Pumping Unit System Research Articles

A novel hybrid efficiency prediction model for pumping well system based on MDS–SSA–GNN

AbstractThe prediction of the efficiency of oil well pumping systems plays an important role in optimizing the energy efficiency parameters of these systems. Currently, the prediction of oil well pumping system efficiency relies primarily on mechanistic models, but these models are often overly complex in predicting efficiency. Some researchers have attempted to use deep learning to predict system efficiency, but due to insufficient consideration of influencing factors and the causal relationships between these factors and system efficiency, they often include irrelevant variables as influencing factors, leading to less accurate prediction models. In this paper, a hybrid model (MDS–SSA–GNN) is proposed for the prediction of pumping well system efficiency. The model consists of six parts: Pearson's product moment correlation coefficient (PPMCC), multidimensional scaling (MDS) transform, maximum–minimum normalization, sparrow optimization algorithm (SSA), graph neural network (GNN), and maximum–minimum inverse normalization. First, the size of the correlation coefficient between each influencing factor and the system efficiency is quantitatively calculated by using PPMCC. Second, the main influencing factors are downscaled by using MDS and normalized based on the principle of maximum–minimum normalization. Third, the GNN algorithm is used for the prediction of the pumping unit system efficiency, and the SSA algorithm is used for the optimization of the initial values of the network parameters. Finally, the prediction results are obtained by the maximum–minimum antinormalization. To validate the model's accuracy, this study randomly selected 100 actual oil wells for comparative analysis and analyzed the impact of structural parameters of the hybrid algorithm on the prediction accuracy of system efficiency. The analysis results demonstrate that the proposed model can effectively predict system efficiency and has a certain role in improving the accuracy of oil well pumping system efficiency predictions.

A Sparse Dimensionality Reduction Approach Based on False Nearest Neighbors for Nonlinear Fault Detection

As a newly emerging multivariate statistical process monitoring method, non-negative matrix factorization (NMF) and its variants avoid the positive and negative cancellations between the extracted features because of the purely additive combination of non-negative components. Thus, they make a good match with this reality that the negative values of both observations and decomposed components are physically meaningless in many kinds of industrial processes. However, these methods are effective only for linearly separable problems and are not suitable for dealing with nonlinear process monitoring. In this article, the kernel-based method is integrated into the projective NMF (KPNMF) to improve the accuracy of fault detection, and the appropriate multiplicative update method is proven to be convergent. Furthermore, inspired by the false nearest neighbors (FNNs) method, a new dimensionality reduction approach (KPNMF-FNN) is presented to further reduce the original variables for determining the smallest dimension regression vector needed. Compared with the traditional methods, the proposed approach can greatly reduce the time and storage space required on the premise of maintaining a high fault detection rate and low false alarm rate. The experimental results on the Tennessee Eastman benchmark process and the pumping unit system show that the proposed algorithms have excellent performance and can effectively detect faults under the circumstances of retaining only the top 60% of the original variables.

Variable speed drive optimization model and analysis of comprehensive performance of beam pumping unit

The beam pumping unit has the characteristics of simple structure, reliability and durability. It is the most widely used artificial lifting method in oil fields worldwide. However, the inherent defects of the 4-bar linkage structure of the beam pumping unit result in high impact, low system efficiency and large motor rated power. In order to improve the efficiency of the pumping unit system and make full use of the inertial load of the moving parts, we established the dynamic model and optimization method of the variable speed drive pumping unit. This paper uses theoretical analysis, programming calculation and experimental research to complete the optimization calculation of variable speed of beam pumping unit, the calculation results show that the appropriate variable speed operation scheme can improve the system efficiency and power saving rate, reduce the motor power peak and torque peak, and reduce the crankcase torque peak and the suspension point load peak. Application results in oilfields show that the variable speed optimization technology can improve the comprehensive performance of the pumping well system, increase production, reduce energy consumption and improve safety.

