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.

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.

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.

Pumpingline管道预制与安装研究——以2023 SH 二次配Pumping-line工程项目为例

本文以中芯南方集成电路制造有限公司负责的2023?SH?二次配Pumping-line工程项目为例,首先对Pumping line管道预制与安装流程进行了简单介绍。在此基础上,本文围绕机台Pumping line会勘、Pumping line管道测量绘图作业、Pumping line管道的预制与现场安装作业要素、机台Monve-in定位后Hook up相关作业要素等展开分析,希望为相关从业人员提供一定的参考。

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.

Factors of Pumping Capacity in Some Different Types of Channel Brownian Pumps

The motion of particles in different channel Brownian pumps can be described by Langevin equations,and the pumping capacity is a useful indicator to demonstrate the strength of a pump’s transportation ability.Via the simulation,there is always an optimal value of temperature and unbiased external force for different pumps which make the concentration ratio between the right tube and left tube derive its maximum and minimum in two asymmetric tubes respectively.Besides,the concentration ratio will keep 1 regardless of radius,temperature or magnitude of force in the tube in a symmetric tube.To obtain more information about pumping capacity,exploring the average probability current(APC) of tubes in different conditions is necessary.Results indicate that as the concentration ratio is 1,the change of the APC when x_(0)=0 is similar to that when x_(0)=π.Also,when the concentration ratio is more than 1,there are optimal values of temperature,radius and magnitude of force where the APC gains a maximum,and the maximum decreases as the concentration in the right tube increases when x_(0)=0.

Spin pumping by higher-order dipole-exchange spin-wave modes

Spin pumping(SP)and inverse spin Hall effect(ISHE)driven by parametrically-excited dipole-exchange spin waves in a yttrium iron garnet film have been systematically investigated.The measured voltage spectrum exhibits a feature of the field-induced transition from parallel pumping to perpendicular pumping because of the inhomogeneous excitation geometry.Thanks to the high precision of the SP-ISHE detection,two sets of fine structures in the voltage spectrum are observed,which can correspond well to two kinds of critical points in the multimode spin-wave spectrum for magnetic films.One is the q=0 point of each higher-order dispersion branch,and the other is the local minimum due to the interplay between the dipolar and exchange interactions.These fine structures on the voltage spectrum confirm the spin pumping by higher-order dipole-exchange spin-wave modes,and are helpful for probing the multimode spin-wave spectrum.

A cladding-pumping based power-scaled noise-like and dissipative soliton pulse fiber laser

We report a high-average-power noise-like pulse(NLP) and dissipative soliton(DS) pulse fiber laser. Average power as high as 4.8 W could be obtained at the fundamental mode-locked repetition rate. The NLP can also be transformed into a more powerful DS mode-locking state by optimizing the polarization and losses of intra-cavity pulses in the nonlinear polarization evolution regime. The operation mode between the NLP and DS can be switched, and the laser output performance in both modes has been studied. The main advantage of this work is switchable high-power operation between the NLP and DS. In comparison with conventional single-mode NLP fiber lasers, the multi-function high-power optical source will greatly push its application in supercontinuum generation, coherence tomography, and industrial processing.

An NMOS output-capacitorless low-dropout regulator with dynamic-strength event-driven charge pump

In this paper,an NMOS output-capacitorless low-dropout regulator(OCL-LDO)featuring dual-loop regulation has been proposed,achieving fast transient response with low power consumption.An event-driven charge pump(CP)loop with the dynamic strength control(DSC),is proposed in this paper,which overcomes trade-offs inherent in conventional structures.The presented design addresses and resolves the large signal stability issue,which has been previously overlooked in the event-driven charge pump structure.This breakthrough allows for the full exploitation of the charge-pump structure's poten-tial,particularly in enhancing transient recovery.Moreover,a dynamic error amplifier is utilized to attain precise regulation of the steady-state output voltage,leading to favorable static characteristics.A prototype chip has been fabricated in 65 nm CMOS technology.The measurement results show that the proposed OCL-LDO achieves a 410 nA low quiescent current(IQ)and can recover within 30 ns under 200 mA/10 ns loading change.

