A method, device and medium for dynamically controlling an ESP

Abstract

The application discloses a kind of ESP dynamic control method, equipment and medium, method includes: obtaining ESP in running process in real time running data in well;Wherein, real time running data in well at least includes following any one or more: pump inlet pressure signal, pump outlet pressure signal, motor torque signal, motor current signal and vibration signal;According to real time running data in well, the apparent viscosity value and gas cut value of current well fluid are inverted, and current gas-liquid two-phase flow pattern in well is identified;Wherein, gas-liquid two-phase flow pattern is the characteristic parameter for representing the flow pattern and phase distribution state of gas-liquid two-phase medium at pump suction inlet;According to the apparent viscosity value, gas cut value and gas-liquid two-phase flow pattern obtained by inversion, determine target speed adjustment strategy under current working condition;According to target speed adjustment strategy output speed command, to adjust the speed of ESP by speed command.

Description

Technical Field

[0001] This application relates to the field of electric submersible screw pump technology, specifically to a dynamic control method, equipment, and medium for an electric submersible screw pump. Background Technology

[0002] Electric submersible screw pumps (ESPs) directly connect a submersible motor to a screw pump and are lowered to the bottom of the well, lifting fluids using a volumetric principle. They are particularly suitable for complex conditions such as heavy oil wells, high-sand wells, high gas-liquid ratio wells, horizontal wells, and highly deviated wells. However, downhole fluid characteristics change dynamically in real time with production. Existing control methods, or those relying solely on lagging data such as surface dynamic fluid levels for speed adjustment, cannot respond in real time to the changing states of downhole multiphase flow. This leads to delayed control response, reduced lifting capacity, and even gas lock-up malfunctions. Summary of the Invention

[0003] To address the aforementioned problems, this application proposes a dynamic control method for an electric submersible screw pump, comprising: Acquire real-time downhole operating data of the electric submersible screw pump during operation; wherein the real-time downhole operating data includes at least one or more of the following: pump inlet pressure signal, pump outlet pressure signal, motor torque signal, motor current signal, and vibration signal; Based on the real-time downhole operating data, the apparent viscosity and gas content of the current downhole fluid are retrieved, and the current gas-liquid two-phase flow pattern is identified; wherein, the gas-liquid two-phase flow pattern is a characteristic parameter characterizing the flow pattern and phase distribution of the gas-liquid two-phase medium at the pump inlet. Based on the apparent viscosity value, the gas content value, and the gas-liquid two-phase flow pattern obtained by inversion, the target speed adjustment strategy under the current operating condition is determined. The speed command is output according to the target speed adjustment strategy, so as to adjust the speed of the electric submersible screw pump through the speed command.

[0004] This application provides a dynamic control device for an electric submersible screw pump, the device comprising: 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 are executed by the at least one processor to enable the at least one processor to perform a dynamic control method for an electric submersible screw pump as described in any of the preceding claims.

[0005] This application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: Perform a dynamic control method for an electric submersible screw pump as described in any of the preceding items.

[0006] The dynamic control method for an electric submersible screw pump proposed in this application can bring the following beneficial effects: By acquiring real-time downhole operating data of the ESP (Electric Submersible Screw Pump) during operation, the apparent viscosity, gas content, and gas-liquid two-phase flow pattern of the downhole fluid can be inverted. This allows for the perception of the real-time status of the downhole fluid characteristics. Compared to adjusting the pump speed based solely on lagging data such as the surface dynamic fluid level, this upgrades the input for control decisions from lagging surface signals to real-time multi-parameter downhole signals, fundamentally eliminating the time delay required for data transmission and fluid level recovery. Based on these parameters, a pump speed adjustment strategy can be determined and executed, enabling real-time dynamic adjustment for different downhole conditions. This allows for timely adaptation to changes in fluid viscosity, fluctuations in gas content, and the lifting requirements of different flow patterns, effectively improving the lifting efficiency of the ESP and reducing the probability of malfunctions such as gas lock. Attached Figure Description

[0007] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a dynamic control method for an electric submersible screw pump provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a dynamic control device for an electric submersible screw pump provided in an embodiment of this application. Detailed Implementation

[0008] 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.

