Shale oil flowback effect evaluation method and system based on machine learning

Abstract

The invention discloses a shale oil flow-back effect evaluation method and system based on machine learning, and relates to the technical field of petroleum engineering, and the method comprises the steps: determining the critical flow and critical pressure of a to-be-evaluated shale oil flow-back system based on the logging data of a shale oil well flow-back shaft; based on the critical flow and the critical pressure, dividing a target space taking the flow and the pressure as dimensions into a plurality of category areas; dividing a plurality of flowback data points of the shale oil flowback system to be evaluated into a plurality of category areas by using a clustering method based on machine learning; counting the number of the flowback data points in each category region to obtain a number matrix; calculating a security flowback evaluation index based on the quantity matrix and a preset weight matrix; and based on the safe flowback evaluation index, evaluating the flowback effect of the shale oil flowback system to be evaluated. According to the method, the technical problem that the evaluation of the shale oil flowback effect cannot be quantitatively and specifically guided in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of petroleum engineering technology, and in particular to a shale oil flowback effect evaluation method and system based on machine learning. Background Art

[0002] At present, the focus of oil exploration and development research is shifting from conventional oil to unconventional oil. Shale oil is the focus of unconventional oil and gas research, and has gradually become the focus of actual development in my country's oil fields. Shale oil development is difficult, and natural industrial oil flow cannot be obtained using traditional technology. It is necessary to use the key technology of horizontal well volume fracturing to transform it so that production can be carried out efficiently. The hydraulic fracturing process requires the injection of a large amount of fracturing fluid and proppant to achieve the pressure opening and support of hydraulic fractures. After the hydraulic fracture network is formed or after the well is blocked, the fracturing fluid needs to be returned to prevent formation damage and other problems. The return process is directly related to the hydraulic fracturing transformation effect, directly affects the size of the effective transformation fracture volume, and affects the final production and economic benefits.

[0003] The design and optimization of the flowback system for shale oil is an important part of production. The fracturing technology for shale oil with low porosity and permeability is difficult and costly, so it is particularly important to ensure the fracturing effect. The flowback process is a complex coupling process of formations, fractures, and wellbores. Optimizing the flowback system requires comprehensive research from many aspects. Therefore, a method is needed that can comprehensively consider formations, fractures, and wellbores, ensure the quantitative evaluation of the flowback effect of fracturing, and guide the flowback operation.

[0004] Some scholars have used experimental methods to optimize the flowback technology of tight sandstone gas reservoirs. Liquid nitrogen fracturing experiments were conducted using the colorless and odorless liquid nitrogen with weak chemical properties and slightly soluble in most liquids, and liquid nitrogen was used to assist in drainage. Water lock damage was evaluated using cores from various reservoirs in tight gas reservoirs in western Sichuan, and gas permeability was measured. The results showed that the greater the pressure and the longer the pressurization time, the more serious the water lock damage in the flowback process. Reducing the flowback pressure can reduce the degree of water lock damage.

[0005] However, the above technical solution is aimed at tight sandstone gas reservoirs. The liquid nitrogen fracturing and drainage method has a limited application scope in engineering practice, and the number of experiments is also small. No experiments have been conducted on shale oil wells. Only pressure parameters are considered, and the various problems that may arise during the backflow process are not fully considered. The results are qualitative results and cannot provide quantitative and targeted guidance for the evaluation of shale oil backflow effects. Summary of the invention

[0006] The purpose of the present invention is to provide a shale oil flowback effect evaluation method and system based on machine learning in order to solve at least one of the above technical problems.

[0007] In the first aspect, an embodiment of the present invention provides a shale oil flowback effect evaluation method based on machine learning, comprising: determining the critical flow rate and critical pressure of the shale oil flowback system to be evaluated based on the logging data of the shale oil well flowback wellbore; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure; based on the critical flow rate and the critical pressure, dividing the target space with flow rate and pressure as dimensions into multiple category areas; using a clustering method based on machine learning, dividing multiple flowback data points of the shale oil flowback system to be evaluated into the multiple category areas; counting the number of flowback data points in each category area to obtain a quantity matrix; calculating a safe flowback evaluation index based on the quantity matrix and a preset weight matrix; and evaluating the flowback effect of the shale oil flowback system to be evaluated based on the safe flowback evaluation index.

