of mud flow rate, mud specific heat and mud density.

Reasons resulting in the collapsed tubing near wellhead in high pressure and high temperature deep well during well testing and measures to prevent the collapsing

Because various reasons, the tubing near wellhead was collapsed during well testing in high pressure and high temperature deep well when the outer pressure was less than collapsing strength. To find the reasons in the abnormally collapse and countermeasures, first the quality of the tubing was checked. It was founded that the collapse was not resulted from the defect of the tubing. Then, force and stress exerted in the tubing was analyzed taking XS2 well as an example. The analysis results were concluded as follows. The collapsing strength of tubing decreased due to the axial tensile, which is seriously at the upper tubing especially. During injecting, the additional axial force that was caused by the temperature effect increased the tubing near wellhead to suffer axial tensile and further reduced the collapsing strength of tubing near wellhead. Reinforcing defect, prohibiting defect tubing to trip in hole, according to the calculation to impose appropriate annular pressure, selecting size nozzle to reverse pumping and controlling the reverse pumping speed and pressure, prohibiting to be opened flow and reducing or releasing the annular pressure can prevent the well testing tubing down-hole being collapsed at the wellhead.

Stability control of gate groups in deep wells

In order to study stability control methods for a deep gate group under complex stresses,we conducted field investigations and analyses of reasons for damage in the Xuzhou mining district.Three reasons are proposed:deep high stress,improper roadway layout and support technology.The stability control countermeasures of the gate group consist of an intensive design technology and responding bolt-mesh-anchor truss support technology.Our research method has been applied at the -1000 m level gate group in Qishan Coal Mine.Suitable countermeasures have been tested by field monitoring.

Mechanism and prevention method of drill string uplift during shut-in after overflow in an ultra-deep well

Drill string will sustain large uplift force during the shut-in period after gas overflow in an ultra-deep well, and in serious case, it will run out of the wellhead. A calculation model of uplift force was established to analyze dynamic change characteristics of the uplift force of drill string during the shut-in period, and then a management procedure for the uplift risk during the shut-in period after gas overflow in the ultra-deep well was formed. Cross section method and pressure area method were used to analyze the force on drill string after shut-in of well, it was found that the source of uplift force was the "fictitious force" caused by the hydrostatic pressure in the well. When the fictitious force is in the opposite direction to the gravity, it is the uplift force. By adopting the theory of annular multiphase flow, considering the effects of wellbore afterflow and gas slippage, the dynamic change of the pressure and fluid in the wellbore and the uplift force of drill string during the shut-in period were analyzed. The magnitude and direction of uplift force are related to the length of drill string in the wellbore and shut-in time, and there is the risk of uplift of drill string when the length of drill string in the wellbore is smaller than the critical drill string length or the shut in time exceeds the critical shut in time. A set of treatment method and process to prevent the uplift of drill string is advanced during the shut-in period after overflow in the ultra-deep well, which makes the risk management of the drill string uplift in the ultra-deep well more rigorous and scientific.

Extreme massive hydraulic fracturing in deep coalbed methane horizontal wells:A case study of the Linxing Block,eastern Ordos Basin,NW China

Deep coal seams show low permeability,low elastic modulus,high Poisson’s ratio,strong plasticity,high fracture initiation pressure,difficulty in fracture extension,and difficulty in proppants addition.We proposed the concept of large-scale stimulation by fracture network,balanced propagation and effective support of fracture network in fracturing design and developed the extreme massive hydraulic fracturing technique for deep coalbed methane(CBM)horizontal wells.This technique involves massive injection with high pumping rate+high-intensity proppant injection+perforation with equal apertures and limited flow+temporary plugging and diverting fractures+slick water with integrated variable viscosity+graded proppants with multiple sizes.The technique was applied in the pioneering test of a multi-stage fracturing horizontal well in deep CBM of Linxing Block,eastern margin of the Ordos Basin.The injection flow rate is 18 m^(3)/min,proppant intensity is 2.1 m^(3)/m,and fracturing fluid intensity is 16.5 m^(3)/m.After fracturing,a complex fracture network was formed,with an average fracture length of 205 m.The stimulated reservoir volume was 1987×10^(4)m^(3),and the peak gas production rate reached 6.0×10^(4)m^(3)/d,which achieved efficient development of deep CBM.

