An electric submersible screw pump anti-gas lock method and device based on working condition identification and a medium

Abstract

The application discloses a method and device for preventing gas locking of an electric submersible screw pump based on working condition identification, and a medium, and relates to the technical field of oil exploitation equipment. The method comprises the following steps: based on a downhole detection device and a ground control cabinet sensor of an electric submersible screw pump unit, collecting operation parameters of the electric submersible screw pump unit in real time, and preprocessing the operation parameters to obtain standard operation parameters; wherein the operation parameters comprise pump inlet pressure and motor output current; extracting pressure-current correlation characteristics in a gas locking working condition to construct a gas locking working condition identification model, and inputting the standard operation parameters into the gas locking working condition identification model to obtain a gas locking state grade; and based on the gas locking state grade, adjusting an operation regulation and control strategy of the electric submersible screw pump unit to eliminate the gas locking phenomenon. The application collects real-time data of downhole and ground sensors, judges the gas locking grade in advance through the gas locking working condition identification model, and automatically adjusts the operation state, so that early warning of the gas locking is realized.

Description

Technical Field

[0001] This application relates to the field of oil extraction equipment technology, and in particular to a method, equipment and medium for preventing airlock in electric submersible screw pumps based on operating condition identification. Background Technology

[0002] In the field of oil extraction, electric submersible screw pumps (ESPCPs) are widely used due to their good adaptability to high viscosity, high sand content and high gas content gases. However, in the production of high gas content wells, ESPCPs face serious gas lock problems. When the free gas content in the well fluid is high, the gas tends to accumulate at the pump inlet, forming a gas bag, which hinders the continuous entry of liquid into the pump chamber, resulting in a sharp drop in pump efficiency or even complete failure.

[0003] Currently, conventional technical approaches to address gas lock issues in electric submersible screw pumps mainly fall into two categories. The first category is based on preset fixed operating parameters, such as setting a low constant speed, attempting to reduce the impact of gas by decreasing the pumping intensity. This approach lacks responsiveness to dynamic downhole conditions and cannot effectively intervene when gas lock occurs. When gas lock does not occur, the overly conservative parameters may limit production capacity. The second category is passive protection based on a single parameter, such as monitoring the pump inlet pressure and shutting down when the pressure falls below a certain fixed threshold. This reactive shutdown strategy is lagging, usually only taking effect after the gas lock has severely damaged pump efficiency or triggered the risk of dry running. This not only affects production continuity but also fails to proactively eliminate the gas lock.

[0004] Therefore, how to dynamically identify the characteristics of different stages of gas lock occurrence by real-time monitoring and analysis of the unit's multi-dimensional operating parameters, and automatically trigger corresponding phased active control strategies accordingly, so as to achieve early warning, online intervention and autonomous recovery of gas lock conditions, and improve the operational stability, production efficiency and equipment safety of electric submersible screw pumps in high gas-content well conditions, has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method, device, and medium for preventing gas lock in electric submersible screw pumps based on operating condition identification, in order to solve the following technical problem: how to dynamically identify the characteristics of different stages of gas lock occurrence by real-time monitoring and analysis of the multi-dimensional operating parameters of the unit, and automatically trigger corresponding, phased active control strategies accordingly, so as to achieve early warning, online intervention, and autonomous recovery of gas lock conditions, and improve the operating stability, production efficiency, and equipment safety of electric submersible screw pumps under high gas content well conditions.

[0006] In a first aspect, embodiments of this application provide a method for preventing gas lock in an electric submersible screw pump based on operating condition identification. The method includes: real-time acquisition of operating parameters of the electric submersible screw pump unit using downhole detection devices and sensors in the surface control cabinet, and preprocessing the operating parameters to obtain standard operating parameters; wherein, the operating parameters include pump inlet pressure and motor output current; extracting pressure-current correlation features under gas lock conditions to construct a gas lock condition identification model, and inputting the standard operating parameters into the gas lock condition identification model to obtain a gas lock status level; and adjusting the operation control strategy of the electric submersible screw pump unit based on the gas lock status level to eliminate the gas lock phenomenon.

[0007] In one implementation of this application, the method further includes: constructing an airlock condition identification model, specifically including: acquiring first historical data of the electric submersible screw pump unit operating under normal and stable liquid supply conditions to obtain a benchmark sample set; extracting second historical data of the electric submersible screw pump unit before and after an airlock failure, and marking the time point of the airlock failure to obtain an airlock failure dataset; performing correlation analysis on the pump inlet pressure and motor output current based on the benchmark sample set and the airlock failure dataset to obtain pressure-current correlation features characterizing the occurrence of airlock; and constructing a judgment rule base for distinguishing between normal operating conditions and airlock conditions based on the pressure-current correlation features to obtain an airlock condition identification model.

[0008] In one implementation of this application, a correlation analysis is performed on the pump inlet pressure and motor output current based on a benchmark sample set and an airlock fault dataset to obtain pressure-current correlation characteristics characterizing airlock occurrence. Specifically, this includes: extracting the variation law of pump inlet pressure and the stable range of motor output current under normal operating conditions from the benchmark sample set to establish a pressure-current benchmark correlation under normal operating conditions; splitting segmented data from the airlock fault dataset for the stages before airlock occurrence, airlock development, and airlock mitigation to generate segmented data for each stage of airlock; comparing the segmented data for each stage of airlock with the pressure-current benchmark correlation under normal operating conditions, and analyzing the variation trend of pump inlet pressure and the fluctuation law of motor output current at each stage of airlock to obtain pressure-current correlation characteristics.

