Sucker Rod Pumping System Research Articles

A Novel Hybrid Method for Indirect Measurement Dynamometer Card Using Measured Motor Power in Sucker Rod Pumping System

The dynamometer card (DC) is crucial for the remote monitoring of the sucker rod pumping system (SRPS). However, the DC sensors have poor real-time performance and high maintenance costs leading to difficulties in obtaining datasets of the downhole working states from different oil wells. Moreover, the motor power curve is easy to obtain in real-time and can reflect the changes in pumping unit load. Thus, this paper proposed a novel hybrid model for indirect measurement DC based on measured motor power. Firstly, based on the mechanical model analysis of SRPS, the dataset is constructed by transforming the motor power and geometric parameters of the SRPS into the polished rod torque, the first-derivative of polished rod torque, the second-derivative polished rod torque, and the torque factor. These four parameters are merged as the inputs of the data-driven model. Subsequently, a data-driven model implements the particle swarm (PSO) algorithm to optimize the weights and thresholds of the Back Propagation (BP) neural network model, which was trained to predict DCs of three common working states. Finally, the proposed method is verified experimentally through the measured DC and motor power data. Both experimental and prediction results demonstrate the effectiveness of the proposed method for generating DC. The mean DC area relative error of the hybrid method proposed in this paper is 2.52%.

Multi-Weighted Partial Domain Adaptation for Sucker Rod Pump Fault Diagnosis Using Motor Power Data

Motor power curves (MPCs) have received great attention for use in diagnosing the working conditions of sucker rod pumping systems (SRPSs) because of their advantages in accessibility and real-time performance. However, existing MPC-based approaches mostly need a rigorous assumption that the MPC instances of different working conditions are sufficient, which does not hold in industrial scenarios. To this end, this paper proposes an unsupervised fault diagnosis methodology to leverage readily available dynamometer cards (DCs) to diagnose collected unlabeled MPCs. Firstly, a mathematical model of the SRPS is presented to convert actual DCs to MPCs. Secondly, a novel diagnostic methodology based on adversarial domain adaptation is proposed for the problem of data distribution discrepancy across the collected and converted MPCs. Specifically, the collected unlabeled MPCs may only cover a subset of the working conditions of the abundant DCs, which will easily cause negative transfer and lead to dramatic performance degradation. This proposed methodology employs class-level and distribution-level weighting strategies so as to guide the network to focus on the instances from shared categories and down-weight the outlier ones. Validation experiments are performed to evaluate the mathematical model and the diagnostic methodology with a set of actual MPCs collected by a self-developed device. The experimental result indicates that the accuracy of the proposed algorithm can reach 99.3% in diagnosing actual MPCs when only labeled DCs and unlabeled actual MPCs are used.

Unsupervised Fault Diagnosis of Sucker Rod Pump Using Domain Adaptation with Generated Motor Power Curves

The poor real-time performance and high maintenance costs of the dynamometer card (DC) sensors have been significant obstacles to the timely fault diagnosis in the sucker rod pumping system (SRPS). In contrast to the DCs, the motor power curves (MPCs), which are accessible easily and highly associated with the entire system, have been attempted to predict the working conditions of the SRPS in recent years. However, the lack of labeled MPCs limits the successful applications in the industrial scenario. Thereby, this paper presents an unsupervised fault diagnosis methodology to leverage the generated MPCs of different working conditions to diagnose the actual unlabeled MPCs. Firstly, the MPCs of six working conditions are generated with an integrated dynamics mathematical model. Secondly, a framework named mechanism-assisted domain adaptation network (MADAN) is proposed to minimize the distribution discrepancy between the generated and actual MPCs. Specifically, benefiting from introducing the mechanism analysis to label the collected MPCs preliminarily, a conditional distribution discrepancy metric is defined to guarantee a more accurate distribution matching with respect to different working conditions. Eventually, validation experiments are performed to evaluate the mathematical model and the diagnosis method with a set of actual MPCs collected by a self-developed device. The experimental result demonstrates that the proposed method offers a promising approach for the unsupervised diagnosis of the SRPS.

