Dynamometer Card Research Articles

Augmented Deep Transfer Learning for SRP Condition Monitoring via Physically-Informed WGAN-GP Approach

Abstract Traditional dynamometer card sensors are costly and complex, making them unsuitable for real-time sucker rod pumping (SRP) well diagnostics. Recently, SRP diagnosis models using motor power curves offer an alternative, but irregular power curves and limited labeled data present challenges. To address this, we propose a deep transfer model enhanced by Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) data augmentation. First, a physics-driven model reconstructs polished rod torque from motor power, emphasizing fault features. Second, WGAN-GP generates faulty SRP torque-displacement samples to expand training data. Finally, a fully parameter-tuned deep transfer SRP diagnosis framework is established, which improves the automatic learning of advanced fault features and enhances diagnostic accuracy using the augmented dataset. Experiments confirm the model's superior performance and generalization.

A Well-Tested Pump Card Classification and Identification Algorithm Based on Time Series Analysis Techniques

Abstract To accurately identify the operational conditions of oil pumping wells, promptly monitor the working status of oil wells, expedite responses to sudden pumping well accidents, and ensure orderly production at the oil extraction site, this paper introduces a time segment-based oil pumping well condition identification algorithm. This method no longer relies on drawn dynamometer cards for condition identification. Instead, it solely utilizes sensor-provided polished rod displacement and load time series, aligning more closely with the data’s intrinsic nature. The algorithm is sufficiently lightweight, highly responsive, and does not require GPU resources, making it suitable for edge deployment. Furthermore, this approach provides evidence of the time continuity and numerical continuity of time series data. Compared to traditional identification methods, this approach maintains a high level of accuracy, offers a streamlined model, and is interpretable, presenting a novel perspective for oil pumping well condition identification.

Enhancing commercial check valves in downhole pump applications through laboratory testing system development

In this study, we aim to enhance the performance and longevity of downhole pumps employed in crude oil extraction in the oil industry. Downhole pumps play a pivotal role in the rod-pump system, comprising traveling and standing valves that function similarly to ball check valves. However, these valves often experience premature wear and tear. To address this concern, we embarked on experiments involving various check valve alternatives to conventional ball valves within downhole pumps. The testing conditions were controlled precisely. Furthermore, we evaluated four distinct check valve types, the original (representing the incumbent ball valves), spring-poppet (C), spring-ball (CB), and spring-poppet with soft-seated (S6C) check valves, within a controlled laboratory environment. We employed a TEXAPON N70 solution to replicate the properties and temperature conditions of crude oil. A portable ultrasonic flow meter was used to quantify the pump flow rate and assess its volumetric efficiency. In addition, we recorded data on the polished-rod load and plunger displacement to generate dynamometer cards, thereby enabling a comprehensive evaluation of the operational performance of the pump. Furthermore, we conducted a vacuum test to scrutinize valve leakage, which is a crucial indicator of the operational lifespan of a downhole pump. Our findings show that incorporating the CB check valve with the RHB pump in oil wells operated by the PTT Exploration and Production Public Company Limited (PTTEP) could result in a 15 % increase in volumetric efficiency and a remarkable 160 % improvement in durability compared to the original ball check valve.

INVESTIGATION OF THE LOADS ON THE ROD PUMPING UNIT WHEN THE FLUID LEVEL IN THE WELL CHANGES

The balance of the pumpjack, which is the most common type of drive for downhole rod pumps, has a significant impact on the efficiency of pumping operation of the well. It determines the degree of loading of the pumpjack, the amount of electricity consumed. However, during the operation of the well, the balance of the drive may be disrupted due to a change in the load on the balancer head due to the weight of the liquid column in the annulus and acting on the pump plunger. This situation is noted for wells operating in the periodic pumping mode, as well as when the inflow of reservoir fluid changes for various reasons (unstable inflow, deterioration of permeability of the downhole zone of the formation, changes in reservoir pressure during development and other reasons). The paper considers the issues of forming loads on the drive of rod installations at a variable dynamic fluid level in the well. A mathematical model is presented describing the formation of loads on the head of the pumpjack balancer, taking into account possible fluctuations in the dynamic level. Verification of the proposed model was performed and a good agreement was obtained between the model and field dynamometer cards. A field example shows that a decrease in the dynamic liquid level causes an increase in maximum loads on the balancer head by more than 10 %. It was found that due to a change in the balance of loads on the drive, the torque on the crank shaft increases when the rods move upwards, which leads to an increase in the asymmetry of loads on the drive and a violation of the balance of the rocking machine. The relevance of the use of dynamic balancing systems is substantiated, which allow maintaining the balance of loads acting on the drive in changing external conditions.