An LED-Side-Pumped Intracavity Frequency-Doubled Nd,Ce:YAG Laser Producing a 2W Q-Switched Red Beam

We report a high-average-power acousto-optic(AO)Q-switched intracavity frequency-doubled red laser based on a high-efficiency light-emitting-diode(LED)pumped two-rod Nd,Ce:YAG laser module.Under quasi-continuous wave operation conditions,a maximum output power of 1319.08 nm wavelength was achieved at 11.26 W at a repetition rate of 100 Hz.

Wear dependent virtual flow rate sensor for progressing cavity pumps with deformable stator

This contribution presents a novel wear dependent virtual flow rate sensor for single stage single lobe progressing cavity pumps. We study the wear-induced material loss of the pump components and the impact of this material loss on the volumetric efficiency. The results are combined with an established backflow model to implement a backflow calculation procedure that is adaptive to wear. We use a laboratory test setup with a highly abrasive fluid and operate a pump from new to worn condition to validate our approach. The obtained measurement data show that the presented virtual sensor is capable of calculating the flow rate of a pump being subject to wear during its regular operation.

Research on Feature Extraction Method for Low-Speed Reciprocating Bearings Based on Segmented Short Signal Modulation Signal Bispectrum Slicing

Bearing condition monitoring and fault diagnosis (CMFD) can investigate bearing faults in the early stages, preventing the subsequent impacts of machine bearing failures effectively. CMFD for low-speed, non-continuous operation bearings, such as yaw bearings and pitch bearings in wind turbines, and rotating support bearings in space launch towers, presents more challenges compared to continuous rolling bearings. Firstly, these bearings have very slow speeds, resulting in weak collected fault signals that are heavily masked by severe noise interference. Secondly, their limited rotational angles during operation lead to a restricted number of fault signals. Lastly, the interference from deceleration and direction-changing impact signals significantly affects fault impact signals. To address these challenges, this paper proposes a method for extracting fault features in low-speed reciprocating bearings based on short signal segmentation and modulation signal bispectrum (MSB) slicing. This method initially separates short signals corresponding to individual cycles from the vibration signals based on encoder signals. Subsequently, MSB analysis is performed on each short signal to generate MSB carrier-slice spectra. The optimal carrier frequency and its corresponding modulation signal slice spectrum are determined based on the carrier-slice spectra. Finally, the MSB modulation signal slice spectra of the short signal set are averaged to obtain the overall average feature of the sliced spectra.

Dual-wavelength pumped latticed Fermi-Pasta-Ulam recurrences in nonlinear Schrödinger equation

We show that the nonlinear stage of the dual-wavelength pumped modulation instability(MI)in nonlinear Schrödinger equation(NLSE)can be effectively analyzed by mode truncation methods.The resulting complicated heteroclinic structure of instability unveils all possible dynamic trajectories of nonlinear waves.Significantly,the latticed-Fermi-Pasta-Ulam recurrences on the modulated-wave background in NLSE are also investigated and their dynamic trajectories run along the Hamiltonian contours of the heteroclinic structure.It is demonstrated that there has much richer dynamic behavior,in contrast to the nonlinear waves reported before.This novel nonlinear wave promises to inject new vitality into the study of MI.

Research on Cavitation Characteristics and Influencing Factors of Herringbone Gear Pump

Cavitation is a common issue in pumps,causing a decrease in pump head,a fall in volumetric efficiency,and an intensification of outlet flow pulsation.It is one of the main hazards that affect the regular operation of the pump.Research on pump cavitation mainly focuses on mixed flow pumps,jet pumps,external spur gear pumps,etc.However,there are few cavitation studies on external herringbone gear pumps.In addition,pumps with different working principles significantly differ in the flow and complexity of the internal flow field.Therefore,it is urgent to study the cavitation characteristics of external herringbone gear pumps.Compared with experimentalmethods,visual research and cavitation area identification are achieved through computation fluid dynamic(CFD),and changing the boundary conditions and shape of the gear rotor is easier.The simulation yields a head error of only 0.003%under different grid numbers,and the deviation between experimental and simulation results is less than 5%.The study revealed that cavitation causes flow pulsation at the outlet,and the cavitation serious area is mainly distributed in the meshing gap and meshing area.Cavitation can be inhibited by reducing the speed,increasing the inlet pressure,and changing the helix angle can be achieved.For example,when the inlet pressure is 5 bar,the maximumgas volume fraction in themeshing area is less than 50%.These results provide a reference for optimizing the design and finding the optimal design parameters to reduce or eliminate cavitation.