[0008] Furthermore, the calculation formula of the minimum flow rate includes:

[0009]

[0010] in,

[0011] ρ f =ρ o f o +ρ w f w

[0012]

[0013] Q1 is the minimum flow rate, d s is the proppant particle diameter, ρ s is the proppant particle density, ρ f is the wellbore fluid density, d W is the flowback wellbore diameter, C D is the drag coefficient, ρ w is the water phase density, ρ o is the density of the oil phase, q w is the water phase flow rate, q o is the oil phase flow rate.

[0014] Furthermore, the calculation formula of the maximum flow rate includes:

[0015]

[0016] Where Q2 is the maximum flow rate, n is the total number of holes in the wellbore, γ is the surface tension, μ is the fluid viscosity, and d s is the proppant particle diameter, ρ s is the proppant particle density, ρ f is the wellbore fluid density, and △P is the effective stress on the proppant.

[0017] Further, determining the minimum bottom hole flow pressure includes: based on the logging data, respectively calculating the flowback pressure and the shale oil bubble point pressure of the flowback wellbore; and determining the maximum value of the flowback pressure and the shale oil bubble point pressure as the minimum bottom hole flow pressure.

[0018] Further, the flowback pressure is the sum of the wellhead pressure and the pressure drop of the flowback wellbore; wherein the pressure drop includes:

[0019]

[0020] In the formula,

[0021]

[0022] p is the pressure in the return wellbore, dp / dL is the pressure drop, L is the length of the return wellbore section, θ is the angle between the return wellbore and the horizontal direction, R e is the Reynolds number, ρ f is the wellbore fluid density, d W is the flowback wellbore diameter, v m is the flow velocity of the mixture, q w is the water phase flow rate, q o is the oil phase flow rate.

[0023] Furthermore, the calculation formula for the shale oil bubble point pressure includes:

[0024]

[0025] In the formula, R s is the dissolved gas-oil ratio, γ g is the relative density of dissolved gas, γ0 is the relative density of degassed crude oil, p exp is the bubble point pressure of the shale oil, and T is the formation temperature.

[0026] Furthermore, based on the quantity matrix and the preset weight matrix, a safe flowback evaluation index is calculated, including: calculating the Hadamard product of the quantity matrix and the preset weight matrix to obtain a product matrix; and calculating the safe flowback evaluation index based on the product matrix.

[0027] In a second aspect, an embodiment of the present invention further provides a shale oil flowback effect evaluation system based on machine learning, comprising: a determination module, a division module, a clustering module, a statistical module, a calculation module and an evaluation module; wherein the determination module is used to determine the critical flow rate and critical pressure of the shale oil flowback system to be evaluated based on the logging data of the shale oil well flowback wellbore; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure; the division module is used to divide the target space with flow rate and pressure as dimensions into multiple category areas based on the critical flow rate and the critical pressure; the clustering module is used to divide the multiple flowback data points of the shale oil flowback system to be evaluated into the multiple category areas by using a clustering method based on machine learning; the statistical module is used to count the number of flowback data points in each category area to obtain a quantity matrix; the calculation module is used to calculate the safety flowback evaluation index based on the quantity matrix and the preset weight matrix; the evaluation module is used to evaluate the flowback effect of the shale oil flowback system to be evaluated based on the safety flowback evaluation index.

[0028] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.

