A method, device and medium for regulating dry grinding and gas locking of an electric submersible screw pump

Abstract

The application discloses a kind of electric submersible screw pump dry grinding and air lock regulation and control method, equipment and medium, it is related to mining equipment fault regulation and control field.The method comprises: obtaining motor winding temperature data, pump inlet pressure data and unit vibration data in the operation process of electric submersible screw pump;According to motor winding temperature data and pump inlet pressure data respectively, extract temperature change rate and pressure fluctuation amplitude, and according to unit vibration data, extract the energy value of preset frequency band in vibration spectrum;Temperature change rate, pressure fluctuation amplitude and the energy value of preset frequency band are input into the risk identification model constructed in advance, and the risk type is output;When the output risk type is dry grinding risk or air lock risk, adaptive control sequence is carried out.The application realizes the multi-parameter fusion identification of dry grinding risk and air lock risk by the above method, can accurately distinguish the early signs of two fault modes, avoids the misjudgment and missed judgment caused by single parameter monitoring.

Description

Technical Field

[0001] This application relates to the field of fault control technology for mining equipment, and in particular to a method, equipment and medium for controlling dry grinding and air lock of an electric submersible screw pump. Background Technology

[0002] Electric submersible screw pumps (ESPs), as a type of artificial lift equipment, are widely used in oil extraction operations in complex well conditions such as heavy oil, high sand content, and steep inclination. During ESP operation, insufficient downhole fluid supply leads to a lack of lubrication and cooling within the pump, causing dry friction between the rotor and stator, resulting in rapid ablation and damage to the stator rubber. Furthermore, excessively high gas content in the well fluid causes gas to accumulate at the pump inlet, forming an airlock that drastically reduces pump efficiency or even prevents fluid discharge. These two failure modes are the most common causes of ESP failure, severely impacting equipment lifespan and oil production efficiency.

[0003] In existing technologies, early warning of dry grinding and airlock risks mainly relies on monitoring a single parameter, such as judging the liquid supply status by the pump inlet pressure or judging the load change by the motor current. However, a single parameter is difficult to accurately distinguish the early signs of dry grinding and airlock, which can easily lead to misjudgment or missed judgment. Moreover, most existing technologies take shutdown protection measures after the failure occurs, and cannot actively intervene before the failure occurs, making it difficult to achieve continuous production and maximize equipment life.

[0004] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0005] Existing technologies for dry running and air lock warnings in electric submersible screw pumps cannot accurately distinguish between the early signs of dry running and air lock, nor can they intervene before a failure occurs. Summary of the Invention

[0006] This application provides a method, device, and medium for controlling dry running and air lock in an electric submersible screw pump. It can solve the problems in the prior art where early warning of dry running and air lock in electric submersible screw pumps cannot accurately distinguish the early signs of dry running and air lock, and cannot intervene before the failure occurs.

[0007] In a first aspect, embodiments of this application provide a method for controlling dry running and airlock in an electric submersible screw pump. The method comprises: acquiring motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of the electric submersible screw pump; extracting the temperature change rate and pressure fluctuation amplitude based on the motor winding temperature data and pump inlet pressure data, and extracting the energy value of a preset frequency band from the vibration spectrum based on the unit vibration data; inputting the temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band into a pre-constructed risk identification model, and outputting a risk type, including dry running risk, airlock risk, and no risk; when the output risk type is dry running risk or airlock risk, performing an adaptive control sequence, which includes a deceleration phase, a pulse backflush phase, and a recovery phase executed sequentially.

[0008] In one implementation of this application, acquiring motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of an electric submersible screw pump specifically includes: obtaining motor winding temperature data through electrical parameter inversion of the motor winding, specifically including: injecting a high-frequency detection signal into the motor winding to collect the impedance spectrum characteristics of the motor winding; and calculating the motor winding temperature data based on the mapping relationship between the impedance spectrum characteristics and temperature.

[0009] In one implementation of this application, before extracting the energy value of a preset frequency band from the vibration spectrum based on the unit vibration data, the method further includes: performing blind source separation on the unit vibration data to obtain the motor excitation source component, the fluid excitation source component, and the mechanical friction source component; the energy value of the preset frequency band is extracted from the mechanical friction source component to eliminate the interference of motor excitation and fluid excitation on the dry grinding feature identification.

[0010] In one implementation of this application, the temperature change rate and pressure fluctuation amplitude are extracted based on the motor winding temperature data and pump inlet pressure data, respectively. Furthermore, the energy value of a preset frequency band in the vibration spectrum is extracted based on the unit vibration data. Specifically, this includes: extracting the temperature difference and time interval of the motor winding temperature data within a sliding time window to obtain the temperature change rate; extracting the maximum and minimum pressure values ​​of the pump inlet pressure data within a sliding time window to obtain the pressure fluctuation amplitude; performing a fast Fourier transform on the mechanical friction source component to obtain the vibration spectrum; and extracting the energy value of a preset frequency band in the vibration spectrum, where the preset frequency band corresponds to the characteristic frequency range generated by dry friction between the rotor and stator.