[0009] In one implementation of this application, a judgment rule base for distinguishing between normal operating conditions and airlock operating conditions is constructed based on pressure-current correlation features to obtain an airlock operating condition identification model. Specifically, this includes: classifying pressure-current correlation features to output airlock early warning features, airlock development features, and airlock mitigation features; setting operating condition matching conditions and judgment priorities for airlock early warning features, airlock development features, and airlock mitigation features based on the pressure-current baseline correlation under normal operating conditions to obtain a judgment rule base; and optimizing the judgment rule base based on a baseline sample set and an airlock fault dataset to output an airlock operating condition identification model.

[0010] In one implementation of this application, the operating parameters of the electric submersible screw pump unit are collected in real time based on the downhole monitoring device and the surface control cabinet sensor. These operating parameters are then preprocessed to obtain standard operating parameters. Specifically, this includes: collecting the pump inlet pressure analog signal output by the downhole monitoring device and the motor output current analog signal from the surface control cabinet sensor during operation; performing analog-to-digital conversion on the pump inlet pressure analog signal and the motor output current analog signal to obtain a first pressure digital sequence corresponding to the pump inlet pressure analog signal and a first current digital sequence corresponding to the motor output current analog signal; performing sliding filtering on the first pressure digital sequence and the first current digital sequence to obtain a filtered second pressure digital sequence and a second current digital sequence; and aligning and standardizing the second pressure digital sequence and the second current digital sequence according to a preset timestamp to generate standard operating parameters.

[0011] In one implementation of this application, pressure-current correlation features under airlock conditions are extracted to construct an airlock condition identification model. Standard operating parameters are input into the airlock condition identification model to obtain the airlock status level. Specifically, this includes: coupling and analyzing the second pressure digital sequence and the second current digital sequence in the standard operating parameters to generate condition analysis data; matching the condition analysis data with the judgment rule base in the airlock condition identification model to obtain the airlock status level; wherein, the airlock status level is divided into no airlock, initial airlock, severe airlock, and airlock relief.

[0012] In one implementation of this application, the operation control strategy of the electric submersible screw pump unit is adjusted based on the gas lock status level to eliminate the gas lock phenomenon. Specifically, this includes: if the gas lock status level is the initial stage of gas lock, adjusting the operating speed of the electric submersible screw pump and controlling the downhole dynamic fluid level to be in a stable state; if the gas lock status is severe gas lock, stopping the operation of the electric submersible screw pump unit and increasing the speed using a low-frequency start-up method after the gas in the pump is discharged; if the gas lock status is gas lock relief, maintaining the current operating speed of the electric submersible screw pump unit until the electric submersible screw pump unit returns to a non-gas lock state.

[0013] In one implementation of this application, after adjusting the operating state of the electric submersible screw pump unit, the method further includes: real-time monitoring of the adjusted operating parameters of the electric submersible screw pump unit and the corresponding airlock state change trend to generate control effect feedback data; based on the control effect feedback data, evaluating the actual effectiveness of adjusting for each airlock state, and optimizing and updating the judgment rule base in the airlock condition identification model based on the actual effectiveness.

[0014] Secondly, embodiments of this application also provide an anti-gas lock device for an electric submersible screw pump based on operating condition identification. The device includes: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: collect real-time operating parameters of the electric submersible screw pump unit based on downhole detection devices and surface control cabinet sensors, and preprocess the operating parameters to obtain standard operating parameters; wherein the operating parameters include pump inlet pressure and motor output current; extract pressure-current correlation features under gas lock conditions to construct a gas lock condition identification model, and input the standard operating parameters into the gas lock condition identification model to obtain a gas lock status level; and adjust the operating control strategy of the electric submersible screw pump unit based on the gas lock status level to eliminate the gas lock phenomenon.

[0015] Thirdly, this application also provides a non-volatile computer storage medium for preventing gas lock in electric submersible screw pumps based on operating condition identification. The medium stores computer-executable instructions, which are configured to: collect real-time operating parameters of the electric submersible screw pump unit based on downhole detection devices and surface control cabinet sensors, and preprocess these parameters to obtain standard operating parameters; wherein the operating parameters include pump inlet pressure and motor output current; extract pressure-current correlation features under gas lock conditions to construct a gas lock condition identification model, and input the standard operating parameters into the gas lock condition identification model to obtain a gas lock status level; and adjust the operating control strategy of the electric submersible screw pump unit based on the gas lock status level to eliminate the gas lock phenomenon.