[0029] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0030] The present invention provides a shale oil flowback effect evaluation method and system based on machine learning. The acceptable flowback pressure and flow rate in the shale oil flowback process are determined by logging data, and combined with the machine learning clustering principle, a flowback effect evaluation method is formed, which alleviates the technical problem of the prior art that it is impossible to quantify and specifically guide the evaluation of shale oil flowback effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 A flow chart of a shale oil flowback effect evaluation method based on machine learning provided in an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of carrying a flowback wellbore proppant provided in an embodiment of the present invention;

[0034] Figure 3 A schematic diagram of the force of a fracture proppant provided by an embodiment of the present invention;

[0035] Figure 4 A rectangular coordinate system diagram after partitioning provided by an embodiment of the present invention;

[0036] Figure 5 A rectangular coordinate system diagram after another partition provided by an embodiment of the present invention;

[0037] Figure 6 A schematic diagram of a shale oil flowback effect evaluation system based on machine learning provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Embodiment 1

[0040] Figure 1 1 is a flow chart of a shale oil flowback effect evaluation method based on machine learning according to an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:

[0041] Step S102, based on the logging data of the shale oil well flowback wellbore, determine the critical flow rate and critical pressure of the shale oil flowback system to be evaluated; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure.

[0042] Step S104, based on the critical flow rate and the critical pressure, the target space with flow rate and pressure as dimensions is divided into multiple category areas.

[0043] Step S106, using a clustering method based on machine learning, divide multiple flowback data points of the shale oil flowback system to be evaluated into multiple category areas.

[0044] Step S108, counting the number of return flow data points in each category area to obtain a quantity matrix.

[0045] Step S110, calculating the safety flowback evaluation index based on the quantity matrix and the preset weight matrix.

[0046] Step S112, based on the safety flowback evaluation index, the flowback effect of the shale oil flowback system to be evaluated is evaluated.

[0047] Specifically, in step S102, the maximum bottom hole flow pressure is determined as follows: Since high-pressure liquid is used to break the formation to generate hydraulic fractures during hydraulic fracturing, and proppant is carried by injecting sand-carrying fluid to support the hydraulic fractures. When the well is blocked, the pressure in the fracture is continuously dissipated, and the proppant settles in the fracture. When the well is opened, if the pressure in the fracture is insufficiently dissipated, resulting in the pressure in the fracture being higher than the fracture closing pressure, the fracture is in an open state, and the proppant in the fracture is not clamped by the fracture stress and will be in a loose settlement state. The backflow of the well will cause the proppant to easily flow back, so the bottom hole flow pressure when the well is opened is used as one of the indicators for evaluating the backflow effect. When the well is opened, the fracture fluid pressure must be lower than the fracture closing pressure. If it is higher, it is in an unfavorable backflow system. For the convenience of application, combined with actual practice, it can be considered that the fracture fluid pressure is equal to the bottom hole flow pressure, and the fracture closing pressure is equal to the minimum horizontal principal stress.

[0048] In actual flowback operations, the minimum horizontal principal stress can be directly obtained from well logging interpretation, while the bottom hole flowing pressure needs to be converted and calculated from the wellhead pressure. The calculation formula is as follows:

[0049]

[0050] In the formula, p wfo is the bottom hole flow pressure at the well opening, in MPa; MD is the vertical depth of the well, in m; p H is the wellhead pressure, unit: MPa; h w It is the friction head loss along the way, unit is m.

[0051] Then, the maximum bottom hole flow pressure P2 allowed by the optimal design is determined based on the bottom hole flow pressure.

[0052] Figure 2 Schematic diagram of a flowback wellbore proppant carrying method according to an embodiment of the present invention. Figure 2 As shown in the figure, if there is residual proppant in the wellbore during the fracturing process of shale oil or sand is produced during the flowback process, the residual proppant in the wellbore will have an adverse effect on the flowback process of shale oil. For example, the deposited bottom of the wellbore and the inclination will occupy the flow channel of the wellbore, causing blockage of the wellbore or even stopping production. The moving proppant will flush the wellbore and downhole instruments, shortening their service life. Therefore, the evaluation of the flowback effect needs to use this as a basis to judge whether the flowback flow rate is greater than the critical sedimentation flow rate of the wellbore proppant and whether the proppant in the wellbore can be carried out of the wellhead in time. If it is less than this flow rate, it cannot be carried, which is unfavorable to the flowback system.

[0053] Specifically, the calculation formula for the minimum flow rate includes:

[0054]

[0055] in,

[0056] ρ f =ρ o f o +ρ w f w

[0057]

[0058] Q1 is the minimum flow rate, d s is the proppant particle diameter, unit: m; ρ s is the proppant particle density, in kg / m 3 ρ f is the wellbore fluid density, unit: kg / m 3 ;d W is the diameter of the return wellbore, in m; C D is the drag coefficient, dimensionless; ρ w is the water phase density, ρ o is the density of the oil phase, q w is the water phase flow rate, q o is the oil phase flow rate.

