An oil-water two-phase flow phase fraction prediction method and system based on image recognition

Abstract

The present invention relates to an oil-water two-phase flow phase fraction prediction method and system based on image recognition, which includes: using image target detection to obtain the corresponding downhole acoustic velocity of oil and gas from the frequency-wavenumber image of DAS acoustic data; calculating the corresponding two-phase flow phase fraction through the acoustic velocity value of the two-phase flow to complete the prediction of the oil-water two-phase flow phase fraction. The present invention solves the problems such as the small recognition range of downhole flow velocity and acoustic velocity and the poor recognition quality of acoustic velocity in multiphase flow before, and maintains a high recognition accuracy while ensuring a certain recognition speed, thereby ensuring the effective prediction of the downhole two-phase flow phase fraction. The present invention can be applied in the field of oil production in oil and gas wells.

Description

Technical Field

[0001] The present invention relates to the technical field of oil production in oil and gas wells, and particularly to a method and system for predicting the phase fraction of oil-water two-phase flow based on image recognition. Background Art

[0002] In the oil and gas production industry, the prediction of the phase fraction of downhole two-phase flow is very important. The phase fraction of multiphase flow can be determined by the calculated sound speed and mixed density, so as to optimize the oil production process of oil and gas wells. The idea of using well logging noise to identify the movement of downhole fluids has a long history. For example, using noise logging downhole as a spectrometer of relative amplitude versus frequency, the leakage is related to the maximum noise amplitude and high pressure gradient level, but this method is limited to tracking slow fluid movement because the equipment function only records the low frequency range. Some people also use a downhole flowmeter based on acoustic measurement to measure the sound speed of downhole two-phase flow, and then calculate the fluid phase fraction. It is accurate for the measurement of the two-phase oil and water case, while in the presence of gas, the results are only acceptable qualitatively.

[0003] Moreover, in the prior art, the following several methods are disclosed: (1) Relatively simple off-line sampling of oil-water mixture samples, and then determining the corresponding oil-water mixture phase fraction by gravity or centrifugal separation in the laboratory. (2) Measuring the oil-water mixture with a capacitance probe sensor to obtain the corresponding dielectric constant, and obtaining the approximate oil-water mixture phase fraction through the impedance characteristics of the oil-water mixture. (3) Lowering a listening device downhole, correlating the leakage point with the recorded peak noise, then using well logging noise to identify the movement of downhole fluids, and finally calculating the corresponding phase fraction. (4) Using a flowmeter based on passive acoustic navigation and ranging (sonar) technology. The flowmeter uses a sensor array to track the spatially coherent structures (vortices) moving with the water flow, then processes the signals of each sensor to deconvolve its frequency and wavelength, and then uses these frequencies and wavelengths to calculate the convection velocity of the vortices and the sound speed in the fluid, and finally calculates the corresponding phase fraction. (5) Using the recorded noise data as a spectrometer of relative amplitude versus frequency, where the leakage is related to the maximum noise amplitude and high pressure gradient level. This method can track slow fluid movement, obtain the final two-phase flow sound speed, and finally calculate the corresponding phase fraction. (6) Using an optical sensor-based flowmeter to measure the downhole flow velocity. The flowmeter consists of an outer pipe, and an optical fiber coil is wrapped around the outer surface of the outer pipe. When the fluid passes through the pipe, the sound wave will cause local changes in the radial strain of the pipe wall. This strain is captured by the optical sensor, and the pulsating pressure (and thus the corresponding sound speed value) is calculated by correlating the strain with the pipe radius and pipe thickness, and finally the corresponding phase fraction is calculated.