[0009] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0010] like Figure 1 As shown in the embodiment of this application, a dynamic control method for an electric submersible screw pump includes: S101: Acquire real-time downhole operating data of the electric submersible screw pump during operation; wherein, the real-time downhole operating data includes at least one or more of the following: pump inlet pressure signal, pump outlet pressure signal, motor torque signal, motor current signal, and vibration signal.

[0011] Sensors such as pressure sensors, temperature sensors, triaxial accelerometers, strain gauge torque sensors, and current transformers, installed at the inlet and motor of the electric submersible screw pump, are used to collect pump inlet pressure signals, pump outlet pressure signals, motor torque signals, motor current signals, and vibration signals along the X, Y, and Z axes, respectively. The analog signals collected by these sensors are amplified, filtered, and converted from analog to digital by a signal conditioning and digitization module. Then, they are modulated by a carrier communication module and coupled to the motor's power cable for transmission to the surface. Upon receiving the signals, the surface system first performs outlier removal and digital filtering preprocessing to eliminate downhole environmental noise and transmission interference. Then, it synchronizes multiple signals from different acquisition frequencies using timestamp alignment to form real-time downhole operating data that can be used for subsequent inversion calculations.

[0012] S102: Based on real-time downhole operating data, invert the apparent viscosity and gas content of the current downhole fluid, and identify the current gas-liquid two-phase flow pattern in the downhole; wherein, the gas-liquid two-phase flow pattern is a characteristic parameter that characterizes the flow pattern and phase distribution of the gas-liquid two-phase medium at the pump inlet.

[0013] Based on the collected real-time downhole operating data, the downhole fluid properties and flow state, which cannot be directly measured, are calculated in reverse. Specifically, by using directly measurable pump inlet pressure signals, pump outlet pressure signals, motor torque signals, motor current signals, and vibration signals, the apparent viscosity, gas content, and current gas-liquid two-phase flow pattern of the downhole fluid are obtained, providing accurate operating condition data for subsequent speed control. The gas-liquid two-phase flow pattern is a characteristic parameter characterizing the flow pattern and phase distribution of the gas-liquid two-phase medium at the pump inlet.

[0014] In one embodiment, the apparent viscosity value is inverted based on the physical relationship between the drive torque of the electric submersible screw pump and the fluid viscosity. First, the measured motor torque, pump inlet pressure, and pump outlet pressure are extracted from the pre-processed real-time operating data. Then, the current operating speed of the electric submersible screw pump is obtained, and the pump inlet and outlet pressure difference is calculated based on the pump inlet and outlet pressures. The apparent viscosity value of the current downhole fluid can then be inverted using the motor torque, current operating speed, and pump inlet and outlet pressure difference.

[0015] Specifically, the viscous additional torque value is obtained by subtracting the rated torque value and the mechanical friction torque value from the motor torque value. The rated torque value refers to the driving torque required by the pump to operate with clean water as the medium under the same speed and pressure difference conditions. It is obtained through clean water tests completed on a screw pump performance test bench before leaving the factory and pre-stored in a calibration database. The value is then obtained by interpolation from this database based on the current operating speed and pressure difference. The mechanical friction torque value refers to the frictional torque generated between the rotor and stator, and between mechanical components such as bearings during pump operation. Its magnitude is related to the current speed and is obtained through pre-measured friction characteristic curves. The viscous additional torque is the additional resistance torque exerted by the fluid viscosity on pump operation. After obtaining this value, it is substituted into a viscous additional torque model based on the annular spiral flow theory. This model uses the pump's geometric parameters as known quantities and establishes a positive correlation between the viscous additional torque and the apparent viscosity of the fluid and the rotor speed. Based on this, the apparent viscosity value of the current downhole fluid can be calculated, reflecting the equivalent viscosity of a non-Newtonian fluid at a specific shear rate. Based on this, combined with the downhole temperature values ​​collected synchronously, the apparent viscosity value is corrected for temperature reduction according to the viscosity-temperature relationship commonly used in oilfields, and the apparent viscosity value reduced to the standard temperature is output to eliminate the interference of temperature fluctuations on viscosity determination.

