A method and system for regulating pump pressure

Abstract

This application discloses a pump pressure regulation method and system, belonging to the field of oil and gas extraction technology. The method includes: arranging several pressure sensors along the fluid channel on the oil well pump device, arranging several temperature sensors along the well depth direction on the oil well tubing string, and setting a flow sensor at the pump inlet; transmitting the output signal to a downhole data acquisition box for preprocessing to obtain a correction signal; sending the correction signal to a surface receiving host to construct a multivariate coupled model and solve it to obtain the target pump pressure; and determining the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure. The pump pressure regulation method proposed in this application, by real-time monitoring of key parameters such as temperature, pressure, and flow rate in the oil well, and based on multi-point temperature and pressure data, calculates the target pump pressure through a multivariate coupled model, providing a more accurate target pump pressure value, rather than relying on a single variable or simple empirical formula, thus improving the accuracy of pump pressure regulation.

Description

Technical Field

[0001] This application belongs to the field of oil and gas extraction technology, and specifically relates to a pump pressure regulation method and system. Background Technology

[0002] Oil well pumps are crucial equipment in oilfield extraction, primarily responsible for transporting oil and gas from underground wellbores to surface processing systems. During the long-term operation of an oil well, pump pressure control is a key factor in ensuring efficient oil and gas transport and equipment safety.

[0003] During long-term or seasonal oil well production, fluctuations in formation temperature (such as the temperature difference between summer and winter) lead to temperature changes within the well. These temperature changes directly affect the viscosity, flowability, and pump efficiency of the fluids within the well. However, traditional pump pressure settings generally do not dynamically adjust according to temperature changes, resulting in a mismatch between the preset pump pressure and actual operating conditions. Furthermore, traditional oil well pump pressure regulation methods mostly rely on a single pressure sensor for pump pressure adjustment, ignoring dynamic temperature changes. Temperature variations directly impact the fluid properties of the oil well, the pump's operating status, and equipment wear. Ignoring the effects of temperature changes prevents the pump pressure regulation system from adapting to temperature changes in real time, easily leading to problems such as excessively high or low pump pressures. This, in turn, affects oil and gas extraction efficiency and equipment safety, and prevents the achievement of real-time adjustment capabilities.

[0004] Therefore, overcoming the shortcomings of the existing technology is an urgent problem to be solved in this technical field. Summary of the Invention

[0005] To address the above problems, this application provides a pump pressure regulation method, comprising the following steps: Several pressure sensors are installed along the fluid channel on the oil well pump unit, several temperature sensors are installed along the well depth direction on the oil well tubing string, and a flow sensor is installed at the pump inlet. The output signals of the pressure sensor, temperature sensor and flow sensor are transmitted to the downhole data acquisition box in real time, and preprocessed to obtain correction signals; The downhole data acquisition box sends a correction signal to the ground receiving host via a wireless transmission module. The receiving host constructs a multivariable coupled model based on the correction signal and solves the multivariable coupled model to obtain the target pump pressure. The actual pump pressure is obtained based on the pressure sensor, and the opening adjustment amount of the electric valve is determined based on the actual pump pressure and the target pump pressure.

[0006] Furthermore, the preprocessing specifically includes: Kalman filtering is used to remove high-frequency noise from the output signal, resulting in a smooth signal; The low-frequency drift in the smoothed signal is eliminated by using a moving average filter to obtain a corrected signal.

[0007] Furthermore, the calculation formula for the multivariate coupling model is as follows:

[0008] In the formula, P target (t) represents the target pump pressure, P base T represents the reference pump pressure. set Indicates the target temperature. This represents a weighted average of temperatures at multiple points. Let Q(t) represent the rate of temperature change and Q(t) represent the real-time flow rate. The gas holdup is represented by T, temperature by Q, and flow rate by f. nl Let k1, k2, k3, and k4 represent the nonlinear compensation function, and k1, k2, k3, and k4 represent the real-time updated system gain coefficients.

[0009] Furthermore, the establishment of the nonlinear compensation function includes the following steps: Temperature, pressure, and flow data were collected under wax-containing conditions, high gas content conditions, and crude oil viscosity change conditions to form a dataset. A neural network model is trained using a dataset, and the output of the neural network model is used as the pump pressure distortion compensation amount to generate a nonlinear compensation function.

