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.

Adoption of Solar Pumping Systems by Vegetable Farmers in Niayes Agro-Ecological Zone of Senegal: Adoption as a Sequential Process

This article examines the determinants of the adoption of solar pumping systems (PV) by vegetable farmers in the Niayes area of Senegal. To measure the determinants, we used a sequential logit model to translate the adoption process from becoming aware of solar pumping systems to testing them, i.e. using them at least once, and then continuing to use them over time. The results show that the main variables affecting awareness of the use of solar pumping systems (PV) are age, marital status, experience, access to credit, the farmer’s knowledge of climate change, the farmer’s origin in the Thiès region and length of time in the Niayes area. The first use of PVs is influenced by factors such as the size of the plot, the distance of the plot from the main road or from the market. Finally, the decision to adopt or continue use is influenced by gender, experience, household size and access to credit. Surprisingly, access to credit does not affect the first use of solar pumping systems, but plays a key role in their continued use.

Comparative Study of the Types of Photovoltaic Panels Used in Solar Pumping Systems in Dry Tropical Zones: Case of Adamawa Region in Cameroon

In the dry tropical zone where access to water is increasingly difficult for populations, solar pumping units are increasingly installed to provide water to population. In the local market, there are essentially two types of solar panels, namely monocrystalline and polycrystalline. However, the part of the local market is more dominated by the polycrystalline panel. In this work, comparative studies are carried out in order to characterize the two types of solar panels with regard to local constraints. Tests were carried out over the course of the sun to establish the performance of each type. The panels used have the same electrical characteristics and are connected to loads with same characteristics. Under the set operating conditions, the monocrystalline panel presents more performance than the polycrystalline panel. Although the local market is dominated by the polycrystalline panel, dust deposition tests on the surface of the panels show that the performance of the polycrystalline panel is more affected compared to the performance of the monocrystalline panel.

Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

Fault diagnosis for down-hole conditions of sucker rod pumping systems based on the FBH-SC method

Dynamometer cards are commonly used to analyze down-hole working conditions of pumping systems in actual oil production. Nowadays, the traditional supervised learning methods heavily rely on the classification accuracy of the training samples. In order to reduce the errors of manual classification, an automatic clustering algorithm is proposed and applied to diagnose down-hole conditions of pumping systems. The spectral clustering （SC） is a new clustering algorithm, which is suitable for any data distribution. However, it is sensitive to initial cluster centers and scale parameters, and needs to predefine the cluster number. In order to overcome these shortcom- ings, we propose an automatic clustering algorithm, fast black hole-spectral clustering （FBH-SC）. The FBH algo- rithm is used to replace the K-mean method in SC, and a CritC index function is used as the target function to automatically choose the best scale parameter and clus- tering number in the clustering process. Different simulation experiments were designed to define the relationship among scale parameter, clustering number, CritC index value, and clustering accuracy. Finally, an example is given to validate the effectiveness of the proposed algorithm.

Dynamic simulation and efficiency analysis of beam pumping system

An improved whole model of beam pumping system was built. In the detail, for surface transmission system(STS), a new mathematical model was established considering the influence of some factors on the STS's torsional vibration, such as the time variation characteristic of equivalent stiffness of belt and equivalent rotational inertia of crank. For the sucker rod string(SRS), an improved mathematical model was built considering the influence of some parameters on the SRS's longitudinal vibration, such as the nonlinear friction of plunger, hydraulic loss of pump and clearance leakage. The dynamic response and system efficiency of whole system were analyzed. The results show that there is a jumping phenomenon in the amplitude frequency curve, and the system efficiency is sensitive to motor power, pump diameter, stroke number, ratio of gas and oil, and submergence depth. The simulation results have important significance for improving the efficiency of beam pumping system.