Interval estimation of dynamic liquid level of sucker-rod pumping systems based on dynamometer card

This paper is concerned with the interval estimation problem of the dynamic liquid level for sucker-rod pumping systems via dynamometer cards. Firstly, a surface dynamometer card-based dynamic liquid level model is established in terms of the operational mechanism of the pump and the dynamics of the rod strings. Then, an underdamped oscillation method and a boxplot-based denoising method are developed respectively to determine the damping coefficient in the dynamics of the rod strings and deal with the uncertainties in the dynamometer card. Based on these, a finite difference-based interval estimation strategy is proposed to determine dynamic liquid level via the surface dynamometer card. Finally, simulation results with the field measurements demonstrate the validity of the proposed method.

Automatic sucker rod pump fault diagnostics by transfer learning using googlenet integrated machine learning classifiers

Oil and gas extraction is vital for meeting the energy needs of a growing global population. Artificial lift (AL) systems play a crucial role in oilfields, especially when reservoir pressure is low. Among these systems, sucker rod pumps (SRPs) are extensively employed for onshore hydrocarbon recovery operations. However, SRPs are susceptible to mechanical failures and operational challenges arising from evolving reservoir conditions. This study proposes an approach for fault diagnosis in SRPs using real-time data from sensors and machine learning (ML) algorithms to detect anomalies and patterns associated with potential problems. The proposed method involves deep learning (DL) for automated feature extraction from dynamometer cards and error-correcting output codes (ECOC) model-based supervised machine learners for efficiently assessing the operational state of the SRP. By forecasting potential failures, preemptive measures can be taken to minimize downtime and reduce maintenance costs. The application of ML in the analysis of SRP provides a potential tool for diagnosing and predicting failures, improving productivity efficiency, and reducing downtime. Also, the accuracy of Convolutional Neural Networks (CNN) models was compared with that of CNN-ECOC model-based learners in this study, and the results demonstrated that integrating algorithms such as Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) with the network caused significant improvements in the accuracy; however, Decision Tree (DT) and Naive Bayes (NB) did not perform well in the pattern classification task. Specifically, the GoogLeNet model achieved improved accuracy of 96.40 % and 99.40 % when SVM and k-NN were integrated, respectively. Conversely, with DT and NB, the accuracies dropped to 66.30 % and 75.10 %, respectively.

Trajectory Recognition and Working Condition Analysis of Rod Pumping Systems Based on Pose Estimation Method with Heatmap-Free Joint Detection

Summary Rod pump systems are the primary production tools in oilfield development. Analyzing their working conditions provides a theoretical foundation for formulating production optimization plans and adjusting equipment parameters. Existing machine learning–based condition analysis methods rely on dynamometer cards and cannot capture the actual operational trajectory of the pumping unit. To address this issue, this paper proposes a keypoint detection method for pumping units based on pose estimation of heatmap-free joint detection from video data. A data annotation scheme suitable for the task of detecting pumping unit keypoints was developed, and the learning criteria for this task were optimized. An end-to-end heatmap-free pose estimation algorithm was used to process images of the pumping unit, yielding predicted keypoint positions, thereby enabling the identification of the keypoint motion trajectories of the pumping unit. Experiments validated the proposed method and compared it with general learning criteria. Results show that this method accurately captures the keypoint positions of the pumping unit, with the optimized learning criteria model improving by more than 5% compared with general methods and increasing the keypoint object keypoint similarity (OKS) by more than 30%. The model’s results can be used for the actual operational trajectory recognition of the pumping unit, automatically calculating the motion parameters of the polished rod, and intelligently assessing the balance and working condition analysis of the pumping unit. This realizes the intelligent application of video surveillance data, significantly contributing to the dynamic study of rod pump systems.

