Throttling well killing control method and system, storage medium and program product

Abstract

The invention discloses a throttling well killing control method and system, a storage medium and a program product, and relates to the field of intelligent control. According to the application, the control system collects wellhead pressure, casing pressure, throttle valve opening and shaft temperature gradient data; comparing the shaft temperature gradient data with a preset temperature reference curve to obtain a temperature deviation sequence, and performing Fourier decomposition on the temperature deviation sequence to obtain a main frequency component; on the basis of the main frequency component and a preset frequency threshold value, downhole flow situation parameters are determined, and a pressure dynamic compensation function is established according to the downhole flow situation parameters; the wellhead pressure and the casing pressure are input into the pressure dynamic compensation function, and the corrected wellhead pressure and the corrected casing pressure are obtained; and on the basis of the corrected wellhead pressure, the corrected casing pressure and the throttle valve opening, the throttle valve opening adjusting amount is calculated, the throttle valve is controlled to be adjusted according to the throttle valve opening adjusting amount, and therefore the reliability and accuracy of throttle well killing control are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent control, and in particular to a throttling and well-killing control method, control system, storage medium, and program product. Background Technology

[0002] In oil and gas well production, wellhead pressure control is a crucial aspect of ensuring safe production. Due to factors such as wellbore flow conditions, wellhead pressure can fluctuate to varying degrees, potentially leading to safety hazards. To maintain stable wellhead pressure, throttling and well control methods are typically employed to ensure smooth production.

[0003] Currently, throttling and well-killing control technology mainly employs the PID control algorithm. This algorithm calculates the deviation between the current pressure and the target pressure in real time and determines the control quantity based on the calculation results of the proportional, integral, and derivative components. This throttling and well-killing control method directly inputs the measured pressure signal into the controller, which then outputs a control signal after PID calculation, thereby adjusting the opening of the throttle valve.

[0004] However, in practical applications, due to the nonlinear and time-varying characteristics of wellbore flow, the PID control method with fixed parameters is difficult to adapt to the complex and ever-changing downhole environment, making it difficult to guarantee pressure control accuracy and hindering the safe and efficient production of oil and gas wells. Summary of the Invention

[0005] This application provides a choke control method, control system, storage medium, and program product for improving the reliability and accuracy of choke control.

[0006] Firstly, this application provides a choke control method for well control, applied to a control system. The method includes: acquiring wellhead pressure, casing pressure, choke valve opening, and wellbore temperature gradient data. Wellhead pressure represents the fluid pressure at the wellhead, casing pressure represents the fluid pressure within the annulus, choke valve opening represents the degree of opening of the current control channel of the choke valve, and wellbore temperature gradient data represents the temperature distribution data at different depths from the wellhead to the bottom of the well. The wellbore temperature gradient data is compared with a preset temperature reference curve to obtain a temperature deviation sequence. The temperature deviation sequence is then subjected to Fourier decomposition to obtain the main frequency components. The preset temperature reference curve represents the temperature distribution data of the wellbore at different depths from the wellhead to the bottom of the well. Standard temperature distribution data under normal flow conditions are used, with the main frequency component representing the periodic variation characteristics of wellbore temperature deviation. Based on the main frequency component and a preset frequency threshold, downhole flow condition parameters are determined, and a pressure dynamic compensation function is established according to these parameters. These parameters represent the degree of deviation of the fluid flow intensity within the wellbore from the normal flow condition. The wellhead pressure and casing pressure are input into the pressure dynamic compensation function to obtain the corrected wellhead pressure and corrected casing pressure. Based on the corrected wellhead pressure, corrected casing pressure, and throttle valve opening, the throttle valve opening adjustment amount is calculated, and the throttle valve is controlled to adjust according to this adjustment amount.

[0007] By adopting the above technical solution, abnormal changes in downhole flow can be detected in real time, and a dynamic pressure compensation function can be established to correct wellhead pressure and casing pressure, eliminating the lag and inaccuracy caused by relying solely on surface pressure data in traditional well control. This dynamic compensation mechanism makes the adjustment of the choke valve more precise, enabling effective intervention in the early stages of abnormal situations, preventing serious safety accidents such as well blowouts, and improving the reliability and accuracy of choke well control.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, Fourier decomposition is performed on the temperature deviation sequence to obtain the main frequency components, specifically including: performing discrete Fourier transform on the temperature deviation sequence to obtain a frequency component sequence, the frequency component sequence including multiple frequency components; calculating the amplitude of each frequency component, and determining the frequency component with an amplitude exceeding a preset amplitude threshold as the main frequency component.

[0009] By employing the above technical solution, a discrete Fourier transform is performed on the temperature deviation sequence, and the main frequency components with amplitudes exceeding a preset amplitude threshold are selected, thereby effectively filtering noise signals and secondary frequency interference. This precise frequency extraction mechanism enables the control system to accurately identify the true periodic variation characteristics of downhole fluid flow, focusing only on the main frequency components, unaffected by random disturbances, reducing computational complexity, and improving the response speed of the control system.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the downhole flow situation parameters are determined based on the main frequency components and a preset frequency threshold. Specifically, this includes: if the main frequency component is greater than the preset frequency threshold, the ratio of the main frequency component to the preset frequency threshold is determined as a weighting coefficient; if the main frequency component is less than or equal to the preset frequency threshold, a preset value is determined as a weighting coefficient; the sum of the products of the weighting coefficients and amplitudes of each main frequency component is calculated and divided by the sum of the amplitudes to obtain the downhole flow situation parameters.

[0011] By employing the above technical solution, the main frequency components are compared with preset frequency thresholds, and a weighting coefficient calculation mechanism is introduced to achieve precise quantification of flow anomalies of different degrees. When the main frequency component is greater than the preset frequency threshold, a dynamic weighting coefficient calculation method is used, allowing the downhole flow situation parameters to increase non-linearly with the increase of anomaly severity. When the main frequency component is less than or equal to the preset frequency threshold, a fixed weighting coefficient is used to ensure stability. This adaptive weighting calculation mechanism enables the control system to respond differently to minor and severe anomalies, avoiding the problems of over- or under-control.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, a dynamic pressure compensation function is established based on downhole flow situation parameters, specifically including: determining the flow state based on the downhole flow situation parameters, the flow state including a slight deviation range, a moderate deviation range, and a severe deviation range; determining the pressure compensation coefficient based on the flow state, the slight deviation range corresponding to the first compensation coefficient, the moderate deviation range corresponding to the second compensation coefficient, and the severe deviation range corresponding to the third compensation coefficient, wherein the first compensation coefficient is less than the second compensation coefficient, and the second compensation coefficient is less than the third compensation coefficient; establishing a dynamic pressure compensation function based on the pressure compensation coefficient; the dynamic pressure compensation function is: P'=P×(1+kλ); where P' represents the compensated pressure, P represents the original pressure, k represents the pressure compensation coefficient, and λ represents the downhole flow situation parameters.

