Wellbore flow parameter inversion method, device and equipment based on gas well blowout flame form and medium

Abstract

The invention discloses a shaft flow parameter inversion method, device and equipment based on a gas well blowout flame form and a medium. The method comprises the following steps: determining a gas well nozzle inversion model adopted during blowout of a gas well; the current blowout flame height and the current gas well working condition parameters collected at the current moment during gas well blowout are obtained; on the basis of the current blowout flame height and the current gas well working condition parameters, the virtual nozzle flow velocity at the current moment during gas well blowout is inverted through a gas well nozzle inversion model; according to the virtual nozzle flow velocity during gas well blowout at the current moment, the real nozzle jet flow pressure and the real nozzle flow velocity during gas well blowout at the current moment are determined; and on the basis of the real nozzle jet flow pressure and the real nozzle flow speed during gas well blowout at the current moment, shaft flow parameters during gas well blowout at the current moment are determined. According to the scheme, the wellbore flow parameters are calculated based on the blowout flame height and the gas well working condition parameters during gas well blowout.

Description

Methods, apparatus, equipment, and media for inverting wellbore flow parameters based on gas well blowout flame morphology Technical Field

[0001] This invention relates to the field of oil and gas field development technology, and in particular to a method, apparatus, equipment and medium for inverting wellbore flow parameters based on the blowout flame morphology of gas wells. Background Technology

[0002] In the process of oil and gas field development, well blowout is a common and serious accident. When a well blowout occurs, a large amount of high-pressure formation fluid is ejected from the wellhead, which not only poses a direct threat to the life safety of on-site personnel, but also causes serious damage to various equipment, resulting in huge economic losses.

[0003] In gas well blowout accidents, the situation is more complex and dangerous. On the one hand, gas well blowouts are often accompanied by multiple risks, including massive explosions, fires, and poisoning from toxic and harmful gases, making them particularly dangerous. During a blowout, improper on-site operation or impacts that generate sparks can easily ignite the jet stream, leading to an explosion or uncontrolled fire. On the other hand, when the jet stream contains toxic and harmful gases that cannot be effectively controlled, the jet stream is often actively ignited to reduce harm to on-site personnel and surrounding residents. However, whether the jet stream is actively ignited or accidentally ignited, it creates a large-scale blowout flame and releases intense heat radiation. This intense heat radiation makes it difficult for on-site personnel and equipment to approach the wellhead, making it difficult to directly obtain key wellbore flow parameters such as blowout flow rate and bottom hole pressure. Without accurate wellbore flow parameters, it is difficult to formulate a scientific and effective rescue plan, and well control and well control operations cannot be carried out smoothly. This will further prolong the impact time of the accident and increase the losses and difficulty of handling it. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for inverting wellbore flow parameters based on the blowout flame morphology of a gas well, in order to solve the problem that it is difficult to effectively obtain key wellbore flow parameters such as blowout flow rate and bottom hole pressure when a gas well blows out.

[0005] According to one aspect of the present invention, a method for inverting wellbore flow parameters based on the blowout flame morphology of a gas well is provided, the method comprising:

[0006] The gas well nozzle inversion model used during a gas well blowout is determined. This model is trained using input and output sample data. It takes the blowout flame height and gas well operating parameters as inputs and outputs the virtual nozzle velocity of the gas well. The input sample data used for training includes the blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter, the gas composition during the blowout, the wellhead fluid temperature, and the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is calculated using a preset virtual nozzle calculation model corresponding to the gas well, based on the actual nozzle diameter of the gas well. The virtual nozzle velocity is calculated using a preset virtual nozzle calculation model corresponding to the gas well, based on the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when the blowout gas expands to atmospheric pressure.

[0007] Obtain the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout;

[0008] Based on the current blowout flame height and current gas well operating parameters, the virtual nozzle velocity at the current moment during the gas well blowout is inverted using the gas well nozzle inversion model.

[0009] Based on the virtual nozzle velocity at the current moment during a gas well blowout, determine the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout.

[0010] Based on the actual jet pressure and actual flow velocity at the current gas well blowout, determine the wellbore flow parameters at the current gas well blowout.

[0011] According to another aspect of the present invention, a wellbore flow parameter inversion device based on the gas well blowout flame pattern is provided, the device comprising:

[0012] The first determining module is used to determine the gas well nozzle inversion model used during a gas well blowout. The gas well nozzle inversion model is an inversion model trained based on the input sample data and output sample data used for training. It is used to input the blowout flame height and gas well operating parameters and output the virtual nozzle velocity of the gas well. The input sample data used for training includes the blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter of the gas well, the gas composition during the gas well blowout, the wellhead fluid temperature, the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is the nozzle diameter calculated by using the corresponding preset virtual nozzle calculation model of the gas well based on the actual nozzle diameter of the gas well. The virtual nozzle velocity is the nozzle velocity calculated by using the corresponding preset virtual nozzle calculation model of the gas well based on the actual nozzle velocity of the gas well. The virtual nozzle is the state of the gas when the blowout gas expands to atmospheric pressure.

[0013] The parameter acquisition module is used to acquire the current blowout flame height and current gas well operating parameters collected at the current moment during a gas well blowout.

[0014] The virtual nozzle velocity inversion module is used to invert the virtual nozzle velocity at the current moment of a gas well blowout based on the current blowout flame height and current gas well operating parameters, using the gas well nozzle inversion model.

[0015] The second determining module is used to determine the actual nozzle jet pressure and actual nozzle velocity at the current time of gas well blowout based on the virtual nozzle velocity at the current time of gas well blowout.