[0011] In one implementation of this application, the temperature change rate, pressure fluctuation amplitude, and energy value of a preset frequency band are input into a pre-constructed risk identification model, and the risk type is output. Specifically, this includes: determining a contact force threshold based on the preset interference fit between the rotor and stator of the electric submersible screw pump and the allowable contact stress of the stator rubber material; during bench testing, when the contact force between the rotor and stator reaches the contact force threshold, collecting a first temperature change rate, a first pressure fluctuation amplitude, and a first vibration spectrum energy value as the dry friction risk characteristic center; and considering the influence of the gas volume fraction at the pump inlet of the electric submersible screw pump on the pump efficiency. The following steps are taken: First, a gas phase volume fraction threshold is determined. Second, during bench testing, when the gas phase volume fraction at the pump inlet reaches the gas phase volume fraction threshold, the second temperature change rate, the second pressure fluctuation amplitude, and the second vibration spectrum energy value are collected as the airlock risk characteristic center. Third, during bench testing of the electric submersible screw pump under rated operating conditions, the third temperature change rate, the third pressure fluctuation amplitude, and the third vibration spectrum energy value are collected as the risk-free characteristic center. The similarity between the temperature change rate, pressure fluctuation amplitude, and the energy value of the preset frequency band and the dry grinding risk characteristic center, the airlock risk characteristic center, and the risk-free characteristic center is calculated to determine the risk type.

[0012] In one implementation of this application, when the output risk type is dry grinding risk or airlock risk, an adaptive control sequence is performed, specifically including: reducing the speed of the electric submersible screw pump to a first target speed at a preset deceleration rate and maintaining it for a first preset duration, while continuously monitoring the pump inlet pressure data; if the pump inlet pressure data recovers to the normal value during the deceleration process, the deceleration phase ends and the recovery phase begins.

[0013] In one implementation of this application, the method further includes: after the deceleration phase ends, entering the pulse backflush phase, controlling the rotational speed of the electric submersible screw pump to alternately accelerate and decelerate in a preset pulse pattern to generate pressure pulses to break the airlock; the pulse pattern includes multiple pulse cycles, each pulse cycle including the process of accelerating to a second target speed and then immediately decelerating to a third target speed; during the pulse backflush phase, continuously monitoring the pump inlet pressure data and unit vibration data, and ending the pulse backflush phase when the pump inlet pressure data is stable and the energy value of the preset frequency band in the vibration spectrum is lower than a preset threshold.

[0014] In one implementation of this application, the method further includes: after the pulse backflush phase ends, increasing the speed of the electric submersible screw pump to the original speed at a preset acceleration rate; during the acceleration process, acquiring real-time data on motor winding temperature, pump inlet pressure, and unit vibration.

[0015] Secondly, embodiments of this application also provide a control device for dry grinding and airlock of an electric submersible screw pump. 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 are executed by the at least one processor to enable the at least one processor to perform any step of a control method for dry grinding and airlock of an electric submersible screw pump.

[0016] Thirdly, embodiments of this application also provide a non-volatile computer storage medium for regulating dry grinding and airlock of an electric submersible screw pump, storing computer-executable instructions, which are configured to execute any one of the steps of a method for regulating dry grinding and airlock of an electric submersible screw pump.

[0017] This application provides a method for controlling dry running and airlock in an electric submersible screw pump. The first affected medium is obtained by acquiring motor winding temperature data, pump inlet pressure data, and unit vibration data. Temperature change rate, pressure fluctuation amplitude, and energy values ​​of preset frequency bands in the vibration spectrum are extracted respectively, achieving multi-parameter fusion identification of dry running and airlock risks. This accurately distinguishes early signs of the two fault modes, avoiding misjudgments and omissions caused by single-parameter monitoring. Through a pre-constructed risk identification model, the risk type can be output in a timely manner before dry running or airlock occurs, providing a basis for proactive intervention. When a risk is identified, an adaptive control sequence including a deceleration phase, a pulse backflush phase, and a recovery phase is executed. Deceleration alleviates the degree of dry running, pulse backflush breaks the airlock, and step-wise recovery avoids secondary risks. Attached Figure Description

[0018] 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:

[0019] Figure 1 A flowchart illustrating a method for controlling dry grinding and air lock in an electric submersible screw pump, provided in an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of the internal structure of a control device for dry grinding and air lock of an electric submersible screw pump, provided in an embodiment of this application. Detailed Implementation

[0021] 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.

[0022] This application provides a method, device, and medium for controlling dry running and air lock in an electric submersible screw pump, which solves the problems in the prior art where early warning of dry running and air lock in electric submersible screw pumps cannot accurately distinguish the early signs of dry running and air lock, and cannot intervene before the failure occurs.

[0023] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0024] Figure 1 This is a flowchart illustrating a method for controlling dry grinding and airlock in an electric submersible screw pump, as provided in an embodiment of this application. Figure 1 As shown in the embodiment of this application, a method for controlling dry grinding and air lock of an electric submersible screw pump specifically includes the following steps:

[0025] Step 10: Obtain motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of the electric submersible screw pump.

[0026] In this step, the working state of the electric submersible screw pump during downhole operation is affected by various factors such as fluid supply capacity, fluid properties, and equipment wear. The motor winding temperature data reflects the motor's heat dissipation and load conditions. When dry friction is about to occur, the friction between the rotor and stator intensifies, the motor load increases, and the winding temperature shows a rapid upward trend. The pump inlet pressure data reflects the downhole fluid supply capacity and pump suction conditions. When gas lock is about to occur, gas periodically accumulates and releases at the pump inlet, causing significant fluctuations in the pump inlet pressure. When dry friction occurs between the rotor and stator, impact vibrations within a specific frequency range will be generated.