Automatic depth matching method of well log based on deep reinforcement learning

In the traditional well log depth matching tasks,manual adjustments are required,which means significantly labor-intensive for multiple wells,leading to low work efficiency.This paper introduces a multi-agent deep reinforcement learning(MARL)method to automate the depth matching of multi-well logs.This method defines multiple top-down dual sliding windows based on the convolutional neural network(CNN)to extract and capture similar feature sequences on well logs,and it establishes an interaction mechanism between agents and the environment to control the depth matching process.Specifically,the agent selects an action to translate or scale the feature sequence based on the double deep Q-network(DDQN).Through the feedback of the reward signal,it evaluates the effectiveness of each action,aiming to obtain the optimal strategy and improve the accuracy of the matching task.Our experiments show that MARL can automatically perform depth matches for well-logs in multiple wells,and reduce manual intervention.In the application to the oil field,a comparative analysis of dynamic time warping(DTW),deep Q-learning network(DQN),and DDQN methods revealed that the DDQN algorithm,with its dual-network evaluation mechanism,significantly improves performance by identifying and aligning more details in the well log feature sequences,thus achieving higher depth matching accuracy.

Evaluation and Application of Flowback Effect in Deep Shale Gas Wells

The pivotal areas for the extensive and effective exploitation of shale gas in the Southern Sichuan Basin have recently transitioned from mid-deep layers to deep layers.Given challenges such as intricate data analysis,absence of effective assessment methodologies,real-time control strategies,and scarce knowledge of the factors influencing deep gas wells in the so-called flowback stage,a comprehensive study was undertaken on over 160 deep gas wells in Luzhou block utilizing linear flow models and advanced big data analytics techniques.The research results show that:(1)The flowback stage of a deep gas well presents the characteristics of late gas channeling,high flowback rate after gas channeling,low 30-day flowback rate,and high flowback rate corresponding to peak production;(2)The comprehensive parameter AcmKm1/2 in the flowback stage exhibits a strong correlation with the Estimated Ultimate Recovery(EUR),allowing for the establishment of a standardized chart to evaluate EUR classification in typical shale gas wells during this stage.This enables quantitative assessment of gas well EUR,providing valuable insights into production potential and performance;(3)The spacing range and the initial productivity of gas wells have a significant impact on the overall effectiveness of gas wells.Therefore,it is crucial to further explore rational well patterns and spacing,as well as optimize initial drainage and production technical strategies in order to improve their performance.

Optimizing the Diameter of Plugging Balls in Deep Shale Gas Wells

Deep shale gas reserves that have been fractured typically have many relatively close perforation holes. Due to theproximity of each fracture during the formation of the fracture network, there is significant stress interference,which results in uneven fracture propagation. It is common practice to use “balls” to temporarily plug fractureopenings in order to lessen liquid intake and achieve uniform propagation in each cluster. In this study, a diameteroptimization model is introduced for these plugging balls based on a multi-cluster fracture propagationmodel and a perforation dynamic abrasion model. This approach relies on proper consideration of the multiphasenature of the considered problem and the interaction force between the involved fluid and solid phases. Accordingly,it can take into account the behavior of the gradually changing hole diameter due to proppant continuousperforation erosion. Moreover, it can provide useful information about the fluid-dynamic behavior of the consideredsystem before and after plugging. It is shown that when the diameter of the temporary plugging ball is1.2 times that of the perforation hole, the perforation holes of each cluster can be effectively blocked.

Deep sea mineral resources and underground space as well as infrastructure for sustainable and liveable cities

This issue covers the papers on two special themes:(1)Mineral resources from deep sea—Science and Engineering and(2)Planning and development of underground space and infrastructure for sustainable and liveable cities.

基于Deep Forest算法的对虾急性肝胰腺坏死病(AHPND)预警数学模型构建

为预报池塘养殖凡纳对虾(Penaeus vannamei)急性肝胰腺坏死病(AHPND)的发生,自2020年开始,笔者对凡纳对虾养殖区开展了连续监测工作,包括与疾病发生相关的环境理化因子、微生物因子、虾体自身健康状况等18个候选预警因子指标,通过数据标准化处理后分析病原、宿主与环境之间的相关性,对候选预警因子进行筛选,基于Python语言编程结合Deep Forest、Light GBM、XGBoost算法进行数据建模和预测性能评判,仿真环境为Python2.7,以预警因子指标作为输入样本(即警兆),以对虾是否发病指标作为输出结果(即警情),根据输入样本和输出结果各自建立输入数据矩阵和目标数据矩阵,利用原始数据矩阵对输入样本进行初始化,结合函数方程进行拟合,拟合的源代码能利用已知环境、病原及对虾免疫指标数据对目标警情进行预测。最终建立了基于Deep Forest算法的虾体(肝胰腺内)细菌总数、虾体弧菌(Vibrio)占比、水体细菌总数和盐度的4维向量预警预报模型,准确率达89.00%。本研究将人工智能算法应用到对虾AHPND发生的预测预报,相关研究结果为对虾AHPND疾病预警预报建立了预警数学模型,并为对虾健康养殖和疾病防控提供了技术支撑和有力保障。

Deep learning-based inpainting of saturation artifacts in optical coherence tomography images

Limited by the dynamic range of the detector,saturation artifacts usually occur in optical coherence tomography(OCT)imaging for high scattering media.The available methods are difficult to remove saturation artifacts and restore texture completely in OCT images.We proposed a deep learning-based inpainting method of saturation artifacts in this paper.The generation mechanism of saturation artifacts was analyzed,and experimental and simulated datasets were built based on the mechanism.Enhanced super-resolution generative adversarial networks were trained by the clear–saturated phantom image pairs.The perfect reconstructed results of experimental zebrafish and thyroid OCT images proved its feasibility,strong generalization,and robustness.