Adaptive fault diagnosis of sucker rod pump systems based on optimal perceptron and simulation data

A highly precise and timely diagnosis technology can help effectively monitor and adjust the sucker rod production system (SRPS) used in oil wells to ensure a safe and efficient production. The current diagnosis method is pattern recognition of a dynamometer card (DC) based on feature extraction and perceptron. The premise of this method is that the training and target data have the same distribution. However, the training data are collected from a field SRPS with different system parameters designed to adapt to production conditions, which may significantly affect the diagnostic accuracy. To address this issue, in this study, an improved model of the sucker rod string (SRS) is derived by adding fault-parameter dimensions, with which DCs under 16 working conditions could be generated. Subsequently an adaptive diagnosis method is proposed by taking simulated DCs generated near the working point of the target SRPS as training data. Meanwhile, to further improve the accuracy of the proposed method, the DC features are improved by relative normalization and using additional features of the DC position to increase the distance between different types of samples. The parameters of the perceptron are optimized to promote its discriminability. Finally, the accuracy and real-time performance of the proposed adaptive diagnosis method are validated using field data.

A critical analysis of power conditions in sucker-rod pumping systems

The most decisive constituent of operating expenditures in sucker-rod pumping operations is related to the system's electric power use as most installations are driven by electric motors. Consequently, the reduction of operating costs can be translated to the reduction of energy losses both downhole and on the surface. Therefore, the energy efficiency of the surface and downhole components of the pumping system as well as the overall system efficiency play a big role in maximizing profits. The paper presents a critical analysis of the energy efficiency of the individual components of the sucker-rod pumping system and introduces novel models to find the system's total efficiency. The typical energy losses in the sucker-rod pumping system's main components (the downhole pump, the sucker-rod string, the surface pumping unit, the gearbox, the V-belt drive, and the prime mover) are discussed in detail. It is demonstrated that the level of the pumping unit's counterbalancing as well as any inertial effects do not impact on the net gearbox torques and on the required average mechanical output power of the motor. The energy consumption of the electric motor, however, is affected by the pumping unit's counterbalancing and the inertial effects because of the changes in motor efficiency due its variable loading within the pumping cycle. The system's useful output power is performed by the downhole pump when it lifts the produced liquid to the surface. The paper demonstrates that the so-called hydraulic power, calculated from the increase of the produced liquid's potential energy, is a reliable indicator of the system's useful power. Using the hydraulic power together with the electric power taken from the power supply permits an easy way to assess the over-all energy efficiency of the pumping system. The paper proposes several other variants of system efficiency calculations; they are based on the fact that all components of the pumping system are connected in series to each other. Sizing of electric motors for sucker-rod pumping installations is normally done with the use of a cyclic load factor (CLF) that accounts for the fluctuations in motor load during the pumping cycle. Originally, CLFs were found from the variation of motor current, but mechanical CLFs based on net gearbox torques are much more practical to use. This practice is fully justified in the paper by proving that the correlation between the motor's real current and its net torque loading is nearly linear. It is further shown that the safety of sucker-rod pumping installation design is improved if the electric motor is sized with the use of a mechanical CLF because that case gives the highest required nameplate motor power. • A critical analysis of the energy efficiency of the individual components of the sucker-rod pumping system is presented. • Novel models to calculate the over-all system efficiency of sucker-rod pumping systems are introduced and demonstrated. • The effects of counterbalancing on net gearbox torques and on the motor's mechanical power are evaluated. • Hydraulic power, representing the increase of the produced liquid's potential energy, is a reliable indicator of the system's useful power. • The use of mechanical instead of electrical CLFs to size electric motors is fully justified.

Fault Diagnosis for Sucker Rod Pumping Systems: A Parallel System Approach

Fault Diagnosis for Sucker Rod Pumping Systems: A Parallel System Approach

A Novel Method for Trajectory Recognition and Working Condition Diagnosis of Sucker Rod Pumping Systems Based on High-Resolution Representation Learning

A Novel Method for Trajectory Recognition and Working Condition Diagnosis of Sucker Rod Pumping Systems Based on High-Resolution Representation Learning

Optimization of Sucker Rod Pump Operations Using Parallel Systems

With the exploitation of oil, oil pumping units are facing with the challenges such as low efficiency, increased mining difficulties and old infrastructures. The requirement of digital construction on oilfields is emerging, especially to these sucker sod pump (SRP) units built in last century. In this article, to facilitate the intelligent development of SRP systems, the concept of the parallel digital sucker rod pump systems (PDSRPS) was presented first, and their optimization framework was designed to efficiently improve the design and balance by data interactions. The real oil pump systems were integrated with their customized digital twins to establish the cyber-physical systems. The adaptive optimization on pumping processes was continuously developing with the interaction between physical pump units and their digital versions. The feasibility of the proposed framework has been demonstrated through the computational experiments on conventional beam-pumping units.