[0004] The application scopes of the above-mentioned solutions have many limitations, such as: labor-intensive, requiring a large amount of time to complete, and not allowing continuous monitoring of liquid-liquid systems; capacitive probe sensors are easily covered by paraffin and inaccurate in a short time. In addition, when the medium is conductive (for example, continuous water), such sensors will also have problems; limited to tracking slow fluid motion; the device function only records the low-frequency range and cannot effectively record all acoustic wave information; only applicable to relatively high oil and gas wells; the measurement effect is not ideal in multiphase flow problems; accurate sound velocity can only be obtained in well sections where the acoustic wave energy propagation is strong and continuous. Summary of the Invention

[0005] In view of the above problems, the object of the present invention is to provide an oil-water two-phase flow phase fraction prediction method and system based on image recognition, which solves the problems such as the small recognition range of downhole flow velocity and sound velocity and the poor sound velocity recognition quality in multiphase flow, and maintains a high recognition accuracy while ensuring a certain recognition speed, thereby ensuring the effective prediction of the downhole two-phase flow phase fraction.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An oil-water two-phase flow phase fraction prediction method based on image recognition, which includes: using image target detection to obtain the corresponding downhole oil and gas sound velocity from the frequency-wavenumber image of DAS acoustic data; calculating the corresponding two-phase flow phase fraction through the sound velocity value of the two-phase flow to complete the prediction of the oil-water two-phase flow phase fraction.

[0007] Further, the frequency-wavenumber image includes:

[0008] Using DAS to measure the propagated acoustic waves in the time domain and spatial domain, and storing the corresponding acoustic wave data;

[0009] Through signal processing based on two-dimensional Fourier transform, transferring the acoustic wave data from the time-depth domain to the frequency-wavenumber domain to obtain the corresponding frequency-wavenumber image.

[0010] Further, in the frequency-wavenumber image, the up-going sound velocity and the down-going sound velocity will be displayed as positive slope and negative slope respectively.

[0011] Further, the image target detection adopts an image recognition method based on Radon transform.

[0012] Further, the downhole oil and gas sound velocity includes:

[0013] Identifying the inclined straight lines in the frequency-wave velocity image through image target detection, and fitting to obtain two corresponding oblique lines;

[0014] Calculating the two oblique lines respectively to obtain the positive slope and negative slope, and further obtaining the up-going sound velocity and down-going sound velocity corresponding to the acoustic waves.

[0015] Furthermore, the calculation of the two-phase flow phase fraction includes: substituting the two-phase flow sound speed equivalent value into the formula for calculating the phase fraction of oil in the oil-water two-phase flow to calculate the corresponding phase fraction value, and finally obtaining the prediction result of the two-phase flow phase fraction.

[0016] The formula for calculating the phase fraction is:

[0017]

[0018]

[0019]

[0020]

[0021] In the formula, α o is the oil phase fraction, c m is the sound speed of the oil-water mixed fluid, c ω is the sound speed of water, c o is the sound speed of water, ρ m is the density of the oil-water mixed fluid, ρ o represents the oil phase density, ρ ω represents the water phase density, d is the pipe diameter, t is the wall thickness, and E is the Young's modulus of the pipe material.

[0022] An oil-water two-phase flow phase fraction prediction system based on image recognition, which includes: a sound speed acquisition module that uses image object detection to obtain the corresponding downhole oil-gas sound speed from the frequency-wavenumber image of DAS acoustic data; a phase fraction prediction module that calculates the corresponding two-phase flow phase fraction through the sound speed value of the two-phase flow to complete the prediction of the oil-water two-phase flow phase fraction.

[0023] Furthermore, in the sound speed acquisition module, the downhole oil-gas sound speed includes:

[0024] A fitting module that identifies the inclined straight lines in the frequency-wave speed image through image object detection and fits two corresponding oblique lines;

[0025] A slope calculation module that calculates the two oblique lines respectively to obtain the positive slope and the negative slope, and further obtains the upward sound speed and the downward sound speed corresponding to the sound wave.

[0026] A computer-readable storage medium storing one or more programs, where the one or more programs include instructions that, when executed by a computing device, cause the computing device to execute any of the above methods.

