Search

Aiming at the problems of the current production and operation status of the progressive cavity pump (PCP) in coalbed methane (CBM) wells which cannot be timely monitored, quantitatively evaluated, and accurately predicted, a five-step method for evaluating and predicting the health status of PCP wells is proposed: data preprocessing, principal parameter optimization, health index construction, health degree division, and health index prediction. Therein, a health index (HI) formulation was made based on deep learning, and a statistical method was used to define the health status of PCP wells as being healthy, subhealthy, or faulty. This allowed further research on the HI prediction model of PCP wells based on the long short-term memory (LSTM) network. As demonstrated in the study, they can reflect both the change trend and the contextual relevance of the health status of PCP wells with high accuracy to achieve real-time, quantitative, and accurate assessment and prediction. At the same time, the conclusion gives good guidance on the production performance analysis and failure warning of the PCP wells and suggests a new direction for the health status assessment and warning of other artificial lift equipment.

Deep neural networks have recently demonstrated high performance for deblurring. However, few methods are designed for both non-uniform image blur estimation and removal with highly efficient. In this study, the authors proposed a fully convolutional network that outputs estimated blur and restored image in one feed-forward pass for the non-uniformly blurred image of any input-size. The proposed network contains two subnets. The parameter estimation subnet P-net predicts pixel-wise parameters of multiple blur types with high accuracy. The output of P-net is used as a condition, which guides the blur removal subnet G-net to restore a high quality latent sharp image. P-net and G-net are ultimately integrated into a single framework called PG-net, which guarantees the consistency of parameter estimation and blur removal, thereby improves algorithm efficiency. Experiment results show that the authors blur parameter estimation method as well as their deblurring method outperforms the comparison methods both quantitatively and qualitatively.

The coal fine output from coalbed methane (CBM) formation during the production of CBM wells seems to be a common occurrence. At the lower section of wellbore, the aggregation of coal fine particles may occur, that lead to the increase of local coal fine concentration and the negative effect on the work of downhole equipment. To investigate the migration of coal fine particles in gas-liquid flow, the gas-liquid-solid three-phase flow experiments were carried out. The experiments were conducted in a downbent V-shaped pipe with different incline angles (5°, 15° and 25°), and recorded the real-time liquid holdup at certain positions of the lower elbow with the conductivity method. The terrain-induced slugs can be identified on the time series curves of liquid holdup. And the characteristic parameters of each slug, such as slug length and translational velocity, were calculated. By injecting marked coal fine particles into the multiphase flow loop and observing whether they can be discharged from the V-shaped pipe, the lower limits of gas and liquid velocities to void the particle retention at the lower elbow were collected. According to the experimental observation of the coal fine particle movement in one slug unit, we defined dimensionless particle velocity function FD to analyze the particle transport mechanism in the terrain slug flow. The FD value distribution of terrain slugs, calculated by the use of slug parameters, changed with the slug dissipation and coalescence in the experimental incline pipeline. Detail analyses of FD statistical parameters show that the mean values of FD increase with the rise of mixture flow velocity, and the decrease of inclination angle. The mean values of FD at the critical particle discharge conditions are positively correlated to particle concentration. And a linear relationship between the critical means of FD and the particle concentrations is presented.

Natural gas is a clean fossil energy and an important sector in the energy consumption chart. Because of its reliability and low carbon-hydrogen ratio, the demand for natural gas increases steadily to replace coal and wood to better protect environment. To accommodate the ever rising in natural gas production and transportation, more gas pipelines are being constructed. Meanwhile, the existing gas pipelines are aging inevitably. One of the critical needs in natural gas flow assurance is detecting and locating pipeline leak in a timely manner. A reliable and timely detection of the leakage of gas pipeline can not only reduce the loss of hydrocarbon, but also limit the damage to facilities, possible loss of life, and the extent of environmental pollution. Two or more leakage points in a pipeline were observed in the field. Physical methods and mathematical models were employed to detect pipeline leakages. However, literature review indicates that no mathematical model has been developed to detect multiple leaks in the same pipeline. This study focused on the detection of two leak points in a pipeline. Multi-flowrate tests are proposed to evaluate the locations and sizes of leakages in two leak points. The new mathematical model is crucial when no physical inspection is available. The proposed model can be used to monitor possible leak in real-time because flowrate and pressure that are utilized to estimate multiple leaks are monitored in real-time and are available almost simultaneously. Therefore, the new method provides a practical, quick, and low computational cost approach to detect multiple leakages. The proposed method is important because existing mathematical models assumed single leak in a pipeline, which limits their applications because the detection will be misleading if there is more than one leakage in the same pipeline. The proposed model can differentiate single-leakage scenario from multi-leakage scenario based on multi-rate tests. The identification is critical because it guides the leakage detection to the right direction.

