Pumping Wells Research Articles (Page 1)

Under the "dual carbon" goal, the mismatch between the intermittent nature of wind-solar power generation and the stable energy demand of oil wells hinders efficient green energy utilization in oilfields, leading to low green electricity consumption, high curtailment rates, and poor economic benefits. To address this challenge, an optimization approach for oil well operation scheduling is proposed, which couples photovoltaic power fluctuations with the characteristics of intermittent pumping technology. Firstly, a multiobjective optimization model was developed to minimize grid electricity consumption per unit of liquid production and maximize the share of green electricity. The on-off schedule was mapped into a constrained binary sequence using a run-length encoding to reducing the solution space. Non-dominated Sorting Genetic Algorithm II (NSGA-II) was improved to increase both accuracy and convergence speed by introducing: (1) dual-mode initialization strategy guided by historical operating schedules and photovoltaic fluctuations. (2) a key-gene-preserving crossover operator to retain high-matching time segments; and (3) a peak-valley-guided mutation strategy to enable dynamic pruning of the solution space and goal-directed optimization. Case studies showed that the proposed method doubled green electricity consumption under stable production conditions, reduced grid electricity consumption per unit liquid by 41.67%, improved computational efficiency by two to three orders of magnitude, and enhanced the solution accuracy by 26.69%, indicating strong practical applicability.

Testing and applying analytical depletion functions for multiple pumping wells in two hydrogeological landscapes

Multi-function composite data generation and PIMamba model for fault diagnosis in sucker-rod pumping wells

Intensive groundwater extraction and a severe 2021 drought have worsened land subsidence in Taiwan's Choshui Delta, highlighting the need for effective predictive modeling to guide mitigation. In this study, we develop a machine learning framework for subsidence analysis using electricity consumption data from pumping wells as a proxy for groundwater extraction. A long short-term memory (LSTM) neural network is trained to reconstruct missing subsidence records and forecast subsidence trends, while an artificial neural network links well electricity usage to groundwater level fluctuations. Using these tools, we identify groundwater-level decline from pumping as a key driver of subsidence. The LSTM model achieves high accuracy in reproducing historical subsidence and provides reliable predictions of subsidence behavior. Scenario simulations indicate that reducing groundwater pumping, simulated by lowering well electricity use, allows groundwater levels to recover and significantly slows the rate of land subsidence. To assess the effectiveness of pumping reduction strategies, two artificial scenarios were simulated. The average subsidence rate at the Xiutan Elementary School multi-layer compression monitoring well (MLCW) decreased from 2.23 cm/year (observed) to 1.94 cm/year in first scenario and 1.34 cm/year in second scenario, demonstrating the potential of groundwater control in mitigating land subsidence. These findings underscore the importance of integrating groundwater-use indicators into subsidence models and demonstrate that curtailing groundwater extraction can effectively mitigate land subsidence in vulnerable deltaic regions.

Great technical advances have been achieved since the first atom-trap trace analysis (ATTA) -based radiokrypton application in Egypt, where 1 Myr old groundwater was discovered. Beyond advances in ATTA measurement capabilities, including reduction in sample size, analysis duration, and analytical uncertainty, major progress has been achieved over the past two decades in the sample collection and preparation techniques. These advances paved the expansion of ATTA-based noble gas applications to many other aquifers worldwide, illuminating the nature and flow pattern of deep groundwater systems. While the potential of this new analytical technique for old groundwater dating is well recognized, another important aspect yet to be examined is the reproducibility of radiokrypton in aquifers over time, i.e., how representative is a discrete groundwater sample, collected at a specific time and location, for the natural groundwater system? The likelihood of a negative answer is increased by flow-field disturbance in aquifers following massive groundwater abstraction. Here, we present repeated 81Kr sampling and measurements in twenty-one sites over Israel, mostly of deep (up to 1 km) wells tapping confined aquifers in the arid to hyperarid Negev desert. The results demonstrate that radiokrypton measurements are indeed reproducible, even in cases where samples were collected as long as nine years apart and from highly productive (∼1 Mm3/yr order) pumping wells. Furthermore, many of the repeated measurements in this study (17 out of the 21 sites) were conducted with different ATTA Instruments in two different laboratories using slightly different sampling, preparation, and analysis techniques, yet with an overall good agreement. The consistency in the ATTA-based 81Kr-dating results over time highlights the robustness of this state-of-the-art technique as a tool to unravel groundwater flow patterns and encourages further applications to many other yet-to-be-explored deep aquifers.