[0016] The inversion of the gas content value is based on the frequency domain response characteristics of the pump inlet pressure signal and the motor current signal. The pump inlet pressure signal, pump outlet pressure signal, and motor current signal are extracted and subjected to spectral analysis. The pressure pulsation amplitude, the dominant frequency of the pressure pulsation, the current fluctuation amplitude, and the coherence coefficient of the pressure and current signals at characteristic frequencies are extracted as characteristic parameters of the gas content. Specifically, the pressure pulsation amplitude characterizes the intensity of pressure fluctuations caused by the gas-liquid two-phase flow within the pump; the dominant frequency of the pressure pulsation is the frequency component where the pressure fluctuation energy is most concentrated; the current fluctuation amplitude reflects the alternating component caused by changes in motor load with the gas content; and the coherence coefficient characterizes the degree of linear correlation between the pressure and current signals at characteristic frequencies. A higher coefficient indicates that the pressure pulsation and current fluctuation originate from the same source, which can be used to enhance the determination of the gas content. The extracted gas content feature parameters, together with the current operating speed and the pump inlet / outlet pressure difference, are used to form an input feature vector, which is then input into a pre-trained gas content inversion neural network model. This model uses feature parameter samples collected under different gas content conditions as training data and the actual gas content as a supervision label. After training, it can output the current pump inlet gas content value based on the input feature vector.

[0017] In one embodiment, the identification of the gas-liquid two-phase flow pattern is achieved based on the combined time-frequency domain characteristics of the pump inlet pressure signal and vibration signal. In this embodiment, the gas-liquid two-phase flow pattern refers to the characteristic parameters of the flow morphology and phase distribution state of the gas-liquid two-phase medium at the pump inlet, specifically including bubbly flow, slug flow, annular flow, and airlock state. Different flow patterns correspond to different gas-liquid distribution patterns and flow characteristics, which have a decisive impact on the pump's lifting performance. The pump inlet pressure signal and vibration signal are extracted from the preprocessed real-time operating data, and multi-scale time-frequency decomposition is performed on both types of signals. The energy proportion characteristics of the pump inlet pressure signal in three preset frequency bands (low frequency, mid frequency, and high frequency) are extracted. These energy proportion characteristics reflect the energy distribution of pressure fluctuations at different scales and are key characteristics for distinguishing between bubbly flow, slug flow, and annular flow states. The rotor frequency and amplitude characteristics at its harmonics are extracted from the vibration signal. These amplitude characteristics integrate the vibration response in three axes and reflect the difference in the degree of vibration of the pump body when impacted by different flow patterns, especially showing obvious frequency domain characteristic changes under slug flow and annular flow conditions. The extracted energy proportion features and amplitude features are used to construct a flow pattern discrimination feature vector, which is then input into a pre-trained flow pattern classifier based on support vector machine to output the current gas-liquid two-phase flow pattern category in the well.

[0018] S103: Based on the apparent viscosity value, gas content value and gas-liquid two-phase flow pattern obtained by inversion, determine the target speed adjustment strategy under the current operating conditions.

[0019] Apparent viscosity reflects the equivalent viscosity of the downhole fluid under pumping conditions, and its level directly determines the magnitude of viscous resistance and volumetric efficiency during pump operation. Gas content reflects the volume ratio of gas at the pump inlet, and its level determines the compressibility of the gas-liquid two-phase medium inside the pump and the degree of filling of the sealing cavity. Gas-liquid two-phase flow pattern describes the phase distribution state of the gas-liquid two-phase medium at the pump inlet from the perspective of flow morphology. Different flow patterns have different mechanisms of influence on pump lifting performance. In bubbly flow, gas is uniformly dispersed in the liquid phase in the form of small bubbles, and its impact on pump efficiency is relatively small. In slug flow, gas and liquid alternately enter the pump cavity in a slug-like manner, which can easily cause periodic load fluctuations and may develop into a precursor to gas lock. In annular flow and gas lock states, gas occupies the main volume of the pump cavity, and the pump cannot establish an effective lifting pressure difference. The three parameters mentioned above collectively characterize the real-time status of downhole conditions from different dimensions. Therefore, it is necessary to combine these three parameters to jointly determine the target speed adjustment strategy required for the electric submersible screw pump, so as to adjust the speed to adapt the electric submersible screw pump to the real-time downhole conditions, maintain maximum lifting efficiency, and avoid failures such as gas lock.