Although currently, large-scale and multilateral horizontal wells are an important way to improve the oil recovery in the unconventional reservoirs, the flow behavior of fluid from the reservoir into the horizontal wellbore becomes more challenged compared to the single small-scale horizontal well. One of the main challenges is that pressure loss from the well completion section and wellbore cannot be ignored in the coupling process between the reservoir and the horizontal well. In this paper, a new method is presented to solve the coupling flow between the reservoir and the horizontal well with different well completions. The new coupling model is compared with Ouyang’s model (1998) and Penmatcha’s model (1997), and the predicted data are consistent with each other at both early and late times. Meanwhile, four different cases have been proposed to verify the application of the new coupling model with different well completions, and the results indicate that the uneven inflow profile can be effectively alleviated via reasonable completion parameters and different well completions. Based on two types of flow-node units, it can quickly model and solve the coupling problem between the reservoir and the horizontal well with complex completion cases. It can also depict the inflow profile of the horizontal well with different well completions, which is conducive to understand the coupling process. The new coupling model can provide theoretical support for further optimization of completion parameters and well completions and finally improve oil recovery.

Rock thin section recognition provides geological information, which is crucial in petroleum geology, exploration, and mining research as a kind of fundamental work. Although many machine learning methods solve this research, there are still problems of data hierarchy and model pertinence. We use the hierarchical classification method to divide the dataset into sedimentary, metamorphic, and igneous rock as first-level, and to subdivide a total of 105 s-level further from the three categories. We propose the MaSE-ResNeXt model based on the fundamental work in the SeNet that can enhance the feature connection between different channels. The MaSE-ResNeXt adopted hierarchical filter groups, bottleneck stacking, and other strategies to enhance the representational capability of the model which advances the solving ability in rock recognition. Six data enhancement methods and other techniques are used to improve the robustness and effectiveness. The accuracy in the test set was 90.89% and 81.97% for the first and second level, respectively, with the inference duration is only 0.0357s. This study also designs a degeneration experiment and model comparison to demonstrate the model's effectiveness. Future research can employ this model as the fundamental base of transfer learning in geology to save time in the training of study.

The tight reservoirs have been successfully developed by horizontal wells with massive hydraulic fractures. The inherent heterogeneity along the wellbore, complex fracture networks generated due to the pre-existing natural fracture and stress isotropy, the difference of reservoir properties between the stimulated reservoir volume (SRV) and the unstimulated region all bring huge challenges in predicting pressure and rate transient responses. Previous study always simplified the whole reservoir as homogeneous or radial composite region, and treated the complex networks as orthogonal fracture networks. In the light of this situation, by using the source function, boundary element method and composite reservoir model, a rigorous semi-analytical model for a horizontal well with complex fracture networks in heterogeneous reservoirs was presented in this paper. A previous semi-analytical model and numerical model established by commercial simulator were both used to verify the feasibility of the proposed model. The effects of critical parameters on the transient pressure behaviors are discussed. The results show that heterogeneity of the reservoir has a significant influence on pressure behavior. The sensitivity analysis of fracture number, fracture geometry, storage coefficient and inter-porosity factor of SRV, reservoir sizes and relative position between SRV and the outer boundaries are conducted to further understand the transient pressure behaviors of volume fractured horizontal well. In this paper, both the heterogeneity along the horizontal well in the SRV and the heterogeneity between the SRV and the unstimulated region is brought into consideration. In addition, the complex fracture geometry is also captured. Therefore, our model can be capable of studying the transient pressure behaviors of volume fractured horizontal wells in heterogeneous reservoir. The research results provided by this work have some significance for well test interpretation of tight reservoirs.

A new rotary volumetric pump, called a ‘Sliding-Vane Rotary Pump (SVRP)’, which was applied in the Xinjiang oilfield for its resistance to high temperature in well downhole was introduced in this paper. Compared to a conventional artificial lift pump, the volumetric efficiency and the energy saving are the obvious advantages of this pump. Based on the analysis of SVRP’s internal mechanical structure, the inner pressure distribution model of SVRP was established according to the compressibility of crude oil. Then, the load torque of both sides of the sliding-vane was calculated on the basis of the SVRP chamber pressure distribution model that has been established in the paper, and then the SVRP load torque curve was plotted. The pump load torque curve trend is consistent with the trend of the pressure curve. A conclusion was drawn that the ‘sealed angular difference’ of SVRP should be optimized to reduce the pump leakage and load torque for the reason of chamber pressure difference. The pressure va...