[0016] This application provides a method, device, and medium for preventing airlock in an electric submersible screw pump based on operating condition identification. These methods offer the following advantages: By analyzing the correlation between pump inlet pressure and motor output current and matching multi-dimensional features, they achieve accurate, tiered identification of airlock precursors, initial stages, and severe airlocks. This avoids the missed or incorrect judgments caused by static assessments in traditional technologies, significantly improving the accuracy of airlock identification. Differentiated adjustment strategies are developed for different airlock levels. Initial airlocks are actively intervened through speed adjustment and dynamic liquid level stabilization control. Severe airlocks are efficiently resolved through a combination of pump shutdown for venting and low-frequency start-up. Compared to traditional one-size-fits-all prevention methods, the success rate of airlock resolution is greatly improved, effectively preventing chain reactions such as sudden drops in pump efficiency and stator wear caused by escalating airlocks. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1A flowchart of an anti-airlock method for an electric submersible screw pump based on working condition identification is provided in an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of the internal structure of an anti-airlock device for an electric submersible screw pump based on working condition identification, provided as an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a method, device, and medium for preventing gas lock in electric submersible screw pumps based on operating condition identification, in order to solve the following technical problem: how to dynamically identify the characteristics of different stages of gas lock occurrence by real-time monitoring and analysis of the multi-dimensional operating parameters of the unit, and automatically trigger corresponding, phased active control strategies accordingly, so as to achieve early warning, online intervention, and autonomous recovery of gas lock conditions, and improve the operating stability, production efficiency, and equipment safety of electric submersible screw pumps under high gas content well conditions.

[0022] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 This document presents a flowchart of a method for preventing airlock in an electric submersible screw pump based on operating condition identification, as provided in an embodiment of this application. Figure 1 As shown in the figure, the present application provides a method for preventing airlock in an electric submersible screw pump based on operating condition identification, which specifically includes the following steps:

[0024] Step 10: Based on the downhole detection device and surface control cabinet sensors of the electric submersible screw pump unit, the operating parameters of the electric submersible screw pump unit are collected in real time, and the operating parameters are preprocessed to obtain standard operating parameters.

[0025] As an optional embodiment, based on the downhole detection device and the surface control cabinet sensor of the electric submersible screw pump unit, the operating parameters of the electric submersible screw pump unit are collected in real time, and the operating parameters are preprocessed to obtain standard operating parameters. Specifically, it may include: Step 101: Collect the pump inlet pressure analog signal output by the downhole detection device and the motor output current analog signal of the surface control cabinet sensor when the electric submersible screw pump unit is running.

[0026] In this step, during the normal operation of the electric submersible screw pump unit, the downhole monitoring device continuously captures analog signals related to the pump inlet pressure. This signal reflects the pressure changes at the downhole pump inlet in real time, and these changes are directly related to the flowability, supply stability, and working status of the pump suction end. Abnormal fluctuations or deviations from the normal range in the pump inlet pressure can promptly indicate potential problems such as insufficient downhole medium supply, suction pipeline blockage, and changes in medium properties. These problems directly affect the pump's suction efficiency, leading to cavitation, dry running, and other faults, threatening the safe operation of the unit. Simultaneously, directly acquiring the pump inlet pressure through the downhole monitoring device avoids interference during surface parameter transmission, accurately capturing original downhole operating information and providing a reliable basis for judging the pump suction system and downhole medium conditions. At the same time, a dedicated sensor mounted on the surface control cabinet synchronously acquires analog signals related to the motor output current. This signal accurately reflects the motor's operation during operation. The dynamic fluctuation of the current, as a direct reflection of the motor load state, is closely related to the pump's operating resistance and output power. The change in the motor's output current is determined by the change in the load borne by the pump, which is affected by various factors such as the viscosity of the downhole medium, the discharge demand, internal wear, and jamming. When the pump experiences accelerated wear, abnormal rotor-stator matching, or increased downhole medium viscosity and pipeline resistance, the motor needs to output more power to maintain normal operation, which in turn causes a corresponding change in the output current. By collecting the motor's output current through sensors in the ground control cabinet, the load intensity of the motor and the operating resistance state of the pump can be reflected in real time, and problems such as pump mechanical failures and sudden changes in medium conditions can be detected in a timely manner, providing key support for assessing the unit's operating load and providing fault early warning. The acquisition process of the two types of analog signals is synchronized with the unit's operating status in real time, ensuring that the acquired signals can accurately and continuously reflect the core operating parameters during equipment operation, providing basic data support for subsequent signal processing and operating condition identification.

[0027] Step 102: Perform analog-to-digital conversion on the pump inlet pressure analog signal and the motor output current analog signal to obtain the first pressure digital sequence corresponding to the pump inlet pressure analog signal and the first current digital sequence corresponding to the motor output current analog signal.

[0028] In this step, the analog signals of pump inlet pressure and motor output current are converted from analog to digital. This conversion process transforms the continuously changing analog pressure signal into a discrete digital signal, forming a first pressure digital sequence that corresponds one-to-one with the original analog pressure signal. Simultaneously, using the same conversion logic and processing standards, the continuously fluctuating analog motor output current signal is converted into a discrete digital signal, generating a first current digital sequence that precisely matches the original analog current signal. The conversion process strictly adheres to the principle of signal transmission integrity, ensuring that the digital sequence can accurately reproduce the changing characteristics of the original analog signal, providing a high-quality digital data foundation for subsequent signal filtering, standardization processing, and operating condition analysis.

[0029] Step 103: Perform sliding filtering on the first pressure digital sequence and the first current digital sequence to obtain the filtered second pressure digital sequence and the second current digital sequence.

[0030] In this step, based on a preset sliding window, the data points in the acquired first pressure digital sequence and first current digital sequence are smoothed segment by segment. Abnormal data points caused by detection interference, signal fluctuations, and other factors are filtered out, while retaining the core data features that reflect real operating conditions. For the first pressure digital sequence, after sliding filtering, a second pressure digital sequence with smoother data fluctuations and removed interference signals is formed. For the first current digital sequence, the same filtering logic and processing standards are used to generate a second current digital sequence that is more accurate and stable. The filtered digital sequences effectively reduce the impact of noise interference on data accuracy, providing reliable data support for subsequent timestamp alignment, standardization, and operating condition correlation analysis.