Dynamometer card generation for pumping units based on CNN and electrical parameters

In the actual production process of oil fields, the real-time and accurate acquisition of dynamic recorder data from the pumping unit is of great significance for the diagnosis of well failures. The traditional method of obtaining the card of the dynamometer usually includes installing a load sensor on the auxiliary head of the pumping unit. However, due to the harsh environment of the oil field production site, these load sensors often suffer from damage, distortion, and aging, resulting in large measurement errors and low reliability. This paper proposes a mixed model of pumping based on motor electrical parameter data and CNN convolutional neural network, which has good consistency with actual data in terms of predictive performance. Thus, the highlights of this paper can be summed up in two points: (1) Based on the mathematical model of the AC motor, the speed of the motor and the torque output of the motor are accurately estimated. (2) The convolutional neural network is introduced to compensate for the errors caused by the defects of the pumping unit mechanism model.

A Working Conditions Warning Method for Sucker Rod Wells Based on Temporal Sequence Prediction

The warning of the potential faults occurring in the future in a sucker rod well can help technicians adjust production strategies in time. It is of great significance for safety during well production. In this paper, the key characteristic parameters of dynamometer cards were predicted by a temporal neural network to implement the warning of different working conditions which might result in failures. First, a one-dimensional damped-wave equation was used to eliminate the dynamic loads’ effect of surface dynamometer cards by converting them into down-hole dynamometer cards. Based on the down-hole dynamometer cards, the characteristic parameters were extracted, including the load change, the position of the valve opening and closing point, the dynamometer card area, and so on. The mapping relationship between the characteristic parameters and working conditions (classification model) was obtained by the Xgboost algorithm. Meanwhile, the noise in these parameters was reduced by wavelet transformation, and the rationality of the results was verified. Second, the Encoder–Decoder and multi-head attention structures were used to set up the time series prediction model. Then, the characteristic parameters were predicted in a sequence-to-sequence way by using historical characteristic parameters, date, and pumping parameters as input. At last, by inputting the predicted results into the classification model, a working conditions warning method was created. The results showed that noise reduction improved the prediction accuracy significantly. The prediction relative error of most characteristic parameters was less than 15% after noise reduction. In most working conditions, their F1 values were more than 85%. Most Recall values could be restored to over 90% of those calculated by real parameters, indicating few false negative cases. In general, the warning method proposed in this paper can predict faulty working conditions that may occur in the future in a timely manner.

Intelligent diagnosis method of torque-angle dynamometer cards for beam pumping units based on transfer learning

Remote monitoring and intelligent diagnosis of operating conditions are two critical aspects for achieving cloud intelligent diagnosis of the beam pumping unit. However, the current manual detection method restricts real-time diagnostic efficiency. Due to poor sensor real-time performance and high maintenance costs, the technical conditions of the dynamometer card for remote monitoring are inferior to those of motor power. This paper establishes a torque-angle dynamometer card fault diagnosis method based on transfer learning to diagnose working conditions effectively based on motor power. Firstly, based on the existing production data and mechanism model, the torque-angle dynamometer card dataset was built by converting motor parameters and dynamometer cards. Secondly, five convolutional neural networks (AlexNet, VGG16, ResNet_V2, MobileNet_V3_large, and DenseNet) were constructed, and three pre-training models (ResNet_V2, MobileNet_V3_large, and DenseNet) based on ImageNet dataset were developed based on the transfer learning. Finally, utilizing the dataset above, the recognition models were trained. The overall recognition performances of the models and the recognition performance under each working condition were evaluated and compared. The results indicated that, excluding MobileNet_V3_large, the recognition accuracies of these base models achieved 90%, while the recognition performance of each working condition generally fell below 80%. This highlighted the significant impact of the dataset quality on the recognition performance of convolutional neural networks. In contrast, the pre-trained models based on transfer learning achieved a recognition performance of 95% overall and 90% for each working condition. The recognition accuracy, speed, and generalization performance of the pre-trained models were significantly better than the base models.

