Method and device for predicting unsteady productivity of closed boundary fractured horizontal well

Abstract

The invention relates to the technical field of data analysis and prediction, in particular to a method and a device for predicting unsteady productivity of a closed boundary fractured horizontal well. The method comprises the following steps: performing data acquisition on a closed boundary fractured horizontal well to generate fractured horizontal well data; preprocessing the fractured horizontal well data to obtain standard fractured horizontal well data; performing closed boundary fracturing feature identification on the standard fractured horizontal well data to obtain closed boundary fracturing data; performing crack feature extraction on the closed boundary fracturing data to generate boundary crack feature information; according to the method, through a data processing technology, a mode identification technology and a deep learning technology, bottom hole pressure and boundary crack characteristics are subjected to crack correlation identification; and oil gas flow state detection is carried out on the oil gas characteristics according to the boundary crack relation condition, so that the accuracy of unsteady productivity prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis and prediction, and in particular to a method and device for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well. Background Art

[0002] For the prediction of the non-steady-state production capacity of horizontal wells, fracturing and production enhancement technology was initially used, including hydraulic jet staged fracturing technology, open hole packer staged fracturing technology and fast drilling bridge plug staged fracturing technology. In particular, the open hole packer staged fracturing technology is widely used in the measurement and analysis of oil and gas non-steady-state production capacity. With the transformation of fracturing technology, especially the closed boundary fracturing technology, the well location coordinates of all mirror wells corresponding to the closed boundary formation fracturing equivalent well can be determined according to the well location coordinates of the fracture equivalent well, and then the distance from all mirror wells to the equivalent well can be determined; so that the non-steady-state production capacity can be predicted according to the relevant parameters. However, the existing technology fails to identify the relationship between the bottom hole pressure and the boundary fracture characteristics; and fails to detect the oil and gas flow state of the oil and gas characteristics according to the boundary fracture relationship, resulting in a low accuracy of non-steady-state production capacity prediction. Summary of the invention

[0003] Based on this, it is necessary to provide a method and device for predicting the non-steady-state production capacity of a closed boundary fracturing horizontal well to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well is provided, the method comprising the following steps: Step S1: collecting data from closed boundary fractured horizontal wells to generate fractured horizontal well data; preprocessing the fractured horizontal well data to obtain standard fractured horizontal well data; Step S2: performing closed boundary fracturing feature recognition on the standard fracturing horizontal well data to obtain closed boundary fracturing data; performing crack feature extraction on the closed boundary fracturing data to generate boundary crack feature information; performing fracturing porosity determination on the standard fracturing horizontal well data according to the boundary crack feature information to obtain fracturing porosity data; performing oil and gas feature simulation on the standard fracturing horizontal well data based on the boundary crack feature information and the fracturing porosity data to generate oil and gas feature data; Step S3: extracting fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identifying wellbore position of standard fractured horizontal well data according to boundary fracture parameter information to obtain wellbore position data; associating and mapping boundary fracture parameter information with wellbore position data to generate fracture wellbore associated data; measuring bottom hole pressure of standard fractured horizontal well data based on fracture wellbore associated data to obtain bottom hole pressure data; Step S4: perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state on oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index on standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0005] The present invention uses sensors to collect data from closed boundary fractured horizontal wells, ensuring that original and direct information about fractured horizontal wells is obtained, which can provide basic information for subsequent analysis; pre-processing of fractured horizontal well data helps to eliminate noise and outliers in the data, ensuring the consistency and accuracy of the data, and providing key data input for subsequent fracture porosity determination and oil and gas characteristic simulation. Closed boundary fracture feature identification of standard fractured horizontal well data can be the key to evaluating fracture network and reservoir connectivity; fracture feature extraction of closed boundary fracture data can clarify boundary fracture feature information; fracture porosity determination of standard fractured horizontal well data based on boundary fracture feature information can accurately reflect the pore structure of the fractured area, which is crucial for evaluating the reservoir characteristics of oil and gas reservoirs; oil and gas feature simulation of standard fractured horizontal well data based on boundary fracture feature information and fracture porosity data can simulate the distribution and flow of oil and gas in fractured horizontal wells. By extracting fracture parameters from boundary fracture characteristic information using oil and gas characteristic data, the geometric characteristics and distribution characteristics of fractures can be described in detail; by identifying the wellbore position of standard fracturing horizontal well data based on boundary fracture parameter information, the accurate position of the wellbore in the oil and gas reservoir can be determined; by associating and mapping boundary fracture parameter information with wellbore position data, the fracture parameters can be associated with the wellbore position, providing data support for bottom hole pressure measurement; by measuring the bottom hole pressure of standard fracturing horizontal well data based on fracture-wellbore association data, the bottom hole pressure data can be clarified. According to the bottom hole pressure data, the boundary cracks feature information is subjected to the boundary cracks mutual coupling analysis, which can reveal the interaction and influence between the cracks; according to the boundary cracks relationship data, the oil and gas flow state is identified for the oil and gas feature data, which can identify the flow state of oil and gas in the crack network; the oil and gas non-steady-state capacity index is measured for the standard fracturing horizontal well data through the oil and gas flow state data, which can provide the dynamic change information of the oil and gas production; the non-steady-state capacity prediction model is constructed by using the oil and gas non-steady-state capacity index to obtain the non-steady-state capacity prediction model; the non-steady-state capacity prediction is performed on the standard fracturing horizontal well data based on the non-steady-state capacity prediction model, and the non-steady-state capacity prediction report is generated. Therefore, the present invention realizes the identification of the relationship between the bottom hole pressure and the boundary crack characteristics through data processing technology, pattern recognition technology, and deep learning technology; and realizes the oil and gas flow state detection for the oil and gas characteristics according to the boundary crack relationship, thereby improving the accuracy of the non-steady-state capacity prediction.