[0027] In this way, the temperature data of the motor windings can be obtained by inverting the electrical parameters of the motor windings, eliminating the need to install additional temperature sensors downhole. This avoids the problem of sensors easily failing under high temperature and high pressure environments, while also reducing the number of connection points and sealing links in the downhole unit, thus improving system reliability.

[0028] As an optional embodiment, acquiring motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of the electric submersible screw pump can specifically include: obtaining motor winding temperature data through electrical parameter inversion of the motor winding, specifically including: step 101: injecting a high-frequency detection signal into the motor winding and collecting the impedance spectrum characteristics of the motor winding.

[0029] In this step, the frequency of the detection signal should be much higher than the driving frequency of the motor during normal operation to avoid interfering with the normal operation of the motor; the amplitude of the detection signal should be small enough to ensure that it does not cause additional stress to the motor insulation system; the response signal is collected at the input end of the motor winding. Since the injected detection signal and the motor drive signal are in different frequency bands, they can be separated by filtering; the collected response signal is subjected to spectrum analysis or impedance analysis to calculate the impedance spectrum characteristics of the motor winding at the current moment, which may include the relationship between the resistance component and the frequency, the relationship between the inductance component and the frequency, or the resistance and inductance values ​​at a specific frequency point.

[0030] Step 102: Calculate the motor winding temperature data based on the mapping relationship between impedance spectrum characteristics and temperature.

[0031] In this step, the resistivity of the motor windings changes with temperature. This physical characteristic establishes a definite mapping relationship between the resistance component and temperature. Simultaneously, the inductance component of the windings is also affected by temperature, as temperature changes cause slight changes in the permeability of the winding material. An impedance spectrum-temperature mapping database for this type of motor winding is pre-established in a laboratory environment. The motor is placed in a precisely temperature-controlled chamber, and high-frequency detection signals are injected at different temperature points to collect and record the impedance spectrum characteristics corresponding to each temperature point. Furthermore, during actual operation, the current impedance spectrum characteristics collected in step 101 are compared. A nearest neighbor search algorithm can be used to find the temperature value that best matches the current impedance spectrum characteristics in a lookup table, or an interpolation algorithm can be used to calculate continuous temperature values ​​between adjacent temperature points. The final calculated temperature value is the current motor winding temperature data.

[0032] As an optional embodiment, before extracting the energy value of a preset frequency band in the vibration spectrum based on the unit vibration data, the method may further include: Step 01: performing blind source separation on the unit vibration data to obtain the motor excitation source component, the fluid excitation source component, and the mechanical friction source component.

[0033] In this step, the unit vibration data can be acquired by a triaxial accelerometer installed on the motor housing or the protector housing. The vibration acceleration signals in the X, Y, and Z directions form a multidimensional observation signal. In order to improve the effect of blind source separation, multiple sensors can be used to collect vibration signals at different locations to construct a higher-dimensional observation signal matrix.

[0034] Furthermore, independent component analysis (ICA) is employed for blind source separation. The acquired multi-channel vibration data are used to construct an observation signal matrix X. Assuming the existence of an unknown mixing matrix A and mutually independent source signal matrices S, satisfying X = A·S, the ICA algorithm estimates the unmixing matrix W by optimizing the objective function, thus ensuring the estimated source signal... = W·X The components are made as independent as possible from each other. Through iterative calculation, multiple independent source components are finally separated.

[0035] Then, based on frequency characteristics and physical meaning, three typical components can be identified from the separated source components: motor excitation source component, fluid excitation source component, and mechanical friction source component. The frequency characteristics of the motor excitation source component are closely related to the motor's rotational speed. For asynchronous motors, the vibration frequency mainly includes the rotational frequency and harmonics, as well as the rotor bar passing frequency. For permanent magnet synchronous motors, the vibration frequency mainly includes the rotational frequency and harmonics, as well as the vibration frequency caused by cogging torque, and its amplitude is usually proportional to the motor's load current and electromagnetic force. The frequency characteristics of the fluid excitation source component are related to the flow state of the fluid within the pump. When fluid flows through the suction chamber, delivery chamber, and discharge chamber of a screw pump, pressure pulsations related to the rotational speed and pump structural parameters are generated, which are transmitted to the pump body to form vibrations. The amplitude is usually related to the pump inlet pressure, fluid viscosity, and gas content. The time domain characteristics of the mechanical friction source component are non-stationary impact waveforms, and the frequency domain characteristics are broadband energy distributions, with energy concentrated in a specific frequency band related to the rotor rotation frequency. When dry friction occurs between the rotor and stator, the impact force generated by the friction will excite the structural resonance of the pump body, generating high-frequency vibration components. The energy magnitude is positively correlated with the severity of dry friction.

[0036] Step 02: Extract the energy value of the preset frequency band from the mechanical friction source component to eliminate the interference of motor excitation and fluid excitation on the dry grinding feature identification.

[0037] In this step, after separating the mechanical friction source component, the component is subjected to subsequent feature extraction, rather than processing the original vibration signal or the motor excitation source component or the fluid excitation source component.