Novel sucker rod pumping system based on linear motor technology

Obtaining petroleum at the cost of electrical energy is a common problem in almost all oil fields, and it is mainly caused by low duty radio of induction motor used in beam pumping units. Traditional beam-pumping units have many intrinsic disadvantages such as low efficiency, complex transmission devices, poor flexibility, tremendous volume and weight in long stroke, etc.Therefore, a novel direct driven linear electromagnetic pumping unit (EMPU) has been developed by combining oil extraction technology with linear motor technology. The thrust of EMPU matches the changing of suspension center load to improve the system efficiency and cut down the consumption of energy. Based on previous experience, a small-scale prototype was developed and a simulation was conducted with it. Both theoretical analyses and experimental study showed that the problems exiting in beam pumping units can be solved with EMPU system, and this is a new method which can be used to solve high energy waste in oil fields.

ENERGY-SAVING MATCHING STRATEGY AND EXPERIMENTAL STUDY OF PUMPING SYSTEM FOR TRUCK-MOUNTED CONCRETE PUMP

Aiming at the high fuel consumption and use-cost of truck-mounted concrete pump , an energy-saving matching strategy of pumping system is presented and the experimental study is conducted.Since pumping system occupies most resources of engine , the matching strategy between engine and main pump is analyzed to meet the load demand and reduce the engine rational speed drop.The testing method is established to measure the fuel consumption of engine under various working conditions , and the experimental data are analyzed to find the law of the fuel consumption of engine.The system performance can be improved by adjusting the system input value.Finally , the energy-saving matching strategy is established to reduce the fuel consumption of truck for unit workload , which provides a new approach for the energy-saving of truck-mounted concrete pump.

DYNAMIC MATHEMATICAL MODELING AND APPLICATION FOR PUMPING SYSTEM PERFORMANCE INTEGRATED EVALUATION

A mathematical model is set to evaluate the overall centrifugal pumpingsystem using asynchronous motor as power. This method can be used to affirm system performanceaccording the transform and the aberrance of interior parameters and exterior performance curves soas to give a reference to the equipment amelioration. The analysis of emulation experiment datasuggests the model is effectively used.

Comprehensive Study,Design and Economic Feasibility Analysis of Solar PV Powered Water Pumping System

The energy efficient product can be operated with longer duration.They offer wonderful solutions compared to other conventional water pumping system as it needs less maintenance,simple in installation,zero fuel cost,longer operating life,highly reliable and free from production of greenhouse gases.In this paper we analyzed the different topologies of DC–DC converter in terms of their operating region of MPPT,quality of input and output currents.We discussed the MPPT algorithms to address partial shading effects in SPV array,present state of the technology,factors affecting the performance of the system,efficiency improvements and identified the research gaps.Also,the economic feasibility analysis has been done for the real time scenario using the Homer Pro software.The estimation of total dynamic head and horse power calculation has been done to decide the total load capacity.The economic analysis results such as cumulative cash flow over project lifetime of 25 years are presented.It is observed that the capital investment requirement is$7,425 for installing Fronius PV system that has a nominal capacity of 2.47 kW and annualized savings will be$134.93.In the long-term perspective,the return on investment is−2.18%as per the present tariff plan.

Optimised Design and Analysis of Solar Water Pumping Systems for Pakistani Conditions

This paper is about the optimized design and analysis of two solar water pumping systems in which one of the systems is designed with a battery bank and other with a cylindrical water tank for a selected site in Pakistan. The design, sizing, cost analysis and steady state analysis of the proposed systems were done in HOMER and dynamic analysis of the designed system with battery bank was performed in MATLAB/Simulink. The simulations performed in HOMER involved proper mapping of the loads which helped to evaluate the PV panel requirement, inverter rating, batteries (in case of battery based solution), modeling of water tank as a deferrable load (in case of solution based of water tank) and detailed cost analysis for a life time of 25 years. To verify the design of the solar water pumping system with battery bank, a simulation in MATLAB/Simulink for study of dynamic behavior of the overall system was performed which involved mathematical modeling of a PV panel, buckboost converter, inverter, battery bank and motor/pump, a perturb and observe maximum power point tracking algorithm based control system. Analysis was conducted based on the economic results that indicate designed solar water pumping system with water tank would be a cheaper solution as compared to solar water pumping system with a battery bank. This work can be taken as a case study for the understanding and optimized designs of solar water pumping system with battery bank and with cylindrical tank in Pakistani conditions.