The free gas evolved in the pump chamber results in a low rod pump working efficiency, and it can even lead to a failure. A common and effective solution is to install a downhole gas separator before fluid entering the chamber, which can divert the free gas to the annulus. If we can re-inject the diverted gas back to the tubing at a shallower depth above the pump, the flowing gas is then re-combined with the liquid and decreases fluid density. Consequently, the injected gas also creates additional lifting drive for the liquid. A new technology based on this concept has been developed and called Casing Gas Assisted Rod Pumping (CGARP). This paper firstly presents an analytical model to optimize the overall lifting performance and minimize the operating expenditure. It is especially useful in producing hydrocarbon at high GOR. As the gas is re-combined with the liquid above the pump installation depth, the hydrostatic pressure gradient is reduced consequently. However, if the gas reinjection valve is placed at a shallow depth, the well segment at reduced fluid density is subsequently short, so the contribution of gas lift is restricted. Vice versa, if the gas reinjection valve is placed at the depth close to the pump, it requires high pressure to open the gas injection valve, so the gas reinjection can happen infrequently and the production rate is unsfplease. This paper has proposed a genetic optimization method to maximize the overall production system efficiency. A multi-variable vector has been defined, which includes pumping speed and depth, mechanical power, rod string diameter and length, surface stroke length, downhole separator efficiency, as well as gas reinjection valve depth. The optimized object can be the system lifting efficiency or Net Present Value, which must be a function of this vector in the constraint of mass and momentum conservations. This work has been applied as the primary guide for four oil producers with rod pump installed in Jilin field, China. The average system lifting efficiency and production rate have been increased by 20% and 15% respectively. This analytical model has enhanced the field performance. Most importantly, the same concept can be applied for other pump-assisted wells.

Defined as the backflow of a liquid film into a wellbore, liquid loading is a severe issue for gas wells because it decreases the production rate of gas. If the rate of liquid accumulation in the wellbore is extremely high, the production rate will significantly decrease, and, under extreme cases of accumulation, the operating company will abandon the well, leading to substantial financial losses. Consequently, to avoid this, it is appropriate for the operating company to predict and identify the liquid loading status of the gas wells and use practical tools and pathways to prevent such a loading. This paper introduces a model based on a liquid film reversal to predict liquid loading. It adopts the momentum balance equation of each phase as a basis and transcends the limits of earlier models. The proposed model relies on the theory, which assumes that the loading phenomenon initiates when the transition from an annular flow (liquid film surrounding the gas core) into a slug or churn flow takes place. Furthermore, the developed model considers the influences of the deviation angle, the tubing diameter, and the void fraction. The efficiency of the proposed model is evaluated by comparing it with few renowned existing models using vertical, inclined, and near-horizontal published gas field datasets, newly acquired ones, as well as laboratory datasets from published papers. As a result, the proposed model provides both the highest prediction accuracy and the least average errors. Further results show that the tubing diameter and the inclination angle are the leading influential parameters of the critical gas flow velocity/rate. Consequently, as the proposed model outperforms the earlier published models, it is the most suitable model for identifying and predicting the liquid loading in vertical, inclined, and near-horizontal gas wells.

Electric Submersible Pump (ESP) is currently widely employed to help enhance production for nonlinear-flowing well with high production and high water cut well. However, ESP broken shaft is common in the oil industry. The broken shaft leads to production disruptions, resulting in significant economic losses. The objective of this paper is to evaluate Principal Component Analysis (PCA) as an unsupervised machine learning technique to detect the cause of the breakage of the ESP shaft. This method was successfully applied in the Penglai block of Bohai Oilfield in China to detect the ESP shaft fracture in real-time. A two-dimensional plot of scores of Principal Component 1 and Principal Component 2 can be used to identify different clusters of the stable region, unstable region and failure region. By this means, potential ESP shaft fracture will be found when the cluster starts deviating away from the stable region. Moreover, a PCA diagnostic model is built to predict the time at which the ESP shaft fracture occurs and to determine the main decision variable most responsible for ESP broken shaft. This paper demonstrates that the application of the PCA method performs well in monitoring the ESP operation system and predicts the impending breakage of ESP shaft with high accuracy.