[0020] In one embodiment, determining the target speed adjustment strategy under the current operating condition means comparing the inverted apparent viscosity value, gas content value, and identified gas-liquid two-phase flow pattern with their respective preset thresholds and states, calculating the corresponding speed adjustment components in the three dimensions of deceleration adjustment, acceleration adjustment, and flow pattern response, and then forming a unique speed command value after weighted summation.

[0021] The triggering condition for the speed reduction adjustment component depends on the apparent viscosity value. When the apparent viscosity value exceeds the preset viscosity threshold, it indicates that the downhole fluid viscosity is too high, which leads to increased viscous resistance and decreased volumetric efficiency of the pump. At this time, it is necessary to reduce the speed to reduce the slip loss of the fluid in the pump cavity and bring the pump back to the high-efficiency operating range. The magnitude of the speed reduction adjustment component is positively correlated with the first deviation of the apparent viscosity value exceeding the threshold. That is, the higher the viscosity, the greater the speed reduction. However, the speed reduction is limited by the preset minimum effective speed value to ensure basic lifting capacity.

[0022] Specifically, when calculating the speed reduction adjustment component, it is first necessary to calculate the first deviation between the apparent viscosity value and the preset viscosity threshold. The first deviation characterizes the degree to which the current downhole fluid viscosity exceeds the limit. When the first deviation is positive, it indicates that the apparent viscosity value has exceeded the preset viscosity threshold, triggering the speed reduction adjustment condition. At this time, it is necessary to determine the specific absolute value of the speed reduction adjustment based on the preset speed reduction characteristic curve. The speed reduction characteristic curve is an empirical curve obtained in advance through performance tests of screw pumps under different viscosity media. Its horizontal axis is the first deviation, and the vertical axis is the absolute value of the speed reduction adjustment. The curve shape is a power function increasing relationship. The power function increasing relationship means that the absolute value of the speed reduction adjustment increases monotonically according to the power function law as the first deviation increases. Its characteristic is that when the deviation is small, the speed reduction increases slowly, and as the deviation continues to increase, the speed reduction gradually accelerates. This shape conforms to the nonlinear law of pump efficiency decay under high viscosity conditions. When the viscosity is slightly exceeded, only a small speed reduction is needed to bring the pump back to the high-efficiency range. However, when the viscosity is severely exceeded, since the pump efficiency has dropped significantly, a larger speed reduction is needed to effectively improve the working condition. After obtaining the absolute value of the speed reduction adjustment corresponding to the first deviation through the speed reduction characteristic curve, this absolute value is taken as negative to form the speed reduction adjustment component. This negative value indicates that the corresponding speed needs to be subtracted from the current speed during subsequent weighted summation. To ensure the safe operation of the equipment and basic lifting capacity, the absolute value of the speed reduction adjustment component is limited to no more than a first preset percentage of the current operating speed value. For example, the first preset percentage can be set to 10% of the current operating speed value, meaning that no matter how severe the viscosity exceedance, the single speed reduction will not exceed 10% of the current speed. This limiting mechanism avoids supply and discharge imbalance caused by excessive single speed reduction, and also reserves space for continuous adjustment in subsequent control cycles, allowing the speed to gradually approach the optimal value.