A review of reservoir damage during hydraulic fracturing of deep and ultra-deep reservoirs

Deep and ultra-deep reservoirs have gradually become the primary focus of hydrocarbon exploration as a result of a series of significant discoveries in deep hydrocarbon exploration worldwide.These reservoirs present unique challenges due to their deep burial depth(4500-8882 m),low matrix permeability,complex crustal stress conditions,high temperature and pressure(HTHP,150-200℃,105-155 MPa),coupled with high salinity of formation water.Consequently,the costs associated with their exploitation and development are exceptionally high.In deep and ultra-deep reservoirs,hydraulic fracturing is commonly used to achieve high and stable production.During hydraulic fracturing,a substantial volume of fluid is injected into the reservoir.However,statistical analysis reveals that the flowback rate is typically less than 30%,leaving the majority of the fluid trapped within the reservoir.Therefore,hydraulic fracturing in deep reservoirs not only enhances the reservoir permeability by creating artificial fractures but also damages reservoirs due to the fracturing fluids involved.The challenging“three-high”environment of a deep reservoir,characterized by high temperature,high pressure,and high salinity,exacerbates conventional forms of damage,including water sensitivity,retention of fracturing fluids,rock creep,and proppant breakage.In addition,specific damage mechanisms come into play,such as fracturing fluid decomposition at elevated temperatures and proppant diagenetic reactions at HTHP conditions.Presently,the foremost concern in deep oil and gas development lies in effectively assessing the damage inflicted on these reservoirs by hydraulic fracturing,comprehending the underlying mechanisms,and selecting appropriate solutions.It's noteworthy that the majority of existing studies on reservoir damage primarily focus on conventional reservoirs,with limited attention given to deep reservoirs and a lack of systematic summaries.In light of this,our approach entails initially summarizing the current knowledge pertaining to the types of fracturing fluids employed in deep and ultra-deep reservoirs.Subsequently,we delve into a systematic examination of the damage processes and mechanisms caused by fracturing fluids within the context of hydraulic fracturing in deep reservoirs,taking into account the unique reservoir characteristics of high temperature,high pressure,and high in-situ stress.In addition,we provide an overview of research progress related to high-temperature deep reservoir fracturing fluid and the damage of aqueous fracturing fluids to rock matrix,both artificial and natural fractures,and sand-packed fractures.We conclude by offering a summary of current research advancements and future directions,which hold significant potential for facilitating the efficient development of deep oil and gas reservoirs while effectively mitigating reservoir damage.

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

Dendritic Deep Learning for Medical Segmentation

Dear Editor,This letter presents a novel segmentation approach that leverages dendritic neurons to tackle the challenges of medical imaging segmentation.In this study,we enhance the segmentation accuracy based on a SegNet variant including an encoder-decoder structure,an upsampling index,and a deep supervision method.Furthermore,we introduce a dendritic neuron-based convolutional block to enable nonlinear feature mapping,thereby further improving the effectiveness of our approach.

Enhancing Deep Learning Soil Moisture Forecasting Models by Integrating Physics-based Models

Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient representation of land-surface processes.In addition to PB models,deep learning(DL)models have been widely used in SM predictions recently.However,few pure DL models have notably high success rates due to lacking physical information.Thus,we developed hybrid models to effectively integrate the outputs of PB models into DL models to improve SM predictions.To this end,we first developed a hybrid model based on the attention mechanism to take advantage of PB models at each forecast time scale(attention model).We further built an ensemble model that combined the advantages of different hybrid schemes(ensemble model).We utilized SM forecasts from the Global Forecast System to enhance the convolutional long short-term memory(ConvLSTM)model for 1–16 days of SM predictions.The performances of the proposed hybrid models were investigated and compared with two existing hybrid models.The results showed that the attention model could leverage benefits of PB models and achieved the best predictability of drought events among the different hybrid models.Moreover,the ensemble model performed best among all hybrid models at all forecast time scales and different soil conditions.It is highlighted that the ensemble model outperformed the pure DL model over 79.5%of in situ stations for 16-day predictions.These findings suggest that our proposed hybrid models can adequately exploit the benefits of PB model outputs to aid DL models in making SM predictions.

ST-LSTM-SA:A New Ocean Sound Velocity Field Prediction Model Based on Deep Learning

The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.