The real-time dynamic liquid level calculation method of the sucker rod well based on multi-view features fusion

In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the dynamic liquid level real-time calculation. In this paper, the multi-source data are regarded as the different views including the load of the sucker rod and liquid in the wellbore, the image of the dynamometer card and production dynamics parameters. These views can be fused by the multi-branch neural network with special fusion layer. With this method, the features of different views can be extracted by considering the difference of the modality and physical meaning between them. Then, the extraction results which are selected by multinomial sampling can be the input of the fusion layer. During the fusion process, the availability under different views determines whether the views are fused in the fusion layer or not. In this way, not only the correlation between the views can be considered, but also the missing data can be processed automatically. The results have shown that the load and production features fusion (the method proposed in this paper) performs best with the lowest mean absolute error (MAE) 39.63 m, followed by the features concatenation with MAE 42.47 m. They both performed better than only a single view and the lower MAE of the features fusion indicates that its generalization ability is stronger. In contrast, the image feature as a single view contributes little to the accuracy improvement after fused with other views with the highest MAE. When there is data missing in some view, compared with the features concatenation, the multi-view features fusion will not result in the unavailability of a large number of samples. When the missing rate is 10%, 30%, 50% and 80%, the method proposed in this paper can reduce MAE by 5.8, 7, 9.3 and 20.3 m respectively. In general, the multi-view features fusion method proposed in this paper can improve the accuracy obviously and process the missing data effectively, which helps provide technical support for real-time monitoring of the dynamic liquid level in oil fields.

A Novel Method for Predicting the Behavior of a Sucker Rod Pumping Unit Based on the Polished Rod Velocity

Fault dynamometer cards are the basis of the diagnosis technique for sucker rod pumping systems. Predicting fault cards with a pumping condition model is an economical and effective method. The usual model is described by a mixed function of the pump displacement and pump load, and it is difficult to use in the prediction method based on the analytical solution of the sucker rod string wave equation. In this paper, a normal pumping condition model described by a function of polished rod velocity is proposed. For the analytical solution of the sucker rod wave equation, an iterative prediction algorithm with pumping condition models is proposed, its convergence is analyzed, and then it is validated by classical finite difference method simulated cards and measured surface dynamometer cards. The results show that the proposed algorithm is accurate. The algorithm has a maximum relative error of 0.10% for the classical method simulated card area and 1.45% for the measured card area. The research of this paper provides an effective scheme for the design, prediction, and fault diagnosis of a sucker rod pumping system with an analytical solution.

Multisource working condition recognition via nonlinear kernel learning and p-Laplacian manifold learning

Effectively utilizing information from multiple sources and fewer labeled operating condition samples from a sucker-rod pumping system for oil production can improve the recognition effects and engineering practicability. Nevertheless, this is a challenging energy environment scientific application research subject, and therefore, this study proposes an operating state recognition scheme that relies on multisource nonlinear kernel learning and p-Laplacian high-order manifold regularization logistic regress. Specifically, three measured features are selected and extracted, i.e., wellhead temperature signal, electrical power signal, and ground dynamometer cards, based on mechanism analysis, expert experience, and prior knowledge. Finally, we establish the operating condition recognition model to recognize by the multisource p-Laplacian regularization kernel logistic regress algorithm. The experimental data are derived from 60 wells of a common high-pressure and low-permeability thin oil reservoir block of an oil field in China. The corresponding trials highlight that our scheme outperforms traditional recognition methods by exploiting single-source and multiple-feature data. In the context of fewer labeled samples, the proposed method has a greater recognition effect, engineering practicability, and better model robustness than the existing schemes based on other high-order manifold learning, verifying our method's effectiveness.

Selecting a Monitoring Technology for a Control System of Distributed Oil Production Facilities

The article proposes the structure of a SCADA system for monitoring and control of oil production facilities that are distributed over a large area. The main emphasis is on the selection of technology that will enable effective monitoring of the equipment of each oil well. Factors such as reliability, ease of use, availability of protection against third-party interference, as well as availability and accessibility of an open-source software code were taken into account. After reviewing the most common software platforms, a system based on Prometheus and Grafana was selected. It is a combination of the Prometheus time series database server and the Grafana information visualization and analysis system. The important factors that determined the choice of this platform were the availability of the open source code and a large library of ready-made templates for displaying the well parameters in real time. An example of the created visualization window of the dynamometer card of the well, built on the basis of the experimentally recorded data, is presented.