[0027] A computing device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0028] Due to the above technical solutions adopted by the present invention, it has the following advantages:

[0029] The present invention can identify and calculate the corresponding acoustic velocity in the oil and gas well from the frequency - wavenumber domain image of the acoustic data, and finally calculate the corresponding oil - water mixture phase fraction. This technology of obtaining the downhole corresponding flow velocity through image recognition technology has the advantages of being convenient, efficient, and highly real - time, solving the disadvantages of poor robustness and limited acoustic velocity recognition range in the previous flow velocity recognition solutions, and can efficiently identify the change trend of the acoustic velocity of the oil - water mixture in the oil and gas well, and then obtain the real - time multi - phase fraction in the oil and gas well. Through these real - time water - oil phase fraction data, it can provide a more accurate well configuration for the oil production company and can well improve the oil production of the oil and gas well. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a schematic flow chart of a method for predicting the oil - water two - phase flow phase fraction based on image recognition in an embodiment of the present invention;

[0031] Figure 2 is a schematic diagram of obtaining the backscattered light data of the sound field through a DAS system in an embodiment of the present invention;

[0032] Figure 3 is a schematic diagram of the original acoustic data collected from a branched well in an embodiment of the present invention;

[0033] Figure 4 is a frequency - wavenumber domain image of the acoustic wave data in an embodiment of the present invention;

[0034] Figure 5It is a graph of the predicted sound velocity of two-phase flow in an oil and gas well in an embodiment of the present invention; wherein, Figure a is a DAS image to be recognized (the straight line in the figure is the recognized result, which is drawn on the original DAS image. The sound velocity in the oil and gas well of the present invention is the slope of the straight line in the figure, and the calculated sound velocity is 3054.77 m / s); Figure b is a Radon transform image. The essence of the Radon transform is to perform a spatial transformation on the original function, that is, map the points in the original XY plane to the Xθ plane. Then, all the points on a straight line in the original Xθ plane are located at the same point in the AB plane. By recording the accumulated thickness of the points in the Xθ plane, the existence of the line in the XY plane can be known. The black dots in the figure are local maxima, and it is very likely to be the position of a straight line; Figure c is a confidence image of the radial direction X of the Radon transform image. The position marked with a dotted line in the middle of the confidence image is the position with the maximum X confidence. The present invention takes it as the X position for recognizing the image; Figure d is a confidence image of the projection angle θ of the Radon transform image. The position marked with a dotted line in the middle of the confidence image is the position with the maximum θ confidence. The present invention takes it as the θ position for recognizing the image;

[0035] Figure 6 It is a graph of the predicted phase fraction of two-phase flow in an oil and gas well in an embodiment of the present invention. Specific implementation manners

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments 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 some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention fall within the scope of protection of the present invention.

[0037] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0038] To solve the problems of poor robustness of the flow velocity identification scheme and limited sound velocity identification range in the prior art, the present invention proposes a method and system for predicting the phase fraction of oil-water two-phase flow based on image recognition for the problem of flow velocity identification in oil and gas wells. Through image target detection based on the Randon transform, the corresponding sound velocity in the oil and gas well is obtained from the frequency-wavenumber domain image of DAS (distributed acoustic sensor) acoustic data, and then the corresponding two-phase flow phase fraction can be obtained through calculation. The present invention can directly identify the frequency-wavenumber domain image of the acoustic wave data, obtain the sound velocity in the oil and gas well more efficiently and accurately, and finally obtain the corresponding phase fraction value through calculation, so as to realize the rapid detection of the two-phase flow phase fraction in the oil and gas well.

[0039] In an embodiment of the present invention, a method for predicting the phase fraction of oil-water two-phase flow based on image recognition is provided. In this embodiment, as Figure 1 shown, the method includes the following steps:

[0040] 1) Through image target detection based on the Randon transform, obtain the corresponding sound velocity in the oil and gas well from the frequency-wavenumber domain image of DAS acoustic data;

[0041] 2) Calculate the corresponding two-phase flow phase fraction through the sound velocity value of the two-phase flow to complete the prediction of the oil-water two-phase flow phase fraction.

[0042] In the above step 1), the acquisition of the frequency-wavenumber image includes the following steps:

[0043] 1.1.1) Use DAS to measure the propagated acoustic waves in the time domain and space domain (as Figure 2 shown), and store the corresponding acoustic wave data;

[0044] In this embodiment, when the fluid passes through the interval control valve ICV, acoustic waves will be generated. In this embodiment, the distributed optical wave sensor DAS is used as the acoustic wave data collection module, and the scattered light data of the sound field is obtained through the DAS system, and then the obtained acoustic wave data, as Figure 3 shown.