Development and Application of a Shaft-type Tubular Pumping System with a Siphon Discharge Passage

Based on the characteristics of large flow rate , low head , short annual operation time , and high reliability of the city flood-control pumping stations , a new-type shaft tubular pumping system featuring a shaft suction box and a siphon-type discharge passage with a vacuum breaker as the cutoff device was developed , which possesses such advantages as simple structure , reliable cutoff , and high energy performance.Taking some pumping stations as the case studies , in the light of the specified operation conditions , the hydraulic optimal design of the shaft-type tubular pumping system was determined and the optimized shape of the system was recommended.The performance prediction based on the computational fluid dynamics methodology was determined and the model test verification was conducted.The results show that the predicted data agree with the experimental head and efficiency so that both methods can be used to determine the performance of a real pumping station.Finally , the in-situ measurements of a pumping station during the commissioning period further verified that the shaft-type tubular pumping station with a siphon discharge passage is of higher efficiency , more reliable and stable.

Approach to the Design Calculation of Sucker Rod Pumping Systems in Coalbed Methane Wells

The existing design of the pumping systems mainly focuses on the approximate computational formulae and procedures,which are developed based on the analytic approaches of conventional oil/gas fields.The calculation of polished rod loads usually just concerns about the static and inertial loads.And the computation of gearbox torque generally uses empirical formulae and correction factors.The above modeling procedures,if applied to the coalbed methane（CBM） wells,can not give the desired accuracy of the system design and its pertinent analysis.In this paper,based on the kinematic and dynamic analysis of the pumping system,the kinematic relation of polished rod is analyzed,and the variation of the total loads of polished rod is developed with the limits of CBM well conditions along the string.The gearbox torque calculation model is established by combining the counterbalance effect with the calculated dynamometer cards and torque factors.The application characteristics of this model are demonstrated by the example of ZH002-4 well in Qinshui basin.The interpretations of results show that the cranks of beam units should rotate in a counter clockwise direction viewed with the wellhead to the right.Compared with oil？gas fields,the dynamic and friction to polished rod load ratios are relatively high and the computation of polished rod loads should involve the static and inertial loads,as well as vibration and friction loads.And the dynamic load ratio decreases rapidly during the production.Besides,the total deformation of the string is small in CBM wells.As for balanced operation,the gearbox torque load usually has two approximately equal peaks and the magnitudes of instantaneous torque are just within 50% of unbalanced gearbox loadings.The proposed research improves efficiency of the pumping system,loads the pumping unit more uniformly,and provides the reasonable basis for selecting the units.

A new diagnostic method for identifying working conditions of submersible reciprocating pumping systems

The submersible pumping unit is a new type of pumping system for lifting formation fluids from onshore oil wells, and the identification of its working condition has an important influence on oil production. In this paper we proposed a diagnostic method for identifying the working condition of the submersible pumping system. Based on analyzing the working principle of the pumping unit and the pump structure, different characteristics in loading and unloading processes of the submersible linear motor were obtained at different working conditions. The characteristic quantities were extracted from operation data of the submersible linear motor. A diagnostic model based on the support vector machine （SVM） method was proposed for identifying the working condition of the submersible pumping unit, where the inputs of the SVM classifier were the characteristic quantities. The performance and the misjudgment rate of this method were analyzed and validated by the data acquired from an experimental simulation platform. The model proposed had an excellent performance in failure diagnosis of the submersible pumping system. The SVM classifier had higher diagnostic accuracy than the learning vector quantization （LVQ） classifier.

Calculation of dynamic loads of the sucker rod pumping system in CBM wells

The mathematical model of dynamic loads was developed based on an analysis of the polished rod load of beam pumps, and the variation of the dynamic loads and the computation of the minimum and maximum limits during a complete pumping cycle were given out by solving the model.Field examples verify that it is necessary to take into account the inertial and vibration loads while calculating polished rod loads.During the prophase of the pumping production, the dynamic to polished rod load ratio is relatively large.Then the ratio decreases rapidly and becomes small after entering stable production.Moreover, the total deformation of rod and tubing in CBM wells is much smaller than that in oil fields, and the deformation caused by the dynamic loads is also relatively small.The result of this work is the calculation of the dynamic loads.The application of this calculation for the sucker rod pumping system in CBM wells can give the desired accuracy of polished rod load and the dynamometer cards, which provides a reasonable basis for the design and selection of beam pumps.