[0013] By employing the aforementioned technical solution, the flow state is divided into slight deviation, moderate deviation, and severe deviation ranges, and an increasing pressure compensation coefficient is assigned to each range. This achieves precise pressure compensation for different degrees of abnormality: gentle adjustments are made for slight abnormalities to avoid overreaction; and the compensation intensity is rapidly increased for severe abnormalities to respond promptly to emergencies. This adaptive pressure compensation method based on flow conditions effectively solves the problem of untimely control caused by pressure signal lag in traditional well control, significantly improving the response speed and processing accuracy of the control system to downhole anomalies, and providing a more reliable guarantee for preventing blowout accidents.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the adjustment amount of the choke valve opening is calculated based on the corrected wellhead pressure, the corrected casing pressure, and the choke valve opening. Specifically, this includes: calculating a first pressure difference between the corrected wellhead pressure and the target wellhead pressure range, and a second pressure difference between the corrected casing pressure and the target casing pressure range; calculating a pressure adjustment coefficient based on the first and second pressure differences; multiplying the pressure adjustment coefficient, the choke valve opening, and a preset opening reference value to obtain the target choke valve opening; and determining the difference between the target choke valve opening and the choke valve opening as the adjustment amount of the choke valve opening.

[0015] By adopting the above technical solutions, the control of the throttle valve becomes more precise and stable, avoiding the oscillations and over-adjustment that may be caused by single-parameter control. In particular, the introduction of a pressure regulation coefficient calculation method enables the control system to adaptively adjust the range of throttle valve opening changes according to the magnitude of pressure deviation, realizing an intelligent control strategy of "small adjustment for small deviations and large adjustment for large deviations". This not only improves the stability and safety of the well control process, but also reduces equipment wear and energy consumption, extends service life, and ensures the efficient completion of well control operations.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after calculating the choke valve opening adjustment amount based on the corrected wellhead pressure, the corrected casing pressure, and the choke valve opening, and controlling the choke valve to adjust according to the choke valve opening adjustment amount, the method further includes: obtaining real-time pressure values ​​during the choke valve adjustment process to determine the wellhead pressure change rate and the casing pressure change rate per unit time; when the wellhead pressure change rate or the casing pressure change rate exceeds its respective preset change rate threshold, increasing or decreasing the choke valve opening adjustment amount by a preset compensation amount according to the downhole flow situation parameters and the preset situation threshold.

[0017] By adopting the above technical solution, the wellhead pressure change rate and casing pressure change rate during the choke valve adjustment process are monitored in real time. When the wellhead pressure change rate or casing pressure change rate exceeds its corresponding preset change rate threshold, the control system can perform a secondary correction on the choke valve opening adjustment based on the downhole flow situation parameters and the preset situation threshold. This dynamic feedback mechanism can effectively cope with rapid changes in downhole conditions and prevent pressure runaway due to untimely or insufficient adjustment. Especially under complex formation conditions, when the pressure response shows nonlinear changes, it can adjust the control intensity in a timely manner to avoid system oscillation or instability. The control system introduces downhole flow situation parameters into the real-time adjustment process, establishing a closed-loop control from the bottom of the well to the wellhead, which greatly improves the response capability and processing efficiency to emergencies, provides multiple guarantees for the safety of oil and gas well operations, and also improves the success rate of well control operations.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the pressure regulation coefficient is calculated based on the first pressure difference and the second pressure difference, specifically including: calculating the weighted sum of the first pressure difference and the second pressure difference based on a preset pressure weighting coefficient to obtain a comprehensive pressure deviation value; determining the basic regulation coefficient based on the comprehensive pressure deviation value; establishing a pressure response prediction model based on the historical regulation data of the throttle valve, the historical regulation data including the pressure value before regulation, the pressure value after regulation, and the corresponding regulation coefficient; the pressure response prediction model is used to predict the pressure change trend under different regulation coefficients; inputting the comprehensive pressure deviation value into the pressure response prediction model to obtain the predicted pressure change curve; correcting the basic regulation coefficient based on the pressure change curve to obtain a correction coefficient; multiplying the basic regulation coefficient and the correction coefficient to obtain the final pressure regulation coefficient.

[0019] By adopting the above technical solution, the control system establishes a pressure response prediction model, which can predict the pressure change trend under different regulation coefficients based on historical regulation data, thereby accurately correcting the basic regulation coefficients. This adaptive control strategy combined with machine learning can automatically optimize control parameters according to specific well conditions and historical experience. Especially in environments with complex geological conditions and variable fluid properties, traditional fixed parameter control is difficult to adapt to. This method, through a prediction model driven by historical data, can capture nonlinear pressure response characteristics and achieve more accurate regulation coefficient calculation. This not only improves control accuracy but also shortens stabilization time, reduces the number of adjustments, and significantly enhances the intelligence and adaptability of the control system.

[0020] In a second aspect, embodiments of this application provide a control system comprising: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein the one or more processors invoke the computer instructions to cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: By adopting the above technical solution, abnormal changes in downhole flow can be detected in real time, and a dynamic pressure compensation function can be established to correct wellhead pressure and casing pressure, eliminating the lag and inaccuracy caused by relying solely on surface pressure data in traditional well control. This dynamic compensation mechanism makes the adjustment of the choke valve more precise, enabling effective intervention in the early stages of abnormal situations, preventing serious safety accidents such as well blowouts, and improving the reliability and accuracy of choke well control.

[0025] 2. By adopting the above technical solution, the main frequency components are compared with preset frequency thresholds, and a weighting coefficient calculation mechanism is introduced to achieve accurate quantification of flow anomalies of different degrees. When the main frequency component is greater than the preset frequency threshold, a dynamic weighting coefficient calculation method is used, so that the downhole flow situation parameters can increase non-linearly with the increase of anomaly degree; when the main frequency component is less than or equal to the preset frequency threshold, a fixed weighting coefficient is used to ensure stability. This adaptive weighting calculation mechanism enables the control system to make differentiated responses to minor and severe anomalies, avoiding the problems of over- or under-control.