[0059] Among them, C D The values ​​of are shown in Table 1:

[0060] Table 1 Drag coefficient values

[0061]

[0062] in,

[0063]

[0064] In the formula, u f is the wellbore fluid velocity, in m / s; μ f is the viscosity of the wellbore fluid, in Pa·s.

[0065] Figure 3 FIG. 1 is a schematic diagram of a fracture proppant stress according to an embodiment of the present invention. Figure 3 As shown, it is judged whether the current flowback system can prevent the proppant in the fracture from rushing out of the fracture. If the current flowback system is greater than the flow rate, the proppant in the fracture will flow back, which is an unfavorable phenomenon.

[0066] Specifically, the calculation formula for the maximum flow rate includes:

[0067]

[0068] Where Q2 is the maximum flow rate, n is the total number of holes in the wellbore, γ is the surface tension, which is 0.03N / m; μ is the fluid viscosity, in Pa·s; d s is the proppant particle diameter, ρ s is the proppant particle density, ρ f is the wellbore fluid density, and △P is the effective stress on the proppant.

[0069] Specifically, in step S102, determining the minimum bottom hole flowing pressure includes:

[0070] Based on the well logging data, the flowback pressure of the flowback wellbore and the bubble point pressure of the shale oil are calculated respectively;

[0071] The maximum value of the flowback pressure and the shale oil bubble point pressure is determined as the minimum bottom hole flowing pressure.

[0072] In the embodiment of the present invention, in order to ensure the smooth flowback, a certain flowback pressure needs to be guaranteed. The flowback pressure is the minimum bottom hole flow pressure. Therefore, this indicator is established to determine whether the pressure during the flowback process is greater than the flowback pressure. If it is less than the flowback pressure, the flowback fluid cannot be returned to the wellhead, and the flowback cannot be carried out smoothly. In the case of homogeneous oil-water multiphase flow, the flowback pressure is the sum of the wellhead pressure and the pressure drop of the flowback wellbore; wherein, the pressure drop includes:

[0073]

[0074] In the formula,

[0075]

[0076] p is the pressure in the return wellbore, dp / dL is the pressure drop, L is the length of the return wellbore section, θ is the angle between the return wellbore and the horizontal direction, R e is the Reynolds number, ρ f is the wellbore fluid density, d W is the flowback wellbore diameter, v m is the flow velocity of the mixture, q w is the water phase flow rate, q o is the oil phase flow rate.

[0077] At the same time, in order to ensure that the crude oil in the return wellbore does not undergo phase change during the return process, the bottom hole flow pressure needs to be greater than the shale oil bubble point pressure. The calculation formula for the shale oil bubble point pressure includes:

[0078]

[0079] In the formula, R s is the dissolved gas-oil ratio, γ gis the relative density of dissolved gas (air = 1), γ0 is the relative density of degassed crude oil (water = 1), p exp is the bubble point pressure of shale oil, unit is MPa; T is the formation temperature. All the above parameters are obtained from the on-site fluid PVT physical property parameter experiment.

[0080] In an optional implementation provided by an embodiment of the present invention, step S104 includes:

[0081] First, a rectangular coordinate system diagram is drawn with flow rate as the horizontal axis and pressure as the vertical axis to obtain the target space with flow rate and pressure as the dimensions; then, the rectangular coordinate system diagram is divided into 9 category areas with critical flow rates Q1, Q2 and critical pressures P1, P2 as boundaries. The coordinate values ​​of the center points of each area are as follows: Figure 4 shown.

[0082] Then, in the rectangular coordinate system diagram, the Euclidean distance between each return flow data point and each center point is calculated, and each return flow data point is divided into the category area where the nearest center point (that is, the one with the smallest Euclidean distance) is located.

[0083] Then, the number of return flow data points in each category area is counted to obtain a quantity matrix. Optionally, the quantity matrix M is a 3×3 matrix.