[0006] Preferably, step S2 comprises the following steps: Step S21: performing nonlinear feature decomposition on standard fracturing horizontal well data to generate nonlinear fracturing horizontal well features; performing fracturing feature enhancement on the nonlinear fracturing horizontal well features to obtain fracturing feature enhancement data; performing closed boundary fracturing feature extraction on the fracturing feature enhancement data to obtain closed boundary fracturing data; Step S22: extracting fracturing morphological features from closed boundary fracturing data to generate fracturing morphological feature data; quantifying geometric features from standard fracturing horizontal well data to obtain fracturing morphological geometric features; identifying fracture features from fracturing morphological geometric features to generate boundary fracture feature information; Step S23: determining the distribution range of the boundary crack feature information to obtain the boundary crack distribution range; identifying the crack space distribution characteristics of the boundary crack distribution range to generate the crack space distribution characteristics; performing crack space distribution morphological characteristics on the fracturing morphological geometric characteristics according to the crack space distribution characteristics to obtain the crack space distribution morphological characteristics; Step S24: Calculate the fracture density of the fracture space distribution morphology to generate fracture space density data; perform fracturing pore characteristics on the boundary fracture feature information based on the fracture space density data to obtain fracturing pore characteristics; perform fracturing porosity measurement on the standard fracturing horizontal well data through the fracturing pore characteristics to obtain fracturing porosity data; Step S25: Perform porosity gradient division on the fracturing porosity data to generate porosity gradient data; perform oil and gas characteristic simulation on the standard fracturing horizontal well data based on the porosity gradient data and boundary fracture characteristic information to generate oil and gas characteristic data.

[0007] The present invention performs nonlinear feature decomposition on standard fractured horizontal well data, which can reveal complex patterns and trends in the data; performs fracture feature enhancement on nonlinear fractured horizontal well features, which can improve the recognition of key features in the data; performs closed boundary fracture feature extraction on fracture feature enhanced data, which can clearly identify fracture features related to closed boundaries; performs fracture morphology feature extraction on closed boundary fracture data, which can describe in detail the geometric shape and distribution of fracture cracks; the implementation of geometric feature quantification can provide data support for quantitative analysis of fractures; the implementation of fracture feature identification can accurately describe the properties of fractures; the distribution range of boundary fracture feature information is determined, which can clarify the expansion range of fractures in oil and gas reservoirs; the fracture space distribution feature identification of the boundary fracture distribution range can reveal the spatial distribution of fractures. The distribution law is determined; the spatial distribution morphological characteristics of the fracture morphology are determined according to the spatial distribution characteristics of the fractures, which can refine the spatial distribution characteristics of the fractures for fracture density calculation and fracturing pore characteristics; the fracture density is calculated based on the spatial distribution morphological characteristics of the fractures to quantify the density of the fractures; the fracturing pore characteristics are determined based on the boundary fracture characteristic information based on the fracture spatial density data to describe the influence of the fracture on the pore structure; the fracturing porosity of the standard fracturing horizontal well data is calculated through the fracturing pore characteristics to clarify the fracturing porosity data; the porosity gradient division of the fracturing porosity data can reveal the spatial variation of porosity in oil and gas; the oil and gas characteristics of the standard fracturing horizontal well data are simulated based on the porosity gradient data and the boundary fracture characteristic information to simulate the distribution and flow of oil and gas in the fracture network.

[0008] Preferably, step S3 comprises the following steps: Step S31: performing fracture geometric feature recognition on the boundary fracture feature information to generate fracture geometric feature data; performing fracture geometric parameter extraction on the fracture geometric feature data according to the oil and gas feature data to obtain fracture geometric parameters; Step S32: performing fracture connectivity detection on the boundary fracture characteristic information by using fracture geometric parameters to generate fracture connectivity data; performing fracture permeability evaluation on the boundary fracture characteristic information based on the fracture connectivity data to obtain fracture permeability data; performing fracture fluid flow simulation on the oil and gas characteristic data according to the fracture permeability data to obtain fracture fluid flow simulation data; Step S33: Integrate the fracture connectivity data, fracture permeability data and fracture fluid flow simulation data to obtain boundary fracture parameter information; perform wellbore feature recognition on the standard fracturing horizontal well data to generate wellbore feature data; perform wellbore position detection on the wellbore feature data according to the boundary fracture parameter information to obtain wellbore position data; Step S34: associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of the standard fracturing horizontal well data based on the fracture wellbore associated data to obtain the bottom hole pressure data.

[0009] The present invention identifies fracture geometry characteristics of boundary fracture feature information, and can describe fracture geometry in detail, including key parameters such as fracture strike, inclination and dip angle; extracts fracture geometry parameters from fracture geometry feature data based on oil and gas feature data, and can quantify fracture size and shape; detects fracture connectivity from boundary fracture feature information through fracture geometry parameters, and can reveal the interconnectedness between fractures; evaluates fracture permeability from boundary fracture feature information based on fracture connectivity data, and clearly quantifies fracture permeability; simulates fracture fluid flow from oil and gas feature data based on fracture permeability data, and can clearly simulate the flow behavior of oil and gas in fractures. To: Integrate fracture connectivity data, fracture permeability data and fracture fluid flow simulation data to comprehensively describe fracture characteristics and provide key data support for wellbore feature identification and wellbore position detection; perform wellbore feature identification on standard fracturing horizontal well data to clarify the geometric characteristics and spatial position of the wellbore; perform wellbore position detection on wellbore feature data based on boundary fracture parameter information to determine the specific position of the wellbore in the oil and gas reservoir; associate and map boundary fracture parameter information with wellbore position data to generate fracture-wellbore associated data; perform bottom hole pressure measurement on standard fracturing horizontal well data based on fracture-wellbore associated data to directly reflect the dynamic pressure situation at the bottom of the well.

[0010] Preferably, step S34 includes the following steps: Step S341: quantifying the connectivity of the fracture connectivity data to obtain fracture connectivity quantitative data; associating the fracture connectivity quantitative data with the wellbore position data to generate fracture wellbore connectivity association data; Step S342: performing permeability parameterization on the fracture permeability data to obtain fracture permeability parameterized data; performing fracture permeability correlation on the fracture permeability parameterized data and the wellbore position data to generate fracture wellbore permeability correlation data; Step S343: extracting flow characteristics of fracture fluid flow simulation data to obtain fracture fluid flow characteristic data; correlating the fracture fluid flow characteristic data with wellbore position data to generate fracture wellbore fluidity correlation data; Step S344: Integrate the fracture wellbore connectivity correlation data, the fracture wellbore permeability correlation data and the fracture wellbore fluidity correlation data to obtain the fracture wellbore correlation data; Step S345: measuring the bottom hole pressure of the standard fractured horizontal well data based on the fracture wellbore correlation data to obtain the bottom hole pressure data.