[0016] The third determination module is used to determine the wellbore flow parameters at the current moment of a gas well blowout based on the actual nozzle jet pressure and actual nozzle flow velocity at the current moment of the blowout.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory that is communicatively connected to at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the wellbore flow parameter inversion method based on the gas well blowout flame morphology according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the wellbore flow parameter inversion method based on the gas well blowout flame morphology of any embodiment of the present invention.

[0022] The technical solution of this invention involves determining a gas well nozzle inversion model used during a gas well blowout. This model is trained using input and output sample data. It takes the blowout flame height and gas well operating parameters as input and outputs the virtual nozzle velocity of the gas well. The input sample data includes historical data collected during gas well blowouts, including the virtual nozzle diameter, gas composition during the blowout, and wellhead velocity. The system incorporates the body temperature, ambient temperature and wind speed around the gas well. The virtual nozzle diameter is calculated using a pre-defined virtual nozzle calculation model corresponding to the actual nozzle diameter of the gas well. The virtual nozzle velocity is calculated using a pre-defined virtual nozzle calculation model corresponding to the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when it expands to atmospheric pressure. This system utilizes historical data on the blowout flame height and gas well operating parameters to establish a gas well nozzle inversion model, thereby improving the convergence and accuracy of the results. It also obtains the current... The system collects current blowout flame height and well operating parameters from the gas well during a previous blowout. Based on these parameters, it uses a gas well nozzle inversion model to derive the virtual nozzle velocity at the current moment during the blowout. This allows the system to input the current blowout flame height and well operating parameters collected during the blowout into the gas well nozzle inversion model for inversion, obtaining the virtual nozzle velocity at the current moment during the blowout. This provides effective data support for subsequent steps. The nozzle velocity is used to determine the actual nozzle jet pressure and velocity at the current moment during a gas well blowout. This enables the inversion of the virtual nozzle velocity to obtain the actual nozzle jet pressure and velocity. Based on the actual nozzle jet pressure and velocity at the current moment during a gas well blowout, the wellbore flow parameters at the current moment during a gas well blowout are determined. This enables the calculation of wellbore flow rate, bottom hole pressure, and other wellbore flow parameters at the time of a gas well blowout, providing important data references for blowout fire rescue and well control.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 is a flowchart of a wellbore flow parameter inversion method based on the gas well blowout flame pattern provided in Embodiment 1 of the present invention;

[0026] Figure 2 is a schematic diagram of a blowout flame height measuring device and a gas well operating parameter measuring device provided in Embodiment 1 of the present invention;

[0027] Figure 3 is a schematic diagram of a wellbore flow parameter inversion device based on the gas well blowout flame pattern provided in Embodiment 2 of the present invention;

[0028] Figure 4 is a schematic diagram of an electronic device for implementing a wellbore flow parameter inversion method based on the gas well blowout flame morphology, according to Embodiment 3 of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 is a flowchart of a wellbore flow parameter inversion method based on the gas well blowout flame pattern provided in Embodiment 1 of the present invention. This embodiment of the invention is applicable to the calculation of wellbore flow parameters when a gas well blows out. The method can be executed by a wellbore flow parameter inversion device based on the gas well blowout flame pattern. This device can be implemented in hardware and / or software and can be configured in an electronic device that implements the wellbore flow parameter inversion method based on the gas well blowout flame pattern. As shown in Figure 1, the method includes:

[0033] S101. Determine the gas well nozzle inversion model used during a gas well blowout. The gas well nozzle inversion model is an inversion model trained based on the input sample data and output sample data used for training. It is used to input the blowout flame height and gas well operating parameters and output the virtual nozzle velocity of the gas well. The input sample data used for training includes the blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter of the gas well, the gas composition during the gas well blowout, the wellhead fluid temperature, and the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is the nozzle diameter calculated by using the corresponding preset virtual nozzle calculation model based on the actual nozzle diameter of the gas well. The virtual nozzle velocity is the nozzle velocity calculated by using the corresponding preset virtual nozzle calculation model based on the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when the blowout gas expands to atmospheric pressure.

[0034] In this embodiment of the invention, a gas well blowout refers to one of the common accidents during oil and gas field development. It is usually caused by improper on-site operation or sparks generated by impact, leading to the accidental ignition of the well gas flow, resulting in an explosion or uncontrolled fire, which may be accompanied by the spread of toxic gases, posing a serious threat to the environment and personnel safety. The gas well blowout inversion model refers to an inversion model pre-established using deep learning training, capable of determining the virtual blowout velocity of the gas well based on the blowout flame height and corresponding gas well operating parameters.

[0035] Input sample data refers to the blowout flame height and well operating parameters obtained through on-site collection or calculation when a gas well experiences a blowout at a historical time. These parameters can be obtained through actual measurements using blowout flame height measuring devices and well operating parameter measuring devices deployed on-site. The gas well blowout operating parameters are a series of indicators describing various physical characteristics and operating conditions of the gas well under blowout conditions, including the virtual nozzle diameter, gas composition during the blowout, wellhead fluid temperature, and ambient temperature and wind speed around the well. Output sample data refers to the calculated virtual nozzle velocity of the gas well.

[0036] Virtual nozzle diameter and virtual nozzle velocity refer to the nozzle diameter and velocity calculated using a pre-defined virtual nozzle calculation model based on the actual nozzle diameter and velocity of the gas well. These values ​​are used to replace the actual nozzle diameter and velocity during a well blowout, improving the convergence of subsequent steps and ensuring the accuracy of the calculation results. The virtual nozzle calculation model is a pre-established model that calculates the virtual nozzle diameter and velocity based on the actual gas well nozzle jet pressure, velocity, diameter, and gas density at the nozzle location. A virtual nozzle simulates the state of gas when it expands to atmospheric pressure during a well blowout.