An equivalent vibration model for optimization design of carbon/glass hybrid fiber sucker rod pumping system

A carbon/glass hybrid fiber continuous sucker rod (CR) with lower specific gravity, better corrosion resistance and higher strength was developed to replace the steel rod in the application of underground oil extraction. To meet the actual needs of oil fields, the computer-aided design techniques based on mathematical optimization model are used to help engineers in optimizing the CR pumping system. Because the performance of CR pumping system, including the energy consumption and the service life of sucker rod string (SRS) is the complex function related to the system parameters, and the constraints are nonlinear, the enumeration method is used to solve the optimization problem. Moreover, the existing methods for predicting the SRS behavior, including wave equation and finite element analysis (FEA), require iterative calculation, which may result in a low prediction efficiency. Hence, the huge optimization space, i.e. the set of all possible CR pumping systems, will lead to a very long optimization process. Currently, the typical solution for improving the optimization efficiency is to greatly reduce the optimization space based on the experience of steel sucker rod application in the oilfield. However, due to the difference of properties between CR and steel sucker rod, the CR pumping system designed by the current method cannot achieve the best performance.

A fault diagnosis method based on the Support Vector Machine in rod pumping systems

Monitoring the working status of the sucker rod pump is an important part in petroleum engineering. With the development of artificial intelligence technology, more methods have been applied to the fault diagnosis of rod pumping systems. An evolutional fault diagnosis method based on Support Vector Machine (SVM) in sucker rod pumping systems is proposed. Fourier descriptors and Light Field compression algorithm are used in this method to extract the graphic features of the indicator diagram. SVM is used to build fault classification model. This method is verified experimentally through data of indicator diagrams and the results show that it has a shorter training time and higher accuracy.

A novel method for prediction of paraffin deposit in sucker rod pumping system based on CNN indicator diagram feature deep learning

Paraffin deposit is a major problem associated with water injection in waxy heavy oil reservoirs, therefore accurately and effectively predicting the development of paraffin deposit can avoid some major faults, such as stuck pump, and ensure the stability of the system. Paraffin deposit, as a gradual changing fault, shows a clear trend of development. Based on the convolutional neutral network (CNN) combined with deep learning, the indicator diagram is extracted to calculate the growth rate, and then the timing of serious paraffin problems can be predicted. The paper firstly analyzes and calculates the force of the column in the process of paraffin deposition and obtains the theoretical maximum load in the upper stroke and the theoretical minimum load in the lower stroke, then the load difference is selected as the parameter to characterize the paraffin deposit. In a case study, an experimental well is selected to determine maximum load difference in paraffin deposit process and load difference in normal production, and then the percentage of paraffin deposit is determined based on the growth law as the label of each indicator diagram. The structure of convolutional neural network is designed, and the accuracy rate is taken as the index to optimize the matching scheme of convolutional neural network structure parameters. Finally, the convolution neural network is trained by using training sets of 1.3 million well data. This method is an effective way to predict the paraffin deposit with CNN combined with deep learning and indicator diagram with an accuracy rate of 98.08% and loss less than 0.633. The prediction method in this paper can facilitate the intelligent management of oilfield safety and ensure the efficient production of pumping system.

Acceptance Sampling Scheme with Warranty for Life Testing Using Bayesian Inference Methods

Abstract We propose an empirical Bayesian (EB) procedure with a rebate warranty policy to search for optimal sampling plans for three-parameter Burr-type XII distribution (3pBXIID) under truncated life testing. The proposed method requires fewer assumptions than its competitors to search for optimal sampling plans when the lifetimes of products follow a 3pBXIID. The Newton–Raphson method using the quasi-Newton (QN) algorithm, the evolution algorithm method using the particle swarm optimization (PSO) algorithm and genetic algorithm (GA) are used in the proposed EB procedure to search for reliable estimates of the parameters in the Bayesian model, and the obtained estimates are denoted as QN-EB, PSO-EB, and GA-EB, respectively. The performance of the QN-EB, PSO-EB, and GA-EB estimates were evaluated by performing Monte Carlo simulations. The simulation results show that the PSO-EB method outperforms the GA-EB and QN-EB methods in obtaining reliable estimates of the parameters in terms of bias and mean squared error. A grid-searching algorithm with the plug-in parameters of PSO-EB estimates to search for the optimal EB sampling plans is presented. Two examples pertaining to the lifetime of an oil-well pump in a sucker-rod oil pumping system and the first failure time of a small electric cart are used to illustrate the application of the proposed EB method.