[0011] The present invention quantifies the connectivity of fracture connectivity data, and can provide an accurate value for the connectivity of the fracture network; associates the fracture connectivity quantitative data with the wellbore position data for fracture connectivity, and can clarify the connectivity relationship between the fracture and the wellbore; performs permeability parameterization on the fracture permeability data, and can clarify the permeability characteristics of the fracture; associates the fracture permeability parameterized data with the wellbore position data for fracture permeability, and can reveal the influence of the fracture permeability on the wellbore flow characteristics; extracts the flow characteristics of fracture fluid flow simulation data, and can simulate the flow behavior of oil and gas in the fracture; associates the fracture fluid flow characteristics data with the wellbore position data for fluid flow characteristics, and can combine the flow characteristics in the fracture with the wellbore position information; integrates the fracture wellbore connectivity association data, the fracture wellbore permeability association data and the fracture wellbore fluidity association data, and can comprehensively describe the interaction between the fracture and the wellbore; and performs bottom hole pressure measurement on the standard fracturing horizontal well data based on the fracture wellbore association data, and can directly reflect the dynamic pressure situation at the bottom of the well.

[0012] Preferably, step S345 includes the following steps: Step S3451: extracting the bottom hole stress characteristics of the standard fractured horizontal well data based on the fracture wellbore correlation data to generate the bottom hole stress characteristics; simulating the bottom hole pressure distribution of the standard fractured horizontal well data according to the bottom hole stress characteristics to obtain the bottom hole pressure distribution simulation data; Step S3452: performing bottom hole pressure response identification on the bottom hole pressure distribution simulation data to generate bottom hole pressure response data; performing pressure numerical calculation on the bottom hole pressure response data to obtain bottom hole pressure numerical information; performing pressure gradient division on the bottom hole pressure numerical information to generate bottom hole pressure gradient data; Step S3453: performing real-time bottom hole pressure monitoring on the bottom hole pressure distribution simulation data through the bottom hole pressure gradient data to obtain bottom hole pressure change data; performing bottom hole pressure state identification on the bottom hole pressure change data to generate bottom hole pressure state information; Step S3454: perform bottom hole pressure anomaly detection on the bottom hole pressure status information to obtain bottom hole pressure anomaly data; perform pressure stability evaluation on the bottom hole pressure distribution simulation data based on the bottom hole pressure anomaly data to obtain bottom hole pressure stability data; perform bottom hole pressure measurement on the standard fracturing horizontal well data based on the bottom hole pressure stability data to obtain bottom hole pressure data.

[0013] The present invention extracts the bottom hole force characteristics of the standard fractured horizontal well data based on the fracture wellbore associated data, and can clarify the effects of various forces on the bottom hole; simulates the bottom hole pressure distribution of the standard fractured horizontal well data according to the bottom hole force characteristics, and can simulate the pressure state of different areas of the bottom hole; identifies the bottom hole pressure response of the bottom hole pressure distribution simulation data, and can reflect the sensitivity of the bottom hole to the pressure change during the oil and gas production process; calculates the pressure value of the bottom hole pressure response data, and can provide the specific value of the bottom hole pressure; divides the bottom hole pressure numerical information into pressure gradients, and can reveal the bottom hole pressure in different areas The bottom hole pressure gradient data is used to monitor the bottom hole pressure distribution simulation data in real time, which can reflect the dynamic changes of the bottom hole pressure in real time; the bottom hole pressure state is identified on the bottom hole pressure change data, which can clarify the current state of the bottom hole pressure; the bottom hole pressure anomaly detection is performed on the bottom hole pressure state information, which can timely discover the abnormal changes of the bottom hole pressure; the pressure stability of the bottom hole pressure distribution simulation data is evaluated according to the bottom hole pressure anomaly data, so as to evaluate the stability of the bottom hole pressure; the bottom hole pressure of the standard fracturing horizontal well data is measured based on the bottom hole pressure stability data to clarify the bottom hole pressure data.

[0014] Preferably, step S4 comprises the following steps: Step S41: performing boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; Step S42: identifying the oil and gas flow state of the oil and gas characteristic data according to the boundary fracture relationship data to obtain the oil and gas flow state data; Step S43: calculating the oil and gas non-steady-state production capacity index for the standard fractured horizontal well data by using the oil and gas flow state data to generate the oil and gas non-steady-state production capacity index; Step S44: constructing a non-steady-state capacity prediction model according to the oil and gas non-steady-state capacity index to obtain a non-steady-state capacity prediction pre-model; and training the non-steady-state capacity prediction pre-model using the oil and gas non-steady-state capacity index to obtain a non-steady-state capacity prediction training model; Step S45: performing a model cross-validation evaluation on the non-steady-state capacity prediction training model to obtain model evaluation data; adjusting model parameters of the non-steady-state capacity prediction training model using the model evaluation data to obtain a non-steady-state capacity prediction model; Step S46: Perform non-steady-state capacity prediction on the standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0015] The present invention performs boundary fracture mutual coupling analysis on boundary fracture characteristic information based on bottom hole pressure data, and can clarify the mutual relationship and interaction between fractures; identifies oil and gas flow state on oil and gas characteristic data based on boundary fracture relationship data, and can accurately reflect the flow characteristics of oil and gas in the fracture network, including the flow direction, speed and flow pattern of oil and gas; measures oil and gas non-steady-state capacity index on standard fractured horizontal well data through oil and gas flow state data, so as to quantify the capacity change of oil and gas reservoirs, and can reflect the output capacity of oil and gas reservoirs in different production stages; constructs a non-steady-state capacity prediction model based on the oil and gas non-steady-state capacity index, and obtains a non-steady-state capacity prediction pre-model , which can predict the production capacity changes of oil and gas at different time points in the future, and use the non-steady-state production capacity indicators of oil and gas to train the non-steady-state production capacity prediction pre-model, which can improve the accuracy of the prediction; the non-steady-state production capacity prediction training model is cross-validated and evaluated to evaluate the prediction performance and generalization ability of the model; the model parameters of the non-steady-state production capacity prediction training model are adjusted through the model evaluation data, which can more accurately reflect the actual production capacity changes of the oil and gas reservoir and improve the reliability of the prediction results; based on the non-steady-state production capacity prediction model, the standard fractured horizontal well data is predicted to generate a non-steady-state production capacity prediction report, which can perform the non-steady-state production capacity prediction operation of the closed boundary fractured horizontal well.