[0037] Specifically, the system acquires data from on-site measuring devices at the gas well, including the actual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed around the well at historical times when a blowout occurs. Simultaneously, a pre-established virtual nozzle calculation model is used to calculate the corresponding virtual nozzle diameter and virtual nozzle velocity. Then, the virtual nozzle diameter, gas composition at the time of the blowout, wellhead fluid temperature, ambient temperature and wind speed, and blowout flame height at historical times are used as input data, while the virtual nozzle velocity is used as output data. This data is then fed into the inversion model algorithm for deep learning training, establishing a gas well blowout inversion model.

[0038] For example, a high-definition camera can be used to capture and record the height of the blowout flame, taking pictures of the flame when it is stable, and comparing them with the actual objects on site to estimate the height of the blowout flame based on the size of the comparison objects; a thermometer and anemometer can be used to measure the ambient temperature and wind speed around the gas well during a blowout; the gas composition of the gas well during a blowout can be obtained from pre-drilling geological data of the block or data from adjacent gas reservoirs; and the temperature of the fluid at the wellhead during a blowout can be estimated by combining the temperature at the bottom of the gas well before the blowout with a temperature field model of the wellbore.

[0039] As an optional step, the construction process of the gas well nozzle inversion model includes the following steps A1-A4:

[0040] Step A1: Based on the validated blowout flame CFD model and the gas well operating parameters collected at historical times during gas well blowouts, generate a blowout flame height CFD database. The blowout flame height CFD database records the correlation between gas well operating parameters and blowout flame height. The correlation between gas well operating parameters and blowout flame height is used to indicate the influence of the actual nozzle diameter, gas composition during gas well blowouts, wellhead fluid temperature, ambient temperature and wind speed around the gas well collected at historical times on the blowout flame height.

[0041] Step A2: Based on the actual nozzle diameter of the gas well, use the corresponding preset virtual nozzle calculation model to adjust the actual nozzle diameter in the blowout flame height CFD database to the corresponding virtual nozzle diameter.

[0042] Step A3: Based on the constructed blowout flame height CFD database, determine the virtual nozzle velocity corresponding to the gas well operating parameters collected at historical times during gas well blowouts.

[0043] Step A4: Based on the blowout flame height CFD database, determine the input sample data and output sample data used for training, and use the input sample data and output sample data used for training to generate a gas well blowout inversion model.

[0044] In this embodiment of the invention, the blowout flame CFD model refers to a computational fluid dynamics (CFD) model used to simulate and calculate blowout flame phenomena. By solving fundamental equations related to fluid flow, heat transfer, and combustion, it predicts the morphology, temperature distribution, velocity field, and pollutant emissions of the blowout flame. The blowout flame CFD model can consider the influence of various factors, such as gas flow rate, pressure, composition, and surrounding environmental conditions, providing important technical support for the analysis and emergency response of gas well blowout accidents. Validating the blowout flame CFD model involves collecting historical vertical gas jet flame test data to verify the accuracy of the model. When the error between the two is within a threshold range, the established blowout flame CFD model is considered to be able to reasonably calculate the blowout flame height. The blowout flame height CFD database is a database used to store the correlation between gas well operating parameters and blowout flame height.

[0045] Specifically, based on a validated CFD model of blowout flames and combined with actual gas well operating parameters collected at historical times during gas well blowouts, the influence of the actual nozzle diameter, gas composition during blowouts, wellhead fluid temperature, and ambient temperature and wind speed around the gas well on the height of the blowout flame is analyzed. This establishes the correlation between gas well operating parameters and blowout flame height, forming a blowout flame height CFD database. The virtual nozzle diameter of the gas well is calculated using a corresponding preset virtual nozzle calculation model based on the actual nozzle diameter, and this calculated virtual nozzle diameter replaces the corresponding actual nozzle diameter in the blowout flame height CFD database. The gas well operating parameters at historical times during gas well blowouts are determined from the blowout flame height CFD database, and the virtual nozzle velocity is calculated using the corresponding preset virtual nozzle calculation model. Furthermore, based on the blowout flame height CFD database, the gas well operating parameters and blowout flame height are used as input sample data, and the virtual nozzle velocity is used as output sample data to train and generate a gas well nozzle inversion model.

[0046] For example, when establishing a CFD model of a blowout flame, it is necessary to select appropriate turbulence models, combustion models, radiation models, and mesh sizes. For instance: the turbulence model can use the SST k-ω turbulence model; the thermal radiation model can use the P1 thermal radiation model; the combustion model can use the EDM model; the methane flame boundary can be defined using R = Yco / Yco-max = 0.01; the length, width, and height of the entire model should be no less than 80m, 80m, and 150m respectively; and the minimum mesh area can be 12.3mm². 3 The collected historical data should be the blowout flame height data of vertically ejected gas, and the collected blowout flame height data should include actual gas well operating parameters with a flame height greater than 5m.

[0047] Alternatively, a gas well nozzle inversion model can be generated by training using the input sample data and the output sample data used for training, including the following steps B1-B3:

[0048] Step B1: Use an autoencoder to reduce the dimensionality of the input sample data used for training, and extract the key features from the input sample data used for training as the input values ​​of the radial basis function network.

[0049] Step B2: Train and construct mapping relationships using the output sample data for training based on the input values ​​of the radial basis function network.

[0050] Step B3: Use the Bayesian global optimization method to optimize the hyperparameters of the radial basis function network for parameter configuration until a converged gas well nozzle inversion model is obtained.

[0051] In this embodiment of the invention, an autoencoder refers to an unsupervised learning model that attempts to learn the mapping relationship of input data through a neural network to obtain a reconstructed output, typically including an encoder and a decoder. A radial basis function network (RBF network) is a special type of feedforward neural network whose hidden layer activation functions are radial basis functions. The Bayesian global optimization method is a global optimization strategy based on a probabilistic model, suitable for black-box functions, such as hyperparameter tuning of machine learning models. The hyperparameters of a RDF network refer to parameters related to the characteristics of the radial basis functions and the network structure.