A Numerical Study on the Effect of the Backflow Hole Position on the Performances of a Self-Priming Pump

A self-priming pump is a centrifugal pump that has the ability to prime itself. Typically, its performance dependson the configuration of its reflux hole. In this study, the ANSYS FLUENT software is used to investigate the effectsof three different radial positions of the reflux hole on gas-liquid two-phase distribution, pressure pulsation, andimp during self-priming. The research results indicate that: (1) The effective channel size for the reflux liquid toenter the volute varies depending on the location of the reflux hole. The effect of the impeller rotation on thereflux liquid becomes more obvious as the setting distance of the reflux aperture decreases. (2) The position ofthe reflux hole significantly affects the gas phase mass fraction inside the impeller, resulting in a significant reductionin the time it takes for the mass fraction to exceed 80%. (3) The position of the reflux hole significantly affectsthe average pressure on each monitoring surface. (4) Placing the reflux hole at a excessively distant radial distancecan result in an excessive vertical component. (5) The self-priming performance of the pump can be improved tosome extent by placing the return hole at a small radial distance.

Overlapping approach Proton Pump Inhibitors/Nux vomica-Heel as new intervention for gastro-esophageal reflux management:Delphi consensus study

BACKGROUND Gastro-esophageal reflux disease(GERD)may affect the upper digestive tract;up to 20%of population in Western nations are affected by GERD.Antacids,histamine H2-receptor antagonists,and Proton Pump Inhibitors(PPIs)are considered the referring medications for GERD.Nevertheless,PPIs must be managed carefully because their use,especially chronic,could be linked with some adverse effects.An effective and safe alternative pharmacological tool for GERD is needed.After the identification of potentially new medications to flank PPIs,it is mandatory to revise and improve good clinical practices even through a consensus process.AIM To optimize diagnosis and treatment guidelines for GERD through a consensus based on Delphi method.METHODS The availability of clinical studies describing the action of the multicomponent/multitarget medication Nux vomica-Heel,subject of the consensus,is the basic prerequisite for the consensus itself.A modified Delphi process was used to reach a consensus among a panel of Italian GERD specialists on the overlapping approach PPIs/Nux vomica-Heel as a new intervention model for the management of GERD.The Voting Consensus group was composed of 49 Italian Medical Doctors with different specializations:Gastroenterology,otolaryngology,geriatrics,and general medicine.A scientific committee analyzed the literature,determined areas that required investigation(in agreement with the multiple-choice questionnaire results),and identified two topics of interest:(1)GERD disease;and(2)GERD treatment.Statements for each of these topics were then formulated and validated.The Delphi process involved two rounds of questioning submitted to the panel experts using an online platform.RESULTS According to their routinary GERD practice and current clinical evidence,the panel members provided feedback to each questionnaire statement.The experts evaluated 15 statements and reached consensus on all 15.The statements regarding the GERD disease showed high levels of agreement,with consensus ranging from 70%to 92%.The statements regarding the GERD treatment also showed very high levels of agreement,with consensus ranging from 90%to 100%.This Delphi process was able to reach consensus among physicians in relevant aspects of GERD management,such as the adoption of a new approach to treat patients with GERD based on the overlapping between PPIs and Nux vomica-Heel.The consensus was unanimous among the physicians with different specializations,underlying the uniqueness of the agreement reached to identify in the overlapping approach between PPIs and Nux vomica-Heel a new intervention model for GERD management.The results support that an effective approach to deprescribe PPIs through a progressive decalage timetable(reducing PPIs administration to as-needed use),should be considered.CONCLUSION Nux vomica-Heel appears to be a valid opportunity for GERD treatment to favor the deprescription of PPIs and to maintain low disease activity together with the symptomatology remission.