[0038] Specifically, a Fast Fourier Transform (FFT) is performed on the mechanical friction source component to obtain its vibration spectrum. Then, the energy value of a preset frequency band is extracted from this vibration spectrum. This preset frequency band corresponds to the characteristic frequency range generated by dry friction between the rotor and stator, and can be predetermined based on the structural and operating parameters of the screw pump. The method for determining the preset frequency band is as follows: First, obtain the current rotational speed and number of rotor heads of the electric submersible screw pump, and calculate the rotor frequency and its harmonics. Second, obtain the natural frequencies of the stator rubber and pump casing through modal analysis or impact tests. Finally, the intersection of the higher harmonic frequency band of the rotor frequency and the stator natural frequency band is taken as the preset frequency band, covering the main energy concentration area during dry friction. The energy value can be extracted by integrating the square of the amplitude within the preset frequency band to obtain the total energy within that band; or by calculating the root mean square value within the preset frequency band as the energy characteristic value of that band. The extracted energy value serves as an input feature for the subsequent risk identification model.

[0039] This effectively eliminates interference from motor excitation and fluid excitation on the identification of dry running characteristics. When fluctuations in motor load or changes in fluid conditions cause changes in the energy of the motor excitation source component or the fluid excitation source component, these changes will not affect the energy value extracted from the mechanical friction source component, thus avoiding misjudgments caused by changes in operating conditions. At the same time, the mechanical friction source component has higher sensitivity to dry running faults. In the early stages of dry running, even if the contact force between the rotor and stator has not yet caused a significant rise in the motor winding temperature, the high-frequency impact energy in the mechanical friction source component can already be detected, thus achieving early warning of dry running risks.

[0040] Step 20: Extract the temperature change rate and pressure fluctuation amplitude based on the motor winding temperature data and pump inlet pressure data, and extract the energy value of the preset frequency band in the vibration spectrum based on the unit vibration data;

[0041] As an optional embodiment, the temperature change rate and pressure fluctuation amplitude are extracted based on the motor winding temperature data and pump inlet pressure data, respectively, and the energy value of the preset frequency band in the vibration spectrum is extracted based on the unit vibration data. Specifically, it may include: Step 201: Extract the temperature difference and time interval of the motor winding temperature data within the sliding time window to obtain the temperature change rate.

[0042] In this step, the motor winding temperature data is a sequence that changes continuously over time. When dry friction is about to occur, the friction between the rotor and stator intensifies, the motor load increases, and the winding temperature shows a rapid upward trend. Therefore, the rate of temperature change is more reflective of the occurrence and development of dry friction risk than the absolute value of temperature.

[0043] To calculate the temperature change rate, this embodiment uses a sliding time window method. Specifically, a fixed-duration time window is set and continuously slides forward over time. At each sampling moment, the temperature data sequence of the current moment and the previous time window is taken. Within the sliding time window, the temperature values ​​at the start and end moments are extracted, and the difference between the two is calculated as the temperature difference. At the same time, the time difference between the start and end moments is calculated as the time interval. The temperature difference is divided by the time interval to obtain the temperature change rate at the current moment. When the temperature change rate is positive and gradually increases, it indicates that the winding temperature is rising rapidly, which may pose a risk of dry friction. When the temperature change rate is close to zero or negative, it indicates that the temperature is stable or decreasing, and the equipment is operating normally.

[0044] Step 202: Extract the maximum and minimum pressure values ​​of the pump inlet pressure data within the sliding time window to obtain the pressure fluctuation amplitude.

[0045] In this step, when an airlock is about to occur, the gas periodically accumulates and is released at the pump inlet, causing a large fluctuation in the pump inlet pressure. Therefore, the amplitude of the pressure fluctuation is more indicative of the occurrence and development of the airlock risk than the absolute value of the pressure.

[0046] To calculate the pressure fluctuation amplitude, this embodiment also uses a sliding time window method. Specifically, a fixed-length time window is set. At each sampling moment, the pressure data sequence of the current moment and the previous time window is taken. Within the sliding time window, all pressure data points are traversed to find the maximum and minimum pressure values ​​within the window. The difference between the maximum and minimum pressure values ​​is taken as the pressure fluctuation amplitude at the current moment. When the pressure fluctuation amplitude is small, it indicates that the pump inlet pressure is stable and the fluid suction conditions are good. When the pressure fluctuation amplitude gradually increases, it indicates that the pump inlet pressure is fluctuating violently, which may pose a risk of airlock. Similar to the calculation of the temperature change rate, the length of the sliding time window can be adjusted according to the actual operating conditions.

[0047] Step 203: Perform a fast Fourier transform on the mechanical friction source component to obtain the vibration spectrum, and extract the energy value of the preset frequency band in the vibration spectrum. The preset frequency band corresponds to the characteristic frequency range generated by dry friction between the rotor and the stator.

[0048] In this step, a fast Fourier transform is performed on the mechanical friction source component. Since the mechanical friction source component has eliminated the interference of motor excitation and fluid excitation, the spectral characteristics can more accurately reflect the dry friction state between the rotor and the stator. After obtaining the vibration spectrum of the mechanical friction source component, the energy value of the preset frequency band in the spectrum is extracted. The preset frequency band corresponds to the characteristic frequency range generated by dry friction between the rotor and the stator, which can be predetermined according to the structural parameters and operating parameters of the screw pump.