[0010] Furthermore, the opening adjustment amount of the electric valve is determined based on the actual pump pressure and the target pump pressure, including: Calculate the pump pressure deviation between the actual pump pressure and the target pump pressure; The pump pressure deviation value is input into the proportional-integral-derivative controller to obtain the opening adjustment amount of the electric valve.

[0011] Furthermore, the formula for calculating the opening adjustment amount is:

[0012] In the formula, It is the pump opening adjustment amount; e(t) represents the pump pressure deviation between the actual pump pressure and the target pump pressure; K p It is the proportionality coefficient; K i It is the integral coefficient; K d These are the differential coefficients; ∫e(t)dt is the integral term of the pump pressure deviation value; It is the rate of change of the pump pressure deviation, i.e., the differential term.

[0013] Furthermore, the pressure sensor includes: Pump inlet pressure sensor, used for installation in the pump inlet pipe section; Pump outlet pressure sensor, used for installation at the pump outlet or wellhead; Mid-section pressure sensor, used to be installed in the middle of the pump body or wellbore.

[0014] Furthermore, the temperature sensor includes: Wellhead temperature sensor, used for installation at pump outlet or wellhead location; Mid-section temperature sensor, used to be installed in the middle of the oil pipe; Bottom-of-well temperature sensor, used for installation at the pump inlet.

[0015] Furthermore, the bottom-hole temperature sensor and the flow sensor are spaced less than or equal to 0.5m apart.

[0016] The present invention also discloses a pump pressure regulating system, the system comprising: The data acquisition module is used to install several pressure sensors along the fluid channel on the oil well pump unit, several temperature sensors along the well depth direction on the oil well tubing string, and a flow sensor at the pump inlet. The preprocessing module is used to transmit the output signals of the pressure sensor, temperature sensor and flow sensor to the downhole data acquisition box in real time, and to perform preprocessing to obtain correction signals; The model building module is used by the downhole data acquisition box to send correction signals to the ground receiving host via the wireless transmission module. The receiving host builds a multivariable coupled model based on the correction signals and solves the multivariable coupled model to obtain the target pump pressure. The control module is used to obtain the actual pump pressure based on the pressure sensor, and to determine the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure.

[0017] Compared with the prior art, this application has the following advantages: The pump pressure regulation method proposed in this application involves deploying multiple pressure and temperature sensors along the fluid channel and at different depths of the well tubing in the pump unit, and installing a flow sensor at the pump inlet. This allows for real-time monitoring of key parameters such as temperature, pressure, and flow rate in the well. Based on multi-point temperature and pressure data, the target pump pressure is calculated through a multivariate coupling model. This model considers the interaction of multiple factors, including temperature and pressure, to provide a more accurate target pump pressure value, rather than relying on a single variable or simple empirical formula. This improves the accuracy of pump pressure regulation, effectively avoids pump pressure fluctuations, over-regulation, or under-regulation, and enhances the stability of the system.

[0018] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures pointed out in the description and the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A schematic flowchart of the pump pressure regulation method in an embodiment of the present invention is shown; Figure 2 A system block diagram of the pump pressure regulation system in an embodiment of the present invention is shown. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of 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 invention provides a pump pressure regulation method and system. Figure 1 A schematic flowchart of a pump pressure regulation method according to an embodiment of the present invention is shown, which specifically includes the following steps: S101. Install several pressure sensors along the fluid channel on the oil well pump unit, install several temperature sensors along the well depth direction on the oil well tubing string, and install a flow sensor at the pump inlet. The pressure sensors include at least a pump inlet pressure sensor, a pump outlet pressure sensor, and a mid-section pressure sensor. The pump inlet pressure sensor is installed in the pump inlet pipe section to monitor the pressure on the water inlet side in real time, reflecting the downhole liquid level and inlet resistance. Pump outlet pressure sensor is used to be installed at the pump outlet or wellhead to monitor the pump discharge pressure in real time and reflect changes in pump head and pipeline resistance. Mid-section pressure sensors are installed in the middle of the pump body or wellbore to obtain pressure drop information along the pipeline.