Sucker rod pump frequency-elastic drive mode development – from the numerical model to the field test

A frequency-elastic drive mode for a sucker rod pumping system is introduced to reduce its polished rod peak loads and the total energy consumption. Numerical modeling and an extensive field test verify the concept. The frequency-elastic drive mode is a software solution for variable speed drive systems, which can be applied in the controller and does not require any hardware adjustments. The novel drive mode adjusts the set frequency, sent by the controller to the frequency converter, depending on the actual power requirements. An increase in power consumption results in a reduction of the set frequency, which is proportional to the power consumption increase. A reduction in power consumption results in the opposite effect to achieve a similar pumping speed as for regular operation. The frequency-elastic drive mode is simulated by a numerical model, which covers the entire pumping system. An extensive field test was performed to verify the concept and the numerical model. The simulation and the field test have confirmed the concept of the frequency-elastic drive mode and quantified its saving potential. The evaluation of the field test has shown that the energy-saving potential can reach five percent. In addition, a peak polished rod load reduction of up to three percent was seen. At the tested pumping system the frequency elastic drive mode under optimized parameters yields the best results in terms of total energy savings in the pumping speed range between 7 to 10 strokes per minute. A downhole system efficiency increase was seen for any pumping speed. The numerical model matches the field test data and allows the performance prediction of the novel drive mode for changed parameters and wellbore configurations without extensive field testing. The novelty of the presented paper is the concept of the frequency-elastic drive mode, which is a pure software solution for variable speed drive sucker rod pumping systems. The holistic model includes the entire pumping system and matches the field test data at remarkable accuracy.

Sucker rod pump downhole dynamometer card determination based on a novel finite element method

An advanced dynamic finite element model is presented that diagnoses the downhole pump performance of sucker rod pumping systems, applicable for any pumping conditions and equipment used. The results are compared to downhole measurements and other evaluation techniques. Buckling is an undesirable phenomenon occurring in sucker rod pumping. It essentially depends on the plunger load, which is a function of time and typically not measured but evaluated by diagnostic tools. Existing diagnostic tools exhibit specific limitations that reduce their applicability and output quality. This paper introduces a diagnostic tool, which can predict the rod string's stress field and its movement not only at the pump plunger but all along the rod string. Moreover, this tool can account for the interaction between rod guides and tubing as well as rod string and tubing. To this end, innovative tube-to-tube contact modeling is applied. The high precision results are accomplished by running a dynamic finite element simulation. The basic principle is to evaluate the plunger load incrementally by consecutively applying restarts of each time step, fully automated and computation time optimized. This publication shows that both the plunger load and the rod string’s dynamic behavior can be determined for any given wellbore as long as the borehole trajectory and surface dynamometer measurements are known. The dynamic finite element model is evaluated for a deviated system and a vertical system equipped with two different downhole pump types. Comparing the simulation results with the available downhole measurements and the analytical solution shows an excellent match, whereas the proposed solution provides a considerable amount of details about the overall system’s behavior. The evaluation has shown that the performance of standard and novel downhole pump types can be successfully diagnosed in detail, which is just possible under limitations with commercial software solutions. This tool can correctly predict whether or not the sucker rod string is subjected to buckling during the downstroke, which has a considerable effect on increasing the mean time between failures of a sucker rod pumping system. From the economic point of view, this means that the economic limit of a wellbore can be postponed. The novelty of the shown technique is the consideration of the full 3D trajectory and the implementation of only physical properties, result in an excellent accuracy of the output.