[0052] Specifically, the input data used for training the gas well nozzle inversion model is dimensionality-reduced using an autoencoder, and key features are extracted and used as input values ​​for the radial basis function network (RBF network). The output data used for training the gas well nozzle inversion model is then trained using the input values ​​of the RBF network to construct a mapping relationship. Furthermore, a Bayesian global optimization method based on a probabilistic model is employed to optimize the hyperparameters of the RBF network, ensuring optimal parameter configuration to obtain the optimally converged gas well nozzle inversion model.

[0053] S102. Obtain the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout.

[0054] Specifically, the blowout flame height measuring device and the gas well operating parameter measuring device deployed at the gas well site can be used to collect the current blowout flame height and current gas well operating parameters at the current moment when a blowout occurs. For example, the blowout flame height measuring device and the gas well operating parameter measuring device, as shown in Figure 2, include: a gas well blowout flame 201, a camera 202, an anemometer 203, a thermometer 204, a data cable 205, a computer 206, and a display screen 207.

[0055] As an option, the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout are obtained, including the following steps C1-C3:

[0056] Step C1: Obtain the actual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed around the gas well at the current moment during the gas well blowout.

[0057] Step C2: Using the preset virtual nozzle calculation model corresponding to the gas well, and combining the nozzle jet pressure, the actual nozzle diameter collected at the current moment when the gas well blows out is converted into the corresponding virtual nozzle diameter.

[0058] Step C3: Determine the virtual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed collected at the current moment during the gas well blowout as the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout.

[0059] Specifically, the system collects data from the corresponding device at the current moment, including the actual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed around the gas well. Using a preset virtual nozzle calculation model corresponding to the virtual nozzle diameter, the system calculates the virtual nozzle diameter corresponding to the actual nozzle diameter collected at the current moment during the gas well blowout. Then, the calculated virtual nozzle diameter, the collected blowout flame height, the gas composition during the blowout, the wellhead fluid temperature, and the ambient temperature and wind speed around the gas well are used as the parameters for the current blowout flame height and the current gas well operating conditions.

[0060] S103. Based on the current blowout flame height and current gas well operating parameters, the virtual nozzle velocity at the current moment during the gas well blowout is inverted using the gas well nozzle inversion model.

[0061] Specifically, the current blowout flame height and current gas well operating parameters at the current moment are input into the gas well nozzle inversion model as input data, and the virtual nozzle velocity at the current moment of the gas well blowout is output.

[0062] S104. Based on the virtual nozzle velocity at the current time of the gas well blowout, determine the actual nozzle jet pressure and actual nozzle velocity at the current time of the gas well blowout.

[0063] Specifically, the virtual nozzle velocity is determined using the gas well nozzle inversion model at the current time of the gas well blowout, and the actual nozzle jet pressure and actual nozzle velocity at the current time of the gas well blowout are determined based on the virtual nozzle velocity.

[0064] Alternatively, based on the virtual nozzle velocity at the current moment during a gas well blowout, the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout are determined, including the following steps D1-D3:

[0065] Step D1: Determine the speed of sound of the gas jet at the current moment during a well blowout.

[0066] Step D2: If the virtual nozzle velocity at the current time of the gas well blowout is greater than the speed of sound of the well jet at the current time, then the preset virtual nozzle calculation model is used to calculate the actual nozzle jet pressure at the current time of the gas well blowout, and the speed of sound of the well jet at the current time is used as the actual nozzle velocity at the current time of the gas well blowout.

[0067] Step D3: If the virtual nozzle velocity at the current time of the gas well blowout is not greater than the speed of sound of the well jet at the current time, then determine the actual nozzle jet pressure at the current time of the gas well blowout as atmospheric pressure, and take the virtual nozzle velocity at the current time of the gas well blowout as the actual nozzle velocity at the current time of the gas well blowout.

[0068] Specifically, when a gas well blowout occurs, the speed of sound of the well jet is acquired at the current moment, and compared with the virtual nozzle velocity at the time of the blowout, determined by the gas well nozzle inversion model. If the virtual nozzle velocity is greater than the speed of sound of the well jet, the actual nozzle jet pressure at the time of the blowout is calculated using a preset virtual nozzle calculation model corresponding to the virtual nozzle jet pressure, and the speed of sound of the well jet is used as the actual nozzle velocity at the time of the blowout. If the virtual nozzle velocity is less than or equal to the speed of sound of the well jet, atmospheric pressure is used as the actual nozzle jet pressure at the time of the blowout, and the virtual nozzle velocity is used as the actual nozzle velocity at the time of the blowout.

[0069] S105. Based on the actual nozzle jet pressure and actual nozzle flow velocity at the current moment during a gas well blowout, determine the wellbore flow parameters at the current moment during a gas well blowout.

[0070] In this embodiment of the invention, wellbore flow parameters refer to various parameters related to fluid flow in the wellbore of an oil and gas well, including wellhead flow rate, wellbore pressure, flow velocity, and other parameters. Determining these wellbore flow parameters can provide an important reference for subsequently implementing reasonable well control measures.

[0071] Specifically, based on the virtual nozzle velocity at the current moment during a gas well blowout, the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout are determined, and the wellbore flow parameters such as the blowout flow rate and bottom hole pressure are predicted in conjunction with the wellbore temperature and pressure field model.

[0072] As an option, based on the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout, the wellbore flow parameters at the current moment during a gas well blowout are determined, including the following steps E1-E3:

[0073] Step E1: Determine the blowout flow rate at the current moment of the gas well blowout based on the actual nozzle jet pressure, actual nozzle flow velocity, and wellhead fluid temperature at the current moment of the gas well blowout.