[0023] The trigger condition for the speed adjustment component depends on the gas content value. When the gas content value exceeds the preset gas content warning threshold, it indicates that the gas content at the pump inlet has increased to a range that may affect the normal operation of the pump. At this time, it is necessary to increase the speed to enhance the shearing effect of the fluid inside the pump, promote the breakup of large bubbles into small bubbles, thereby delaying gas-liquid separation. At the same time, the pump's discharge capacity should be increased to discharge the gas entering the pump in a timely manner, preventing the gas from accumulating at the top of the pump cavity and forming an airlock. The magnitude of the speed adjustment component is positively correlated with the relative position of the current gas content value between the preset gas content warning threshold and the critical gas content value for airlock. That is, the closer the gas content is to the critical value for airlock, the greater the speed increase. However, the speed increase is limited by the preset maximum allowable speed value to ensure the safe operation of the equipment.

[0024] Specifically, the second deviation between the gas content value and the preset gas content warning threshold, and the third deviation between the airlock critical gas content value and the preset gas content warning threshold are calculated. The preset gas content warning threshold refers to the critical point where pump efficiency begins to decline significantly after the gas content rises to this value, requiring active intervention. The airlock critical gas content value refers to the critical point where gas in the pump chamber has occupied the main volume after the gas content rises to this value, and the pump cannot establish an effective lifting pressure difference. Together, they define the dangerous range from requiring intervention to imminent failure. After obtaining the second and third deviations, the ratio of the second deviation to the third deviation is calculated. This ratio is used as the relative position value of the gas content, representing the relative position of the current gas content between the preset gas content warning threshold and the airlock critical gas content value. When the relative position value of the gas content is close to 0, it indicates that the gas content has just exceeded the warning threshold, with a low degree of danger. When the relative position value of the gas content is close to 1, it indicates that the gas content is approaching the airlock critical value, with an extremely high degree of danger.

[0025] When the second deviation is positive, it indicates that the gas content has exceeded the preset gas content warning threshold, triggering the speed adjustment condition. At this point, the speed adjustment amount corresponding to the relative position value of the gas content is determined according to the preset speed adjustment characteristic curve. The speed adjustment characteristic curve is an empirical curve obtained in advance through performance tests of the screw pump under different gas content conditions. Its horizontal axis represents the relative position value of the gas content, and the vertical axis represents the speed adjustment amount. The curve shows a positively increasing relationship between the speed adjustment amount and the relative position value of the gas content. That is, the higher the relative position value of the gas content, the closer the current gas content is to the air lock critical value, and the larger the speed adjustment amount is. This ensures that sufficient speed increase is provided when the gas content approaches the critical value to urgently expel the gas in the pump and avoid air lock. After obtaining the speed adjustment amount through the speed adjustment characteristic curve, this speed adjustment amount is used as the speed adjustment component. This component is positive, indicating that a corresponding speed increase needs to be added to the current speed during subsequent weighted summation. To ensure safe equipment operation, the amplitude of the speed adjustment component is limited to a second preset percentage of the current operating speed. Compared to directly comparing the gas content value with a single threshold and outputting a fixed speed increase, the introduction of the relative position value of the gas content allows the speed increase amplitude to be continuously adjusted with the continuous change of the gas content. When the gas content slightly exceeds the standard, a smaller speed increase is used to maintain pump efficiency, and a larger speed increase is used for emergency intervention when the gas content approaches the gas lock threshold. This achieves fine control throughout the entire range from early warning to critical.

[0026] The triggering condition of the flow pattern response component depends on the identification result of the gas-liquid two-phase flow pattern. When the identification result is bubbly flow, the gas is uniformly dispersed in the liquid phase in the form of small bubbles, which has little impact on pump efficiency, so no special flow pattern response adjustment is required. When the identification result is annular flow or airlock, it indicates that the pump is in a severely gas-laden condition, requiring additional positive speed compensation to forcefully expel the gas accumulated in the pump and attempt to restore the pump's normal filling and lifting capabilities. The compensation slope in the airlock state is greater than that in the annular flow state to accommodate a higher level of urgency. When the identification result is slug flow, it indicates that the pump is in the precursor stage of airlock, requiring additional periodic speed compensation matching the dominant frequency of the slug fluctuation. This is done by actively changing the speed to disrupt the stable formation conditions of the slug flow, making the gas-liquid two-phase flow more homogenized, thereby guiding the flow pattern towards bubbly flow. The amplitude of the periodic speed compensation is positively correlated with the severity reflected by the slug characteristic amplitude, and its frequency must match the dominant frequency of the slug fluctuation to produce an effective resonance destructive effect.