[0016] Preferably, step S41 includes the following steps: Step S411: extracting the pressure distribution characteristics of the bottom hole pressure data to obtain the bottom hole pressure distribution characteristics; identifying the pressure peak area of ​​the bottom hole pressure distribution characteristics to generate the bottom hole pressure peak area; Step S412: Identify the fracture concentration area of ​​the boundary fracture characteristic information according to the fracture space density data to obtain the boundary fracture concentration area; map and match the boundary fracture concentration area with the bottom hole pressure peak area to generate fracture pressure mapping data; Step S413: Calculate the degree of fracture pressure influence on the bottom hole pressure data through the fracture pressure mapping data to obtain fracture pressure influence data; perform fracture sensitivity measurement on the boundary fracture characteristic information according to the fracture pressure influence data to generate fracture sensitivity data; Step S414: using the fracture connectivity data to extract boundary fracture constraint features from the fracture sensitivity data to obtain boundary fracture constraint action data; using the fracture permeability data to extract boundary fracture permeability synergistic features from the boundary fracture constraint action data to generate boundary fracture synergistic action data; based on the boundary fracture constraint action data and the boundary fracture synergistic action data, boundary fracture mutual coupling identification is performed on the boundary fracture feature information to obtain boundary fracture relationship data.

[0017] The present invention extracts pressure distribution characteristics from bottom hole pressure data, and can clarify the distribution of bottom hole pressure; identifies pressure peak areas from bottom hole pressure distribution characteristics, and can accurately locate bottom hole high pressure areas; identifies fracture concentration areas from boundary fracture characteristic information according to fracture space density data, and can clarify the main areas of fracture development; maps and matches boundary fracture concentration areas with bottom hole pressure peak areas, and can provide for subsequent evaluation of the impact of fractures on bottom hole pressure; calculates fracture pressure impact degree from bottom hole pressure data through fracture pressure mapping data, and can quantify the contribution of fractures to bottom hole pressure; determines fracture sensitivity from boundary fracture characteristic information according to fracture pressure impact data, and can reveal the sensitivity of fractures to pressure changes; extracts boundary fracture constraint characteristics from fracture sensitivity data using fracture connectivity data, and can describe the interaction and constraint relationship between fractures; extracts boundary fracture penetration synergistic characteristics from boundary fracture constraint data through fracture permeability data, and can reveal the synergistic effect of fracture permeability on oil and gas flow; identifies boundary fracture mutual coupling from boundary fracture characteristic information according to boundary fracture constraint data and boundary fracture synergistic data, and can comprehensively describe the relationship between fractures.

[0018] Preferably, step S42 includes the following steps: Step S421: performing fracture-oil and gas flow effect correspondence on the oil and gas characteristic data according to the boundary fracture relationship data to obtain fracture-oil and gas flow effect data; Step S422: marking the oil and gas characteristic data for oil and gas flow characteristics to generate oil and gas flow marking data; dividing the oil and gas characteristic data into flow units according to the oil and gas flow marking data to obtain flow unit division data; extracting flow characteristics from the flow unit division data to generate oil and gas flow characteristic data; Step S423: constructing a fracture oil and gas flow network for the oil and gas flow characteristic data based on the fracture-oil and gas flow action data to obtain a fracture oil and gas flow network; identifying the oil and gas flow path for the fracture oil and gas flow network to generate oil and gas flow path data; and calculating the oil and gas flow flow rate for the fracture oil and gas flow network based on the oil and gas flow path data to obtain oil and gas flow flow rate data; Step S424: performing flow state abnormality detection on the fracture oil and gas flow network through the oil and gas flow direction flow data to generate oil and gas flow state abnormality data; performing flow state stability evaluation on the fracture oil and gas flow network to obtain flow state stability data; Step S425: Integrate the oil and gas flow direction flow data, the oil and gas flow state abnormality data and the flow state stability data to obtain the oil and gas flow state data.

[0019] The present invention performs fracture-oil and gas flow action correspondence on oil and gas characteristic data according to boundary fracture relationship data, and can clarify the interaction relationship between fractures and oil and gas flow; performs oil and gas flow feature marking on oil and gas characteristic data, and can identify and distinguish different modes and stages of oil and gas flow; divides oil and gas characteristic data into flow units through oil and gas flow marking data, and specifically divides oil and gas reservoirs into regions with similar flow characteristics; extracts flow characteristics from flow unit division data, and clarifies the flow characteristics of each flow unit, including flow velocity, direction and flow efficiency; constructs a fracture oil and gas flow network for oil and gas flow characteristic data based on fracture-oil and gas flow action data , which can simulate the flow path and flow efficiency of oil and gas in fractures; identify the oil and gas flow path of the fracture oil and gas flow network, and clarify the specific path of the oil and gas flow; calculate the oil and gas flow rate of the fracture oil and gas flow network according to the oil and gas flow path data, and quantify the scale of oil and gas flow; detect flow state anomalies in the fracture oil and gas flow network through oil and gas flow flow data, and timely discover abnormalities in oil and gas flow; evaluate the flow state stability of the fracture oil and gas flow network, and evaluate the stability of oil and gas flow; integrate the oil and gas flow flow data, oil and gas flow state anomaly data and flow state stability data to obtain oil and gas flow state data.

[0020] Preferably, step S43 includes the following steps: Step S431: performing unit oil and gas volume statistics on the oil and gas flow data to obtain unit oil and gas volume data; performing instantaneous oil and gas production calculation on the unit oil and gas volume data to generate instantaneous oil and gas production data; Step S432: Identify the abnormal state type of the abnormal oil and gas flow state data to obtain the abnormal flow state type; record the abnormal instantaneous production of the instantaneous oil and gas production data according to the abnormal flow state type to generate abnormal state instantaneous production data; accumulate the oil and gas production of the abnormal state instantaneous production data to obtain abnormal state cumulative production data; Step S433: recording the instantaneous oil and gas production data in a stable state based on the flow state stability data to generate the instantaneous production data in a stable state; accumulating the oil and gas production in the instantaneous production data in a stable state to obtain the cumulative production data in a stable state; Step S434: Subtract the production value of the steady-state cumulative production data from the abnormal-state cumulative production data to obtain the oil and gas non-steady-state production capacity index.

[0021] The present invention performs unit oil and gas volume statistics on oil and gas flow data, and can quantify the flow scale of oil and gas; performs instantaneous oil and gas production calculation on unit oil and gas volume data, and can clarify the instantaneous oil and gas production information at a specific time point; performs abnormal state type identification on abnormal oil and gas flow state data, and clearly distinguishes abnormal states in oil and gas flow, which is crucial for timely identification and response to potential problems of oil and gas wells; records abnormal instantaneous production of instantaneous oil and gas production data according to the abnormal flow state type, so as to record the oil and gas production under abnormal conditions; accumulates the oil and gas production of abnormal state instantaneous production data, and clarifies the total production caused by abnormal conditions within a period of time; records the stable state instantaneous production of instantaneous oil and gas production data based on flow state stability data, and accurately reflects the production of oil and gas wells under normal conditions; accumulates the oil and gas production of stable state instantaneous production data, and clarifies the normal total production of oil and gas wells within a period of time; and makes a difference in production values ​​between the stable state cumulative production data and the abnormal state cumulative production data, so as to quantify the production capacity change of oil and gas wells under non-steady state conditions.