Working condition recognition of sucker rod pumping system based on 4-segment time-frequency signature matrix and deep learning

High-precision and real-time diagnosis of sucker rod pumping system (SRPS) is important for quickly mastering oil well operations. Deep learning-based method for classifying the dynamometer card (DC) of oil wells is an efficient diagnosis method. However, the input of the DC as a two-dimensional image into the deep learning framework suffers from low feature utilization and high computational effort. Additionally, different SRPSs in an oil field have various system parameters, and the same SRPS generates different DCs at different moments. Thus, there is heterogeneity in field data, which can dramatically impair the diagnostic accuracy. To solve the above problems, a working condition recognition method based on 4-segment time-frequency signature matrix (4S-TFSM) and deep learning is presented in this paper. First, the 4-segment time-frequency signature (4S-TFS) method that can reduce the computing power requirements is proposed for feature extraction of DC data. Subsequently, the 4S-TFSM is constructed by relative normalization and matrix calculation to synthesize the features of multiple data and solve the problem of data heterogeneity. Finally, a convolutional neural network (CNN), one of the deep learning frameworks, is used to determine the functioning conditions based on the 4S-TFSM. Experiments on field data verify that the proposed diagnostic method based on 4S-TFSM and CNN (4S-TFSM-CNN) can significantly improve the accuracy of working condition recognition with lower computational cost. To the best of our knowledge, this is the first work to discuss the effect of data heterogeneity on the working condition recognition performance of SRPS.

Oil-Net: A Learning-Based Framework for Working Conditions Diagnosis of Oil Well Through Dynamometer Cards Identification

Working conditions identification of oil well relies on high-cost and slow-speed artificial inspection in past decades. Working conditions diagnosis through dynamometer cards identification based on machine learning has significant economic value and environmental meaning for oil production. In this paper, we collect dynamometer cards from the famous Chinese Shengli Oil Field as research data. We firstly investigate properties of dynamometers under different working conditions and create a dynamometer card dataset. Further we introduce calibration/visualization preprocess methods, and propose the Oil-Net 1D/2D identification models from the time-series and computer vision views respectively. Experiment results indicate that comparing with other machine learning and time series classification methods, Oil-Net 1D/2D improve identification accuracy significantly. This study provides guidance for the design and implementation of learning-based oil well working conditions intelligent diagnosis system.

Intelligent Diagnosis Model of Working Conditions in Variable Torque Pumping Unit Wells Based on an Electric Power Diagram

Because of the problems, such as the lack of an electric power diagram atlas under different working conditions and the difficulty in intelligent diagnosis of variable torqued pumping unit wells, this paper proposes a diagnosis model of working conditions based on feature recognition. The mathematical relationship model between the polished rod load and motor output power is derived based on the analysis of geometric structure, motion law, and process of energy transformation and transfer of the variable torque pumping unit. It can calculate the electric power diagram based on a dynamometer card. On this basis, the electric power diagram atlas is created, and the feature analysis and eigenvalue extraction of the electric power diagrams under different working conditions are carried out to realize the direct diagnosis of the working conditions in the variable torque pumping unit wells. The application and analysis of examples show that the electric power diagram atlas created in this paper has good practicability, and the working condition diagnosis model accuracy is high. It can provide a theoretical basis and technical support for the intelligent diagnosis of oil production working conditions and improve the intellectual management level of the oilfield, which is conducive to reducing production management costs and improving the oilfield’s production efficiency and benefits.