Abstract Fault prediction in oil pumping wells is crucial for oilfield production, directly impacting well stability and economic efficiency. Pumping well equipment is prone to various failures during long-term operation. This study developed a hybrid CNN-SVM (Convolutional Neural Networkand Support Vector Machine)model for oil well fault prediction, addressing the limitations of standalone CNN and SVM models. By integrating CNN’s powerful feature extraction capabilities with SVM’s classification strengths, the proposed model enhances prediction accuracy and efficiency. Compared to standalone CNN and SVM models, the hybrid model demonstrates superior performance including faster convergence (130 iterations, loss of 0.4), higher accuracy (85%–89%), improved recall (74%–83%), and better F1 scores (87%–91%). It provides a reliable and efficient solution for intelligent fault diagnosis in oilfield automation.

Abstract Securing sufficient food has become a global challenge threatening human survival. Consequently, many governments plan agricultural reclamation projects to increase food production, primarily relying on groundwater due to limited surface freshwater. However, over-exploitation of groundwater jeopardizes the sustainability of these vital resources. This research investigates the impact of one of these agricultural projects on groundwater levels in the Minia governorate of Egypt. Also, this study investigates the effects of groundwater levels on the power needed to extract it. A calibrated 3-D MODFLOW model has been utilized to simulate the response of aquifers, respecting the existing pumping rates and the subjecting of new extension agricultural areas. The findings of the drawdowns demonstrate a decrease in groundwater levels of 21.0, 33.0, 40.0, and 42.0 m, respectively, for 2030, 2050, 2070, and 2100 respecting the current operating pumping wells. Based on the proposed new agricultural extension project, these drawdowns will increase to 24.0, 42.0, 48.0, and 51.0 m for the same investigated years. The values of drawdowns are consistent with the permissible limits of drawdowns, recommending going forward with the project. Groundwater depths range from 60 to 105 m, leading to energy requirements between 25 and 44 kWh, corresponding to an area of 11 to 19 m² of solar panels. As groundwater levels decline, energy demands will increase by 43%, 50%, 60%, and 66% by 2030, 2050, 2070, and 2100, respectively. Energy requirements will necessitate a corresponding expansion of solar panel areas by 46%, 61%, 69%, and 76% by 2030, 2050, 2070, and 2100, respectively. The study’s findings advocate for the ongoing agricultural project, aligning it with the Sustainable Development Goals (SDGs) focused on addressing desertification, poverty, and hunger. Additionally, the research emphasizes the necessity of combining scientific modelling with policy development to foster sustainable agricultural practices while protecting vital water resources.

Managing groundwater flow in crystalline basement aquifers (CBAs) remains challenging due to their dependence on secondary permeability fields characterized by high spatial variability. This study combines pumping and tracer tests to estimate the hydraulic properties and connectivity in four bedrock wells within a CBA in Southwestern Nigeria. The pumping tests caused drawdowns up to 4.13 m and 12.60 m in observation and pumping wells, with significant drawdowns only in three of four wells, revealing poor connection with the fourth well. The time-drawdown plots confirm double porosity effects suggesting fracture and matrix flow and release of water from a fractured dyke. Fracture and matrix hydraulic conductivities exceeded 7.9 × 10−7 m/s and 1.00 × 10−10 m/s, while the aquifer yield ranged from 0.08 to 0.34%. Groundwater flow velocity and dispersivity of 5.80 × 10−4 m/s and 2.60 m were estimated from the tracer test, while a Peclet number of 3.25 suggests dominant advective flow. Calculated sustainable yield shows that each well could provide water for up to 1600 people under controlled low pumping at 0.50 l/s with higher rates possible using larger diameter wells. These results confirm high variability in groundwater flow within CBAs, justifying the need to characterize them effectively.

Abstract During oilfield development, the wear and failure of sucker rod occur frequently, posing a significant threat to the normal operation and economic returns of the oilfield. In light of this situation, this study addresses the wear problems of sucker rods and tubing in screw pump wells used for oil production. Through extensive research, a model was developed to calculate the axial force and torque of sucker rods. This model allows for a detailed analysis of the complex loads experienced by these components. Moreover, based on the borehole trajectory under three-dimensional working conditions, the force calculation method for sucker rod strings is further enhanced, furnishing precise force data to underpin wear analysis. Leveraging the principle of energy transfer and the most recent wear test data, a highly accurate wear prediction model for sucker rod strings and tubing is successfully devised. Experimental findings validate the model's reliability. Additionally, an investigation into the residual strength of worn sucker rod and tubing is carried out, and corresponding countermeasures for addressing sucker rod and tubing problems are put forward. These encompass optimizing rod structures, adjusting process parameters, and implementing lined tubing. Research outcomes indicate that these measures can notably mitigate sucker rod and tubing wear, prolong their service lives, and offer practical and effective technical solutions for managing rod and tube wear during oil production. Consequently, they hold substantial engineering application value and significance.