[0027] Specifically, the gas-liquid two-phase flow pattern identification results output by the aforementioned flow pattern classifier are obtained. When the identification result is an annular flow state or a gas lock state, it indicates that the gas content in the pump is already at a high level and the pump's lifting capacity is seriously threatened. At this time, emergency speed increase intervention is required. The positive speed compensation amount is calculated as the flow pattern response component based on the current gas content value. This positive speed compensation amount is positive, indicating that an additional speed amount needs to be added on the basis of the current speed in the subsequent weighted summation. This is to enhance the fluid shearing and discharge capacity in the pump chamber by forcibly increasing the speed, and to forcibly discharge the gas accumulated in the pump chamber, thereby attempting to restore the pump's normal filling and lifting capacity. When the identification result is a slug flow state, it indicates that the pump is in the early stage of airlock. At this time, it has not yet reached the level where continuous emergency speed increase is required. However, if no intervention is taken, the continued development of the slug flow may further evolve into annular flow or even airlock. Therefore, it is necessary to calculate the periodic speed compensation amount as the flow pattern response component based on the slug fluctuation main frequency of the pump inlet pressure signal. This periodic speed compensation amount is a fluctuation amount with positive and negative alternations centered at zero. That is, within a slug fluctuation cycle, the speed increases for part of the time and decreases for part of the time. Its fluctuation frequency matches the slug fluctuation main frequency. By actively applying a speed disturbance with the same frequency as the slug flow, the stable formation conditions of the slug flow are disrupted, making the gas-liquid two-phase flow tend to be homogenized, thereby guiding the flow pattern towards bubbly flow. Through the above two differentiated flow pattern response rules, the system can actively intervene in the slug flow precursor stage with frequency-matched periodic disturbances to prevent the flow pattern from further deteriorating into annular flow and gas lock state. When it has entered annular flow or gas lock state, it can force the gas to be expelled with continuous positive acceleration and attempt to restore the normal operation of the pump. Thus, control measures adapted to the physical characteristics can be adopted under gas-containing conditions of different severity.

[0028] Finally, the deceleration adjustment component, acceleration adjustment component, and flow pattern response component are multiplied by their respective preset weighting coefficients and summed to obtain the comprehensive speed adjustment amount. This comprehensive speed adjustment amount is then superimposed on the current operating speed value and limited by a preset speed safety boundary to ensure that the final output speed command neither exceeds the safe operating range of the equipment nor fails to optimize the lifting capacity under the current operating conditions. Through the above comprehensive decision-making mechanism, the control signal of the electric submersible screw pump is upgraded from single-parameter drive to multi-parameter joint drive. The apparent viscosity value, gas content value, and flow pattern information obtained from the above inversion are directly converted into an executable target speed adjustment strategy, forming a complete information link from downhole perception to surface decision-making, enabling the pump speed to adaptively adjust in real time according to changes in downhole operating conditions.

[0029] S104: Outputs a speed command according to the target speed adjustment strategy, so as to adjust the speed of the electric submersible screw pump through the speed command.

[0030] Based on the target speed adjustment strategy, a corresponding speed command is output to the frequency converter of the electric submersible screw pump. Upon receiving the speed command, the frequency converter adjusts the motor frequency to regulate the output speed of the electric submersible screw pump. Thus, when downhole conditions are stable, the system outputs a command to maintain the current speed, the frequency converter maintains the existing power supply frequency, and the pump operates smoothly at a fixed speed. However, when downhole conditions change, such as a sudden increase in viscosity due to rising water cut, an increase in gas production leading to higher gas cut, or a change in flow pattern from bubbly to slug flow, the above adjustment mechanism enables the electric submersible screw pump speed to continuously and adaptively adjust to the dynamic changes in downhole fluid characteristics, achieving real-time optimization of lifting capacity.