[0049] The method for determining the preset frequency band is as follows: First, obtain the current rotational speed n of the electric submersible screw pump and calculate the rotor frequency. Then, determine the characteristic frequency of dry friction based on the number of rotor heads. The impact vibration generated by dry friction usually shows energy concentration at integer multiples of the rotational frequency, especially in the higher harmonic frequency band. Considering the natural frequencies of the pump casing and stator rubber, the intersection region of the higher harmonic frequency band and the natural frequency band is taken as the preset frequency band. The energy value can be extracted by integrating the square of the amplitude within the preset frequency band to obtain the total energy within that frequency band; or by calculating the root mean square value within the preset frequency band as the energy characteristic value of that frequency band.

[0050] Step 30: Input the temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band into the pre-built risk identification model, and output the risk type, which includes dry grinding risk, airlock risk, and no risk.

[0051] In this step, dry friction risk indicates that dry friction is about to occur or has already occurred between the rotor and stator, air lock risk indicates that air lock is about to occur or has already occurred at the pump inlet, and no risk indicates that the equipment is operating normally.

[0052] As an optional embodiment, the temperature change rate, pressure fluctuation amplitude, and energy value of a preset frequency band are input into a pre-built risk identification model, and the risk type is output. Specifically, it may include: Step 301: Determine the contact force threshold based on the preset interference between the rotor and stator of the electric submersible screw pump and the allowable contact stress of the stator rubber material.

[0053] In this step, the interference fit between the rotor and stator is the basis for the electric submersible screw pump to achieve sealing and establish working pressure. The preset interference fit refers to the amount of interference fit between the rotor and stator set at the factory when the electric submersible screw pump is shipped. It is usually expressed as the difference between the maximum outer diameter of the rotor and the minimum inner diameter of the stator. When the rotor rotates inside the stator, a contact force will be generated between the two. The magnitude of the contact force is related to factors such as the interference fit, the elastic modulus of the rubber material, and the operating temperature. The allowable contact stress of the stator rubber material is a material parameter obtained through tensile and compression tests. It represents the maximum contact stress that the rubber material can withstand under long-term working conditions. Exceeding this stress value will lead to accelerated wear or damage of the rubber.

[0054] Based on the preset interference fit and the allowable contact stress of the stator rubber material, the contact force threshold can be determined. Specifically, through finite element simulation or theoretical calculation, a mapping relationship between the interference fit and the contact force is established. When the contact force reaches the allowable contact stress, the corresponding contact force value is the contact force threshold, which represents the maximum allowable contact force of the electric submersible screw pump under normal operating conditions. Exceeding this threshold poses a risk of dry friction.

[0055] Step 302: In the bench test, when the contact force between the rotor and the stator reaches the contact force threshold, the first temperature change rate, the first pressure fluctuation amplitude, and the first vibration spectrum energy value are collected as the dry grinding risk characteristic center.

[0056] In this step, during the bench test of the ESP (Electric Submersible Screw Pump) before it leaves the factory, the pump is installed on a test bench to simulate downhole working conditions. The interference fit between the rotor and stator is gradually reduced from the normal value. At the same time, the contact force between the rotor and stator is measured by a force sensor installed on the pump body. When the contact force reaches the contact force threshold, the pump is in a critical state of dry running risk. In this critical state, the temperature change rate, pressure fluctuation amplitude, and vibration spectrum energy value are collected and calculated, and recorded as the first temperature change rate, the first pressure fluctuation amplitude, and the first vibration spectrum energy value, respectively. These three characteristic values ​​constitute a three-dimensional feature vector, which serves as the feature center of dry running risk and represents the typical characteristic mode when the ESP is about to experience dry running.

[0057] Step 303: Determine the gas phase volume fraction threshold based on the influence of the gas phase volume fraction at the pump inlet of the electric submersible screw pump on the pump efficiency.

[0058] In this step, the gas volume fraction at the pump inlet refers to the percentage of gas volume in the fluid flowing into the pump relative to the total volume. When the gas volume fraction is low, the fluid is a continuous liquid phase, and the pump can operate normally. As the gas volume fraction increases, the gas begins to affect the pump's suction efficiency. When the gas volume fraction exceeds a certain critical value, the pump efficiency drops significantly, and even airlock occurs. The pump efficiency change curves under different gas volume fractions are determined experimentally. Specifically, in a bench test, gas is gradually mixed into the fluid at the pump inlet, and the pump efficiency corresponding to different gas volume fractions is measured. When the pump efficiency drops to a certain percentage of the rated pump efficiency, the corresponding gas volume fraction is the gas volume fraction threshold, which characterizes the upper limit of permissible gas content for normal operation of the electric submersible screw pump. Exceeding this threshold poses a risk of airlock.

[0059] Step 304: In the bench test, when the gas volume fraction at the pump inlet reaches the gas volume fraction threshold, the second temperature change rate, the second pressure fluctuation amplitude, and the second vibration spectrum energy value are collected as the gas lock risk characteristic center.