[0074] Step E2: Determine the temperature and pressure field model of the gas wellbore at the current moment during a gas well blowout. The temperature and pressure field model of the gas wellbore is a mathematical model used to describe the temperature and pressure distribution in the wellbore.

[0075] Step E3: Based on the actual nozzle jet pressure, actual nozzle velocity, and wellhead fluid temperature at the current moment during a gas well blowout, the bottom hole pressure at the current moment during a gas well blowout is predicted using a gas well temperature and pressure field model.

[0076] In this embodiment of the invention, the blowout flow rate refers to the flow rate of formation fluid that flows uncontrollably into the wellbore and exits the wellhead when a gas well blows out. The wellbore temperature and pressure field model is a mathematical model used to describe the temperature and pressure distribution within the wellbore. This model is used to determine the temperature and pressure values ​​at different depths within the wellbore. The distribution of temperature and pressure in the wellbore is influenced by various factors, including formation characteristics, fluid flow, heat transfer processes, and boundary conditions at the wellhead and bottom. For example, based on the energy conservation equation, integrating the pressure and depth of the entire wellbore yields the wellbore temperature and pressure field model. Using a discretization method, the wellbore is divided into i segments, and the formula for calculating the pressure in each segment is:

[0077]

[0078] In the formula, P is the pressure, MPa; M g Z is the relative density of the gas; T is the gas temperature, °C; Z is the relative density of the gas. g q is the compressibility factor; f is the coefficient of friction; sc The gas volumetric flow rate is m. 3 ·d -1 d is the wellbore diameter, in meters; h is the length of each well section, in meters.

[0079] Specifically, the actual nozzle jet pressure and actual nozzle velocity at the current time of gas well blowout are determined based on the virtual nozzle flow velocity at the current time of gas well blowout. The blowout flow rate at the current time of gas well blowout is calculated in combination with the predicted wellhead fluid temperature. Finally, the bottom hole pressure at the current time of gas well blowout is predicted in combination with the temperature and pressure field model of the gas wellbore at the current time of gas well blowout.

[0080] For example, the wellhead fluid temperature can be obtained based on a wellbore temperature calculation model. By identifying a single unit within the wellbore and applying the energy conservation principle for the inflow and outflow of that unit, the formula for calculating the outlet temperature of each wellbore segment is as follows:

[0081]

[0082] Among them, h in h out To calculate the well depth at the well entrance and exit of the well section, in meters (m); T in T out To calculate the inlet and outlet gas temperatures of the well section, ℃; T f-in T f-out b represents the formation temperature at the well entrance and exit points, in °C; b is the geothermal gradient, in °C·m. -1 ;r cso U is the outer diameter of the casing, in meters; U is the overall thermal conductivity of the wellbore, in W·m. -2 ·℃ -1 ; y(t) is the transient heat transfer function; v f The mass flow rate of the gas is expressed in kg·s. -1 C p For specific heat capacity, J·kg -1 ·℃ -1 .

[0083] For example, an iterative method can be used to programmatically solve the temperature and pressure field model and the wellbore temperature calculation model. Specifically, the wellbore is divided into n segments, and I0 is calculated based on the actual nozzle jet pressure, the actual nozzle flow velocity, and the wellhead fluid temperature; assuming I... i =I0, calculate the initial value P0 for iteration using the formula for calculating the pressure of each section of the wellbore; then calculate I based on P0. i And calculate P using the formula for calculating the pressure of each section of the wellbore. i If P0 and P i If the absolute value of the difference meets the precision requirement, then P i Assign to P i+1 The temperature of the next well section is calculated using the formula for calculating the outlet temperature of each well section; otherwise, the iteration is repeated until the accuracy requirement is met. When the iteration reaches the nth well section, the bottom hole pressure P is obtained. w =P n .

[0084] As an optional feature, in this embodiment of the invention, the calculation formula for the preset virtual nozzle calculation model is specifically as follows:

[0085]

[0086] In the formula, P b and P cPressure at the actual and virtual nozzle locations, in MPa; u b and u c The velocities at the actual and virtual nozzle positions are in m / s; D b and D c For the actual wellhead and virtual nozzle diameters, m; ρ b and ρ c The densities of the gas at the actual and virtual nozzle locations, respectively, are in kg / m³. 3 .

[0087] Specifically, when the pressure at the gas well nozzle is greater than atmospheric pressure, it is considered a blocked flow, and the actual nozzle velocity is the local speed of sound; when the pressure at the gas well nozzle is equal to atmospheric pressure, the actual nozzle velocity is the velocity at the virtual nozzle location.

[0088] The technical solution of this invention involves determining a gas well nozzle inversion model used during a gas well blowout. This model is trained using input and output sample data. It takes the blowout flame height and gas well operating parameters as input and outputs the virtual nozzle velocity of the gas well. The input sample data includes historical data collected during gas well blowouts, including the virtual nozzle diameter, gas composition during the blowout, and wellhead velocity. The virtual nozzle diameter is calculated using a pre-defined virtual nozzle calculation model based on the actual nozzle diameter of the gas well, taking into account the body temperature, ambient temperature and wind speed around the gas well. The virtual nozzle velocity is calculated using the pre-defined virtual nozzle calculation model based on the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when it expands to atmospheric pressure. This allows for the establishment of a gas well nozzle inversion model using historical data on the blowout flame height and gas well operating parameters, thereby improving the convergence and accuracy of the results. It also allows for the acquisition of current... The system collects current blowout flame height and well operating parameters from the gas well during the previous blowout. Based on these parameters, it uses a gas well nozzle inversion model to derive the virtual nozzle velocity at the current moment during the blowout. This allows the system to input the current blowout flame height and well operating parameters collected at the previous moment into the gas well nozzle inversion model for inversion, obtaining the virtual nozzle velocity at the current moment during the blowout. This provides effective data support for subsequent steps. The nozzle velocity is used to determine the actual nozzle jet pressure and velocity at the current moment during a gas well blowout. This enables the inversion of the virtual nozzle velocity to obtain the actual nozzle jet pressure and velocity. Based on the actual nozzle jet pressure and velocity at the current moment during a gas well blowout, the wellbore flow parameters at the current moment during a gas well blowout are determined. This enables the calculation of wellbore flow rate, bottom hole pressure, and other wellbore flow parameters at the time of a gas well blowout, providing important data references for blowout fire rescue and well control.