[0026] 3. By adopting the above technical solution, the flow state is divided into slight deviation, moderate deviation, and severe deviation ranges, and an increasing pressure compensation coefficient is assigned to each range. This achieves precise pressure compensation for different degrees of abnormality: gentle adjustments are made for slight abnormalities to avoid overreaction; and the compensation intensity is rapidly increased for severe abnormalities to respond promptly to emergencies. This adaptive pressure compensation method based on flow conditions effectively solves the problem of untimely control caused by pressure signal lag in traditional well control, significantly improving the response speed and processing accuracy of the control system to downhole anomalies, and providing a more reliable guarantee for preventing blowout accidents. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a throttling and well-killing control method in an embodiment of this application; Figure 2 This is another schematic flowchart of the throttling and well-killing control method in the embodiments of this application; Figure 3 This is a schematic diagram of the physical device structure of a control system in an embodiment of this application. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating a throttling and well-killing control method in an embodiment of this application.

[0031] S101. Collect wellhead pressure, casing pressure, choke valve opening and wellbore temperature gradient data. Wellhead pressure is used to represent the fluid pressure at the wellhead, casing pressure is used to represent the fluid pressure in the annulus, choke valve opening is used to represent the degree of opening of the current control channel of the choke valve, and wellbore temperature gradient data is used to represent the temperature distribution data of measuring points at different depths from the wellhead to the bottom of the well. Among them, wellhead pressure refers to the fluid pressure measured at the top of the wellhead of the oil and gas well, which reflects the pressure state of the fluid rising from the well to the surface; casing pressure refers to the fluid pressure measured in the annulus cavity of the wellbore, which represents the pressure state of drilling fluid or other fluids in the space between the outer wall of the wellbore and the inner casing; choke valve opening refers to the degree of opening of the current control channel of the choke valve, usually expressed as a percentage, which is used to regulate the flow rate and pressure of the fluid; wellbore temperature gradient data is used to represent the temperature distribution at different depths from the wellhead to the bottom of the well, which is usually collected by multiple temperature sensors distributed along the wellbore, and can reflect the fluid flow state and heat conduction characteristics in the wellbore.

[0032] Specifically, the control system acquires wellhead pressure in real time through pressure sensors distributed at the wellhead, casing pressure through annular pressure gauges, and reads the current opening value (choke valve opening) from the choke valve controller. It also obtains temperature data (wellbore temperature gradient data) at different depths in the wellbore through a distributed temperature sensing system (DTS) or a multi-point temperature sensor array. This data is typically acquired multiple times per second to ensure that rapid changes in downhole fluid flow are captured. The control system preprocesses the raw data, including filtering, outlier removal, and data smoothing, to improve the accuracy of subsequent analysis.

[0033] S102. Compare the wellbore temperature gradient data with the preset temperature reference curve to obtain the temperature deviation sequence. Perform Fourier decomposition on the temperature deviation sequence to obtain the main frequency components. The preset temperature reference curve is used to represent the standard temperature distribution data of the wellbore under normal flow conditions. The main frequency components are used to represent the periodic variation characteristics of the wellbore temperature deviation. Among them, the preset temperature reference curve refers to the standard temperature distribution pattern from the wellhead to the bottom of the well under normal flow conditions, which is usually obtained by statistical analysis of historical data or calculation by theoretical models; the temperature deviation sequence refers to the difference sequence between the actual wellbore temperature gradient data and the preset temperature reference curve, which is used to characterize the degree of deviation between the current temperature distribution and the temperature distribution under normal flow conditions; Fourier decomposition is a mathematical method that decomposes a time-domain or spatial-domain signal into a superposition of sine waves of different frequencies, which is used to extract the periodic features in the signal; the main frequency component is used to represent the periodic change features with significant amplitude in the temperature deviation sequence, which is used to reflect the periodic fluctuation characteristics of fluid flow in the wellbore.

[0034] Specifically, the control system compares the collected wellbore temperature gradient data point-to-point with a pre-stored preset temperature reference curve, calculating the temperature deviation value at each depth measuring point to form a temperature deviation sequence. Then, the control system applies a Discrete Fourier Transform (DFT) algorithm to this temperature deviation sequence, transforming it from the spatial domain to the frequency domain, obtaining a series of frequency components and their corresponding amplitudes. The control system filters out the main frequency components based on a preset amplitude threshold (usually set to 2-3 times the average amplitude). These main frequency components can effectively reflect the abnormal periodic changes in fluid flow within the wellbore. In practical applications, the control system typically uses a Fast Fourier Transform (FFT) algorithm to improve computational efficiency and combines it with window functions (such as Hamming windows) to reduce spectral leakage, ensuring the accuracy of frequency analysis.

[0035] Suppose data from a certain oil well is monitored: Preset temperature baseline data (standard temperature distribution pattern from wellhead to bottom of wellbore under normal flow conditions): 0 meters (wellhead): 25℃; 200 meters: 29℃; 400 meters: 33℃; 600 meters: 37℃; 800 meters: 41℃; 1000 meters (bottom of the well): 45℃; Actual measured wellbore temperature gradient data: 0 meters: 25℃; 200 meters: 31℃ (2℃ higher than the benchmark); 400 meters: 31℃ (2℃ lower than the benchmark); 600 meters: 39℃ (2℃ higher than the benchmark); 800 meters: 39℃ (2℃ lower than the benchmark); 1000 meters: 47℃ (2℃ higher than the benchmark) The calculated temperature deviation sequence: 0 meters: 0℃; 200 meters: +2℃; 400 meters: -2℃; 600 meters: +2℃; 800 meters: -2℃; 1000 meters: +2℃; Fourier decomposition revealed that the main frequency component completes a cycle every 400 meters with an amplitude of 2°C. This indicates that there is a temperature fluctuation within the wellbore that cycles once every 400 meters.

[0036] Optionally, in general, Fourier decomposition of the temperature deviation sequence to obtain the main frequency components can be achieved in the following ways, without limitation: Perform discrete Fourier transform on the temperature deviation sequence to obtain a frequency component sequence, which includes multiple frequency components; calculate the amplitude of each frequency component, and determine the frequency component whose amplitude exceeds a preset amplitude threshold as the main frequency component.