[0045] 1.1.2) Through signal processing based on two-dimensional Fourier transform, transfer the acoustic wave data from the time-depth domain to the frequency-wavenumber domain to obtain the corresponding frequency-wavenumber (f-k) image.

[0046] In this embodiment, since the acoustic wave data is continuously collected over time, the data needs to be divided into several blocks to calculate the sound velocity within a specific time and depth range. For each time-depth block, two-dimensional Fourier transform is applied, so as to transfer the acoustic wave data from the time-depth domain to the frequency-wavenumber domain (f-k), and the corresponding f-k image is obtained, as Figure 4 shown.

[0047] In step 1) above, in the frequency - wavenumber image, the up - going sound velocity and the down - going sound velocity will be displayed as a positive slope and a negative slope respectively.

[0048] In this embodiment, since sound waves propagate in two directions, i.e., downstream and upstream, in the fluid in the wellbore, the up - going velocity and the down - going velocity of the sound can be obtained by tracking these sound waves. In the frequency - wavenumber image, the up - going and down - going sound velocities will be displayed as a positive slope and a negative slope respectively.

[0049] In step 1) above, image target detection uses an image recognition method based on the Radon transform.

[0050] Among them, the method for obtaining the sound velocity in the oil and gas well includes the following steps:

[0051] 1.2.1) Identify the inclined straight lines in the frequency - wave velocity image through image target detection, and fit to obtain two corresponding oblique lines;

[0052] 1.2.2) Calculate the two oblique lines respectively to obtain a positive slope and a negative slope, and then obtain the up - going sound velocity and the down - going sound velocity corresponding to the sound waves, as shown in Figures a to d in Figure 5 below.

[0053] In step 2) above, substituting the sound velocity equivalent of the two - phase flow into the calculation formula of the oil phase fraction in the oil - water two - phase flow, the corresponding phase fraction value can be calculated, and the final prediction result of the two - phase flow phase fraction is as shown in Figure 6 below.

[0054] Specifically, the calculation of the two - phase flow phase fraction includes the following steps:

[0055] The next step of using the sound velocity to characterize the downhole flow information is to convert these measurement values into phase fraction information. This step starts from the definition of the sound velocity given by the Newton - Laplace equation:

[0056]

[0057] where c m is the sound velocity of the oil - water mixed fluid, ρ m is the density of the oil - water mixed fluid, and K t is the total bulk modulus of the oil - water mixed fluid and the pipeline. The total bulk modulus and the density of the oil - water mixed fluid are determined by the mixing equations of these two properties.

[0058] Assuming that the fluid is a homogeneous oil - water mixture, the arithmetic mean of the densities is the density of the mixed fluid, which is:

[0059] ρ m = α o ρ o +(1 - α o )ρω (1.2)

[0060] In the formula, ρ o represents the density of the oil phase, and ρ ω represents the density of the water phase.

[0061] The bulk modulus of the fluid mixture is given by the approximate harmonic mean using R euss as follows:

[0062]

[0063] In the formula, K t is the overall bulk modulus of the oil-water mixture and the pipeline, and K o is the bulk modulus of the oil phase, c o is the sound velocity of the oil phase, α o is the oil-phase fraction, and K ω is the bulk modulus of the water phase, c ω is the sound velocity of the water phase.

[0064] To account for the expansibility of the flow pipeline, the last term in Equation (1.3) above includes the pipeline diameter d, the wall thickness t, and the Young's modulus E of the pipeline material. At this point, substituting Equations (1.2) and (1.3) into Equation (1.1), and expressing the moduli of oil and water in terms of sound velocity and density as and After rearranging the equation, we get:

[0065]

[0066] The left side of this equation is obtained by processing the acoustic signal as described above. All the properties on the right side of the equation are individual phase properties. All these properties are to be evaluated at the wellbore pressure and temperature, which can be obtained from DTS and ICV sensors at a certain depth and time. The only remaining unknown in the equation is α o , which is the oil-phase fraction to be obtained in this embodiment.