[0022] In this specification, a closed boundary fractured horizontal well unsteady-state capacity prediction device is provided, including a prediction system for executing the above-mentioned closed boundary fractured horizontal well unsteady-state capacity prediction method, the prediction system comprising: The data acquisition module is used to collect data from closed boundary fractured horizontal wells to generate fractured horizontal well data; pre-process the fractured horizontal well data to obtain standard fractured horizontal well data; The boundary fracturing oil and gas simulation module is used to identify the closed boundary fracturing characteristics of the standard fracturing horizontal well data to obtain the closed boundary fracturing data; extract the crack characteristics of the closed boundary fracturing data to generate the boundary crack characteristic information; determine the fracturing porosity of the standard fracturing horizontal well data according to the boundary crack characteristic information to obtain the fracturing porosity data; simulate the oil and gas characteristics of the standard fracturing horizontal well data based on the boundary crack characteristic information and the fracturing porosity data to generate the oil and gas characteristic data; The fracturing horizontal well bottom pressure measurement module is used to extract fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identify the wellbore position of standard fracturing horizontal well data according to the boundary fracture parameter information to obtain wellbore position data; associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of standard fracturing horizontal well data based on the fracture wellbore associated data to obtain bottom hole pressure data; The oil and gas non-steady-state capacity index calculation module is used to perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state of oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index of standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0023] The present invention uses a data acquisition module and a sensor to collect data from closed boundary fracturing horizontal wells, ensuring that original and direct information about the fracturing horizontal wells is obtained, which can provide basic information for subsequent analysis; pre-processing the fracturing horizontal well data helps to eliminate noise and outliers in the data, ensure the consistency and accuracy of the data, and provide key data input for subsequent fracturing porosity determination and oil and gas characteristic simulation. Through the boundary fracturing oil and gas simulation module, the closed boundary fracturing feature identification of the standard fracturing horizontal well data can evaluate the key of fracture network and reservoir connectivity; the fracture feature extraction of the closed boundary fracturing data can clarify the boundary fracture feature information; the fracturing porosity of the standard fracturing horizontal well data is determined according to the boundary fracture feature information, which can accurately reflect the pore structure of the fracturing area, which is crucial for evaluating the reservoir characteristics of the oil and gas reservoir; the oil and gas feature simulation of the standard fracturing horizontal well data based on the boundary fracture feature information and the fracturing porosity data can simulate the distribution and flow of oil and gas in the fracturing horizontal well. Through the fracturing horizontal well bottom pressure measurement module, the fracture parameters are extracted from the boundary fracture characteristic information through the oil and gas characteristic data, so that the geometric characteristics and distribution characteristics of the fractures can be described in detail; the wellbore position of the standard fracturing horizontal well data is identified according to the boundary fracture parameter information, so that the accurate position of the wellbore in the oil and gas reservoir can be determined; the boundary fracture parameter information and the wellbore position data are correlated and mapped, so that the fracture parameters can be correlated with the wellbore position, providing data support for the bottom hole pressure measurement; the bottom hole pressure of the standard fracturing horizontal well data is measured based on the fracture wellbore correlation data, so that the bottom hole pressure data can be clarified. Through the oil and gas non-steady-state capacity index calculation module, the boundary crack mutual coupling analysis is performed on the boundary crack characteristic information according to the bottom hole pressure data, which can reveal the interaction and influence between the cracks; the oil and gas flow state is identified on the oil and gas characteristic data according to the boundary crack relationship data, which can identify the flow state of oil and gas in the crack network; the oil and gas non-steady-state capacity index is calculated on the standard fracturing horizontal well data through the oil and gas flow state data, which can provide the dynamic change information of oil and gas production; the non-steady-state capacity prediction model is constructed by using the oil and gas non-steady-state capacity index to obtain the non-steady-state capacity prediction model; the non-steady-state capacity prediction is performed on the standard fracturing horizontal well data based on the non-steady-state capacity prediction model, and the non-steady-state capacity prediction report is generated. Therefore, the present invention realizes the identification of the mutual relationship between the bottom hole pressure and the boundary crack characteristics through data processing technology, pattern recognition technology, and deep learning technology; and realizes the oil and gas flow state detection of the oil and gas characteristics according to the boundary crack relationship, thereby improving the accuracy of the non-steady-state capacity prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic flow chart of the steps of a method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well; Figure 2for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 3 for Figure 2 Detailed implementation steps of step S34; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 , a method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well, the method comprising the following steps: Step S1: collecting data from closed boundary fractured horizontal wells to generate fractured horizontal well data; preprocessing the fractured horizontal well data to obtain standard fractured horizontal well data; Step S2: performing closed boundary fracturing feature recognition on the standard fracturing horizontal well data to obtain closed boundary fracturing data; performing crack feature extraction on the closed boundary fracturing data to generate boundary crack feature information; performing fracturing porosity determination on the standard fracturing horizontal well data according to the boundary crack feature information to obtain fracturing porosity data; performing oil and gas feature simulation on the standard fracturing horizontal well data based on the boundary crack feature information and the fracturing porosity data to generate oil and gas feature data; Step S3: extracting fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identifying wellbore position of standard fractured horizontal well data according to boundary fracture parameter information to obtain wellbore position data; associating and mapping boundary fracture parameter information with wellbore position data to generate fracture wellbore associated data; measuring bottom hole pressure of standard fractured horizontal well data based on fracture wellbore associated data to obtain bottom hole pressure data; Step S4: perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state on oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index on standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0029] The present invention uses sensors to collect data from closed boundary fractured horizontal wells, ensuring that original and direct information about fractured horizontal wells is obtained, which can provide basic information for subsequent analysis; pre-processing of fractured horizontal well data helps to eliminate noise and outliers in the data, ensuring the consistency and accuracy of the data, and providing key data input for subsequent fracture porosity determination and oil and gas characteristic simulation. Closed boundary fracture feature identification of standard fractured horizontal well data can be the key to evaluating fracture network and reservoir connectivity; fracture feature extraction of closed boundary fracture data can clarify boundary fracture feature information; fracture porosity determination of standard fractured horizontal well data based on boundary fracture feature information can accurately reflect the pore structure of the fractured area, which is crucial for evaluating the reservoir characteristics of oil and gas reservoirs; oil and gas feature simulation of standard fractured horizontal well data based on boundary fracture feature information and fracture porosity data can simulate the distribution and flow of oil and gas in fractured horizontal wells. By extracting fracture parameters from boundary fracture characteristic information using oil and gas characteristic data, the geometric characteristics and distribution characteristics of fractures can be described in detail; by identifying the wellbore position of standard fracturing horizontal well data based on boundary fracture parameter information, the accurate position of the wellbore in the oil and gas reservoir can be determined; by associating and mapping boundary fracture parameter information with wellbore position data, the fracture parameters can be associated with the wellbore position, providing data support for bottom hole pressure measurement; by measuring the bottom hole pressure of standard fracturing horizontal well data based on fracture-wellbore association data, the bottom hole pressure data can be clarified. According to the bottom hole pressure data, the boundary cracks feature information is subjected to the boundary cracks mutual coupling analysis, which can reveal the interaction and influence between the cracks; according to the boundary cracks relationship data, the oil and gas flow state is identified for the oil and gas feature data, which can identify the flow state of oil and gas in the crack network; the oil and gas non-steady-state capacity index is measured for the standard fracturing horizontal well data through the oil and gas flow state data, which can provide the dynamic change information of the oil and gas production; the non-steady-state capacity prediction model is constructed by using the oil and gas non-steady-state capacity index to obtain the non-steady-state capacity prediction model; the non-steady-state capacity prediction is performed on the standard fracturing horizontal well data based on the non-steady-state capacity prediction model, and the non-steady-state capacity prediction report is generated. Therefore, the present invention realizes the identification of the relationship between the bottom hole pressure and the boundary crack characteristics through data processing technology, pattern recognition technology, and deep learning technology; and realizes the oil and gas flow state detection for the oil and gas characteristics according to the boundary crack relationship, thereby improving the accuracy of the non-steady-state capacity prediction.