Buckley–Leverett displacement equations have been derived strictly from linear flow systems, and have been verified by linear flow experiments only. This paper presents analytical algorithms to calculate recovery factors for radial flow systems, which is expected to be more accurate for peripheral water-flooding reservoirs. The proposed equations have been verified with field data. The original Buckley–Leverett equation generally results in much lower recovery factors that barely match the well cumulative production at interest. Consequently, the estimated ultimate recovery (EUR) by volumetric methods tends to be low. As a result, the production projection according to volumetric EUR is not reasonable in comparing to the historical performance. The proposed analytical model improves the prediction of reservoir performance.

As the metallic stator progressing cavity pump (PCP) operates with the stator and rotor in clearance fit, the slippage between cavities has a significant influence on the pump performance. In this paper, an analytical model is developed for the flow in the metallic stator PCP. Based on the analyses of the meshing movement and the clearance geometry inside the pump, the slippage through the transversal and longitudinal sealing regions is calculated considering different slippage mechanisms. Then the flow rate is obtained by subtracting the total slippage from the theoretical volumetric rate. This model is validated against results obtained from the performance experiments of commercial metallic stator PCP products from Shihong Petroleum Equipment Company. The model results show that the metallic stator PCP with smaller clearance or more stages is more capable of achieving good performance at high differential pressure. It is suitable for pumping the fluid with certain viscosity, and the influence of the slippage can be compensated by adopting appropriate high rotational speed. Furthermore, the model can be used to predict the pump performance and provide guidance for the pump design and performance optimization in field applications.

Pipeline blockage, which results from solid and hydrocarbon deposition caused by changes in pressure, temperature, or composition, is a critical issue in oil and gas production and transportation systems. Sometimes blockage, which extends several miles in the long-distance pipe, can be approximated as a pipe with a smaller diameter. While the earlier work focused on treating pipeline blockage as a choke for its limited size and length, this study attempts to analyze the relationship between the pressure distribution and the blockage size/length when analyzing the blockage characteristics under different situations. This paper explores the distribution of pressure and pressure gradient around the pipeline blockage under different operating conditions. Three-dimension (3D) computational fluid dynamic (CFD) simulations under steady-state are carried out to examine the effects of blockage diameter, blockage length, and blockage location. The relationship between the pressure drop and blockage characterization is predicted. A forecasting model for blockage sensing and localization is proposed. Lab experiments are conducted to compare the simulation results to measured data and the accuracy of forecasting model is evaluated. The study indicates that CFD simulation results match the experiment data and the model is a useful tool in detection of pipeline blockage.

Real-time data collection, processing, and surveillance are critical in field operations for monitoring well production and assessing effectiveness of well workover and intervention. Conventional metering strategy is unable to keep up with the requirement for continuous and real-time measurement. For marginal fields, surface facility is often shared among many wells due to its high cost. In this paper, an innovative technology is proposed to analyze dynamometer card collected from a SCADA system and accurately derive the individual well production rate in real time. By solving wave equations, the developed system converts the surface dynamometer card to a downhole dynamometer card, which can be analyzed to locate the travelling valve opening and closing points. With non-linear and unconstrained optimization, this technology can accurately determine the effective stroke and liquid leakage, and consequently obtain the production rate. The proposed method has been successfully applied to 170 oil wells with an average measurement error of only 6.66%. It works well for both vertical and deviated wells, and for both light and heavy crude fluid. This digital energy technology can be used not only to determine the production rate for individual wells in real-time, but also to decrease operational expenditure, which can significantly improve the cash flow for managing marginal fields in the current low oil price environment.

In Coalbed Methane (CBM) reservoir, especially the thin low permeability CBM reservoirs, undulating horizontal wells are often drilled to maximize contact area with the reservoir for higher CBM production rates. Coal fines, however, may accumulate in the wellbore, making pressure along the wellbore trajectory more complex, affecting gas production behavior. This paper presents experimental work to study the coal fines-water-gas three-phase flow in transparent pipes to mimic different undulation angles that may occur in horizontal wells. Coal fines with different particle sizes are studied. Observed from the experiments, four flow patterns for coal fines migration were identified: stratification, saltation, moving dunes, and dispersed flow. Moreover, relations between coal fines critical moving velocity and discharge velocity and the size of coal fines are investigated. This paper further investigated the settlement and plugging of coal fines at the curvature section of the pipes under four flow regimes: elongated bubble, transition, slug, and intermittent flows. Using the experimental data, we estimated the boundaries for five flow regimes under five different undulation angles. The analyses indicated that the pressure fluctuation magnitude increases when flow regime evolves from bubble flow to intermittent flow. The largest pressure fluctuation and the lowest fluctuation frequency take place under intermittent flow. Based on the experimental data, this paper derived the critical velocity correlation for coal fines in undulating CBM wellbore. The findings of this study is useful for CBM development in the field, which may help to optimize wellbore geometry to minimize coal fine settlement/plugging, act as a guide in designing well flushing operation to effectively circulate coal fines out of bottomhole.