Quantitative diagnosis method of the sucker rod pump system based on the fault mechanism and inversion algorithm

Computer-aided fault diagnosis based on the dynamometer card (DC) of the sucker-rod pumping system (SRPS) is a crucial technology to reduce operating costs and increase yield. Currently, the conventional method to implement this technology is the pattern recognition of the DC features. However, the training set of DC that determines the diagnostic accuracy of the method is difficult to obtain because of the differences between oil wells. Moreover, this method can only obtain the type of single fault without quantitative analysis, which may affect the formulation of the adjustment measures.Therefore, in the present study, a quantitative diagnosis method independent of the training data is proposed. In order to obtain the operation process of SRPS under the comprehensive conditions of the fault, a simulation model involving fault effects is established according to the fault mechanism. Subsequently, the framework of the optimization inversion method is established to determine the fault parameters by minimizing the difference between the measured DC and the DC generated by the fault-mechanism model. Then, the strategy of the partition parallel optimization is utilized to improve the stability and efficiency of the inversion algorithm. Meanwhile, fifteen indicating parameters that directly reflect the type and degree of faults are defined.Finally, the proposed diagnosis method is verified experimentally through the data of 20 actual wells. The obtained results demonstrate the effectiveness of the proposed method for diagnosing the types of single and coupling faults, as well as predicting the production rate.

An evolutional SVM method based on incremental algorithm and simulated indicator diagrams for fault diagnosis in sucker rod pumping systems

Fault diagnosis of the sucker rod pumping system (SRPS) is a challenging problem in the oil industry. Recently, the computer-aided indicator diagram (ID) recognition techniques are becoming useful measurements to help engineers monitor the wells. However, the slow variation of SRPS state makes it difficult for a well to experience all the fault conditions. Using the IDs collected from other oil wells as training data will lead to a large difference between the distribution of training data and target data because of the interference information including noise and system operation characteristics in IDs. Moreover, the different occurrence probability of each fault leads to the imbalance of training data, therefore the fault tolerance of the diagnosis models will result in lower accuracy in identifying the fault IDs with less training samples. In addition, due to one-off training, the parameters of diagnostic model are always fixed resulting in lack of adaptive ability. To address this issue, an evolutional support vector machine (SVM) method for SRPS diagnosis is proposed. First, to obtain balanced training data with similar distribution to the target data, a novel model describing the working process of SRPS under various fault conditions is established. Subsequently, the static apparent stiffness feature and its extraction algorithm is proposed to fully retain the fault information of SRPS in IDs. Then, the incremental SVM is used to construct the diagnosis model based on generated IDs. At last, the proposed method is verified experimentally through the system parameters and IDs of many wells collected from oilfields, and then some conventional techniques are employed in the comparison studies. The obtained results show that the accuracy of the diagnosis model trained by simulated IDs is 11.2% higher than that trained by collected IDs. Besides, the parameters of proposed diagnosis model can be continuously evolved to improve the diagnosis accuracy and generalization ability. Furthermore, the proposed diagnosis model also has advantages in training efficiency and memory consumption.

Energy saving by reducing motor rating of sucker-rod pump systems

Energy industry can make significant savings by reducing electric motors ratings of the popular Sucker-Rod Pump (SRP) systems. This can be achieved by application of robust controllers, which are fully integrated with the SRP systems. In this work we have developed, modelled and analysed such integrated systems, specifically by examining two control schemes with open- and closed-loop controllers. The open loop scheme employs a genetic algorithm optimizing frequency in order to minimize fluctuations in a motor output power. This approach results in reducing the peak torque and consequently decreases the required motor rating by 20%. However, the scheme relies on a complex model of this electromechanical system, and it is computationally expensive. The second proposed scheme with a closed-loop control, the first of its kind for the SRP systems, is much faster and robust. It allows to reduce the motor rating by further 30% of that required in the open-loop scheme, which can save $246 M through choosing smaller motors and $39 M per year by reducing motor inner loss.