[0030] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of the closed boundary fractured horizontal well unsteady-state capacity prediction method of the present invention. In this example, the closed boundary fractured horizontal well unsteady-state capacity prediction method includes the following steps: Step S1: collecting data from closed boundary fractured horizontal wells to generate fractured horizontal well data; preprocessing the fractured horizontal well data to obtain standard fractured horizontal well data; In an embodiment of the present invention, high-precision sensors, such as pressure sensors and temperature sensors, are deployed to monitor and record physical parameters in a fractured horizontal well in real time; specifically, pressure changes, fluid flow and temperature distribution during the fracturing process are captured to generate fractured horizontal well data; the fractured horizontal well data are preprocessed, and the preprocessing steps include removing unique attributes, processing missing values, attribute encoding, data standardization and regularization; for example, for missing values, mean interpolation or similar mean interpolation methods are used; for data standardization, the min-max normalization method is used to scale the data to a specified range to eliminate the influence of attributes of different magnitudes; thereby obtaining standard fractured horizontal well data.

[0031] Step S2: performing closed boundary fracturing feature recognition on the standard fracturing horizontal well data to obtain closed boundary fracturing data; performing crack feature extraction on the closed boundary fracturing data to generate boundary crack feature information; performing fracturing porosity determination on the standard fracturing horizontal well data according to the boundary crack feature information to obtain fracturing porosity data; performing oil and gas feature simulation on the standard fracturing horizontal well data based on the boundary crack feature information and the fracturing porosity data to generate oil and gas feature data; In an embodiment of the present invention, feature recognition technology is used to identify closed boundary fracturing features of standard fracturing horizontal well data, specifically identifying boundary fracturing feature parameters and boundary fracturing conditions; data detection technology, such as edge detection algorithm, is used to identify crack features of closed boundary fracturing data, specifically obtaining boundary crack edge and width information, thereby obtaining boundary crack feature information; microseismic monitoring technology is used to identify crack pores of standard fracturing horizontal well data based on boundary crack feature information, and the crack pore volume is calculated to obtain the crack pore volume; reservoir porosity is calculated for the crack pore volume, thereby obtaining fracturing porosity data; based on the crack feature information and the determined fracturing porosity data, physical simulation experiment technology, such as visualized three-dimensional physical simulation experiment technology, is used to simulate the oil and gas flow process; specifically, through physical simulation experiments, such as two-dimensional sand box simulation experiments or three-dimensional consolidation model experiments, the distribution and flow behavior of oil and gas in the reservoir are observed to generate oil and gas feature data.

[0032] Step S3: extracting fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identifying wellbore position of standard fractured horizontal well data according to boundary fracture parameter information to obtain wellbore position data; associating and mapping boundary fracture parameter information with wellbore position data to generate fracture wellbore associated data; measuring bottom hole pressure of standard fractured horizontal well data based on fracture wellbore associated data to obtain bottom hole pressure data; In an embodiment of the present invention, an image-based fracture segmentation technology is used, for example, a threshold segmentation method is used to perform fracture segmentation using the OpenCV library; the orthogonal skeleton line method is specifically applied to the segmented fracture image to identify the fracture skeleton line; and in combination with the fracture skeleton line, a width calculation method is used to determine the fracture width to obtain boundary fracture parameter information; a layered parameterization method is used to measure the wellbore range of standard fracturing horizontal well data according to the boundary fracture parameter information to obtain wellbore range measurement data; the wellbore position is identified according to the wellbore range measurement data to obtain wellbore position data; the boundary fracture parameter information is associated and mapped with the wellbore position data, and data fusion technology is specifically used to integrate the fracture parameters and the wellbore position information to generate fracture wellbore associated data; based on the fracture wellbore associated data, a pressure sensor is used to monitor the standard fracturing horizontal well data in real time and record the dynamic pressure, thereby obtaining bottom hole pressure data.