[0037] S103. Based on the main frequency components and preset frequency thresholds, determine the downhole flow situation parameters, and establish a pressure dynamic compensation function according to the downhole flow situation parameters. The downhole flow situation parameters are used to represent the degree of deviation of the fluid flow intensity in the wellbore from the normal flow state. Among them, the preset frequency threshold is used to represent the upper limit of the frequency of temperature fluctuation under normal flow conditions. Exceeding the preset frequency threshold means that the fluid flow is abnormal. The downhole flow state parameter is a dimensionless value used to quantify the degree of deviation of the fluid flow state in the wellbore from the normal flow state.

[0038] Specifically, the control system compares the identified primary frequency components with preset frequency thresholds (usually set based on geological conditions and well depth, generally within the range of 0.05-0.2Hz). When the primary frequency component is greater than the preset frequency threshold, its ratio is calculated as a weighting coefficient, indicating the degree of anomaly; when the primary frequency component is less than or equal to the preset frequency threshold, a preset base weight value (usually 1) is used. The control system then calculates the weighted average of the weighting coefficients and amplitudes of each primary frequency component to obtain the downhole flow situation parameter λ. This downhole flow situation parameter typically varies within the range of 0-10, with larger values ​​indicating more severe anomalies. Based on the downhole flow situation parameter, the control system divides the flow state into three intervals: λ<3 is the slight deviation interval, corresponding to a compensation coefficient k=0.1-0.3; 3≤λ<7 is the moderate deviation interval, corresponding to a compensation coefficient k=0.3-0.6; and λ≥7 is the severe deviation interval, corresponding to a compensation coefficient k=0.6-1.0. Finally, the control system establishes a pressure dynamic compensation function P'=P×(1+kλ) to convert the original pressure P into the compensated pressure P', so as to more accurately reflect the actual downhole condition.

[0039] Optionally, under normal circumstances, the downhole flow situation parameters can be determined based on the main frequency components and preset frequency thresholds in the following ways, without limitation: if the main frequency component is greater than the preset frequency threshold, the ratio of the main frequency component to the preset frequency threshold is determined as the weighting coefficient; if the main frequency component is less than or equal to the preset frequency threshold, the preset value is determined as the weighting coefficient; calculate the sum of the products of the weighting coefficients and amplitudes of each main frequency component, and divide by the sum of amplitudes to obtain the downhole flow situation parameters.

[0040] Among them, the weighting coefficient refers to the importance of different frequency components in the judgment of flow status, and high frequency components usually correspond to greater weight; the pressure dynamic compensation function is a mathematical model used to correct the original pressure data according to the downhole flow status parameters to reflect the true downhole pressure status; the flow status classification is the division of the degree of downhole fluid flow anomaly, including three levels: slight deviation, moderate deviation and severe deviation.

[0041] Assuming a preset frequency threshold of 2Hz, signal analysis yields three main frequency components, as follows: f1=1.5Hz, amplitude A1=10; f2=3Hz, amplitude A2=8; f3=4Hz, amplitude A3=5; (1) Determine the weighting coefficients: f1=1.5Hz<2Hz, set weighting coefficient w1=1 (preset value). f2 = 3Hz > 2Hz, w2 = 3 / 2 = 1.5; f3=4Hz>2Hz, w3=4 / 2=2; (2) Calculate the downhole flow parameters: The numerator is calculated as follows: (w1×A1 + w2×A2 + w3×A3) = (1×10 + 1.5×8 + 2×5) = 32. Denominator = (A1 + A2 + A3) = (10 + 8 + 5) = 23; Downhole flow condition parameters = 32 / 23 ≈ 1.39; (3) Based on the downhole flow status parameters, the flow status can be judged (assuming the classification criteria are: 1.0-1.2 is slight deviation, 1.2-1.5 is moderate deviation, and 1.5 is severe deviation): 1.39 falls within the moderate deviation range, indicating that there is a certain degree of abnormality in the downhole flow, but it has not yet reached a severe level. In this case, it may be necessary to adjust the production parameters appropriately, but no emergency measures need to be taken.

[0042] S104. Input the wellhead pressure and casing pressure into the pressure dynamic compensation function respectively to obtain the corrected wellhead pressure and corrected casing pressure. Among them, the corrected wellhead pressure refers to the wellhead pressure value after adjustment by the pressure dynamic compensation function, which more accurately reflects the pressure state after considering downhole flow anomalies; the corrected casing pressure refers to the casing pressure value after the same compensation process, which is used to more accurately characterize the actual pressure state in the annulus; the pressure dynamic compensation function is the mathematical model established in step S103, which is used to convert the original pressure data into a corrected value that considers the influence of downhole anomalies.

[0043] Specifically, the control system inputs the wellhead pressure and casing pressure collected in step S101 into the pressure dynamic compensation function P'=P×(1+kλ) established in step S103 to calculate the corrected wellhead pressure. Similarly, the control system inputs the casing pressure into the same pressure dynamic compensation function to calculate the corrected casing pressure. This process considers the downhole flow condition parameter λ and the corresponding pressure compensation coefficient k, making the pressure correction proportional to the degree of downhole anomaly. In practical applications, the control system usually sets a compensation upper limit (e.g., not exceeding 50% of the original pressure) to prevent over-compensation in extreme cases. Simultaneously, the control system checks the rationality of the compensation results. If the corrected pressure value exceeds the preset reasonable range, an alarm will be triggered, and a backup algorithm may be used for recalculation. This dynamic compensation mechanism allows the control system to "see" downhole pressure anomalies that traditional detection methods cannot detect in a timely manner, providing the possibility for early intervention.

[0044] Optionally, under normal circumstances, the pressure dynamic compensation function can be established based on the downhole flow situation parameters in the following ways, which are not limited here: Determine the flow state based on the downhole flow situation parameters. The flow state includes a slight deviation range, a moderate deviation range, and a severe deviation range. Determine the pressure compensation coefficient based on the flow state. The slight deviation range corresponds to the first compensation coefficient, the moderate deviation range corresponds to the second compensation coefficient, and the severe deviation range corresponds to the third compensation coefficient. The first compensation coefficient is less than the second compensation coefficient, and the second compensation coefficient is less than the third compensation coefficient. Based on the pressure compensation coefficient, establish the pressure dynamic compensation function. The pressure dynamic compensation function is: P'=P×(1+kλ); where P' represents the compensated pressure, P represents the original pressure, k represents the pressure compensation coefficient, and λ represents the downhole flow situation parameters.

[0045] S105. Based on the corrected wellhead pressure, corrected casing pressure, and throttle valve opening, calculate the throttle valve opening adjustment amount, and control the throttle valve to adjust according to the throttle valve opening adjustment amount.