Transformation of academic teaching and research: Development of a highly automated experimental sucker rod pumping unit

Sucker rod pumps are one of the most popular solutions for artificial lift since their inception in the 19th century with minimum changes in design. Presently, companies are deploying digital technology in the field and, there has been a big push for a networked oilfield in recent years. This means technology is now able to control machines in remote places, evaluate their performances and control safety operating parameters. But these digital solutions are still not available in universities, causing a technological and technical gap for students and researchers.This study presents a prototype of a new dedicated Interactive Digital Sucker Rod Pumping Unit (ID-SRP) system at the University of Oklahoma with representative operating conditions. The prototype mimics sucker rod pump working principles and also imitates different realistic rod string motions. The application and solutions are focused on providing authentic learning experiences for petroleum engineers. The system is also designed to address and optimize SRP well performance and safety through Model Predictive Controller (MPC) implementation and meeting industrial requirements. It connects the physical and virtual interaction with learning technologies. The objective is to bridge the tangible and the abstract for a better understanding of sucker rod concept and implement existing theories into the digital system. Additionally, it aids our future petroleum engineers on how to apply basic industry principles and upsurge their problem-solving skills.The developed unit is capable of simulating any situations in real time and using Internet of Things (IoT) for data acquisition to create tailored diagnostic tools that students and laboratory staff can utilize. The software selected for the system is LabVIEW, which controls all the necessary equipment. This system can build personalized dynocard graphs, intake live data and export them to other programs live Excel, MATLAB, Python or any other programming languages.

Research on energy saving of Coalbed Methane Field pumping wells based on Data Mining

Generally, the CBM well has the characteristics of large variation of the water rate and unstable pumping load, corresponding equipment type, status and parameters adjusted frequently, the utilization rate of energy is generally low, however, the energy transfer relationship of pumping unit system is complex and the coupling between parameters is strong, the theoretical calculation method requires high energy consumption calculation parameters for each node, and the effective dynamic analysis cannot be realized; the experience analysis method has high workload and high requirement for analysts. In southern Qinshui basin CBM Wells, for example, by analyzing the relationship between production parameters and the energy consumption of each node, a multi variable data mining algorithm is constructed for the energy consumption index of the common pumping unit system, according to the energy consumption data characteristics of pumping unit, the single well is classified, and the adjustment optimization strategy of pump replacement, pumping-unit replacement, intermittent pumping and equipment maintenance is put forward according to the different types of energy consumption bias. Verified by practice, the application of this technology can improve the timeliness and accuracy of energy consumption data analysis of CBM pumping well, effectively reduce the cost of energy consumption analysis on mechanical production Wells, and is helpful to improve the intelligent level of CBM gas field production.

A Novel UKF-RBF Method Based on Adaptive Noise Factor for Fault Diagnosis in Pumping Unit

Fault detection and diagnosis in the pumping unit is a challenging industrial problem for the system that exhibits nonlinearity, coupled parameters, and time-varying noise. This paper proposes a novel combined unscented Kalman filter (UKF) and radial basis function (RBF) method based on an adaptive noise factor for fault diagnosis in the pumping unit. First, to reduce computation and complexity of the diagnosis model, the Fourier descriptor method based on an approximate polygon is presented to extract the features of the indicator diagram. RBF neural network is adopted to establish the fault diagnosis model based on indicator diagram data and production data. In particular, UKF is used to train the weights ( $w_{m,l}$ ), the center ( $c_{m}$ ), and the width ( $b_{m}$ ) of the RBF model. Furthermore, the adaptive noise factor method is proposed to address the adaptive filtering issue in the fault diagnosis model. The proposed method is applied to the pumping unit system, and experimental results show the effectiveness and favorable recognition rate in classifying multiple faults.

Fault Diagnosis Method Based on Dynamic Axis Nucleation KPLS for Pumping Unit

Fault diagnosis of pumping unit system has long been a challenging issue owing to the system that exhibits nonlinearity, coupled parameters and time-varying in the production process. In this paper, a novel fault diagnosis method based on dynamic axis nucleation kernel partial least squares (DANKPLS) is proposed for pumping unit. First, the multiple dichotomous regression (MDR) model is established to reflect the hidden dynamic relationship between variables efficiently. Then, a novel axis nucleation kernel partial least squares method is proposed to map the principal axis into a high-dimensional space. In particular, the correlation of the data can be further and clearly represented. Finally, the proposed method is applied to the pumping unit system. Experimental results show the effectiveness and favorable diagnosis rate in false alarm and missing alarm.