Design and Description of a Photovoltaic Pumping System： Application in the Site of Adrar

The Saharan areas and in particular the isolated sites are characterized by low levels of population, in dispersed cores, which suffer from serious problems of water supply for consumption and the irrigation. The photovoltaic pumping systems （PV） are an ideal solution for these problems. Despite the presence of several photovoltaic pumping systems （PVPS） projects, data acquisition system is still missing in most cases. In this work, the authors will present the PVPS installed at the unit of research in renewable energies in Saharan medium （URERMS, Algeria）. This system will enable us to better analyze the performances ofa photovoltaic pumping system in Saharan medium. The principal elements of the chain of the photovoltaic pumping system are： a photovoltaic generator, the power conditioning system, a motor-driven pump immersed group, an electric wiring, a hydraulic infrastructure which comprises a water tank.

Electrokinetic pumping system based on nanochannel membrane for liquid delivery

Nonmechanical pumping of liquids is of key importance for applications from the biomedical microfluidic chip to drug delivery systems. In this paper, a new electrokinetic pump （EOP） system with polycarbonate nanoehannel membrane sandwiched between two membrane holders was constructed. The pump was tested with water and phosphate buffer at 1-6 V applied voltage, the maximum pressure and flow rate are 0.32 MPa （3.2 atm） and 4.2 μL/min for phosphate buffer, respectively. This proof-of-concept pump shows its potential use for drugs or chemical agents delivery by the usage of different membrane materials.

Dynamic Modelling of Submersible Pump Based Solar Water-Pumping System with Three-Phase Induction Motor Using MATLAB

The main purpose of this paper is to design and model a water-pumping system using a submersible multi-stage centrifugal pump driven by a three-phase induction motor. The system is intended for pumping water to the surface from a deep well using three power supply systems: a general network, a photo-voltaic (PV) system, and a PV system with a battery bank. These systems are used to compare two three-phase induction motors—namely, a motor with a drive and another one without a drive. The systems dynamic models are simulated in MATLAB/Simulink and the results compared with the manufacturer’s data for validation purposes. The simulation results generally show system dynamics and expected performance over a range of operation.

Robust <i>H</i>_∞Observer-Based Tracking Control for the Photovoltaic Pumping System

In this paper, we propose a H∞ robust observer-based control DC motor based on a photovoltaic pumping system. Maximum power point tracking is achieved via an algorithm using Perturb and Observe method, with array voltage and current being used to generate the reference voltage which should be the PV panel’s operating voltage to get maximum available power. A Takagi-Sugeno (T-S) observer has been proposed and designed with non-measurable premise variables and the conditions of stability are given in terms of Linear Matrix Inequality (LMI). The simulation results show the effectiveness and robustness of the proposed method.

Pumping System Analysis for Upgrading Works in a Government Owned Water Treatment Plant in Malaysia

Pumping system analysis can be used together with a decision support system to provide information for efficient pumping system operation or system refurbishment and upgrading.The actual operation condition of the water supply system needs to be ascertained.This paper will share experience by the authors in determining the actual pump performance through measurement of flow and pressure in the system.The incremental increase in pressure is achieved by varying head loss induced to the system by valve throttling.Integrating the Bernoulli’s principles of the geodetic,static and dynamic energy,and input power data will enable the analysis of energy input and output and hence arriving to pump efficiency values.This method offers the most accurate operation conditions for refurbishment systems to endure.The on-site measurements will allow the determination of the averaged actual friction coefficient which includes the effect of system deterioration and fittings conditions.This information will be used to determine the expected duty point of an upgrading system more precisely.The study highlighted the actual pump operating efficiencies for an old pumping system installation.