[0046] Among them, the wellhead pressure target range refers to the safe range within which the wellhead pressure should be maintained, usually set by engineers based on formation fracture pressure and well control requirements; the casing pressure target range refers to the safe range within which the casing pressure should be maintained, used to ensure the safety of the wellbore structure and prevent formation fluid intrusion; the first pressure difference is used to represent the deviation between the corrected wellhead pressure and the wellhead pressure target range; the second pressure difference is used to represent the deviation between the corrected casing pressure and the casing pressure target range; the pressure adjustment coefficient is a coefficient calculated based on the pressure deviation, used to determine the adjustment intensity; the preset opening reference value refers to the standard opening value of the throttle valve under normal operating conditions; the throttle valve target opening refers to the ideal opening value to which the throttle valve should be adjusted as calculated by the control system; the throttle valve opening adjustment amount refers to the difference between the current throttle valve opening and the throttle valve target opening, which is the actual adjustment amount executed.

[0047] Specifically, the control system calculates the deviation between the corrected wellhead pressure and the target wellhead pressure range (first pressure difference), and the deviation between the corrected casing pressure and the target casing pressure range (second pressure difference). The control system uses a weighted approach to combine these two deviations, typically with a wellhead pressure deviation weight of 0.6-0.7 and a casing pressure deviation weight of 0.3-0.4, to obtain the comprehensive pressure deviation value. Based on the comprehensive pressure deviation value, the control system calculates the pressure adjustment coefficient (usually varying between 0.1-2.0, with a larger coefficient for larger deviations) by looking up a table or using a function. The control system then multiplies the pressure adjustment coefficient, the current throttle valve opening, and the preset opening reference value (usually 50%-60%) to calculate the target throttle valve opening. Finally, the control system calculates the difference between the target throttle valve opening and the current throttle valve opening to obtain the throttle valve opening adjustment amount, and sends a command to the throttle valve actuator for corresponding adjustments. In practical applications, to prevent system oscillations caused by excessively rapid adjustments, control systems typically set an upper limit for single adjustments (e.g., no more than 5%) and adopt a gradual adjustment strategy, breaking down large adjustments into multiple small adjustments to ensure that the wellbore pressure smoothly transitions to the target range.

[0048] By adopting the above technical solution, abnormal changes in downhole flow can be detected in real time, and a dynamic pressure compensation function can be established to correct wellhead pressure and casing pressure, eliminating the lag and inaccuracy caused by relying solely on surface pressure data in traditional well control. This dynamic compensation mechanism makes the adjustment of the choke valve more precise, enabling effective intervention in the early stages of abnormal situations, preventing serious safety accidents such as well blowouts, and improving the reliability and accuracy of choke well control.

[0049] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the throttling and well-killing control method in this application embodiment.

[0050] The following steps may or may not be performed after step S104; this is not a limitation here: S201. Calculate the first pressure difference between the corrected wellhead pressure and the target wellhead pressure range, and the second pressure difference between the corrected casing pressure and the target casing pressure range. Specifically, the control system reads the preset target range for wellhead pressure (usually set between 85% and 95% of the formation fracture pressure, such as 20MPa-22MPa) and the target range for casing pressure (usually set to a range that can balance formation pressure without damaging the casing, such as 18MPa-20MPa). Then, the control system calculates the deviation between the corrected wellhead pressure and the target range. If the corrected wellhead pressure is lower than the lower limit of the target range, the difference is calculated; if the corrected wellhead pressure is higher than the upper limit, the difference is calculated, resulting in the first pressure difference. The same method is used to calculate the deviation between the corrected casing pressure and the target range, resulting in the second pressure difference. These pressure differences include not only numerical values ​​but also positive and negative information. Positive values ​​indicate that the pressure is too high and the throttle valve opening needs to be increased to reduce pressure, while negative values ​​indicate that the pressure is too low and the throttle valve opening needs to be decreased to increase pressure, providing clear directional guidance for subsequent adjustments.

[0051] S202. Based on the preset pressure weighting coefficient, calculate the weighted sum of the first pressure difference and the second pressure difference to obtain the comprehensive pressure deviation value, and determine the basic adjustment coefficient based on the comprehensive pressure deviation value. Among them, the preset pressure weighting coefficient refers to the proportion of importance allocated to wellhead pressure and casing pressure when calculating the comprehensive pressure deviation, which is used to balance the influence of the two pressures in control decisions; the comprehensive pressure deviation value refers to the overall evaluation value of wellhead pressure deviation and casing pressure deviation after considering the weights, which is used to comprehensively reflect the deviation state of the wellbore pressure system; the basic adjustment coefficient refers to the throttle valve adjustment intensity coefficient initially determined based on the comprehensive pressure deviation value, which is the basic parameter for determining the adjustment range of the throttle valve; the adjustment coefficient-deviation relationship model refers to the pre-established mapping relationship between the comprehensive pressure deviation value and the ideal adjustment coefficient, which is usually derived based on expert experience or historical data analysis.

[0052] Specifically, the control system applies preset pressure weighting coefficients (typically 0.6-0.7 for wellhead pressure and 0.3-0.4 for casing pressure, with a weight sum of 1) to multiply the first pressure difference and the second pressure difference respectively, and then sums them to obtain the comprehensive pressure deviation value. This weighted calculation method can appropriately balance the control requirements of wellhead pressure and casing pressure while ensuring well control safety. Next, the control system inputs the comprehensive pressure deviation value into a pre-established adjustment coefficient-deviation relationship model (which can be a lookup table method or a functional relationship) to determine the basic adjustment coefficient. The adjustment coefficient-deviation relationship model is usually designed with nonlinear characteristics. Small deviation areas (e.g., within ±0.5MPa) correspond to small adjustment coefficients (e.g., 0.1-0.3), medium deviation areas (e.g., ±0.5MPa to ±2MPa) correspond to medium adjustment coefficients (e.g., 0.3-0.6), and large deviation areas (e.g., exceeding ±2MPa) correspond to large adjustment coefficients (e.g., 0.6-1.0). This piecewise nonlinear design ensures gentle adjustment with small deviations, preventing over-adjustment; and increases adjustment intensity with large deviations, enabling rapid response to abnormal situations.