[0031] Step 104: Align and standardize the second pressure digital sequence and the second current digital sequence according to the preset timestamps to generate standard operating parameters.

[0032] In this step, after completing the sliding filter processing, timestamp alignment and standardization are performed on the obtained second pressure digital sequence and second current digital sequence. The timestamp alignment process strictly follows the preset time synchronization rules, accurately matching data corresponding to the same acquisition time in the two types of sequences to ensure that the pressure data and current data correspond one-to-one in the time dimension, eliminating data misalignment caused by differences in acquisition timing, and forming a time-synchronized joint data set. Subsequently, the aligned joint data set is standardized by uniformly converting data formats, normalizing dimensions, and calibrating ranges to eliminate the influence of data differences caused by different detection equipment and acquisition environments, so that the processed data has a unified comparison benchmark and analysis dimension. After the above two steps, standard operating parameters that can accurately and uniformly reflect the operating status of the electric submersible screw pump unit are finally generated, laying a reliable data foundation for subsequent multi-dimensional matching analysis input into the airlock condition identification model.

[0033] Step 20: Extract the pressure-current correlation features under airlock conditions to construct an airlock condition identification model, and input the standard operating parameters into the airlock condition identification model to obtain the airlock status level.

[0034] As an optional embodiment, pressure-current correlation features under airlock conditions are extracted to construct an airlock condition identification model, and standard operating parameters are input into the airlock condition identification model to obtain the airlock status level. Specifically, it may include: Step 201: Constructing an airlock condition identification model.

[0035] As an optional embodiment, constructing a gas lock condition identification model may specifically include: Step 2011: Obtaining the first historical data of the electric submersible screw pump unit under normal and stable liquid supply conditions to obtain a benchmark sample set.

[0036] In this step, when the electric submersible screw pump unit is in normal and stable fluid supply operation, various operating parameters under this condition are continuously collected. These parameters include electrical parameters that reflect the equipment's operating status and relevant parameters that reflect the downhole conditions. The collected parameters are collected and organized, and invalid data caused by accidental factors are removed. Complete data that truly reflects the characteristics of normal and stable fluid supply is retained. These filtered and organized data are classified and integrated to form a benchmark sample set for the subsequent construction of the gas lock condition identification model. This benchmark sample set can provide a clear reference for the determination of gas lock conditions and is the core basic data for distinguishing between normal operating conditions and gas lock conditions.

[0037] Step 2012: Extract the second historical data of the electric submersible screw pump unit before and after the airlock failure, and mark the time point of the airlock failure to obtain the airlock failure dataset.

[0038] In this step, historical data is extracted from the relevant operating records of the electric submersible screw pump unit when airlock failure occurs. The focus is on screening various operating data corresponding to the period before, during, and after the airlock failure, forming a second set of historical data covering the entire airlock failure cycle. During data extraction, the time nodes of the airlock failure are accurately marked by combining equipment operation logs and operating condition monitoring records, clearly defining the time intervals before, during, and after the failure, thus establishing a correlation between the data and the development stages of the airlock failure. Subsequently, the extracted and marked second set of historical data is categorized and organized, removing redundant data unrelated to the airlock failure and retaining effective data content that reflects the characteristics of the airlock failure. Finally, this data is integrated to form an airlock failure dataset, providing core data support for the extraction of pressure-current correlation features and the construction of a judgment rule base in the subsequent airlock operating condition identification model.

[0039] Step 2013: Based on the benchmark sample set and the airlock fault dataset, perform a correlation analysis on the pump inlet pressure and the motor output current to obtain the pressure-current correlation characteristics that characterize the occurrence of airlock.

[0040] As an optional embodiment, based on the benchmark sample set and the airlock fault dataset, a correlation analysis is performed on the pump inlet pressure and the motor output current to obtain the pressure-current correlation characteristics characterizing the occurrence of airlock. Specifically, it may include: Step 20131: Extract the variation law of pump inlet pressure and the stable range of motor output current under normal operating conditions from the benchmark sample set to establish the pressure-current benchmark correlation under normal operating conditions.

[0041] In this step, based on the established benchmark sample set, the focus is on extracting the dynamic variation of the pump inlet pressure under normal and stable liquid supply conditions during operation. Simultaneously, the stable fluctuation range of the motor output current under this condition is analyzed. The extracted pressure variation patterns and current stability range are correlated to clarify the coordinated variation trends and corresponding relationships of these two core parameters under normal operating conditions. Through logical integration and feature induction, a pressure-current benchmark correlation is established that can accurately characterize the normal operating state. This correlation can serve as a core reference for distinguishing between airlock conditions and normal operating conditions, providing crucial benchmark support for building the judgment rule base of the airlock condition identification model.

[0042] Step 20132: Extract segmented data from the airlock fault dataset, including data before airlock occurrence, airlock development process, and airlock mitigation stage, to generate segmented data for each stage of airlock.