Optimal Design of High-Speed Partial Flow Pumps using Orthogonal Tests and Numerical Simulations

To investigate the influence of structural parameters on the performances and internal flow characteristics of partial flow pumps at a low specific speed of 10000 rpm,special attention was paid to the first and second stage impeller guide vanes.Moreover,the impeller blade outlet width,impeller inlet diameter,blade inclination angle,and number of blades were considered for orthogonal tests.Accordingly,nine groups of design solutions were formed,and then used as a basis for the execution of numerical simulations(CFD)aimed at obtaining the efficiency values and heads for each design solution group.The influence of impeller geometric parameters on the efficiency and head was explored,and the“weight”of each factor was obtained via a range analysis.Optimal structural parameters were finally chosen on the basis of the numerical simulation results,and the performances of the optimized model were verified accordingly(yet by means of CFD).Evidence is provided that the increase in the efficiency and head of the optimized model was 12.11%and 23.5 m,respectively,compared with those of the original model.

Clogging caused by coupled grain migration and compaction effect during groundwater recharge for unconsolidated sandstone reservoir in groundwater-source heat pump

In unconsolidated sandstone reservoirs,presence of numerous movable grains and a complex grain size composition necessitates a clear understanding of the physical clogging process for effective groundwater recharge in groundwater-source heat pump systems.To investigate this,a series of seepage experiments was conducted under in situ stress conditions using unconsolidated sandstone samples with varying grain compositions.The clogging phenomenon arises from the combined effects of grain migration and compaction,wherein the migration of both original and secondary crushed fine-grain particles blocks the seepage channels.Notably,grain composition influences the migration and transport properties of the grains.For samples composed of smaller grains,the apparent permeability demonstrates a transition from stability to decrease.In contrast,samples with larger grains experience a skip at the stability stage and directly enter the decrease stage,with a minor exception of a slight increase observed.Furthermore,a unique failure mode characterized by diameter shrinkage in the upper part of the sample is observed due to the combined effects of grain migration and in situ stress-induced compaction.These testing results contribute to a better understanding of the clogging mechanism caused by the coupled effects of grain migration and compaction during groundwater recharge in unconsolidated sandstone reservoirs used in groundwater-source heat pump systems.

Experimental Analysis of Radial Centrifugal Pump Shutdown

Centrifugal pumps are widely used in the metallurgy,coal,and building sectors.In order to study the hydraulic characteristics of a closed impeller centrifugal pump during its shutdown in the so-called power frequency and frequency conversion modes,experiments were carried to determine the characteristic evolution of parameters such as speed,inlet and outlet pressure,head,flow rate and shaft power.A quasi-steady-state method was also used to further investigate these transient behaviors.The results show that,compared to the power frequency input,the performance parameter curves for the frequency conversion input are less volatile and smoother.The characteristic time is longer and the response to shutdown is slower.The quasi-steady-state theoretical head-flow curves match the experimental head-flow curves more closely at low flow rates when the frequency conversion input is considered.Moreover,in this case,the similarity law predicts the hydraulic performance more accurately.

Influence of pressure disturbance wave on dynamic response characteristics of liquid film seal for multiphase pump

Slug flow or high GVF(Gas Volume Fraction)conditions can cause pressure disturbance waves and alternating loads at the boundary of mechanical seals for multiphase pumps,endangering the safety of multiphase pump units.The mechanical seal model is simplified by using periodic boundary conditions and numerical calculations are carried out based on the Zwart-Gerber-Belamri cavitation model.UDF(User Define Function)programs such as structural dynamics equations,alternating load equations,and pressure disturbance equations are embedded in numerical calculations,and the dynamic response characteristics of mechanical seal are studied using layered dynamic mesh technology.The results show that when the pressure disturbance occurs at the inlet,as the amplitude and period of the disturbance increase,the film thickness gradually decreases.And the fundamental reason for the hysteresis of the film thickness change is that the pressure in the high-pressure area cannot be restored in a timely manner.The maximum value of leakage and the minimum value of axial velocity are independent of the disturbance period and determined by the disturbance amplitude.The mutual interference between enhanced waves does not have a significant impact on the film thickness,while the front wave in the attenuated wave has a promoting effect on the subsequent film thickness changes,and the fluctuation of the liquid film cavitation rate and axial velocity under the attenuated wave condition deviates from the initial values.Compared with pressure disturbance conditions,alternating load conditions have a more significant impact on film thickness and leakage.During actual operation,it is necessary to avoid alternating load conditions in multiphase pump mechanical seals.