[0089] Example 2

[0090] Figure 3 is a schematic diagram of a wellbore flow parameter inversion device based on the gas well blowout flame pattern provided in Embodiment 2 of the present invention. This embodiment of the invention is applicable to the calculation of wellbore flow parameters when a gas well blows out. The device can be implemented in hardware and / or software and can be configured in an electronic device that implements the wellbore flow parameter inversion method based on the gas well blowout flame pattern. As shown in Figure 3, the device includes:

[0091] The first determining module 301 is used to determine the gas well nozzle inversion model used during a gas well blowout. The gas well nozzle inversion model is an inversion model trained based on the input sample data and output sample data used for training. It is used to input the blowout flame height and gas well operating parameters and output the virtual nozzle velocity of the gas well. The input sample data used for training includes the blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter of the gas well, the gas composition during the gas well blowout, the wellhead fluid temperature, the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is the nozzle diameter calculated by using the corresponding preset virtual nozzle calculation model of the gas well based on the actual nozzle diameter of the gas well. The virtual nozzle velocity is the nozzle velocity calculated by using the corresponding preset virtual nozzle calculation model of the gas well based on the actual nozzle velocity of the gas well. The virtual nozzle is the state of the gas when the blowout gas expands to atmospheric pressure.

[0092] Parameter acquisition module 302 is used to acquire the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout.

[0093] The virtual nozzle velocity inversion module 303 is used to invert the virtual nozzle velocity at the current moment of the gas well blowout based on the current blowout flame height and the current gas well operating parameters, through the gas well nozzle inversion model.

[0094] The second determining module 304 is used to determine the actual nozzle jet pressure and actual nozzle velocity at the current time of gas well blowout based on the virtual nozzle velocity at the current time of gas well blowout.

[0095] The third determining module 305 is used to determine the wellbore flow parameters at the current time of gas well blowout based on the actual nozzle jet pressure and actual nozzle flow velocity at the current time of gas well blowout.

[0096] As an optional step, the construction process of a gas well nozzle inversion model includes:

[0097] Based on the validated CFD model of the blowout flame and the gas well operating parameters collected at historical times during gas well blowouts, a CFD database of blowout flame height is generated. The CFD database of blowout flame height records the correlation between gas well operating parameters and blowout flame height. The correlation between gas well operating parameters and blowout flame height is used to indicate the influence of the actual nozzle diameter, gas composition during gas well blowout, wellhead fluid temperature, ambient temperature and wind speed around the gas well collected at historical times on the blowout flame height.

[0098] Based on the actual nozzle diameter of the gas well, the corresponding preset virtual nozzle calculation model of the gas well is used, and the actual nozzle diameter in the well blowout flame height CFD database is adjusted to the corresponding virtual nozzle diameter.

[0099] Based on the constructed CFD database of blowout flame height, the virtual nozzle velocity corresponding to the gas well operating parameters collected at historical times during gas well blowouts was determined.

[0100] Based on the CFD database of blowout flame height, the input sample data and output sample data used for training are determined, and the gas well blowout inversion model is generated by training using the input sample data and output sample data used for training.

[0101] Alternatively, a gas well nozzle inversion model can be generated by training using the input sample data and the output sample data used for training, including:

[0102] An autoencoder is used to reduce the dimensionality of the input sample data used for training, and key features in the input sample data used for training are extracted as input values ​​for the radial basis function network.

[0103] The input values ​​of the radial basis function network are used to train and construct the mapping relationship using the output sample data.

[0104] The hyperparameters of the radial basis function network are optimized using the Bayesian global optimization method for parameter configuration until a convergent gas well nozzle inversion model is obtained.

[0105] Optionally, the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout can be obtained, including:

[0106] The system acquires the actual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed around the gas well at the current moment during a gas well blowout.

[0107] Using a pre-set virtual nozzle calculation model corresponding to the gas well, and combining the nozzle jet pressure, the actual nozzle diameter collected at the current moment when the gas well blows out is converted into the corresponding virtual nozzle diameter;

[0108] The virtual nozzle diameter, blowout flame height, gas composition, wellhead fluid temperature, and ambient temperature and wind speed around the gas well collected at the current moment during the gas well blowout are determined as the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout.

[0109] As an option, the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout are determined based on the virtual nozzle velocity at the current moment, including:

[0110] Determine the speed of sound of the gas jet at the current moment during a gas well blowout;

[0111] If the virtual nozzle velocity at the current moment during a gas well blowout is greater than the speed of sound of the well jet at the current moment, then the preset virtual nozzle calculation model is used to calculate the actual nozzle jet pressure at the current moment during a gas well blowout, and the speed of sound of the well jet at the current moment is used as the actual nozzle velocity at the current moment during a gas well blowout.

[0112] If the virtual nozzle velocity at the current moment during a gas well blowout is not greater than the speed of sound of the well jet at the current moment, then the actual nozzle jet pressure at the current moment during a gas well blowout is determined to be atmospheric pressure, and the virtual nozzle velocity at the current moment during a gas well blowout is taken as the actual nozzle velocity at the current moment during a gas well blowout.