[0053] S203. Establish a pressure response prediction model based on the historical adjustment data of the throttle valve. The historical adjustment data includes the pressure value before adjustment, the pressure value after adjustment, and the corresponding adjustment coefficient. The pressure response prediction model is used to predict the pressure change trend under different adjustment coefficients. Historical regulation data refers to a collection of records of throttle valve regulation operations and their effects performed by the control system in the past, including multiple sets of data samples with time-series correlation; the pressure value before regulation refers to the wellhead pressure and casing pressure recorded before the throttle valve regulation operation, serving as the baseline data for the starting point of regulation; the pressure value after regulation refers to the wellhead pressure and casing pressure recorded when the throttle valve regulation is completed and reaches a stable state, reflecting the actual effect of the regulation operation; the corresponding regulation coefficient refers to the pressure regulation coefficient value used in this regulation operation, recording the regulation intensity information; the pressure response prediction model is a mathematical or machine learning model used to predict the pressure change process after a specific regulation operation based on historical data, reflecting the relationship between throttle valve regulation and pressure response under specific well conditions.

[0054] Specifically, the control system extracts historical throttle valve regulation records from the database for a recent period (typically the last 7-30 days). Each record includes a regulation timestamp, wellhead pressure before regulation, casing pressure before regulation, regulation coefficient used, pressure change data after regulation, and the final stable pressure value. The control system preprocesses this data, including outlier removal, data standardization, and time alignment, to ensure data quality. Then, the control system uses machine learning algorithms (such as support vector regression, random forest, or neural networks) to build a pressure response prediction model based on the processed historical data.

[0055] The steps to build a deep learning-based stress response prediction model are as follows: First, the control system stores the collected data on the wellhead pressure before adjustment, the casing pressure before adjustment, the adjustment coefficient used, the pressure change process data after adjustment, and the final stable pressure value in dataset D in chronological order. Each data entry is formatted as (wellhead pressure before adjustment, casing pressure before adjustment, adjustment coefficient used, pressure change process data after adjustment, and final stable pressure value). The wellhead pressure before adjustment, the casing pressure before adjustment, and the adjustment coefficient used serve as input features for model training, while the pressure change process data after adjustment and the final stable pressure value serve as output features for model training.

[0056] Then, the control system constructs an LSTM-based recurrent neural network, including an input layer, two LSTM hidden layers, a fully connected layer, and an output layer. The input layer takes into account the wellhead pressure before adjustment, the casing pressure before adjustment, and the adjustment coefficient used. The number of nodes in the hidden layer is set to 64, and the number of nodes in the fully connected layer is set to 32. The output layer outputs the pressure change process data after adjustment and the final stable pressure value.

[0057] Next, the control system employs the Adam optimizer with a learning rate of 0.001 and a training batch size of 32. These settings can be adjusted based on actual conditions and are not limited here. 80% of the historical data is divided into a training set and 20% into a validation set. Training is performed for 100 epochs, and the model with the highest accuracy on the validation set is saved. These settings can also be adjusted based on actual conditions and are not limited here. An epoch is the process by which the training dataset is completely processed by the neural network once. In machine learning and deep learning, an epoch is a unit used to measure the number of times the entire training set has been repeatedly learned. Specifically, an epoch is completed when the neural network completes one forward computation and one backward propagation, meaning all data has been processed by the network once. The control system uses binary cross-entropy as the loss function and employs Early Stopping to prevent overfitting. When the value of the loss function exceeds a preset threshold, model training is considered complete, and a stress response prediction model is obtained. Early Stopping is a technique in deep learning and machine learning to prevent model overfitting; it determines when to stop training by monitoring the model's performance on the validation set.

[0058] Finally, the control system inputs the input features from the validation set into the stress response prediction model, obtaining its predicted output. This predicted output is then compared with the actual output features in the validation set, and performance metrics such as accuracy, precision, recall, F1 score, and mean squared error (MSE) are used to evaluate the model's performance. Based on the model's performance on the validation set, its parameters are adjusted, including adjusting the learning rate, changing model complexity (e.g., increasing or decreasing the number of layers or nodes in the neural network), and modifying the regularization strength. This process may require multiple iterations, each based on the previous learning outcome, to optimize the stress response prediction model.

[0059] S204. Input the comprehensive pressure deviation value into the pressure response prediction model to obtain the predicted pressure change curve. Based on the pressure change curve, correct the basic adjustment coefficient to obtain the correction coefficient. Among them, the pressure change curve refers to the trajectory data of pressure changing over time in the future, reflecting the dynamic response process of system pressure after using a specific adjustment coefficient; the stabilization time refers to the time required for the pressure change curve to reach a stable state, which is used to evaluate the adjustment efficiency; the stable pressure refers to the pressure value when the pressure change curve finally tends to stabilize, which is used to evaluate whether the adjustment effect can reach the target range.

[0060] Specifically, the control system inputs information such as the current wellhead pressure, casing pressure, overall pressure deviation, and basic adjustment coefficient into the pressure response prediction model established in step S203. After calculation, the pressure response prediction model outputs the predicted pressure change curve. The control system analyzes the key characteristics of this pressure change curve, including the stabilization time (usually expected to reach stability within 5-15 minutes), the deviation between the stable pressure and the target pressure (expected not to exceed ±0.3 MPa), the maximum overshoot (expected not to exceed 5% of the target pressure), and the pressure change rate (expected not to exceed 0.5 MPa per minute). If the prediction result shows that the stable pressure fails to reach the target pressure, the control system will appropriately increase the correction coefficient (e.g., increase by 10%-30%); if the prediction result shows that the overshoot is too large or the pressure change rate is too high, the control system will decrease the correction coefficient (e.g., decrease by 10%-30%); if the prediction result shows that the stabilization time is too long, the control system will appropriately adjust the correction coefficient according to the well conditions to improve the response speed. The control system continuously adjusts the correction coefficient through multiple iterative predictions until it finds the optimal correction value that can both achieve the target pressure and ensure a smooth adjustment process. This correction coefficient is usually between 0.8 and 1.2.

[0061] S205. Multiply the basic adjustment coefficient by the correction coefficient to obtain the final pressure adjustment coefficient; Among them, the basic adjustment coefficient refers to the adjustment intensity coefficient initially determined based on the comprehensive pressure deviation, reflecting the basic correspondence between the pressure deviation and the adjustment range; the correction coefficient refers to the adjustment value of the adjustment coefficient after optimization by the pressure response prediction model, used to compensate for the inadequacy of the basic adjustment under specific well conditions; the final pressure adjustment coefficient refers to the actual execution adjustment intensity coefficient determined after two steps of calculation, which is the direct determining factor for controlling the change in the throttle valve opening; the preset upper limit value represents the maximum adjustment coefficient allowed by the control system, used to prevent over-adjustment in extreme cases; the preset lower limit value represents the minimum adjustment coefficient allowed by the control system, ensuring that the adjustment can have an effective impact.