[0023] Temperature sensors include at least wellhead temperature sensors, bottom hole temperature sensors, and intermediate temperature sensors. The temperature sensors are magnetic steel shape memory alloy temperature sensors to comprehensively monitor the thermal state of the pump and ensure that the temperature sensors accurately reflect the temperature changes of the pump equipment. The wellhead temperature sensor is installed at the pump outlet or wellhead, at the same height or adjacent to the pump outlet pressure sensor. It is used to monitor the liquid temperature and combine it with the outlet pressure data to reflect the heat exchange and energy loss in the upper section of the wellbore. The bottom hole temperature sensor is installed near the pump inlet, adjacent to the pump inlet pressure sensor and flow sensor, and is used to reflect the original temperature state of the fluid in the bottom hole production formation. The mid-section temperature sensor is installed in the middle of the oil pipe, at an adjacent measuring point to the mid-section pressure sensor, and is used to monitor the temperature decay trend along the pipe.

[0024] The flow sensor is installed near the pump inlet, i.e., at the bottom of the well, with a distance of less than or equal to 0.5m between the flow sensor and the bottom-of-well temperature sensor. This is to reduce the deviation caused by flow rate changes in temperature measurement delay and spatial differences.

[0025] Specifically, at the bottom of the well, the flow sensor, pump inlet pressure sensor, and bottom temperature sensor are sequentially arranged along the flow direction, with a spacing of less than or equal to 0.5m between them to ensure that the three parameters correspond to the same fluid cross section, thereby avoiding time delay and spatial deviation caused by the spacing between measuring points during data fusion calculation. When there are multiple water intake branches in the oil well, flow sensors can be arranged on each branch, and the data is weighted and summarized during data acquisition to form a total flow data input model. The flow sensor has a measurement accuracy of not less than ±1%FS, a sampling frequency of not less than 1Hz, and a structural design that is resistant to high temperature (≥120℃) and high pressure (≥30MPa).

[0026] S102. The output signals of the pressure sensor, temperature sensor and flow sensor are transmitted to the downhole data acquisition box in real time, and preprocessed to obtain the correction signal. Specifically, the preprocessing includes: Kalman filtering is used to remove high-frequency noise from the output signal, resulting in a smooth signal and suppressing high-frequency noise. A moving average filter is used to eliminate low-frequency drift in the smoothed signal and obtain a corrected signal, which is then sent to the receiving host.

[0027] By performing data preprocessing and integration downhole, the amount of data transmitted wirelessly is reduced, and communication efficiency is improved. Interference and signal attenuation in wireless transmission are reduced, ensuring data transmission stability. This not only improves system stability and reduces communication burden, but also enhances system flexibility and fault tolerance.

[0028] S103, the downhole data acquisition box sends a correction signal to the ground receiving host via a wireless transmission module. The receiving host constructs a multivariable coupled model based on temperature and pump pressure, and solves the multivariable coupled model to obtain the target pump pressure. The calculation formula for the multivariable coupling model is as follows: (1) In the formula, P target (t) represents the target pump pressure, P base T represents the reference pump pressure. set Indicates the target temperature. This represents a weighted average of temperatures at multiple points. Let Q(t) represent the rate of temperature change and Q(t) represent the real-time flow rate. The gas holdup is represented by T, temperature by Q, and flow rate by f. nl Let k1, k2, k3, and k4 represent the nonlinear compensation function, and k1, k2, k3, and k4 represent the real-time updated system gain coefficients.

[0029] Wherein, the nonlinear compensation function f nl The establishment includes the following steps: This invention collects temperature, pressure, and flow data under wax-containing, high-gas-content, and crude oil viscosity abrupt change conditions to form a dataset. The dataset collection must cover multi-dimensional data (temperature, pressure, flow rate, etc.) under different time periods and conditions to ensure the comprehensiveness and representativeness of the data. A neural network model is trained using the dataset, and its output is used as the pump pressure distortion compensation amount to generate a nonlinear compensation function f. nl .

[0030] S104. Obtain the actual pump pressure based on the pressure sensor, and determine the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure.