[0113] As an option, based on the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout, the wellbore flow parameters at the current moment during a gas well blowout are determined, including:

[0114] Based on the actual nozzle jet pressure, actual nozzle velocity, and wellhead fluid temperature at the current moment during the gas well blowout, determine the blowout flow rate at the current moment during the gas well blowout.

[0115] Determine the temperature and pressure field model of the gas well shaft at the current moment during a gas well blowout. The temperature and pressure field model of the gas well shaft is a mathematical model used to describe the temperature and pressure distribution in the well shaft.

[0116] Based on the actual nozzle jet pressure, actual nozzle velocity, and wellhead fluid temperature at the current moment during a gas well blowout, a gas well temperature and pressure field model is used to predict the bottom hole pressure at the current moment during a gas well blowout.

[0117] As an optional step, the calculation formula for the preset virtual nozzle calculation model is as follows:

[0118]

[0119] In the formula, P b and P c Pressure at the actual and virtual nozzle locations, in MPa; u b and u c The velocities at the actual and virtual nozzle positions are in m / s; D b and D c For the actual wellhead and virtual nozzle diameters, m; ρ b and ρ c The densities of the gas at the actual and virtual nozzle locations, respectively, are in kg / m³. 3 .

[0120] The technical solution of this invention involves determining a gas well nozzle inversion model used during a gas well blowout. This model is trained using input and output sample data. It takes the blowout flame height and gas well operating parameters as input and outputs the virtual nozzle velocity of the gas well. The input sample data includes historical data collected during gas well blowouts, including the virtual nozzle diameter, gas composition during the blowout, and wellhead velocity. The virtual nozzle diameter is calculated using a pre-defined virtual nozzle calculation model based on the actual nozzle diameter of the gas well, taking into account the body temperature, ambient temperature and wind speed around the gas well. The virtual nozzle velocity is calculated using the pre-defined virtual nozzle calculation model based on the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when it expands to atmospheric pressure. This allows for the establishment of a gas well nozzle inversion model using historical data on the blowout flame height and gas well operating parameters, thereby improving the convergence and accuracy of the results. It also allows for the acquisition of current... The system collects current blowout flame height and well operating parameters from the gas well during the previous blowout. Based on these parameters, it uses a gas well nozzle inversion model to derive the virtual nozzle velocity at the current moment during the blowout. This allows the system to input the current blowout flame height and well operating parameters collected at the previous moment into the gas well nozzle inversion model for inversion, obtaining the virtual nozzle velocity at the current moment during the blowout. This provides effective data support for subsequent steps. The nozzle velocity is used to determine the actual nozzle jet pressure and velocity at the current moment during a gas well blowout. This enables the inversion of the virtual nozzle velocity to obtain the actual nozzle jet pressure and velocity. Based on the actual nozzle jet pressure and velocity at the current moment during a gas well blowout, the wellbore flow parameters at the current moment during a gas well blowout are determined. This enables the calculation of wellbore flow rate, bottom hole pressure, and other wellbore flow parameters at the time of a gas well blowout, providing important data references for blowout fire rescue and well control.

[0121] The wellbore flow parameter inversion device based on gas well blowout flame morphology provided in this embodiment of the invention can execute the wellbore flow parameter inversion method based on gas well blowout flame morphology provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0122] Example 3

[0123] Figure 4 is a schematic diagram of an electronic device for implementing a wellbore flow parameter inversion method based on gas well blowout flame morphology, according to Embodiment 3 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] As shown in Figure 4, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the wellbore flow parameter inversion method based on gas well blowout flame morphology.

[0127] In some embodiments, the wellbore flow parameter inversion method based on gas well blowout flame morphology can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the wellbore flow parameter inversion method based on gas well blowout flame morphology described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the wellbore flow parameter inversion method based on gas well blowout flame morphology by any other suitable means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0132] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0133] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0134] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for inverting wellbore flow parameters based on the blowout flame morphology of a gas well, characterized in that, The method includes: determining a gas well nozzle inversion model used during a gas well blowout. The gas well nozzle inversion model is an inversion model trained based on input sample data and output sample data used for training. It takes the blowout flame height and gas well operating parameters as input and outputs the virtual nozzle velocity of the gas well. The input sample data used for training includes blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter of the gas well, the gas composition during the blowout, the wellhead fluid temperature, and the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is the nozzle diameter calculated using a preset virtual nozzle calculation model corresponding to the gas well, based on the actual nozzle diameter of the gas well. The nozzle velocity is calculated using a preset virtual nozzle calculation model corresponding to the gas well, based on the actual nozzle velocity of the gas well. The virtual nozzle represents the state of the gas when it expands to atmospheric pressure. The system acquires the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout. Based on the current blowout flame height and current gas well operating parameters, the virtual nozzle velocity at the current moment during the gas well blowout is inverted using the gas well nozzle inversion model. Based on the virtual nozzle velocity at the current moment during the gas well blowout, the actual nozzle jet pressure and actual nozzle velocity at the current moment during the gas well blowout are determined. Based on the actual nozzle jet pressure and actual nozzle velocity at the current moment during the gas well blowout, the wellbore flow parameters at the current moment during the gas well blowout are determined.