Horizontal wells in bottom-water reservoir equipped with inflow control devices (ICDs) are a proven technology of delaying influx of water to help maximize oil production by creating additional pressure drop, adjusting horizontal wellbore pressure distribution, and thus, achieving an even influx profile. Owing to completion risk and investment venture, especially offshore field, it’s essential to design ICDs (number, location, type, size, etc.) effectively in order to improve production and net present value (NPV), otherwise the ICDs even would be overlooked. Conventional ICDs design is aiming to attain equal influx along the horizontal wellbore, which would delay water production, as well as oil potential production, unfortunately. This paper will use reservoir simulation to study four production strategies and analyze the benefits of delaying water and improving oil production. The four strategies considered are (i) no ICD, (ii) stinger water-control completion, (iii) ICD (conventional design), (iv) ICD (design based on the principle of maximizing oil production). The simulation results and analysis will show the disadvantage of conventional ICDs design method. This paper will develop a novel ICD design philosophy on the basis of maximizing oil production before water breakthrough. In this paper, we will evaluate an offshore field case, which suffers from water coning, to compare the novel design philosophy with conventional one. The actual role of conventional ICDs design in delaying water coning will be found in this paper to sacrifice oil production reduction, which has negative impact on horizontal well performance and eventually results in ultimate oil recovery decrease. Instead, ICDs based on the novel ICD design philosophy presented in this paper will be proven to be more effective to improve oil production, while water coning from bottom-water reservoir can be delayed.

The aggregation of coal fines particles at the bottom of the coal-bed methane well is a common occurrence during production, which could inhibit the flow in the bottom of wells and have adverse effect on the downhole equipment. In this work, gas-liquid-solid three-phase flow experiments were carried out to investigate the migration and discharge of coal fines particles in undulating pipeline. The experiments were conducted in downbent V-shaped pipes with different inclination angles. Based on the conductivity method, the real-time liquid holdup at three positions of the elbow was measured by the developed software. The slugs were identified on the time series curves of liquid holdup, and the characteristics of each slug were calculated, such as length and translational velocity. Meanwhile, the moving of particles with different size and concentration can be observed through visualized flow channel. The dyed coal fines particles are injected into the multiphase flow loop. By observing whether they can be discharged from the V-shaped pipe, the lower limits of superficial gas and liquid velocities to avoid particle retention at the elbow were determined. A correlation to predict the critical gas and liquid velocity was presented, and the accuracy of the calculation model was verified in comparison with the experimental results.

In the past few decades, Coal-Bed Methane (CBM) has become an important source of energy especially in North America. The methane adsorbed within the coal is in a near-liquid state. The open fractures in the cleats are commonly saturated with water. To develop CBM reservoir, water in the fracture and coal seam must be continuously pumped off from coal seam to reduce pressure and desorb gas from matrix. Although operators desire to produce hydrocarbon quickly, a too fast dewatering rate can irreversibly damage matrix desorption process, which can lead to an unfavorable ultimate recovery. Further, the aggressive production rate can potentially release the coal fines and drive them into pump, which increases maintenance effort and cost. Even worse, the de-watering process fluctuates because of the rock porosity and permeability changes resulting from the brittle coal seam and pressure reduction. Therefore, it is critical to adjust the pump operating parameters in a timely manner to maintain a continuous/intermittent production. Ten CBM wells are located in a remote area, which makes the access to wellsites difficult. Previously engineers had to evaluate well performance and optimize the pump on-site, which is limited by a monthly basis. We firstly developed an automatic data processing system using the advanced Echosounders, which can measure the water level in real time. The reservoir pressure can be then monitored dynamically through interpreting the detected water level. With an automatic-wireless data transferring system installed on-site and a closed-loop control program to receive, process, and interpret data, the pump operating parameters can be changed in real time through remote control. This system not only identifies the downhole problems in real time, but also reduces the pump maintenance frequency from 40 days to 75 days statistically and numbers of trip to well site. Further, the gas production rate has been averagely improved by 30% for the 10 wells. The authors firstly developed an automation data processing and control system in the favor of advanced echosounders. Based on the interpreted reservoir pressure, we can avoid aggressive production by adjusting the pump operating parameters in real time, which eventually results in a better ultimate recovery. The developed workflow (automatic echosounder data acquisition, real filed data transferred to central office, data processing, interpretation, and simulation in computational system, adjustment commands to operating system) is especially valuable for the locations difficult to access.