[0033] Step S4: perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state on oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index on standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0034] In the embodiment of the present invention, the boundary fracture characteristic information is determined based on the bottom hole pressure data to determine the boundary fracture correlation. Specifically, the boundary fractures are mutually constrained and coordinated, so as to obtain the correlation relationship between the boundary fractures, and the coupling relationship between the correlation relationship between the boundary fractures is identified to generate the coupling relationship; the correlation relationship between the boundary fractures and the coupling relationship are integrated by using the data fusion technology to obtain the boundary fracture relationship data; the oil and gas flow feature is marked on the oil and gas characteristic data based on the boundary fracture relationship data, and the oil and gas flow feature mark is enhanced; the pattern recognition technology is used to identify the oil and gas flow feature enhancement data based on the oil and gas flow mark feature enhancement data Flow state identification, so as to obtain oil and gas flow state data; according to the boundary fracture relationship data and the oil and gas flow state data, the non-steady-state capacity of the equivalent well is determined specifically through the mirror inversion and pressure drop superposition principle; multiple fracture parameters, time steps and corresponding non-steady-state capacity are calculated specifically to generate oil and gas non-steady-state capacity indicators; the non-steady-state capacity prediction model is constructed using the oil and gas non-steady-state capacity indicators, and the model is constructed specifically using machine learning algorithms to obtain a non-steady-state capacity prediction model; the non-steady-state capacity prediction of standard fractured horizontal well data is performed based on the non-steady-state capacity prediction model; the oil well capacity under non-steady-state conditions is predicted by the model, and a non-steady-state capacity prediction report is generated.

[0035] Preferably, step S2 comprises the following steps: Step S21: performing nonlinear feature decomposition on standard fracturing horizontal well data to generate nonlinear fracturing horizontal well features; performing fracturing feature enhancement on the nonlinear fracturing horizontal well features to obtain fracturing feature enhancement data; performing closed boundary fracturing feature extraction on the fracturing feature enhancement data to obtain closed boundary fracturing data; Step S22: extracting fracturing morphological features from closed boundary fracturing data to generate fracturing morphological feature data; quantifying geometric features from standard fracturing horizontal well data to obtain fracturing morphological geometric features; identifying fracture features from fracturing morphological geometric features to generate boundary fracture feature information; Step S23: determining the distribution range of the boundary crack feature information to obtain the boundary crack distribution range; identifying the crack space distribution characteristics of the boundary crack distribution range to generate the crack space distribution characteristics; performing crack space distribution morphological characteristics on the fracturing morphological geometric characteristics according to the crack space distribution characteristics to obtain the crack space distribution morphological characteristics; Step S24: Calculate the fracture density of the fracture space distribution morphology to generate fracture space density data; perform fracturing pore characteristics on the boundary fracture feature information based on the fracture space density data to obtain fracturing pore characteristics; perform fracturing porosity measurement on the standard fracturing horizontal well data through the fracturing pore characteristics to obtain fracturing porosity data; Step S25: Perform porosity gradient division on the fracturing porosity data to generate porosity gradient data; perform oil and gas characteristic simulation on the standard fracturing horizontal well data based on the porosity gradient data and boundary fracture characteristic information to generate oil and gas characteristic data.

[0036] In an embodiment of the present invention, a singular spectrum analysis (SSA) method with an adaptive threshold is used to perform nonlinear feature decomposition on standard fracturing horizontal well data to generate nonlinear fracturing horizontal well features; the SSA method separates the periodic components and trend components in the data by constructing data reconstruction at different time scales, thereby identifying nonlinear features; a feature enhancement technology based on wavelet transform is used to perform feature enhancement processing on the nonlinear fracturing horizontal well features, specifically providing feature information in the time-frequency domain, and by appropriately selecting the wavelet basis and the number of decomposition layers, the characteristic frequency generated by the fracturing event is highlighted, thereby enhancing the fracturing features; a feature extraction technology is used to extract closed boundary fracturing features from the fracturing feature enhancement data, specifically extracting the geometry and texture information of the cracks; an image processing technology, such as a histogram-based fracture segmentation method, is used to process the closed boundary fracturing data to extract the morphological features of the fractures; a three-dimensional reconstruction technology is used to quantify the geometric features of the standard fracturing horizontal well data, specifically quantifying the morphology and spatial structure geometry information of the fractures; a feature recognition technology is used to recognize the geometric features of the fracturing morphology, specifically recognizing the feature information of the boundary fractures. The fracture network analysis method based on fractal theory is used to determine the characteristic information of boundary fractures and specifically determine the distribution range of fractures; the complexity of the fracture network is specifically quantified, and the distribution range and density of fractures are determined by calculating the fractal dimension of the fracture network; the distribution characteristics of the boundary fracture distribution range are spatially simulated according to the spatial distribution characteristics of the fractures; the fracture skeleton line is extracted from the geometric characteristics of the fracturing morphology by using a width calculation method, such as the orthogonal skeleton line method, and the width and length of the fracture are calculated to obtain the spatial distribution morphological characteristics of the fractures; the fracture density is calculated using the numerical simulation of fractured oil and gas reservoirs, and the density of the spatial distribution morphological characteristics of the fractures is specifically simulated. Analysis; Based on the fracture space density data, the reservoir porosity is calculated specifically through the fracture geometry characteristics and the flow characteristics of the fluid, thereby obtaining the fracturing pore characteristics; the fracturing porosity of the standard fracturing horizontal well data is measured through the fracturing pore characteristics to obtain the fracturing porosity data; based on the fracturing porosity data, an image-based width calculation method, such as the orthogonal skeleton method, is used to perform gradient division on the porosity data to generate porosity gradient data; by analyzing the spatial variation of porosity, areas with different porosity gradients are divided; the porosity gradient data and boundary fracture characteristic information are used to simulate the oil and gas characteristics of the standard fracturing horizontal well data to generate oil and gas characteristic data.

[0037] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes: Step S31: performing fracture geometric feature recognition on the boundary fracture feature information to generate fracture geometric feature data; performing fracture geometric parameter extraction on the fracture geometric feature data according to the oil and gas feature data to obtain fracture geometric parameters; Step S32: performing fracture connectivity detection on the boundary fracture characteristic information by using fracture geometric parameters to generate fracture connectivity data; performing fracture permeability evaluation on the boundary fracture characteristic information based on the fracture connectivity data to obtain fracture permeability data; performing fracture fluid flow simulation on the oil and gas characteristic data according to the fracture permeability data to obtain fracture fluid flow simulation data; Step S33: Integrate the fracture connectivity data, fracture permeability data and fracture fluid flow simulation data to obtain boundary fracture parameter information; perform wellbore feature recognition on the standard fracturing horizontal well data to generate wellbore feature data; perform wellbore position detection on the wellbore feature data according to the boundary fracture parameter information to obtain wellbore position data; Step S34: associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of the standard fracturing horizontal well data based on the fracture wellbore associated data to obtain the bottom hole pressure data.