[0067] Equation (1.4) is processed into a quadratic equation in the form of with its coefficients defined as follows:

[0068]

[0069] Solving this quadratic equation gives two roots:

[0070]

[0071] Through the calculations of the above series of formulas, the finally obtained α oIt is the phase fraction of oil in the oil-water two-phase flow to be solved.

[0072] In summary, the present invention mainly utilizes the image target detection technology based on the Randon transform, which can identify and calculate the corresponding acoustic velocity in the oil and gas well from the frequency-wavenumber domain image of the acoustic data. Finally, the corresponding phase fraction of the oil-water mixture is obtained through calculation. This technology of obtaining the corresponding downhole flow velocity through image recognition technology has the advantages of convenience, high efficiency, and high real-time performance, and solves the disadvantages of poor robustness and limited acoustic velocity recognition range of the previous flow velocity recognition scheme. It can efficiently identify the change trend of the acoustic velocity of the oil-water mixture in the oil and gas well, and then obtain the real-time multi-phase fraction in the oil and gas well. Through these real-time water-oil phase fraction data, it can provide a more accurate well configuration for the oil production company and can well improve the oil production of the oil and gas well.

[0073] Furthermore, the present invention collects downhole acoustic data through a distributed acoustic sensor DAS: the time synchronization of the laser pulse allows the backscattering event to be accurately mapped to the fiber optic distance. At the same time, when the fluid passes through the interval control valve ICV, acoustic waves are generated. In addition, when the traveling light encounters minute changes caused by the flowing acoustic waves when passing through the line, it will experience backscattering. The backscattering signal generated by the laser pulse signal emitted during measurement in the optics is converted into a strain rate record sampled every few meters along the fiber optic. This backscattered light returns along the fiber optic to the DAS for sampling, so a series of acoustic data can be obtained. The two-dimensional Fourier transform technology is used to convert the collected acoustic data from the time-depth domain to the frequency-wavenumber domain, obtaining a frequency-wavenumber domain image, which makes it easier to analyze the relevant information of the acoustic data. The Radon transform is used to directly obtain the up and down acoustic velocities corresponding to the acoustic waves from the frequency-wavenumber domain image. Finally, the obtained acoustic velocity values are substituted into a series of equations to obtain the corresponding phase fraction values, thus efficiently guiding the downhole oil production work.

[0074] In an embodiment of the present invention, a system for predicting the phase fraction of an oil-water two-phase flow based on image recognition is provided, which includes:

[0075] An acoustic velocity acquisition module, which uses image target detection to obtain the corresponding acoustic velocity in the oil and gas well from the frequency-wavenumber image of the DAS acoustic data;

[0076] A phase fraction prediction module, which calculates the corresponding phase fraction of the two-phase flow through the acoustic velocity value of the two-phase flow to complete the prediction of the phase fraction of the oil-water two-phase flow.

[0077] In the above embodiment, in the acoustic velocity acquisition module, the acoustic velocity in the oil and gas well includes:

[0078] A fitting module, which uses image target detection to identify the inclined straight lines in the frequency-wave velocity image and fits to obtain two corresponding oblique lines;

[0079] The slope calculation module calculates two oblique lines respectively to obtain the positive slope and the negative slope, and further obtains the upward sound velocity and the downward sound velocity corresponding to the sound wave.

[0080] The system provided in this embodiment is used to execute the above method embodiments. For the specific process and detailed content, please refer to the above embodiments and will not be elaborated here.

[0081] In a computing device provided in an embodiment of the present invention, the computing device may be a terminal, which may include: a processor, a communications interface, a memory, a display screen, and an input device. Among them, the processor, the communications interface, and the memory complete communication with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. When the computer program is executed by the processor, it implements a method for predicting the phase fraction of oil-water two-phase flow based on image recognition; the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communications interface is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen may be a liquid crystal display screen or an electronic ink display screen. The input device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computing device, or an external keyboard, a touchpad, or a mouse, etc. The processor can call the logical instructions in the memory.

[0082] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the foregoing storage medium includes: USB flash drive, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, or optical disk, etc., which can store program codes.

[0083] In one embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, enable the computer to execute the methods provided in the above method embodiments.

[0084] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium stores server instructions that cause a computer to execute the methods provided in the above embodiments.