[0060] In this step, during the bench test of the electric submersible screw pump before it leaves the factory, the pump is installed on a test bench to simulate downhole working conditions. Gas is gradually mixed into the fluid at the pump inlet, and the gas volume fraction at the pump inlet is monitored. When the gas volume fraction reaches the gas volume fraction threshold, the pump is in a critical state of gas lock risk. In this critical state, the temperature change rate, pressure fluctuation amplitude, and vibration spectrum energy value are collected and calculated, and recorded as the second temperature change rate, the second pressure fluctuation amplitude, and the second vibration spectrum energy value, respectively, forming a three-dimensional feature vector as the gas lock risk feature center.

[0061] Step 305: In the bench test of the electric submersible screw pump under rated operating conditions, the third temperature change rate, the third pressure fluctuation amplitude, and the third vibration spectrum energy value are collected as risk-free characteristic centers.

[0062] In this step, during the bench test of the electric submersible screw pump before it leaves the factory, the pump is installed on a test bench and operated under rated conditions. Rated conditions refer to the pump's normal operating state within its design parameter range, including rated speed, rated displacement, pure liquid phase fluid, and stable inlet pressure. Under normal operating conditions, the temperature change rate, pressure fluctuation amplitude, and vibration spectrum energy value are collected and calculated, denoted as the third temperature change rate, the third pressure fluctuation amplitude, and the third vibration spectrum energy value, respectively. These three characteristic values ​​constitute a three-dimensional feature vector, serving as the risk-free feature center.

[0063] Step 306: Calculate the similarity between the temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band and the risk characteristic center of dry grinding, the risk characteristic center of airlock, and the risk-free characteristic center to determine the risk type.

[0064] In this step, during the actual operation of the electric submersible screw pump, for each sampling moment, the current feature vector is constructed by extracting the temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band at the current moment. The similarity between the current feature vector and the determined dry grinding risk feature center, airlock risk feature center, and no-risk feature center is calculated respectively. The similarity calculation method can be Euclidean distance, Mahalanobis distance, or cosine similarity, etc. If the similarity with the dry grinding risk feature center is the highest, the dry grinding risk is output; if the similarity with the airlock risk feature center is the highest, the airlock risk is output; if the similarity with the no-risk feature center is the highest, no risk is output.

[0065] Step 40: When the output risk type is dry grinding risk or airlock risk, perform an adaptive control sequence. The adaptive control sequence includes a deceleration phase, a pulse backflush phase, and a recovery phase executed sequentially.

[0066] As an optional embodiment, when the output risk type is dry grinding risk or air lock risk, an adaptive control sequence is performed, which may specifically include: Step 401: reduce the speed of the electric submersible screw pump to a first target speed at a preset deceleration rate and maintain it for a first preset duration, while continuously monitoring the pump inlet pressure data.

[0067] In this step, for the risk of dry friction, a faster deceleration rate can be used because it is necessary to quickly reduce the relative speed between the rotor and stator to alleviate friction. For the risk of air lock, a slower deceleration rate can be used because it is necessary to avoid a sudden drop in pressure that could lead to increased gas evolution. For example, the deceleration rate can be set to a reduction of 50 to 200 revolutions per minute, with the specific value pre-calibrated based on the model and operating conditions of the electric submersible screw pump. The first target speed is an intermediate speed lower than the current operating speed, and the specific value can be determined based on the risk type and equipment characteristics. For the risk of dry friction, the first target speed can be set to the lowest speed that can maintain the formation of a hydrodynamic lubrication film between the rotor and stator. For the risk of air lock, the first target speed can be set to the speed that can restore the pump inlet pressure to a stable state. The first preset duration refers to the length of time to maintain the first target speed, and the specific value can be determined based on the equipment characteristics and risk type. The purpose of maintaining the first preset duration is to give the equipment sufficient time to respond to speed changes, allowing the pump inlet pressure and the rotor-stator contact state to stabilize at the new speed.

[0068] Furthermore, during the deceleration process, the pump inlet pressure data is continuously monitored. The pump inlet pressure data reflects real-time changes in downhole fluid supply capacity and pump suction conditions, and is a crucial basis for determining whether the risk has been mitigated.

[0069] Step 402: If the pump inlet pressure data returns to normal during the deceleration process, the deceleration phase ends and the recovery phase begins.

[0070] In this step, if the pump inlet pressure data returns to normal, it indicates that the risk has been mitigated. There is no need to continue with the full deceleration phase; the deceleration phase can be ended early, and the recovery phase can begin directly. The pump inlet pressure data returning to normal means that the pump inlet pressure value returns to the pressure fluctuation range corresponding to the risk-free characteristic center. The current pump inlet pressure data is compared with the pressure fluctuation amplitude corresponding to the risk-free characteristic center. If the current pressure value is within the normal pressure fluctuation range corresponding to the risk-free characteristic center, and the stable period exceeds the preset stability duration, then the pump inlet pressure data is determined to have returned to normal.

[0071] In this way, when the risk is mitigated in the initial stage of deceleration, there is no need to reduce the speed to the first target speed and maintain it for the first preset duration. This allows for a faster recovery of normal equipment operation and reduces the impact on production efficiency. Simultaneously, by continuously monitoring pump inlet pressure data, adaptive adjustments to the control process are achieved, improving control efficiency.

[0072] Furthermore, if the pump inlet pressure data fails to return to normal during the deceleration process, the complete deceleration phase continues until the speed reaches the first target speed and is maintained for the first preset duration, after which the pulse backflush phase begins.