[0043] In this step, the constructed airlock fault dataset is divided into stages according to the pre-labeled airlock fault occurrence time points and the development process of the airlock fault. First, the stable operation period data before the airlock fault occurs is divided. Then, the dynamic change data during the continuous development process after the airlock fault occurs is extracted. Finally, the recovery process data during the stage when the airlock fault is controlled and gradually alleviated is selected. The data of each time period after the division are independently processed, and redundant information irrelevant to the characteristics of each stage of the airlock fault is removed. The core data content that can reflect the working condition of the corresponding stage is retained. Finally, the data is integrated to generate segmented data of each stage of the airlock fault covering the entire life cycle of the airlock fault. This provides accurate staged data support for subsequent comparative analysis of the parameter differences between normal operating conditions and airlock operating conditions.

[0044] Step 20133: Compare the segmented data of each stage of the airlock with the pressure-current benchmark correlation under normal operating conditions, and analyze the changing trend of pump inlet pressure and the fluctuation law of motor output current in each stage of the airlock to obtain pressure-current correlation characteristics.

[0045] In this step, the pressure-current baseline correlation under normal operating conditions is used as a reference standard. The segmented data of each stage of airlock are compared with this baseline correlation to accurately locate the differences between the data of each stage of airlock and the baseline data. On this basis, the segmented data of the airlock before occurrence, the airlock development process, and the airlock relief stage are analyzed in depth to understand the dynamic change trend of the pump inlet pressure over time in each stage. At the same time, the fluctuation characteristics and change law of the motor output current are sorted out. By integrating the correspondence between the pressure change trend and the current fluctuation law of each stage, the coordinated change pattern of the two types of parameters under different airlock stages is extracted. These coordinated change patterns that can accurately characterize the airlock operating conditions together constitute the pressure-current correlation feature used to distinguish between normal operating conditions and airlock operating conditions, providing core feature basis for the subsequent construction of the judgment rule base of the airlock operating condition identification model.

[0046] Step 2014: Based on the pressure-current correlation characteristics, construct a judgment rule base to distinguish between normal operating conditions and airlock operating conditions, so as to obtain an airlock operating condition identification model.

[0047] As an optional embodiment, a judgment rule base for distinguishing between normal operating conditions and airlock operating conditions is constructed based on pressure-current correlation characteristics to obtain an airlock operating condition identification model. Specifically, it may include: Step 20141: classifying pressure-current correlation characteristics to output airlock early warning characteristics, airlock development characteristics, and airlock mitigation characteristics.

[0048] In this step, the extracted pressure-current correlation features are categorized and sorted according to their corresponding airlock fault development stages. Features corresponding to the operating conditions before the airlock fault occurs are selected and summarized as airlock early warning features, which can reflect the potential trend of airlock fault occurrence in advance. Typical features exhibited during the airlock fault development process are extracted and integrated into airlock development features, which can accurately reflect the continuous evolution of the airlock fault. Feature information presented during the airlock fault mitigation stage is sorted and categorized as airlock mitigation features, which can characterize the gradual decline of the airlock fault. Through the above classification process, the stage-based division of the pressure-current correlation features is completed, ultimately outputting three feature sets: airlock early warning features, airlock development features, and airlock mitigation features. This provides a hierarchical feature basis for the subsequent construction of the airlock operating condition identification model judgment rule base.

[0049] Step 20142: Based on the pressure-current reference correlation under normal operating conditions, set the operating condition matching conditions and judgment priorities for airlock early warning characteristics, airlock development characteristics and airlock mitigation characteristics to obtain a judgment rule library.

[0050] In this step, the pressure-current baseline correlation under normal operating conditions is used as the core reference. Corresponding operating condition matching conditions are formulated for the categorized airlock warning features, airlock development features, and airlock mitigation features. During the setting process, the difference thresholds between various features and the baseline correlation, the logic of parameter coordination changes, and the corresponding operating condition representation rules are clearly defined to ensure that each feature can accurately match a specific airlock operating condition. Simultaneously, considering the development process of airlock faults and prevention and control needs, reasonable judgment priorities are set for the three types of features. Early warning features that can predict the occurrence of airlocks are identified first, followed by development features reflecting the evolution of airlock faults, and finally, mitigation features representing the airlock's dissipation process are matched. This avoids conflicts or misjudgments between features at different stages during the identification process. The above-defined operating condition matching conditions and judgment priorities are integrated to form a logically rigorous and hierarchically distinct judgment rule base, providing the core judgment basis for the accurate operation of the airlock operating condition identification model.

[0051] Step 20143: Based on the benchmark sample set and the airlock fault dataset, optimize the judgment rule base to output the airlock condition identification model.

[0052] In this step, normal operating condition data from the benchmark sample set is input into the judgment rule base to verify the accuracy of the rule base in identifying normal operating conditions and to remove redundant rules that might misclassify normal operating conditions as airlock conditions. Simultaneously, segmented data covering each stage of the airlock fault dataset is substituted into the rule base to test the accuracy of the rule base in matching airlock early warning features, airlock development features, and airlock mitigation features. Adjustments and optimizations are made to address issues such as inaccurate feature matching and conflicting judgment priorities. During the optimization process, the operating condition matching conditions and feature judgment logic within the rule base are continuously iterated and corrected to continuously improve the rule base's ability to distinguish different operating conditions and its recognition efficiency. After multiple rounds of data verification and rule iteration, the optimized and improved judgment rule base is encapsulated and integrated, ultimately outputting an airlock condition recognition model that can accurately identify airlock conditions and their corresponding state levels.