[0031] The step of determining the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure includes: Calculate the pump pressure deviation between the actual pump pressure and the target pump pressure; The pump pressure deviation value is input into the proportional-integral-derivative controller, i.e., the PID controller, to obtain the opening adjustment amount of the electric valve.

[0032] The formula for calculating the opening adjustment amount (control algorithm) in the PID controller is as follows: (2) In the formula, Indicates the pump opening adjustment amount; e(t) represents the pump pressure deviation between the actual pump pressure and the target pump pressure; K p K represents the proportionality coefficient. i K represents the integral coefficient; d The differential coefficient is represented by ∫e(t)dt, which represents the integral term of the pump pressure deviation. This represents the rate of change of the pump pressure deviation, i.e., the differential term.

[0033] K p K i K d Adjustments are made online to ensure both response speed and stability under different operating conditions.

[0034] It should be added that K p The proportional gain K is adjusted based on the current pump pressure deviation e(t). When the temperature changes significantly, the PID controller can increase the proportional gain K. p This improves the controller's response speed to rapid changes.

[0035] K i The integral gain is used to eliminate steady-state deviations in the system. A larger integral gain allows the system to better eliminate long-term deviations. If pump pressure fluctuations are too large or the deviation is too significant, the PID controller can increase the derivative gain K. d This improves the ability to suppress pump pressure fluctuations and reduces excessive oscillations.

[0036] K d The derivative gain is used to suppress transient overshoot or oscillations in the system and to predict future changes in the system. A larger derivative gain makes the system more sensitive to changes in deviation. When the flow rate changes significantly, the PID controller needs to adjust the integral gain K. i It is used to eliminate steady-state deviations caused by changes in flow rate.

[0037] Correspondingly, K p K i K d All were optimized using genetic algorithms.

[0038] For example, a global optimization is performed every 12 hours to ensure that the parameters of the PID controller always adapt to changes in the current operating conditions.

[0039] This invention utilizes multiple pressure and temperature sensors deployed along the fluid channel and at different depths within the well tubing of the pump assembly, along with a flow sensor at the pump inlet, to monitor key parameters such as temperature, pressure, and flow rate in the well in real time. Based on multi-point temperature and pressure data, a multivariate coupling model is used to calculate the target pump pressure. This approach considers the interaction of multiple factors, including temperature and pressure, providing a more accurate target pump pressure value rather than relying on a single variable or simple empirical formula. This improves the precision of pump pressure regulation, effectively avoiding pump pressure fluctuations, over-regulation, or under-regulation, and enhancing system stability.

[0040] Furthermore, the deviation in pump pressure calculation is corrected by a nonlinear compensation function optimized by a neural network, which effectively improves the pump pressure regulation accuracy and reduces fluctuations and deviations caused by factors such as environmental changes and changes in liquid properties.

[0041] Based on the above-disclosed technical solutions, and referring to... Figure 2 The present invention also discloses a pump pressure regulating system, including the above-described pump pressure regulating method, wherein the system includes: The data acquisition module is used to install several pressure sensors along the fluid channel on the oil well pump unit, several temperature sensors along the well depth direction on the oil well tubing string, and a flow sensor at the pump inlet. The preprocessing module is used to transmit the output signals of the pressure sensor, temperature sensor and flow sensor to the downhole data acquisition box in real time, and to perform preprocessing to obtain correction signals; The model building module is used by the downhole data acquisition box to send correction signals to the ground receiving host via the wireless transmission module. The receiving host builds a multivariable coupled model based on the correction signals and solves the multivariable coupled model to obtain the target pump pressure. The control module is used to obtain the actual pump pressure based on the pressure sensor, and to determine the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure.

[0042] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they may refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of these terms in this invention according to the specific circumstances.

[0043] It should be understood that all terms used to indicate orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and should not be construed as a limitation of the present invention.