[0031] The above are embodiments of the methods proposed in this application. Based on the same idea, some embodiments of this application also provide devices and non-volatile computer storage media corresponding to the above methods.

[0032] Figure 2 This is a structural schematic diagram of a dynamic control device for an electric submersible screw pump, provided as an embodiment of this application. Figure 2 As shown, it includes: At least one processor; and, At least one processor-communication-connected memory; wherein, The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform a dynamic control method for an electric submersible screw pump as described in any of the preceding claims.

[0033] This application provides a non-volatile computer storage medium storing computer-executable instructions, which are configured as follows: One of the above is a dynamic ad delivery method based on image relevance.

[0034] 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 device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0035] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices 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 devices and media will not be repeated here.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0041] 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.

[0042] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using 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.

[0043] 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.

[0044] 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 dynamic control method for an electric submersible screw pump, characterized in that, The method includes: Acquire real-time downhole operating data of the electric submersible screw pump during operation; wherein the real-time downhole operating data includes at least one or more of the following: pump inlet pressure signal, pump outlet pressure signal, motor torque signal, motor current signal, and vibration signal; Based on the real-time downhole operating data, the apparent viscosity and gas content of the current downhole fluid are retrieved, and the current gas-liquid two-phase flow pattern is identified; wherein, the gas-liquid two-phase flow pattern is a characteristic parameter characterizing the flow pattern and phase distribution of the gas-liquid two-phase medium at the pump inlet. Based on the apparent viscosity value, the gas content value, and the gas-liquid two-phase flow pattern obtained by inversion, the target speed adjustment strategy under the current operating condition is determined. The speed command is output according to the target speed adjustment strategy, so as to adjust the speed of the electric submersible screw pump through the speed command.

2. The dynamic control method for an electric submersible screw pump according to claim 1, characterized in that, Based on the real-time downhole operating data, the apparent viscosity and gas content of the current downhole fluid are retrieved, specifically including: From the real-time downhole operating data, extract the motor torque value, pump inlet pressure value, and pump outlet pressure value; Obtain the current operating speed of the electric submersible screw pump, and calculate the pump inlet and outlet pressure difference based on the pump inlet pressure and the pump outlet pressure. The apparent viscosity of the current downhole fluid is obtained by inverting the motor torque value, the current operating speed value, and the pump inlet and outlet pressure difference value. The pump inlet pressure signal, the pump outlet pressure signal, and the motor current signal are subjected to spectral analysis to extract gas content characteristic parameters; wherein, the gas content characteristic parameters include pressure pulsation amplitude, pressure pulsation frequency, current fluctuation amplitude, and coherence coefficient of pressure signal and current signal at characteristic frequencies; Based on the gas content characteristic parameters, the current operating speed, and the pump inlet and outlet pressure difference, a corresponding feature vector is constructed. The feature vector is input into a pre-trained gas content inversion neural network model to output the gas content value of the electric submersible screw pump.

3. The dynamic control method for an electric submersible screw pump according to claim 2, characterized in that, Based on the motor torque value, the current operating speed value, and the pump inlet and outlet pressure difference value, the apparent viscosity value of the current downhole fluid is obtained by inversion, specifically including: Subtract the rated torque value and the mechanical friction torque value from the motor torque value to obtain the viscous additional torque value; wherein, the rated torque value is obtained by interpolation and table lookup from the calibration database based on the current operating speed value and the pump inlet and outlet pressure difference value, and the mechanical friction torque value is obtained from the friction characteristic curve based on the current operating speed value; The viscous additional torque value is input into a preset viscous additional torque model to invert and obtain the apparent viscosity value of the current downhole fluid. The apparent viscosity value is corrected based on the real-time collected downhole temperature value to obtain the apparent viscosity value at the standard temperature.