[0053] Step 202: Couple the second pressure digital sequence and the second current digital sequence in the standard operating parameters to generate operating condition analysis data.

[0054] In this step, the second pressure and second current digital sequences are extracted from the generated standard operating parameters for coupled analysis. This analysis breaks the independent analysis mode of the two types of data, establishes a dynamic correlation logic between them, focuses on exploring the synergistic response relationship between pressure changes and current fluctuations, clarifies the corresponding change patterns of the two types of parameters in the time series dimension, and captures the synchronicity and difference characteristics of parameter changes. Through deep coupling and feature extraction of the two types of digital sequences, the originally independent pressure and current data are integrated into a composite data set that can comprehensively reflect the real-time operating status of the electric submersible screw pump unit. Finally, operating condition analysis data for subsequent operating condition determination is generated, providing a comprehensive and correlated analytical basis for the accurate matching of the airlock operating condition identification model.

[0055] Step 203: Match the working condition analysis data with the judgment rule base in the airlock working condition identification model to obtain the airlock status level.

[0056] In this step, the generated operating condition analysis data is input into a pre-built airlock operating condition identification model. Based on the operating condition matching conditions set in the rule base, the model verifies whether airlock early warning features, airlock development features, and airlock mitigation features exist in the operating condition analysis data one by one. At the same time, following the judgment priority preset in the rule base, the early warning features are matched and verified first, and then the development features and mitigation features are matched and analyzed in turn. By sorting out the matching fit of features and combining the corresponding logic between features and airlock status in the rule base, the airlock status category of the current unit operation is accurately determined, and finally a clear airlock status level is output, providing a direct judgment basis for subsequent targeted adjustments to the operating status.

[0057] Step 30: Based on the airlock status level, adjust the operation control strategy of the electric submersible screw pump unit to eliminate the airlock phenomenon.

[0058] As an optional embodiment, the operation control strategy of the electric submersible screw pump unit is adjusted based on the gas lock status level to eliminate the gas lock phenomenon. Specifically, it may include: Step 301: If the gas lock status level is the initial stage of gas lock, the operating speed of the electric submersible screw pump is adjusted, and the downhole dynamic fluid level is controlled to be in a stable state.

[0059] In this step, when the gas lock condition identification model determines the gas lock status level to be in the initial stage of gas lock, a targeted operational status adjustment strategy is immediately initiated. First, the operating speed of the electric submersible screw pump is adaptively adjusted. By reasonably controlling the speed, the pumping rhythm of the pump body is changed, thereby alleviating the tendency of gas accumulation in the pump and preventing the gas lock failure from developing further. At the same time, downhole dynamic fluid level stabilization control is carried out simultaneously. By monitoring the changes in the dynamic fluid level in real time and taking corresponding control measures, the dynamic fluid level is maintained in a suitable stable state, ensuring the pump body's suction conditions and providing stable downhole operating conditions to alleviate the initial gas lock failure. Through the synergistic effect of speed adjustment and dynamic fluid level stabilization control, efficient intervention in the initial gas lock failure is achieved, prompting the unit to return to normal operation as soon as possible.

[0060] Step 302: If the airlock condition is severe airlock, stop the operation of the electric submersible screw pump unit, and after the gas in the pump is discharged, use a low-frequency start method to increase the speed.

[0061] In this step, when the airlock condition identification model determines that the current airlock status level is severe airlock, an emergency response strategy is immediately activated. First, a shutdown command is issued to stop the operation of the electric submersible screw pump unit to prevent further airlock escalation leading to more serious equipment failures such as pump component wear and motor overload. After the unit stops operating, relevant pipelines are kept clear, while unnecessary branch valves are closed. The focus is on ensuring the unobstructed flow of the gas discharge channel, providing a directional discharge path for the high-pressure gas accumulated inside the pump. During this process, real-time monitoring of pump pressure changes ensures that the gas is fully discharged and the internal pressure returns to a safe and stable state. Once the gas inside the pump has been fully discharged and the internal pressure has returned to a stable level... After the system returns to a stable state, the unit restart procedure is initiated. First, the pump body sealing performance, pipeline connection reliability, and initial state of the downhole dynamic fluid level are checked to eliminate potential restart hazards. During the restart process, a low-frequency start method is used to gradually increase the operating speed of the electric submersible screw pump. Simultaneously, the dynamic response of the pump inlet pressure and motor output current is monitored in real time. The speed increase rate is dynamically adjusted according to the parameter change trend to avoid gas accumulation caused by the instantaneous load impact of high-frequency start. Through a smooth speed increase process, the pump body gradually restores its normal pumping function, effectively resolving the severe gas lock fault and promoting the unit to smoothly return to normal operation.

[0062] Step 303: If the airlock status is airlock released, maintain the current operating speed of the electric submersible screw pump unit until the electric submersible screw pump unit returns to the non-airlock state.