[0084] In an optional implementation provided by an embodiment of the present invention, the preset weight matrix is ​​as follows:

[0085]

[0086] Specifically, step S110 also includes the following steps:

[0087] Step S1101, calculate the Hadamard product of the quantity matrix and the preset weight matrix to obtain a product matrix; specifically, the product matrix

[0088] Step S1102, calculate the safety return evaluation index based on the product matrix. Specifically, the calculation formula of the safety return evaluation index F is as follows:

[0089]

[0090] In the formula, h ij are the elements of the product matrix H.

[0091] In the embodiment of the present invention, the closer the safety return evaluation index F value is to 9, the better the return system is. However, due to actual engineering limitations and the need to shorten the return operation period as much as possible, the F value of some shale oil wells cannot be equal to 9. Based on actual return operation experience, achieving an F value of > 2 is within the acceptable range of engineering practice.

[0092] From the above description, it can be seen that an embodiment of the present invention provides a shale oil flowback effect evaluation method based on machine learning. The acceptable flowback pressure and flow rate in the shale oil flowback process are determined by logging data, and combined with the machine learning clustering principle, a flowback effect evaluation method is formed, which alleviates the technical problem that the prior art cannot provide quantitative and targeted guidance for the evaluation of shale oil flowback effects.

[0093] Embodiment 2

[0094] Taking a shale oil well as an example, the well was subjected to fracturing test and flowback operation in 2023. From the logging data, it can be seen that the average value of the minimum horizontal principal stress of the well is 73.5MPa, that is, the maximum bottom hole flow pressure P2 = 73.5MPa; the critical flow rate of wellbore proppant sedimentation, that is, the minimum flowback flow rate Q1 = 68m 3 / d; Critical backflow flow rate of fracture proppant, i.e., maximum backflow flow rate Q2 = 104m 3 / d, the actual return flow pressure point is plotted in a rectangular coordinate system with flow as the horizontal axis and pressure as the vertical axis, and divided into the nine parts mentioned above, such as Figure 5 shown.

[0095] The Euclidean distance between each point in the coordinate graph and each center point is calculated according to the method provided in the embodiment of the present invention, and each return flow data point is classified into the category of the nearest center point (with the smallest Euclidean distance).

[0096] Perform cluster analysis and record the number of return flow data points in each area as a 3×3 matrix M.

[0097]

[0098] F>2 is within the safe flowback range that is actually acceptable to the project, the flowback system is reasonable, and the well did not experience any phenomenon that is not conducive to production, such as sand production, production cessation, or sudden drop in production, during the flowback process.

[0099] Embodiment 3

[0100] Figure 6 Schematic diagram of a shale oil flowback effect evaluation system based on machine learning provided according to an embodiment of the present invention. Figure 6 As shown, the system includes: a determination module 10 , a division module 20 , a clustering module 30 , a statistics module 40 , a calculation module 50 and an evaluation module 60 .

[0101] Specifically, the determination module 10 is used to determine the critical flow rate and critical pressure of the shale oil flowback system to be evaluated based on the logging data of the shale oil well flowback wellbore; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure.

[0102] The division module 20 is used to divide the target space with flow and pressure as dimensions into multiple category areas based on the critical flow and critical pressure.

[0103] The clustering module 30 is used to classify multiple flowback data points of the shale oil flowback system to be evaluated into multiple category areas using a clustering method based on machine learning.

[0104] The statistical module 40 is used to count the number of flowback data points in each category area to obtain a quantity matrix.

[0105] The calculation module 50 is used to calculate the safety flowback evaluation index based on the quantity matrix and the preset weight matrix.

[0106] The evaluation module 60 is used to evaluate the flowback effect of the shale oil flowback system to be evaluated based on the safety flowback evaluation index.

[0107] Specifically, the calculation module 50 is further used to: calculate the Hadamard product of the quantity matrix and the preset weight matrix to obtain the product matrix; and calculate the safety flowback evaluation index based on the product matrix.

[0108] The present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the embodiment of the present invention when executing the computer program.