[0085] For a computer-readable storage medium provided in the above embodiments, its implementation principle and technical effects are similar to those of the above method embodiments, and will not be elaborated here.

[0086] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0087] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for predicting the phase fraction of oil-water two-phase flow based on image recognition, characterized in that, Comprising: Using image object detection, obtaining the corresponding downhole acoustic velocity of oil and gas from the frequency - wavenumber image of DAS acoustic data; Calculating the corresponding two - phase flow phase fraction through the acoustic velocity value of the two - phase flow, and completing the prediction of the oil - water two - phase flow phase fraction; The downhole acoustic velocity of oil and gas includes: Identifying the inclined straight lines in the frequency - wave velocity image through image object detection, and fitting to obtain two corresponding oblique lines; Calculating the two oblique lines respectively to obtain the positive slope and the negative slope, and further obtaining the upward acoustic velocity and the downward acoustic velocity corresponding to the sound wave; The calculation of the two - phase flow phase fraction includes: substituting the two - phase flow acoustic velocity equivalent value into the phase fraction calculation formula of oil in the oil - water two - phase flow, calculating to obtain the corresponding phase fraction value, and finally the prediction result of the two - phase flow phase fraction; The phase fraction calculation formula is: Wherein, is the oil-phase volume fraction, is the sound velocity of the oil-water mixture fluid, is the sound velocity of the water phase, is the sound velocity of the water phase, is the density of the oil-water mixture fluid, represents the density of the oil phase, represents the density of the water phase, d is the pipe diameter, t is the wall thickness of the pipe, E is the Young's modulus of the pipe material.

2. The oil-water two-phase flow phase fraction prediction method based on image recognition according to claim 1, characterized in that The frequency - wavenumber image includes: Measuring the propagating sound wave using DAS in the time domain and the spatial domain, and storing the corresponding acoustic wave data; Through signal processing based on two - dimensional Fourier transform, transferring the acoustic wave data from the time - depth domain to the frequency - wavenumber domain to obtain the corresponding frequency - wavenumber image.

3. The oil-water two-phase flow phase fraction prediction method based on image recognition according to claim 1 or 2, characterized in that, In the frequency - wavenumber image, the upward acoustic velocity and the downward acoustic velocity will be respectively displayed as the positive slope and the negative slope.

4. The oil-water two-phase flow phase fraction prediction method based on image recognition according to claim 1, characterized in that, The image object detection adopts an image recognition method based on the Radon transform.

5. An oil-water two-phase flow phase fraction prediction system based on image recognition, characterized in that, Comprising: An acoustic velocity acquisition module, which uses image object detection to obtain the corresponding downhole acoustic velocity of oil and gas from the frequency - wavenumber image of DAS acoustic data; A phase fraction prediction module, which calculates the corresponding two - phase flow phase fraction through the acoustic velocity value of the two - phase flow, and completes the prediction of the oil - water two - phase flow phase fraction; In the acoustic velocity acquisition module, the downhole acoustic velocity of oil and gas includes: A fitting module, which identifies the inclined straight lines in the frequency - wave velocity image through image object detection, and fits to obtain two corresponding oblique lines; A slope calculation module, which calculates the two oblique lines respectively to obtain the positive slope and the negative slope, and further obtains the upward acoustic velocity and the downward acoustic velocity corresponding to the sound wave; The calculation of the two - phase flow phase fraction includes: substituting the two - phase flow acoustic velocity equivalent value into the phase fraction calculation formula of oil in the oil - water two - phase flow, calculating to obtain the corresponding phase fraction value, and finally the prediction result of the two - phase flow phase fraction; The phase fraction calculation formula is: In the formula, is the oil phase fraction, is the sound velocity of the oil-water mixed fluid, is the sound velocity of the water phase, is the sound velocity of the water phase, is the density of the oil-water mixed fluid, represents the density of the oil phase, represents the density of the water phase, d is the pipe diameter, t is the wall thickness of the pipe, E is the Young's modulus of the pipe material.

6. A computer-readable storage medium storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to execute any of the methods described in claims 1 to 4.

7. A computing device, characterized in that, Comprising: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described in claims 1 to 4.

Images