[0063] In this step, if the gas lock status is "gas lock relieved," it indicates that the control measures taken in the early stage to address the gas lock phenomenon have been effective, the gas discharge process in the pump is progressing steadily, and the unit's operating conditions are gradually transitioning to a stable state. At this time, the current operating speed of the electric submersible screw pump unit should be maintained to avoid fluctuations in the downhole dynamic fluid level and unstable pump inlet pressure caused by frequent speed adjustments, which could interfere with the gas lock resolution process. While maintaining the speed, it is necessary to continuously monitor the dynamic changes in pump inlet pressure and motor output current, capture subtle adjustments in the unit's operating status in real time, and judge the sustained effect of gas lock relief in conjunction with the stability of downhole medium supply. By maintaining the existing suitable operating conditions, a stable drainage environment is created for the pump body, which helps to fully discharge residual gas and ensures that key indicators such as downhole dynamic fluid level and pump load gradually return to the normal range until all operating parameters of the unit stably meet the standards of the non-gas lock state, thus achieving the complete elimination of the gas lock phenomenon and the smooth recovery of the unit.

[0064] Step 304: Monitor the operating parameters of the adjusted electric submersible screw pump unit and the corresponding airlock status change trend in real time to generate control effect feedback data.

[0065] In this step, after adjusting the corresponding operating status for the airlock condition, real-time monitoring of the electric submersible screw pump unit is initiated. The monitoring process focuses on the core operating parameters of the unit after adjustment, while tracking the airlock status change trends related to these parameters to ensure a complete capture of the dynamic evolution of the unit's operating status after the implementation of adjustment measures. Based on this, the operating parameter data and airlock status change information acquired during monitoring are collected, integrated, and sorted simultaneously. Invalid interference data generated during the monitoring process are eliminated, and key content that reflects the effectiveness of the adjustment measures is retained. Finally, comprehensive control effect feedback data is generated. This feedback data can not only be used to evaluate the effectiveness of the airlock prevention and control measures, but also provide direct data support for subsequent optimization of the judgment rules of the airlock condition identification model and improvement of differentiated adjustment strategies.

[0066] Step 305: Based on the control effect feedback data, evaluate the actual effectiveness of the adjustments made for each airlock state, and based on the actual effectiveness, optimize and update the judgment rule base in the airlock condition identification model.

[0067] In this step, the generated control effect feedback data serves as the core basis for evaluating the actual effectiveness of adjustment measures for different airlock states. The evaluation focuses on analyzing the changing trends of unit operating parameters and the improvement of the airlock state in the feedback data. It clarifies the effects of different adjustment strategies on different states such as initial and severe airlock, assesses the adaptability of adjustment measures to the corresponding airlock states, identifies the most effective control logic and execution path, and pinpoints deficiencies and areas for optimization in the adjustment process. Based on the evaluation results, the built-in judgment rule library of the airlock condition identification model is specifically optimized and updated. The operating condition matching conditions and feature judgment priorities within the rule library are adjusted in conjunction with actual control effectiveness, new effective feature information is added, and rule content inconsistent with actual operating conditions is corrected. This achieves dynamic adaptation between the judgment rule library and actual on-site operating conditions, continuously improving the accuracy and reliability of the airlock condition identification model, and ensuring that subsequent airlock prevention and control measures can achieve better results.

[0068] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide an anti-airlock device for an electric submersible screw pump based on operating condition identification, the structure of which is as follows: Figure 2 As shown.

[0069] Figure 2 This is a schematic diagram of the internal structure of an anti-airlock device for an electric submersible screw pump based on operating condition identification, provided as an embodiment of this application. Figure 2 As shown, the device includes:

[0070] At least one processor 201;

[0071] And a memory 202 that is communicatively connected to at least one processor;

[0072] The memory 202 stores instructions executable by at least one processor. These instructions are executed by at least one processor 201 to enable the processor 201 to: collect real-time operating parameters of the electric submersible screw pump unit based on the downhole detection device and surface control cabinet sensors of the unit, and preprocess the operating parameters to obtain standard operating parameters; wherein the operating parameters include pump inlet pressure and motor output current; extract pressure-current correlation features under airlock conditions to construct an airlock condition identification model, and input the standard operating parameters into the airlock condition identification model to obtain the airlock status level; and adjust the operation control strategy of the electric submersible screw pump unit based on the airlock status level to eliminate the airlock phenomenon.

[0073] Some embodiments of this application provide corresponding to Figure 1A non-volatile computer storage medium for preventing gas lock in an electric submersible screw pump based on operating condition identification is disclosed. The computer-executable instructions are configured to: collect real-time operating parameters of the electric submersible screw pump unit based on downhole detection devices and surface control cabinet sensors, and preprocess these parameters to obtain standard operating parameters; wherein the operating parameters include pump inlet pressure and motor output current; extract pressure-current correlation features under gas lock conditions to construct a gas lock condition identification model, and input the standard operating parameters into the gas lock condition identification model to obtain the gas lock status level; based on the gas lock status level, adjust the operating control strategy of the electric submersible screw pump unit to eliminate the gas lock phenomenon.