[0044] Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A pump pressure regulating method, characterized by, Includes the following steps: Several pressure sensors are installed along the fluid channel on the oil well pump unit, several temperature sensors are installed along the well depth direction on the oil well tubing string, and a flow sensor is installed at the pump inlet. The output signals of the pressure sensor, temperature sensor and flow sensor are transmitted to the downhole data acquisition box in real time, and preprocessed to obtain correction signals; The downhole data acquisition box sends a correction signal to the ground receiving host via a wireless transmission module. The receiving host constructs a multivariable coupled model based on the correction signal and solves the multivariable coupled model to obtain the target pump pressure. The actual pump pressure is obtained based on the pressure sensor, and the opening adjustment amount of the electric valve is determined based on the actual pump pressure and the target pump pressure.

2. The pump pressure regulation method of claim 1, wherein, The preprocessing specifically includes: Kalman filtering is used to remove high-frequency noise from the output signal, resulting in a smooth signal; The low-frequency drift in the smoothed signal is eliminated by using a moving average filter to obtain a corrected signal.

3. The pump pressure regulation method of claim 2, wherein, The calculation formula for the multivariate coupling model is as follows: In the formula, P target (t) represents the target pump pressure, P base T represents the reference pump pressure. set Indicates the target temperature. This represents a weighted average of temperatures at multiple points. Let Q(t) represent the rate of temperature change and Q(t) represent the real-time flow rate. The gas holdup is represented by T, the temperature by Q, and the flow rate by f. nl Let k1, k2, k3, and k4 represent the nonlinear compensation function, and k1, k2, k3, and k4 represent the real-time updated system gain coefficients.

4. The pump pressure regulation method of claim 3, wherein, The establishment of the nonlinear compensation function includes the following steps: Temperature, pressure, and flow data were collected under wax-containing conditions, high gas content conditions, and crude oil viscosity change conditions to form a dataset. A neural network model is trained using the dataset, and the output of the neural network model is used as the pump pressure distortion compensation amount to generate a nonlinear compensation function.

5. The pump pressure regulation method of claim 3, wherein, The determination of the electric valve opening adjustment amount based on the actual pump pressure and the target pump pressure includes: Calculate the pump pressure deviation between the actual pump pressure and the target pump pressure; The pump pressure deviation value is input into the proportional-integral-derivative controller to obtain the opening adjustment amount of the electric valve.

6. The pump pressure regulation method of claim 5, wherein, The formula for calculating the opening adjustment amount is: In the formula, Indicates the pump opening adjustment amount; e(t) represents the pump pressure deviation between the actual pump pressure and the target pump pressure; K p K represents the proportionality coefficient. i K represents the integral coefficient; d The differential coefficient is represented by ∫e(t)dt, which represents the integral term of the pump pressure deviation. This represents the rate of change of the pump pressure deviation, i.e., the differential term.

7. The pump pressure regulating method according to any one of claims 1-6, characterized in that, The pressure sensor includes: Pump inlet pressure sensor, used for installation in the pump inlet pipe section; Pump outlet pressure sensor, used for installation at the pump outlet or wellhead; Mid-section pressure sensor, used to be installed in the middle of the pump body or wellbore.

8. The pump pressure regulation method of claim 7, wherein, The temperature sensor includes: Wellhead temperature sensor, used for installation at pump outlet or wellhead location; Mid-section temperature sensor, used to be installed in the middle of the oil pipe; Bottom-of-well temperature sensor, used for installation at the pump inlet.

9. The pump pressure regulation method of claim 8, wherein, The bottom temperature sensor and the flow sensor are located at a distance of less than or equal to 0.5m.

10. A pump pressure regulating system characterized by, The system includes: The data acquisition module is used to install several pressure sensors along the fluid channel on the oil well pump unit, several temperature sensors along the well depth direction on the oil well tubing string, and a flow sensor at the pump inlet. The preprocessing module is used to transmit the output signals of the pressure sensor, temperature sensor and flow sensor to the downhole data acquisition box in real time, and to perform preprocessing to obtain correction signals; The model building module is used by the downhole data acquisition box to send correction signals to the ground receiving host via the wireless transmission module. The receiving host builds a multivariable coupled model based on the correction signals and solves the multivariable coupled model to obtain the target pump pressure. The control module is used to obtain the actual pump pressure based on the pressure sensor, and to determine the opening adjustment amount of the electric valve based on the actual pump pressure and the target pump pressure.

Images