[0109] The present invention also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0110] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0111] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A shale oil flowback effect evaluation method based on machine learning, characterized in that: include: Based on the logging data of the shale oil well flowback wellbore, determine the critical flow rate and critical pressure of the shale oil flowback system to be evaluated; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure; Based on the critical flow rate and the critical pressure, the target space with flow rate and pressure as dimensions is divided into a plurality of category areas; Using a clustering method based on machine learning, a plurality of flowback data points of the shale oil flowback system to be evaluated are divided into the plurality of category areas; Count the number of return flow data points in each category area to obtain a quantity matrix; Based on the quantity matrix and the preset weight matrix, calculate the safety return flow evaluation index; Based on the safety flowback evaluation index, the flowback effect of the shale oil flowback system to be evaluated is evaluated.

2. The method according to claim 1, characterized in that: The calculation formula of the minimum flow rate includes: in, r f =ρ o f o +r w f w Q1 is the minimum flow rate, d s is the proppant particle diameter, ρ s is the proppant particle density, ρ f is the wellbore fluid density, d w is the flowback wellbore diameter, C D is the drag coefficient, ρ w is the water phase density, ρ o is the density of the oil phase, q w is the water phase flow rate, q o is the oil phase flow rate.

3. The method according to claim 1, characterized in that: The calculation formula of the maximum flow rate includes: Where Q2 is the maximum flow rate, n is the total number of holes in the wellbore, γ is the surface tension, μ is the fluid viscosity, and d s is the proppant particle diameter, ρ s is the proppant particle density, ρ f is the wellbore fluid density, and ΔP is the effective stress on the proppant.

4. The method according to claim 1, characterized in that: Determining the minimum bottom hole flowing pressure includes: Based on the well logging data, respectively calculating the flowback pressure of the flowback wellbore and the shale oil bubble point pressure; The maximum value of the flowback pressure and the shale oil bubble point pressure is determined as the minimum bottom hole flow pressure.

5. The method according to claim 4, characterized in that: The flowback pressure is the sum of the wellhead pressure and the pressure drop of the flowback wellbore; wherein the pressure drop includes: In the formula, p is the pressure in the return wellbore, dp / dL is the pressure drop, L is the length of the return wellbore section, θ is the angle between the return wellbore and the horizontal direction, R e is the Reynolds number, ρ f is the wellbore fluid density, d w is the flowback wellbore diameter, v m is the flow velocity of the mixture, q w is the water phase flow rate, q o is the oil phase flow rate.

6. The method according to claim 4, characterized in that: The calculation formula for the shale oil bubble point pressure includes: In the formula, R s is the dissolved gas-oil ratio, γ g is the relative density of dissolved gas, γ0 is the relative density of degassed crude oil, p exp is the bubble point pressure of the shale oil, and T is the formation temperature.

7. The method according to claim 1, characterized in that: Based on the quantity matrix and the preset weight matrix, the safety flowback evaluation index is calculated, including: Calculating the Hadamard product of the quantity matrix and the preset weight matrix to obtain a product matrix; The safety flowback evaluation index is calculated based on the product matrix.

8. A shale oil flowback effect evaluation system based on machine learning, characterized in that: include: Determination module, division module, clustering module, statistics module, calculation module and evaluation module; among them, The determination module is used to determine the critical flow rate and critical pressure of the shale oil flowback system to be evaluated based on the logging data of the shale oil well flowback wellbore; the critical flow rate includes the maximum flow rate and the minimum flow rate, and the critical pressure includes the maximum bottom hole flow pressure and the minimum bottom hole flow pressure; The division module is used to divide the target space with flow and pressure as dimensions into a plurality of category areas based on the critical flow and the critical pressure; The clustering module is used to classify the multiple flowback data points of the shale oil flowback system to be evaluated into the multiple category areas by using a clustering method based on machine learning; The statistical module is used to count the number of return flow data points in each category area to obtain a quantity matrix; The calculation module is used to calculate the safety return flow evaluation index based on the quantity matrix and the preset weight matrix; The evaluation module is used to evaluate the flowback effect of the shale oil flowback system to be evaluated based on the safety flowback evaluation index.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images