[0074] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0075] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0076] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0078] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0079] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0082] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0084] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for preventing airlock in an electric submersible screw pump based on operating condition identification, characterized in that, The method includes: Based on the downhole detection device and surface control cabinet sensors of the electric submersible screw pump unit, the operating parameters of the electric submersible screw pump unit are collected in real time, and the operating parameters are preprocessed to obtain standard operating parameters; wherein, the operating parameters include pump inlet pressure and motor output current; The pressure-current correlation features under airlock conditions are extracted to construct an airlock condition identification model, and the standard operating parameters are input into the airlock condition identification model to obtain the airlock status level. Based on the airlock status level, adjust the operation control strategy of the electric submersible screw pump unit to eliminate the airlock phenomenon; The method further includes: Constructing an airlock operating condition identification model, specifically including: The first historical data of the electric submersible screw pump unit under normal and stable liquid supply conditions is obtained to obtain a benchmark sample set. Extract the second historical data of the electric submersible screw pump unit before and after the airlock failure, and mark the time point of the airlock failure to obtain the airlock failure dataset; Based on the benchmark sample set and the airlock fault dataset, a correlation analysis is performed on the pump inlet pressure and the motor output current to obtain pressure-current correlation characteristics that characterize the occurrence of airlock. Based on the pressure-current correlation characteristics, a judgment rule base is constructed to distinguish between normal operating conditions and airlock operating conditions, so as to obtain the airlock operating condition identification model. Based on the airlock status level, the operation control strategy of the electric submersible screw pump unit is adjusted to eliminate the airlock phenomenon, specifically including: If the gas lock status level is the initial stage of gas lock, then adjust the operating speed of the electric submersible screw pump and control the downhole dynamic fluid level to be in a stable state; If the airlock condition is severe airlock, the operation of the electric submersible screw pump unit shall be stopped, and the speed shall be increased by low-frequency start after the gas in the pump is discharged. If the airlock state is airlock released, the current operating speed of the electric submersible screw pump unit is maintained until the electric submersible screw pump unit returns to the non-airlock state.

2. The method for preventing airlock in an electric submersible screw pump based on operating condition identification according to claim 1, characterized in that, Based on the benchmark sample set and the airlock fault dataset, a correlation analysis is performed on the pump inlet pressure and the motor output current to obtain pressure-current correlation characteristics characterizing airlock occurrence, specifically including: The variation law of pump inlet pressure and the stable range of motor output current under normal operating conditions are extracted from the reference sample set to establish the pressure-current reference correlation under normal operating conditions. The data of airlock failure is divided into segments before airlock occurs, during airlock development, and during airlock mitigation to generate segmented data for each stage of airlock. The segmented data of each stage of the airlock are compared with the pressure-current benchmark correlation under normal operating conditions, and the changing trend of pump inlet pressure and the fluctuation law of motor output current in each stage of the airlock are analyzed to obtain the pressure-current correlation characteristics.

3. The method for preventing airlock in an electric submersible screw pump based on operating condition identification according to claim 2, characterized in that, Based on the pressure-current correlation characteristics, a rule base for distinguishing between normal operating conditions and airlock operating conditions is constructed to obtain the airlock operating condition identification model, specifically including: The pressure-current correlation features are classified to output airlock early warning features, airlock development features, and airlock mitigation features; Based on the pressure-current reference correlation under normal operating conditions, the operating condition matching conditions and judgment priorities of the airlock early warning feature, the airlock development feature and the airlock mitigation feature are set to obtain the judgment rule base; Based on the benchmark sample set and the airlock fault dataset, the judgment rule base is optimized to output the airlock operating condition identification model.

4. The method for preventing airlock in an electric submersible screw pump based on operating condition identification according to claim 1, characterized in that, Based on the downhole monitoring device and surface control cabinet sensors of the electric submersible screw pump unit, the operating parameters of the electric submersible screw pump unit are collected in real time, and the operating parameters are preprocessed to obtain standard operating parameters, specifically including: The analog signal of pump inlet pressure output by the downhole detection device and the analog signal of motor output current of the sensor in the surface control cabinet are collected during the operation of the electric submersible screw pump unit. The analog signal of the pump inlet pressure and the analog signal of the motor output current are converted from analog to digital to obtain a first pressure digital sequence corresponding to the analog signal of the pump inlet pressure and a first current digital sequence corresponding to the analog signal of the motor output current. The first pressure digital sequence and the first current digital sequence are subjected to sliding filtering to obtain the filtered second pressure digital sequence and the second current digital sequence. The second pressure digital sequence and the second current digital sequence are aligned and standardized according to a preset timestamp to generate the standard operating parameters.

5. A method for preventing airlock in an electric submersible screw pump based on operating condition identification according to claim 4, characterized in that, Pressure-current correlation features under airlock conditions are extracted to construct an airlock condition identification model. The standard operating parameters are then input into the airlock condition identification model to obtain the airlock status level, specifically including: The second pressure digital sequence and the second current digital sequence in the standard operating parameters are coupled and analyzed to generate operating condition analysis data; The working condition analysis data is matched with the judgment rule base in the airlock working condition identification model to obtain the airlock status level; wherein, the airlock status level is divided into no airlock, initial airlock, severe airlock, and airlock relief.

6. The method for preventing airlock in an electric submersible screw pump based on operating condition identification according to claim 1, characterized in that, After adjusting the operating status of the electric submersible screw pump unit, the method further includes: Real-time monitoring of the adjusted operating parameters of the electric submersible screw pump unit and the corresponding airlock status change trend to generate control effect feedback data; Based on the control effect feedback data, the actual effectiveness of adjusting for each airlock state is evaluated, and based on the actual effectiveness, the judgment rule base in the airlock condition identification model is optimized and updated.

7. A gas lock prevention device for an electric submersible screw pump based on operating condition identification, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method as described in any one of claims 1-6.

8. A non-volatile computer storage medium for an anti-airlock system of an electric submersible screw pump based on operating condition identification, storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, they implement the method as described in any one of claims 1-6.

Images