[0062] Specifically, the control system directly multiplies the basic adjustment coefficient obtained in step S202 with the correction coefficient obtained in step S204 to calculate the final pressure adjustment coefficient. This product calculation method considers both the basic influence of pressure deviation and incorporates optimization suggestions from the pressure response prediction model for specific well conditions. To ensure the safe and stable operation of the system, the control system limits the calculated pressure adjustment coefficient, typically restricting it to a preset upper limit (e.g., 1.5) and a preset lower limit (e.g., 0.05). When the calculation result exceeds the limit range, the control system automatically truncates to the boundary value and records the limiting event for subsequent analysis.

[0063] S206. Multiply the pressure regulation coefficient, the throttle valve opening degree, and the preset opening degree reference value to obtain the target opening degree of the throttle valve; Among them, the throttle valve opening degree refers to the degree of opening of the current throttle valve control channel, usually expressed as a percentage, ranging from 0% (fully closed) to 100% (fully open); the preset opening reference value refers to the ideal opening ratio of the throttle valve under standard operating conditions, usually preset by engineers according to well conditions and equipment characteristics, and used as a reference value; the throttle valve target opening degree indicates the ideal position to which the throttle valve should be adjusted as calculated by the control system, and is the direct target value for performing adjustment operations; the upper limit opening protection value indicates the maximum degree to which the control system allows the throttle valve to open, used to prevent over-opening and pressure runaway; the lower limit opening protection value indicates the minimum degree to which the control system allows the throttle valve to close, used to ensure that the lowest back pressure is maintained.

[0064] Specifically, the control system calculates the target throttle valve opening by multiplying the pressure regulation coefficient by the throttle valve opening and the preset opening reference value (usually set between 40% and 60%). In this calculation method, the pressure regulation coefficient acts as a proportional factor, determining the direction and magnitude of the adjustment: when the pressure regulation coefficient is greater than 1, the target throttle valve opening increases, the valve opens more, and the pressure decreases; when the pressure regulation coefficient is less than 1, the target throttle valve opening decreases, the valve closes more, and the pressure increases. This calculation also considers the current throttle valve opening as a starting point and the preset opening reference value as a reference standard, making the adjustment more reasonable. The control system performs amplitude limiting processing on the calculation results to ensure that the target throttle valve opening does not exceed the safety upper limit (usually 90%, to prevent pressure loss due to full opening) and the safety lower limit (usually 10%, to ensure minimum back pressure capacity). For special well conditions, such as high-pressure gas wells or wells prone to blowouts, the control system will adjust the opening limit range accordingly, usually setting a stricter upper limit value (such as 70%-80%) to maintain more control margin.

[0065] S207. The difference between the target opening degree of the throttle valve and the opening degree of the throttle valve is determined as the throttle valve opening adjustment amount; Specifically, the control system calculates the difference between the target opening of the throttle valve and the actual opening of the throttle valve to determine the adjustment amount of the throttle valve opening. This difference includes both the direction of adjustment (a positive value indicates that the opening needs to be increased, and a negative value indicates that the opening needs to be decreased) and the magnitude of adjustment (the numerical value represents the percentage change in opening).

[0066] S208. Obtain the real-time pressure value during the throttle valve adjustment process to determine the wellhead pressure change rate and casing pressure change rate per unit time. Among them, the real-time pressure value refers to the data points of wellhead pressure and casing pressure collected at high frequency during the adjustment of the throttle valve, which are used to monitor the dynamic change process of pressure; the wellhead pressure change rate refers to the rate of change of wellhead pressure per unit time, usually in MPa / min (megapascals per minute), reflecting the degree of drastic adjustment of wellhead pressure; the casing pressure change rate refers to the rate of change of casing pressure per unit time, also in MPa / min, reflecting the speed of change of annular pressure.

[0067] Specifically, the control system continuously acquires real-time data on wellhead and casing pressure during the throttle valve regulation process using a high-frequency data acquisition system (typically with a sampling frequency of 1-10Hz). The control system uses a sliding time window method (typically with a window length of 30-60 seconds) to calculate the pressure change rate, which is the pressure change within a specified time window divided by the time interval. To reduce the influence of random noise, the control system typically applies a low-pass filter (such as a moving average or exponential smoothing algorithm) to the raw pressure data before calculating the pressure change rate. The calculated wellhead and casing pressure change rates are displayed numerically and plotted as real-time trend graphs.

[0068] S209. When the wellhead pressure change rate or casing pressure change rate exceeds the corresponding preset change rate threshold, the throttle valve opening adjustment amount is increased or decreased according to the downhole flow situation parameters and the preset situation threshold.

[0069] Among them, the preset rate of change threshold refers to the maximum rate of change of wellhead pressure and casing pressure allowed by the control system. Exceeding this threshold means that the pressure change is too fast and may lead to instability. The preset situation threshold is used to represent the warning value of the downhole flow situation parameter. Exceeding this value indicates that the downhole flow state is abnormally severe. The preset compensation amount refers to the additional adjustment value of the throttle valve opening adjustment amount under abnormal conditions, which is used to strengthen or weaken the original adjustment operation.

[0070] Specifically, the control system continuously compares the wellhead pressure change rate and casing pressure change rate calculated in step S208 with their respective preset change rate thresholds (usually the wellhead pressure change rate threshold is set to ±0.8-1.2 MPa / min, and the casing pressure change rate threshold is set to ±0.6-1.0 MPa / min). When any pressure change rate exceeds its corresponding preset change rate threshold, the control system checks the relationship between the downhole flow situation parameters and the preset situation threshold (usually set to 5-7). Based on the comparison results, it determines the emergency response level: If the downhole flow situation parameters are less than the preset situation threshold and the pressure change rate exceeds it only slightly (e.g., exceeding the preset change rate threshold by 10%-30%), a mild response is adopted, adjusting the throttle valve opening adjustment amount to the preset compensation amount (e.g., ±2%-3%); if the downhole flow situation parameters are close to or equal to the preset situation threshold and the pressure change rate exceeds it significantly (e.g., exceeding the preset change rate threshold by 30%-80%), a moderate response is adopted, adjusting to a larger compensation amount (e.g., ±5%-8%); if the downhole flow situation parameters exceed the preset situation threshold and the pressure change rate exceeds it severely (e.g., exceeding the preset change rate threshold by more than 80%), a severe response is adopted, possibly executing the maximum compensation amount (e.g., ±10%-15%) or triggering an emergency shut-in procedure.