Liquid flow rate measurement for sucker-rod pumping wells with incomplete fillage using motor power and MSISSA-BiLSTM

The complex and variable operating conditions of sucker-rod pumping wells pose a significant challenge for the timely and accurate identification of oil well operating conditions. Effective deep learning based on measured multi-source data obtained from the sucker-rod pumping well production site offers a promising solution to the challenge. However, existing deep learning-based operating condition recognition methods are constrained by several factors: the limitations of traditional operating condition recognition methods based on single-source and multi-source data, the need for large amounts of labeled data for training, and the high robustness requirement for recognizing complex and variable data. Therefore, we propose a semi-supervised class-incremental sucker-rod pumping well operating condition recognition method based on measured multi-source data distillation. Firstly, we select measured ground dynamometer cards and measured electrical power cards as information sources, and construct the graph neural network teacher models for data sources, and dynamically fuse the prediction probability of each teacher model through the Squeeze-and-Excitation attention mechanism. Then, we introduce a multi-source data distillation loss. It uses Kullback-Leibler (KL) divergence to measure the difference between the output logic of the teacher and student models. This helps reduce the forgetting of old operating condition category knowledge during class-incremental learning. Finally, we employ a multi-source semi-supervised graph classification method based on enhanced label propagation, which improves the label propagation method through a logistic regression classifier. This method can deeply explore the potential relationship between labeled and unlabeled samples, so as to further enhance the classification performance. Extensive experimental results show that the proposed method achieves superior recognition performance and enhanced engineering practicality in real-world class-incremental oil extraction production scenarios with complex and variable operating conditions.

Source protection zone delineation has evolved over the past decades from fixed radius or analytical and numerical methods which do not consider uncertainty, to more complex stochastic numerical approaches. In this paper we explore options for delineating a source protection zone, while considering the inherent uncertainty involved in characterizing hydraulic conductivity. We consider a representative pumping well in an unconfined alluvial aquifer under steady-state flow conditions, with the hydraulic conductivity distribution inferred from borehole lithology data in the West Melton area near Christchurch, New Zealand. Lithologies are categorized according to their inferred hydraulic flow and transport properties, using two to four hydrofacies groupings. Probabilistic source protection zones are determined for alternative lithology categorization scheme and hydrofacies conductivity parameterization methods. Results show that the choice of calibration method significantly impacts the delineated source protection zone. In heterogeneous aquifers, the degree of protection offered by deeper pumping wells may be overstated, and forward particle tracking proved more comprehensive than backward tracking due to the complexity of flow paths near the well screen. Simple models, such as homogeneous models, require upscaled parameters to effectively represent aquifer heterogeneity, providing insights into how simplified source protection zone delineation could be made more robust in highly heterogeneous contexts.

A mechanistic-based data-driven modeling framework for predicting production of electric submersible pump wells in offshore oilfield

In special industrial fields such as electric submersible pump (ESP) wells, named entity recognition (NER) often suffers from low accuracy and incomplete entity recognition due to the scarcity of high-quality corpora and the prevalence of rare words and nested entities. To address these issues, this study introduces a character-level convolutional neural network (char-CNN) into the Flat-Lattice Transformer (FLAT) model and constructs nested entity matching rules for the ESP well domain, forming the char-CNN-FLAT-CRF model. This model achieves NER in the low-resource context of ESP wells. Through multiple experiments, the char-CNN-FLAT-CRF model demonstrates superior performance in this NER task compared to mainstream models and shows good recognition capabilities for rare words and nested entities. This research provides a methodological and conceptual reference for NER in other industrial fields that lack sufficient high-quality corpora.

This paper analyses the impact of heterogeneity in the horizontal hydraulic conductivity field () on the optimal pumping scenarios in a coastal aquifer and presents a multi-objective management framework to select robust optimal scenarios under high levels of uncertainty. Model speed is significantly improved by training an M5 Decision Tree (MDT) algorithm as a fast surrogate model for the density-dependent flow (DDF) in the SEAWAT code. The developed Tree model was linked to a non-dominated genetic algorithm (NSGAII) to determine Pareto optimal solutions, with the aim of maximizing total pumping volume and minimizing saltwater intrusion in a real case study, i.e., the Qom-Kahak aquifer, Iran. A linear sensitivity analysis explores the relationship between Pareto curves in response to variations in calibrated values of to quantify robust scenarios by a robust decision-making technique. Finally, the conflict resolution between minimum saltwater intrusion length, maximum pumping rate and robustness values is solved using a non-cooperative Nash bargaining theory. Results indicate that maintaining discharge from the pumping wells located far from 3 observation points in the case study, especially near the Salt Lake boundary, increases uncertainty in the Pareto solutions, where increasing by up to 30% of calibrated values induces a maximum 12% shift in the Pareto front for the scenario which led to high saltwater intrusion lengths. Moreover, the non-robust scenario causes the saltwater intrusion zone to sharply advance to the area with a large number of pumping wells, while the scenario with high Nash product values led to a relatively uniform salinized zone which satisfies the allowed SWI length in 5 agricultural zones. In total, the developed MDT-NSGAII model is a computationally effective simulation–optimization model to find the Pareto front with 55 decision variables while achieving a 95% reduction in CPU time compared to the SEAWAT-NSGAII technique.