4. The dynamic control method for an electric submersible screw pump according to claim 1, characterized in that, Identifying the current gas-liquid two-phase flow pattern in the well, specifically including: Multi-scale time-frequency decomposition is performed on the pump inlet pressure signal and the vibration signal respectively to extract the energy proportion characteristics of the pump inlet pressure signal within a preset frequency band and the amplitude characteristics of the vibration signal. Based on the energy proportion characteristics and the amplitude characteristics, a corresponding flow pattern feature vector is constructed; The flow pattern feature vector is input into a pre-trained flow pattern classifier to identify the current gas-liquid two-phase flow pattern in the well; wherein the gas-liquid two-phase flow pattern includes at least bubbly flow, slug flow, annular flow, and gas lock.

5. The dynamic control method for an electric submersible screw pump according to claim 1, characterized in that, Based on the apparent viscosity value, the gas content value, and the gas-liquid two-phase flow pattern obtained from the inversion, a target speed adjustment strategy under the current operating condition is determined, specifically including: Calculate the corresponding deceleration adjustment component based on the first deviation between the apparent viscosity value and the preset viscosity threshold; Calculate the corresponding acceleration adjustment component based on the gas content value and the critical gas content value of the airlock; Calculate the corresponding flow pattern response components according to the flow pattern response rules that match the gas-liquid two-phase flow pattern; The deceleration adjustment component, the acceleration adjustment component, and the flow pattern response component are weighted and summed to obtain the comprehensive speed adjustment amount. The current operating speed value is superimposed with the comprehensive speed adjustment amount, and the amplitude is limited by a preset speed safety boundary to generate the target speed adjustment strategy under the current operating conditions.

6. The dynamic control method for an electric submersible screw pump according to claim 5, characterized in that, Based on the first deviation between the apparent viscosity value and the preset viscosity threshold, the corresponding deceleration adjustment component is calculated, specifically including: Calculate the first deviation between the apparent viscosity value and the preset viscosity threshold. When the first deviation is greater than 0, obtain the absolute value of the deceleration adjustment corresponding to the first deviation according to the preset deceleration characteristic curve. The deceleration characteristic curve represents the power function increasing relationship between the absolute value of the deceleration adjustment and the first deviation. The absolute value of the speed reduction adjustment amount is taken as the speed reduction adjustment component; wherein, the absolute value of the speed reduction adjustment component does not exceed a first preset percentage of the current operating speed value.

7. The dynamic control method for an electric submersible screw pump according to claim 5, characterized in that, Based on the gas content value and the critical gas content value of the airlock, the corresponding acceleration adjustment component is calculated, specifically including: Determine a second deviation between the gas content value and the preset gas content warning threshold, and a third deviation between the gas lock critical gas content value and the preset gas content warning threshold; Calculate the ratio of the second deviation to the third deviation, and use the ratio as the relative position value of the gas content; When the second deviation is greater than 0, the acceleration adjustment amount corresponding to the relative position value of the gas content is determined according to the preset acceleration characteristic curve; wherein, the acceleration characteristic curve represents the positive correlation and increasing relationship between the acceleration adjustment amount and the relative position value of the gas content; The speed adjustment amount is taken as the speed adjustment component; wherein the amplitude of the speed adjustment component does not exceed a second preset percentage of the current operating speed value.

8. The dynamic control method for an electric submersible screw pump according to claim 5, characterized in that, Based on the flow pattern response rules that match the gas-liquid two-phase flow pattern, the corresponding flow pattern response components are calculated, specifically including: Obtain the identification result of the gas-liquid two-phase flow pattern; When the identification result is a ring flow state or an airlock state, the positive speed compensation amount corresponding to the electric submersible screw pump is calculated as the flow pattern response component based on the gas content value. When the identification result is a slug flow state, the periodic speed compensation is calculated as the flow pattern response component based on the slug fluctuation main frequency of the pump inlet pressure signal.

9. A dynamic control device for an electric submersible screw pump, 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 are executed by the at least one processor to enable the at least one processor to perform a dynamic control method for an electric submersible screw pump as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: A dynamic control method for an electric submersible screw pump as described in any one of claims 1-8.

Images