[0071] The control system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3This is a schematic diagram of the physical device structure of the control system in an embodiment of this application.

[0072] It should be noted that, Figure 3 The structure of the control system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0073] like Figure 3 As shown, the control system includes a CPU 301, which can perform various appropriate actions and processes based on a program stored in the read-only memory ROM 302 or a program loaded from the storage section 308 into the random access memory RAM 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0074] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0075] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0076] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0078] Specifically, the control system of this embodiment includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the throttling and well-killing control method provided in the above embodiment.

[0079] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the control system described in the above embodiments; or it may exist independently and not incorporated into the control system. The storage medium carries one or more computer programs that, when executed by a processor of the control system, cause the control system to implement the throttling and well-killing control method provided in the above embodiments.

[0080] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. 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. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0081] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0082] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A throttling and kill well control method, characterized in that, Applied to a control system, the method includes: Data on wellhead pressure, casing pressure, choke valve opening, and wellbore temperature gradient are collected. The wellhead pressure represents the fluid pressure at the wellhead, the casing pressure represents the fluid pressure inside the annulus, the choke valve opening represents the degree of opening of the current control channel of the choke valve, and the wellbore temperature gradient data represents the temperature distribution data at different depths from the wellhead to the bottom of the well. The wellbore temperature gradient data is compared with a preset temperature reference curve to obtain a temperature deviation sequence. The temperature deviation sequence is then subjected to Fourier decomposition to obtain the main frequency components. The preset temperature reference curve is used to represent the standard temperature distribution data of the wellbore under normal flow conditions, and the main frequency components are used to represent the periodic variation characteristics of the wellbore temperature deviation. Based on the main frequency components and the preset frequency threshold, the downhole flow situation parameters are determined, and a pressure dynamic compensation function is established according to the downhole flow situation parameters. The downhole flow situation parameters are used to represent the degree of deviation of the fluid flow intensity in the wellbore from the normal flow state. The wellhead pressure and the casing pressure are respectively input into the pressure dynamic compensation function to obtain the corrected wellhead pressure and the corrected casing pressure. Based on the corrected wellhead pressure, the corrected casing pressure, and the throttle valve opening, the throttle valve opening adjustment amount is calculated, and the throttle valve is controlled to adjust according to the throttle valve opening adjustment amount.

2. The method according to claim 1, characterized in that, The step of performing Fourier decomposition on the temperature deviation sequence to obtain the main frequency components specifically includes: Perform a discrete Fourier transform on the temperature deviation sequence to obtain a frequency component sequence, which includes multiple frequency components. The amplitude of each frequency component is calculated, and the frequency component whose amplitude exceeds a preset amplitude threshold is determined as the main frequency component.

3. The method according to claim 1, characterized in that, The determination of downhole flow state parameters based on the main frequency components and preset frequency thresholds specifically includes: If the main frequency component is greater than the preset frequency threshold, the ratio of the main frequency component to the preset frequency threshold is determined as the weighting coefficient. If the main frequency component is less than or equal to the preset frequency threshold, the preset value will be determined as the weighting coefficient. The downhole flow state parameters are obtained by summing the products of the weighting coefficients and amplitudes of each major frequency component and dividing by the sum of amplitudes.

4. The method according to claim 1, characterized in that, The establishment of the pressure dynamic compensation function based on the downhole flow state parameters specifically includes: The flow state is determined based on the downhole flow situation parameters, and the flow state includes a slight deviation range, a moderate deviation range, and a severe deviation range; The pressure compensation coefficient is determined based on the flow state. The slight deviation range corresponds to the first compensation coefficient, the moderate deviation range corresponds to the second compensation coefficient, and the severe deviation range corresponds to the third compensation coefficient. The first compensation coefficient is less than the second compensation coefficient, and the second compensation coefficient is less than the third compensation coefficient. Based on the pressure compensation coefficient, the pressure dynamic compensation function is established; The pressure dynamic compensation function is: P'=P×(1+kλ) Where P' represents the compensated pressure, P represents the original pressure, k represents the pressure compensation coefficient, and λ represents the downhole flow condition parameter.

5. The method according to claim 1, characterized in that, The calculation of the throttle valve opening adjustment based on the corrected wellhead pressure, the corrected casing pressure, and the throttle valve opening specifically includes: Calculate the first pressure difference between the corrected wellhead pressure and the target wellhead pressure range, and the second pressure difference between the corrected casing pressure and the target casing pressure range; Calculate the pressure regulation coefficient based on the first pressure difference and the second pressure difference; Multiply the pressure regulation coefficient, the throttle valve opening, and the preset opening reference value to obtain the target opening of the throttle valve; The difference between the target opening of the throttle valve and the opening of the throttle valve is determined as the adjustment amount of the throttle valve opening.

6. The method according to claim 5, characterized in that, After the steps of calculating the throttle valve opening adjustment amount based on the corrected wellhead pressure, the corrected casing pressure, and the throttle valve opening, and controlling the throttle valve to adjust according to the throttle valve opening adjustment amount, the method further includes: The real-time pressure value during the throttle valve adjustment process is obtained to determine the wellhead pressure change rate and casing pressure change rate per unit time. When the wellhead pressure change rate or the casing pressure change rate exceeds its respective preset change rate threshold, the throttle valve opening adjustment amount is increased or decreased by a preset compensation amount according to the downhole flow situation parameters and the preset situation threshold.

7. The method according to claim 5, characterized in that, The calculation of the pressure regulation coefficient based on the first pressure difference and the second pressure difference specifically includes: Based on the preset pressure weighting coefficient, the weighted sum of the first pressure difference and the second pressure difference is calculated to obtain the comprehensive pressure deviation value. Based on the comprehensive pressure deviation value, the basic adjustment coefficient is determined. A pressure response prediction model is established based on the historical adjustment data of the throttle valve. The historical adjustment data includes the pressure value before adjustment, the pressure value after adjustment, and the corresponding adjustment coefficient. The pressure response prediction model is used to predict the pressure change trend under different adjustment coefficients. The comprehensive pressure deviation value is input into the pressure response prediction model to obtain the predicted pressure change curve. Based on the pressure change curve, the basic adjustment coefficient is corrected to obtain the correction coefficient. The final pressure regulation coefficient is obtained by multiplying the basic adjustment coefficient by the correction coefficient.

8. A control system, characterized in that, The control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the control system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the control system, it causes the control system to perform the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the control system, the control system performs the method as described in any one of claims 1-7.

Images