Lead (Pb) poses a significant risk to human health and the environment. Global Pb production and consumption have markedly risen due to unregulated development and urbanization, Pb smelting, and Pb-acid battery processing. This study addresses the issue of elevated heavy metal concentrations in dust, soil, and groundwater in Shubra Al Khaymah due to the Awadallah Pb smelter. Pb concentration in soil and groundwater escalates in proximity to the Awadallah smelter and diminishes with distance from it—the surface soil functions as a repository for heavy metals. The concentrations of Pb (50–1500 µg/L), manganese (Mn) (1–750 µg/L), iron (Fe) (200–1250 µg/L), and boron (B) (250–1750 µg/L) in the groundwater stratum exceeded drinking and irrigation standards. A solution to the groundwater system issue is proposed by employing pumping wells adjacent to the riverbed to recover the contaminated water from the hydrogeological environment. Processing Modflow Path (PMPATH) program may delineate groundwater protection zones according to the travel time of 150 days (Zones 1 and 2) and the whole watershed source (Zone 3). An injection well was constructed to replenish excellent water quality in the groundwater aquifer in the upstream region. A 3D model of dissolved matter transport was created to examine the concentration distribution across remediation time in the contaminated region. This model demonstrates that, after 365 days of injection, the C/Co concentration ratio exceeded 70% in the downstream area, rendering it appropriate for drinking and irrigation. The alternate strategy is to encapsulate the severely contaminated zone. All measures aim to decrease the piezometric pressure in the vicinity, directing groundwater flow towards the contaminated zone, as accomplished by Processing Modflow Windows (PMWIN).

Visual-Language contrastive learning for zero-shot compound fault diagnosis in sucker rod wells

To address the issues of low frequency and high costs associated with the current manual production measurement for ESP wells in the Tarim Oilfield, a study was conducted to develop a digital production measurement method for ESP wells. Based on the principle of energy conservation, where the input power of the pump equals the output power of the motor, and incorporating parameters such as surface tubing and casing pressure, motor current, and motor/ pump performance curves, with viscosity correction of the pump performance curve, a corrected power calculation method was proposed. A digital production measurement mathematical model was established. According to feedback from field applications, the calculated results of this method align well with the metered results when corrected using on-site measured flow rate. Furthermore, by applying this model, accurate allocation of merged production well outputs and risk warning or failure diagnosis for oil wells can be achieved. This method not only improves the accuracy and efficiency of ESP well production calculations but also enables real-time reflection of oil well production trends, contributing to intelligent production management in the Tarim Oilfield and significantly enhancing the level of oilfield production management.

The present study seeks to evaluate the hydraulic properties of the aquifer strata. In the absence of observation wells adjacent to the pumping wells, four wells in the research area (P.W1, P.W2, P.W3, and P.W4) were utilized for the single pumping test experiment, employing the Cooper-Jacob and Theis Recovery methodologies as a basis. The transmissivity values of the aquifer in the studied area varied from 0.43 to 1198.61 m²/day. The specific capacity values varied from 1.60 to 3811.76 m²/day, while the hydraulic conductivity ranged from 0.01 to 19.83 m/day. Clay in the aquifer accounts for the substantial difference in values of W.P4. Both transmissivity and hydraulic conductivity are markedly low.

Under the dual carbon mission, more and more coal mines will face shutting down in the future and stop treating mine water drainage, which, if it escapes, may cause severe secondary damage to the local groundwater quality. Wudong Coal Mine is a currently active subsurface coal mine in Xinjiang, China, that shows high-salinity characteristics. To forecast and discuss future possible groundwater quality damages and potential solutions, we here introduce a model prediction study on the effects of water pollution by coal mine drainage. The study protocol first involves creating a calibrated 2D groundwater flow model by use of FEFLOW software, then designing several flow and solute transport prediction analyses under changing mine water drainage conditions, different pollution source areas and water treatment pumping wells to discuss future prominent flow and transport behavior, as well as water treatment-affecting factors. It has been shown that mine water drainage plays a critical role in maintaining the mine water solute distribution, as without mine draining, local flow and solute distribution change dramatically, altering the groundwater capture zone, and may change the plume-migrating direction from upstream to downstream. A larger pollution source could produce a higher concentration of pollutants and a larger pollution-coverage area. To reduce pollutant concentrations, mine water treatment pumping wells with higher pumping rates can be applied as a useful remedial measure to effectively prevent the pollutant plume front from reaching the important drinking and irrigation water source of the region, Urumqi River. The results of this study can give important suggestions and decision-making support for authorities focused on water treatment and environmental protection decision-making in the region.