[0073] As an optional embodiment, the method may further include: Step 403: After the deceleration phase ends, a pulse backflush phase is entered, and the rotational speed of the electric submersible screw pump is controlled to alternately accelerate and decelerate in a preset pulse pattern to generate pressure pulses to break the airlock.

[0074] In this step, after the deceleration phase is completed, if the risk type is airlock risk, or if the risk type is dry grinding risk but the pump inlet pressure data has not returned to normal after the deceleration phase, then it is necessary to enter the pulse backflush phase. The purpose is to actively generate pressure pulses to destroy the air pockets accumulated at the pump inlet, so that the gas is redistributed into the fluid or discharged, thereby breaking the airlock.

[0075] Specifically, the speed of the electric submersible screw pump is controlled to alternately accelerate and decelerate in a preset pulse pattern. The periodic change in speed causes synchronous fluctuations in the pump's internal pressure and flow rate. These fluctuations propagate in the form of pressure waves in the pump's inlet and outlet pipes. When the pressure waves propagate to the airlock area, they exert alternating compression and stretching on the airbag, disrupting its stability, causing it to rupture and be discharged with the fluid.

[0076] In this way, compared with simply maintaining a low speed and waiting for the airlock to dissipate on its own, actively generating pressure pulses can actively destroy the airbag structure, significantly shorten the airlock dissipation time, and reduce the impact on production.

[0077] Step 404: The pulse mode includes multiple pulse cycles, each pulse cycle containing a process of accelerating to the second target speed and then immediately decelerating to the third target speed.

[0078] In this step, the pulse mode consists of multiple pulse cycles, each a complete acceleration-deceleration cycle. Within each pulse cycle, the speed of the ESD screw pump is first accelerated from the current speed to the second target speed, then immediately decelerated to the third target speed. After completing one pulse cycle, the next pulse cycle can be repeated until the termination condition is met. The second target speed is a speed value higher than the current speed, and the third target speed is a speed value lower than the current speed. The specific values ​​of the second and third target speeds can be preset according to the ESD screw pump model, current operating conditions, and the severity of airlock. For example, the second target speed can be set to 110% to 150% of the current speed, and the third target speed can be set to 50% to 90% of the current speed. Immediate deceleration means that after reaching the second target speed, no holding time is set, and the control immediately switches to deceleration, causing the speed to quickly drop back to the third target speed. This rapid speed change generates a steep pressure wave front, enhancing the intensity of the pressure pulse and more effectively damaging the airbag structure.

[0079] Furthermore, the duration and amplitude of each pulse cycle can be adjusted as needed. For severe airlocks, a larger pulse amplitude and a longer pulse cycle can be set; for mild airlocks, a smaller pulse amplitude and a shorter pulse cycle can be set.

[0080] Step 405: During the pulse backflush phase, continuously monitor the pump inlet pressure data and unit vibration data. When the pump inlet pressure data is stable and the energy value of the preset frequency band in the vibration spectrum is lower than the preset threshold, end the pulse backflush phase.

[0081] As an optional embodiment, the method may further include: step 406: after the pulse backflush phase ends, the rotational speed of the electric submersible screw pump is increased to the original rotational speed at a preset acceleration rate.

[0082] In this step, the acceleration rate can be preset according to the equipment characteristics and operating conditions, and a uniform acceleration or stepped acceleration method can be adopted to ensure a smooth recovery process.

[0083] Step 407: During the speed-up process, acquire real-time data on motor winding temperature, pump inlet pressure, and unit vibration.

[0084] In this step, during the speed increase process, the motor winding temperature data, pump inlet pressure data, and unit vibration data are continuously acquired to monitor the equipment operating status during the recovery phase. If abnormal data is detected or the risk identification model outputs dry grinding risk or airlock risk again, the speed increase is stopped immediately and the adaptive control sequence is re-executed to ensure the safety of the recovery process.

[0085] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a control device for dry grinding and airlock of an electric submersible screw pump, the structure of which is as follows: Figure 2 As shown.

[0086] Figure 2 This is a schematic diagram of the internal structure of a control device for dry grinding and airlock of an electric submersible screw pump, provided as an embodiment of this application. Figure 2 As shown, the device includes:

[0087] At least one processor 201;

[0088] And a memory 202 that is communicatively connected to at least one processor;

[0089] The memory 202 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 201 to enable at least one processor 201 to: perform any step of a method for controlling dry grinding and air lock of an electric submersible screw pump.

[0090] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium for regulating dry grinding and airlock of an electric submersible screw pump, storing computer-executable instructions, wherein the computer-executable instructions are configured to execute any one of the steps of a method for regulating dry grinding and airlock of an electric submersible screw pump.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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 controlling dry grinding and airlock in an electric submersible screw pump, characterized in that, The method includes: Acquire motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of the electric submersible screw pump; Blind source separation is performed on the vibration data of the unit to obtain the mechanical friction source component; Based on the motor winding temperature data and pump inlet pressure data, the temperature change rate and pressure fluctuation amplitude are extracted respectively, and the energy value of a preset frequency band in the vibration spectrum is extracted based on the unit vibration data. The energy value of the preset frequency band is extracted from the mechanical friction source component. The temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band are input into the pre-built risk identification model, and the risk type is output. The risk type includes dry grinding risk, airlock risk, and no risk. When the output risk type is dry grinding risk or airlock risk, an adaptive control sequence is performed, which includes a deceleration phase, a pulse backflush phase, and a recovery phase executed sequentially.

2. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 1, characterized in that, The acquisition of motor winding temperature data, pump inlet pressure data, and unit vibration data during the operation of the electric submersible screw pump specifically includes: The motor winding temperature data is obtained by inverting the electrical parameters of the motor winding, specifically including: A high-frequency detection signal is injected into the motor winding, and the impedance spectrum characteristics of the motor winding are collected. The motor winding temperature data is calculated based on the mapping relationship between the impedance spectrum characteristics and temperature.

3. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 1, characterized in that, The method further includes: Blind source separation was performed on the vibration data of the unit to obtain the motor excitation source component and the fluid excitation source component; The energy value of the preset frequency band is extracted from the mechanical friction source component to eliminate the interference of motor excitation and fluid excitation on the dry grinding feature identification.

4. The method for controlling dry grinding and airlock of an electric submersible screw pump according to claim 3, characterized in that, The steps of extracting the temperature change rate and pressure fluctuation amplitude based on the motor winding temperature data and pump inlet pressure data, and extracting the energy value of a preset frequency band in the vibration spectrum based on the unit vibration data, specifically include: The temperature difference and time interval of the motor winding temperature data within the sliding time window are extracted to obtain the temperature change rate; The maximum and minimum pressure values ​​of the pump inlet pressure data within the sliding time window are extracted to obtain the pressure fluctuation amplitude; The vibration spectrum is obtained by performing a fast Fourier transform on the mechanical friction source component, and the energy value of a preset frequency band in the vibration spectrum is extracted. The preset frequency band corresponds to the characteristic frequency range generated by dry friction between the rotor and the stator.

5. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 1, characterized in that, The step of inputting the temperature change rate, pressure fluctuation amplitude, and energy value of a preset frequency band into a pre-built risk identification model and outputting the risk type specifically includes: The contact force threshold is determined based on the preset interference fit between the rotor and stator of the electric submersible screw pump and the allowable contact stress of the stator rubber material. In the bench test, when the contact force between the rotor and the stator reaches the contact force threshold, the first temperature change rate, the first pressure fluctuation amplitude and the first vibration spectrum energy value are collected as the dry friction risk characteristic center. Based on the influence of the gas volume fraction at the pump inlet of the electric submersible screw pump on the pump efficiency, the gas volume fraction threshold is determined. In bench tests, when the gas volume fraction at the pump inlet reaches the gas volume fraction threshold, the second temperature change rate, the second pressure fluctuation amplitude, and the second vibration spectrum energy value are collected as the gas lock risk characteristic center. In the bench test of the electric submersible screw pump under rated operating conditions, the third temperature change rate, the third pressure fluctuation amplitude, and the third vibration spectrum energy value were collected as risk-free characteristic centers. The similarity between the temperature change rate, pressure fluctuation amplitude, and energy value of the preset frequency band and the dry grinding risk characteristic center, airlock risk characteristic center, and no-risk characteristic center is calculated to determine the risk type.

6. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 1, characterized in that, The adaptive control sequence for outputting risk types of dry grinding risk or airlock risk specifically includes: When the risk type is dry grinding risk, the rotational speed of the electric submersible screw pump is reduced to the first target rotational speed at a first deceleration rate; When the risk type is airlock risk, the rotational speed of the electric submersible screw pump is reduced to the first target rotational speed at a second deceleration rate; The first deceleration rate is greater than the second deceleration rate; Maintain the first target rotational speed for a first preset duration, while continuously monitoring the pump inlet pressure data; If the pump inlet pressure data returns to normal during the deceleration process, the deceleration phase ends and the recovery phase begins.

7. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 6, characterized in that, The method further includes: When the risk type is airlock risk, after the deceleration phase ends, the pulse backflush phase begins, and the rotation speed of the electric submersible screw pump is controlled to alternately accelerate and decelerate in a preset pulse pattern to generate pressure pulses to break the airlock. The pulse pattern includes multiple pulse cycles, each pulse cycle containing a process of accelerating to the second target speed and then immediately decelerating to the third target speed; During the pulse backflush phase, the pump inlet pressure data and unit vibration data are continuously monitored. When the pump inlet pressure data is stable and the energy value of the preset frequency band in the vibration spectrum is lower than the preset threshold, the pulse backflush phase ends.

8. The method for controlling dry grinding and air lock of an electric submersible screw pump according to claim 7, characterized in that, The method further includes: After the pulse backflush phase ends, the rotational speed of the electric submersible screw pump is increased to the original rotational speed at a preset acceleration rate; During the acceleration process, the motor winding temperature data, pump inlet pressure data, and unit vibration data are acquired in real time.

9. A control device for dry grinding and air lock of 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 executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: The steps of the method for controlling dry grinding and air lock of an electric submersible screw pump as described in any one of claims 1-8 are performed.

10. A non-volatile computer storage medium for regulating dry grinding and airlock of an electric submersible screw pump, storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: The steps of the method for controlling dry grinding and air lock of an electric submersible screw pump as described in any one of claims 1-8 are performed.

Images