Pumping Unit Suspension Point Direction Balance Theory Analysis Method and Effect Evaluation

In order to reduce the adverse effect of suspension point dynamic load on pumping unit system, according to the suspension point balance principle of conventional type pumping unit, the suspension point direction balance designing scheme is determined. Take CYJ10-3-37HB pumping unit as research object. Establish the virtual prototype simulation analysis model of conventional pumping unit by suspension point direction balance before and after the balance. Through the contrastive analysis of simulation results, the effect of load reduction and energy saving after the pumping unit by suspension point direction balance is determined. The simulation results show that the reduce rate of pumping unit maximum polished rod load is 29.4%, the reduce rate of RMS torque is 15.8%, the load reduction and energy saving effect of suspension point direction balance is obviously. It laid a theoretical basis for the suspension point direction balance device in engineering practice application.

The Energy Saving Pumping Unit System Design and Analysis

With the development of oil field production demand today, pumping unit is developing towards the direction of energy saving, intelligent. According to the present status of the oilfield, this paper designed a kind of intelligent energy saving pumping unit system, the system acceleration and deceleration process is very short, most of their working time in uniform motion in a stroke, and the beam pumping unit has been alternating deceleration process all the time compared with good energy saving effect. Energy store system is designed, the system not only reduces energy consumption, and make the motors can be started with initial velocity, shorten the motor start-up time, the motor starting current is stable running current of 4 to 7 times, so that reduces the starting current impact. To test this idea, modeling of motor, and the simulation analysis, the results confirmed the idea very well. Finally, in the principle of the pumping unit system prototype experiments, the experimental results show that the pumping unit system has significant energy-saving effect and the intelligent characteristics.

Based on Orthogonal Experiment Method PID Simulation Control of Pumping Unit

To study control accuracy of pumping unit system and improve dynamic performance, after ensure every influencing factor, carried out orthogonal test. Permanent magnet synchronous motor of direct torque control was used to model and simulate with experiment parameters based on Matlab/Simulink software, analyzed optimal PID parameter, and can avoid mass and complex test that determine PID parameter combination. The simulation results indicate that it can increase control accuracy clearly and decrease response time, and can reach optimum system performance. Results of simulation analysis have some certain practical value for pumping unit driven by permanent magnet synchronous motor of direct torque control.

Simulation Study on Virtual Prototype of Pumping Well System

The virtual prototype simulation of the underground pumping system can’t realize the timing analysis with the ground pumping unit system. In order to solve this problem, the simulation analysis model of the pumped well virtual prototype was established via the multibody dynamics simulation software Adams by analyzing the working characteristic of the sucker rod string. The simulation was in accordance with the dynamic indicator diagram which verifies the correctness of the simulation analysis model of the pumped well virtual prototype and also offers a new analysis method for the underground pump dianamograph and pumping unit balance, etc.

Research on Power Saving Positive Torque and Constant Power Pumping Unit and Tracking Technique System

Based on the analysis of the negative torque of the common beam pumping unit resulting in lower system efficiency, energy consumption, load alternating amplitude, poor working conditions, the theory of pumping unit with positive torque is proposed, a dynamic model is established, a structure is invented, constant power of intelligent control technology and electrical-line monitoring evaluation technology are studied and positive torque constant power pumping system supporting technology is formed. What's more, a prototype is developed and carried out for laboratory and field tests, developing the data of the positive torque and constant power in the field work. These tests prove the correctness of the theory and the feasibility of the technology. A number of indicators of the installed power, energy consumption size and weight have reduced over 30% compared with the original wells, obtaining good effect of a significant energy saving with positive pumping torque.

Design Research on Working Mechanism of Beam Pumping Unit

Based on the unique geometry and mechanical movement of beam pumping unit, this paper presented a simple swing equation and computed motorial parameter, meanwhile under the conditions of the static load and inertial load of the polished-rod of a conventional pumping unit, it also presented an equivalent dynamic model of the pumping unit system and the type-curves of net torque of the crankshaft with the characteristic of inertial counterbalance having been computed, the model can provide a theoretical base for study on the other transient working parameters of beam pumping unit. Being satisfied with motion accuracy and boundary constraints, the optimization model of beam pumping unit is established. The simulated annealing algorithm with penalty strategy is adopted to solve the optimal model, so that optimization process was simplified and the global optimal solution is ensured reliably.