Metaverses-Based Parallel Oil Fields in CPSS: A Framework and Methodology

Aiming to provide a novel paradigm of oil fields, metaverses-based parallel oil fields are proposed in this article. Compared with the existing smart/intelligent oil fields in cyber–physical systems (CPS), parallel oil fields can take human factors into full consideration and expand the operation space to cyber–physical–social systems (CPSS), which can be regarded as the abstract and scientific explanation of metaverses. In the proposed parallel oil fields, there are three kinds of workers (human workers, digital workers, and robotic workers) coordinating to construct a more reliable and intelligent oil field. Furthermore, the framework and methodology of parallel oil fields are illustrated by parallel systems and the artificial systems, computational experiments, and parallel executions (ACP) approach. Based on the proposed framework, parallel oil fields are capable of generating a more trustworthy artificial system and guaranteeing the realization of the 6S (safety, security, sustainability, sensitivity, service, and smartness) goal. Finally, based on dynamometer cards, fault diagnosis of sucker rod pumping systems (SRPS) is investigated in parallel oil fields.

A Hybrid Approach of the Deep Learning Method and Rule-Based Method for Fault Diagnosis of Sucker Rod Pumping Wells

Accurately obtaining the working status of the sucker rod pumping wells is a challenging problem for oil production. Sensors at the polished rod collect working data to form surface dynamometer cards for fault diagnosis. A prevalent method for recognizing these cards is the convolutional neural network (CNN). However, this approach has two problems: an unbalanced dataset due to varying fault frequencies and similar dynamometer card shapes that complicate recognition. This leads to a low accuracy of fault diagnosis in practice, which is unsatisfactory. Therefore, this paper proposes a hybrid approach of the deep learning method and rule-based method for fault diagnosis of sucker rod pumping wells. Specifically, when the CNN model alone fails to achieve satisfactory accuracy in the working status, historical monitoring data of the relevant wells can be collected, and expert rules can assist CNN to improve diagnostic accuracy. By analyzing time series data of factors such as the maximum and minimum loads, the area of the dynamometer card, and the load difference, a knowledgebase of expert rules can be created. When performing fault diagnosis, both the dynamometer cards and related time series data are used as inputs. The dynamometer cards are used for the CNN model to diagnose, and the related time series data are used for expert rules to diagnose. The diagnostic results and the confidence levels of the two methods are obtained and compared. When the two diagnostic results conflict, the one with higher confidence is preserved. Out of the 2066 wells and 7 fault statuses analyzed in field applications, the hybrid approach demonstrated a 21.25% increase in fault diagnosis accuracy compared with using only the CNN model. Additionally, the overall accuracy rate of the hybrid approach exceeded 95%, indicating its high effectiveness in diagnosing faults in sucker rod pumping wells.

Imbalanced Working States Recognition of Sucker Rod Well Dynamometer Cards Based on Data Generation and Diversity Augmentation

Summary During sucker rod pump production, there is a commonly seen problem of class imbalance, which refers to the differences in the amount of data accumulated under different working conditions. This problem in rod pump diagnosis can lead to unsatisfactory classification results of surface dynamometer cards under working conditions with fewer samples. Therefore, this study adopts the conditional generative adversarial nets (CGANs) improved by mini-batch method to address the problem of class imbalance. CGAN is an efficient method of multiclass data generation, which learns the properties of dynamometer cards by training the generator and discriminator networks. CGAN is modified by mini-batch strategy to avoid mode collapse and enable the interaction among input samples of discriminator, so that the generated dynamometer cards can be much more diverse. Results show that the shapes of generated dynamometer cards are basically consistent with those of real samples, and the structural similarity (SSIM) among the generated samples decreases, indicating that the generated dynamometer cards have more types of shape. Meanwhile, as the generated dynamometer cards become more diverse, their differences with real samples in data distribution are reduced, according to the calculation of sliced Wasserstein (SW) distance. Based on real and generated dynamometer cards, we developed the classifiers for working condition diagnosis of rod pump through convolutional neural network (CNN). The classification results of the validation set indicate that without the mini-batch method, the recall of generated categories for pump hitting down and leakage has increased by 12 and 5.3%, respectively; in contrast, with the mini-batch method, the recall has increased more obviously by 7, 24, and 2%, respectively, for gas lock, pump hitting down, and leakage. Our research results have demonstrated that the proposed method can effectively solve the problem of insufficient data accumulation in the oil field.