Sucker Rod Antibuckling System: Development and Field Application

SummaryWhen the oil price is low, cost optimization is vital, especially in mature oil fields. Reducing lifting costs by increasing the mean time between failure and the overall system efficiency helps to keep wells economical and increase the final recovery factor. A significant portion of artificially lifted wells currently use sucker rod pumping systems. Although its efficiency is in the upper range, there is still room for improvement compared with other artificial-lift systems.This paper presents the field-tested sucker rod antibuckling system (SRABS), which prevents buckling of the entire sucker rod string, achieved by a redesign of the standing valve, the advantageous use of the dynamic liquid level, and, on a case-by-case basis, application of a tension element. The system allows full buckling prevention and a reduction of the overall stresses in the sucker rod string.The resulting reduction in the number of well interventions combined with the higher system efficiency prolongs economic production in mature oil fields, even in times of low oil prices. The analysis of SRABS, using finite-element simulations, showed a significant increase in system efficiency. The SRABS performance and wear tests under large-scale conditions were performed at Montanuniversität Leoben’s Pump Test Facility and in the oil field. The results of intensive laboratory testing were used to optimize the pump-body geometry and improve the wear resistance by selecting optimal materials for the individual pump components. The ongoing field-test evaluation confirmed the theoretical approach and showed the benefits achieved by using SRABS. SRABS itself can be applied within every sucker rod pumping system; the installation is as convenient as a standard pump, and manufacturing costs are comparable with those of a standard pump.This paper shows improved performance of the SRABS pumping system compared with a standard sucker rod pump. SRABS is one of the first systems that prevents the sucker rod string from buckling without any additional equipment, such as sinker bars. Testing of SRABS has identified significant benefits compared with standard sucker rod pumps.

Downhole Dynamometer Sensors for Sucker Rod Pumps

This publication introduces the downhole dynamometer sensor technology for digitalizing sucker rod pumps’ downhole behavior. The presented field application enables insight into the sensor principles, data evaluation processes and highlights the value chain. Sucker rod pumps (SRP) are used worldwide since the last century. Nevertheless, the system is still prone to fail in certain situations. The lack of measured downhole data is a severe problem that significantly slows down the innovation process. The presented downhole dynamometer sensor measurement system can successfully fill this gap and provides valuable, requested information. Each downhole dynamometer sensor records the three-dimensional stress field, the movement characteristics, and the produced fluid temperature. The recorded data allow a critical evaluation of the rod string behavior. Rod string loading and movement, friction forces between rod guides and tubing, and volumetric parameters can be evaluated. The recordings of several sensors are linked together to provide a comprehensive picture of the sucker rod string condition. The field case data analysis has indicated severe wear at specific positions of the sucker rod string and shown a significant optimization potential of the system. This publication shows the significant optimization potential for the tested sucker rod pumping system to postpone the economic limit and increase the recovery factor. The novelty is the wealth of information obtained and the associated detailed evaluation possibilities.

Predicting multi-tapered sucker-rod pumping systems with the analytical solution

The sucker-rod string is an important part of the sucker-rod pumping system. Many methods have been employed to solve the one-dimensional wave equation that describes the longitudinal vibration of the sucker-rod string. The analytical solution with the separation of variables method is an important method. However, the analytical solution is mainly applied for diagnostic analysis and is difficultly applied for predictive analysis. As a result, the characteristics of predictive analysis for multi-tapered sucker-rod string with the analytical solution are misunderstood.In this paper, the analytical solution easily applied for predicting the behaviors of multi-tapered sucker-rod pumping systems is proposed after the general analytical solution of the separation variable method is expressed with a matrix. Based on the same parameters and boundary condition, the prediction results between the analytical solution and the finite differential solution, which is extensively applied to solve the wave equation, are compared; the parameter sensitivity in the predictive analysis of the sampling point number, Fourier coefficient number and viscous damping factor value are explored; and the prediction characteristics of different tapered rod string are simulated.The simulation results show that the polished rod card predicted by the analytical solution has a smooth effect and that the sharp corners of the pump card can be precisely described compared with the finite difference method in the predicate analyses. With an increase in the stage number from 1 to 4 of the sucker-rod string, the program execution time ratio between the finite differential solution and the analytical solution is exponentially increasing from 4.7 to 10.5. The optimal Fourier coefficients number is half of the sample point number; otherwise, there will exist the Gibbs phenomenon in the pump load approximated by the truncated Fourier series. For the same viscous damping factor, the prediction results of the two methods differ, and the analytical solution is insensitive to the viscous damping factor. With an increase in the stage number of the sucker-rod string for the same total length, the polished rod load decreases while the pump stroke may decrease.Eventually, the predicted polished rod card calculated according to the field parameters shows a satisfactory correspondence with the measured card, indicating that the model presented in this paper is feasible.