2. The method according to claim 1, characterized in that, The construction process of the gas well nozzle inversion model includes: generating a blowout flame CFD database based on a validated blowout flame CFD model and gas well operating parameters collected at historical times during gas well blowouts. This database records the correlation between gas well operating parameters and blowout flame height. This correlation indicates the influence of the actual nozzle diameter, gas composition during the blowout, wellhead fluid temperature, and ambient temperature and wind speed around the gas well on the blowout flame height. Based on the actual nozzle diameter of the gas well, a preset virtual nozzle calculation model corresponding to the gas well is used to adjust the actual nozzle diameter in the blowout flame height CFD database to the corresponding virtual nozzle diameter; based on the constructed blowout flame height CFD database, the virtual nozzle velocity corresponding to the gas well operating parameters collected at historical times during gas well blowouts is determined; based on the blowout flame height CFD database, the input sample data and output sample data used for training are determined, and the gas well nozzle inversion model is generated by training using the input sample data and output sample data used for training.

3. The method according to claim 2, characterized in that, A gas well nozzle inversion model is generated by training the input sample data and the output sample data used for training. This includes: using an autoencoder to reduce the dimensionality of the input sample data used for training and extracting key features from the input sample data used for training as input values ​​of the radial basis function network; training the output sample data used for training and constructing mapping relationships based on the input values ​​of the radial basis function network; and using a Bayesian global optimization method to optimize the hyperparameters of the radial basis function network for parameter configuration until a converged gas well nozzle inversion model is obtained.

4. The method according to claim 1, characterized in that, The system acquires the current blowout flame height and current well operating parameters collected during the current gas well blowout, including: acquiring the actual nozzle diameter, blowout flame height, gas composition during the blowout, wellhead fluid temperature, and ambient temperature and wind speed around the well; using a preset virtual nozzle calculation model corresponding to the gas well, combined with the nozzle jet pressure, the actual nozzle diameter collected during the current gas well blowout is converted into the corresponding virtual nozzle diameter; the virtual nozzle diameter, blowout flame height, gas composition during the blowout, wellhead fluid temperature, and ambient temperature and wind speed around the well are determined as the current blowout flame height and current well operating parameters collected during the current gas well blowout.

5. The method according to claim 1, characterized in that, Based on the virtual nozzle velocity at the current moment during a gas well blowout, determine the actual nozzle jet pressure and actual nozzle velocity at the current moment during a gas well blowout. This includes: determining the speed of sound of the well jet at the current moment during a gas well blowout; if the virtual nozzle velocity at the current moment during a gas well blowout is greater than the speed of sound of the well jet at the current moment, then use a preset virtual nozzle calculation model to calculate the actual nozzle jet pressure at the current moment during a gas well blowout, and use the speed of sound of the well jet at the current moment as the actual nozzle velocity at the current moment during a gas well blowout; if the virtual nozzle velocity at the current moment during a gas well blowout is not greater than the speed of sound of the well jet at the current moment, then determine the actual nozzle jet pressure at the current moment during a gas well blowout as atmospheric pressure, and use the virtual nozzle velocity at the current moment during a gas well blowout as the actual nozzle velocity at the current moment during a gas well blowout.

6. The method according to claim 1, characterized in that, Based on the actual jet pressure and velocity at the current gas well blowout, the wellbore flow parameters at the current gas well blowout are determined, including: determining the blowout flow rate at the current gas well blowout based on the actual jet pressure, velocity, and wellhead fluid temperature at the current gas well blowout; determining the temperature and pressure field model of the gas wellbore at the current gas well blowout, which is a mathematical model used to describe the temperature and pressure distribution in the wellbore; and predicting the bottom hole pressure at the current gas well blowout using the temperature and pressure field model of the gas wellbore based on the actual jet pressure, velocity, and wellhead fluid temperature at the current gas well blowout.

7. The method according to any one of claims 1 to 6, characterized in that, The calculation formula for the preset virtual nozzle calculation model is as follows: In the formula, P b and P c Pressure at the actual and virtual nozzle locations, in MPa; u b and u c The velocities at the actual and virtual nozzle positions are in m / s; D b and D c For the actual wellhead and virtual nozzle diameters, m; ρ b and ρ c The densities of the gas at the actual and virtual nozzle locations, respectively, are in kg / m³. 3 .

8. A wellbore flow parameter inversion device based on gas well blowout flame morphology, characterized in that, The device includes: a first determining module, used to determine the gas well nozzle inversion model used during a gas well blowout. The gas well nozzle inversion model is an inversion model trained based on input sample data and output sample data used for training. It takes the blowout flame height and gas well operating parameters as input and outputs the virtual nozzle velocity of the gas well. The input sample data used for training includes the blowout flame height and gas well operating parameters collected at historical moments during gas well blowouts. The gas well operating parameters include the virtual nozzle diameter of the gas well, the gas composition during the blowout, the wellhead fluid temperature, and the ambient temperature and wind speed around the gas well. The virtual nozzle diameter is calculated using a preset virtual nozzle calculation model corresponding to the gas well, based on the actual nozzle diameter of the gas well. The virtual nozzle velocity is calculated based on the actual nozzle velocity of the gas well. The system employs a pre-defined virtual nozzle calculation model corresponding to the gas well to calculate the nozzle velocity, where the virtual nozzle represents the state of the gas when it expands to atmospheric pressure. A parameter acquisition module is used to acquire the current blowout flame height and current gas well operating parameters collected at the current moment during the gas well blowout. A virtual nozzle velocity inversion module is used to invert the virtual nozzle velocity at the current moment during the gas well blowout using the gas well nozzle inversion model based on the current blowout flame height and current gas well operating parameters. A second determination module is used to determine the actual nozzle jet pressure and actual nozzle velocity at the current moment during the gas well blowout based on the virtual nozzle velocity. A third determination module is used to determine the wellbore flow parameters at the current moment during the gas well blowout based on the actual nozzle jet pressure and actual nozzle velocity at the current moment during the gas well blowout.

9. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the wellbore flow parameter inversion method based on the gas well blowout flame morphology as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the wellbore flow parameter inversion method based on the gas well blowout flame morphology as described in any one of claims 1-7.

Images