[0038] In the embodiment of the present invention, a geometric feature recognition method is used to specifically extract the fracture morphology, and through image processing techniques such as connected domain denoising, fracture connection, edge detection, fracture skeletonization and other processes, fracture parameter information is obtained to generate fracture geometric feature data; according to the oil and gas characteristic data, the fracture geometric feature data is analyzed using the orthogonal skeleton line method technology to extract the geometric parameters such as the width and length of the fracture to obtain the fracture geometric data; through the fracture geometric parameters, a multi-scale fracture network distribution inversion method in the fracture medium based on hierarchical parameterization and data-driven evolutionary optimization method is used to perform fracture connectivity detection on the boundary fracture feature information to generate fracture connectivity data; based on the fracture connectivity data, the fluid flow permeability evaluation technology is used to perform fracture permeability evaluation on the boundary fracture feature information to obtain fracture permeability data; according to the fracture permeability Based on the characteristic data of the fracture, the fluid flow simulation technology is used to simulate the fracture fluid flow of the oil and gas characteristic data to obtain the fracture fluid flow simulation data; the data fusion technology is used to integrate the fracture connectivity data, the fracture permeability data and the fracture fluid flow simulation data to obtain the boundary fracture parameter information; the feature recognition technology is used to identify the wellbore characteristics of the standard fracturing horizontal well data to generate the wellbore feature data; according to the boundary fracture parameter information, the wellbore position is detected in combination with the wellbore feature data, and the location information of the wellbore position is specifically detected to obtain the wellbore position data; the boundary fracture parameter information is associated and mapped with the wellbore position data by using the data association technology, and the boundary fracture is specifically associated with the wellbore position; based on the fracture wellbore association data, the real-time pressure monitoring technology is used to measure the bottom hole pressure of the standard fracturing horizontal well data to obtain the bottom hole pressure data.

[0039] As an example of the present invention, refer to Figure 3 As shown, in this example, step S34 includes: Step S341: quantifying the connectivity of the fracture connectivity data to obtain fracture connectivity quantitative data; associating the fracture connectivity quantitative data with the wellbore position data to generate fracture wellbore connectivity association data; Step S342: performing permeability parameterization on the fracture permeability data to obtain fracture permeability parameterized data; performing fracture permeability correlation on the fracture permeability parameterized data and the wellbore position data to generate fracture wellbore permeability correlation data; Step S343: extracting flow characteristics of fracture fluid flow simulation data to obtain fracture fluid flow characteristic data; correlating the fracture fluid flow characteristic data with wellbore position data to generate fracture wellbore fluidity correlation data; Step S344: Integrate the fracture wellbore connectivity correlation data, the fracture wellbore permeability correlation data and the fracture wellbore fluidity correlation data to obtain the fracture wellbore correlation data; Step S345: measuring the bottom hole pressure of the standard fractured horizontal well data based on the fracture wellbore correlation data to obtain the bottom hole pressure data.

[0040] In an embodiment of the present invention, the connectivity of the fracture connectivity data is quantified, specifically by calculating the hydraulic conductivity of the fracture and the shortest distance between the fracture clusters, the fracture connectivity is specifically quantified, so as to obtain the fracture connectivity quantitative data; the fracture connectivity quantitative data is associated with the wellbore position data, and the influence of the fracture connectivity on the wellbore position is specifically calculated to generate the fracture wellbore connectivity associated data; the fracture permeability data is parameterized by using the numerical simulation of the fluid flow in the fracture reservoir, specifically applying the fracture permeability evaluation technology, and obtaining the fracture permeability parameterized data; the fracture permeability parameterized data is associated with the wellbore position data, and the reservoir fluid flow dominated by the fracture is simulated by the numerical simulation method to generate the fracture wellbore connectivity associated data. Wellbore permeability correlation data; using feature extraction technology, extract flow characteristics of fracture fluid flow simulation data to obtain fracture fluid flow characteristic data; correlating fracture fluid flow characteristic data with wellbore position data, and generating fracture wellbore fluidity correlation data by analyzing the impact of fracture network on fluid flow; using data fusion technology, integrating fracture wellbore connectivity correlation data, fracture wellbore permeability correlation data and fracture wellbore fluidity correlation data to obtain fracture wellbore correlation data; based on fracture wellbore correlation data, using underbalanced drilling bottomhole pressure measurement technology, through drilling measurement and annulus multiphase flow bottomhole pressure calculation model, the bottomhole pressure of standard fracturing horizontal well data is measured to obtain bottomhole pressure data.

[0041] Preferably, step S345 includes the following steps: Step S3451: extracting the bottom hole stress characteristics of the standard fractured horizontal well data based on the fracture wellbore correlation data to generate the bottom hole stress characteristics; simulating the bottom hole pressure distribution of the standard fractured horizontal well data according to the bottom hole stress characteristics to obtain the bottom hole pressure distribution simulation data; Step S3452: performing bottom hole pressure response identification on the bottom hole pressure distribution simulation data to generate bottom hole pressure response data; performing pressure numerical calculation on the bottom hole pressure response data to obtain bottom hole pressure numerical information; performing pressure gradient division on the bottom hole pressure numerical information to generate bottom hole pressure gradient data; Step S3453: performing real-time bottom hole pressure monitoring on the bottom hole pressure distribution simulation data through the bottom hole pressure gradient data to obtain bottom hole pressure change data; performing bottom hole pressure state identification on the bottom hole pressure change data to generate bottom hole pressure state information; Step S3454: perform bottom hole pressure anomaly detection on the bottom hole pressure status information to obtain bottom hole pressure anomaly data; perform pressure stability evaluation on the bottom hole pressure distribution simulation data based on the bottom hole pressure anomaly data to obtain bottom hole pressure stability data; perform bottom hole pressure measurement on the standard fracturing horizontal well data based on the bottom hole pressure stability data to obtain bottom hole pressure data.

[0042] In an embodiment of the present invention, based on fracture wellbore correlation data, downhole acoustic wave detection technology is used to extract bottom hole stress characteristics of standard fracturing horizontal well data; the downhole acoustic wave reflection signal is specifically analyzed to determine the stress state of the bottom hole rock and the development of the fractures, and generate bottom hole stress characteristics; according to the bottom hole stress characteristics, the pressure-controlled drilling pressure detection technology is used to simulate the bottom hole pressure distribution of the standard fracturing horizontal well data to obtain bottom hole pressure distribution simulation data; for the bottom hole pressure distribution simulation data, a real-time formation pressure inversion method based on back pressure excitation response is used to identify the bottom hole pressure response and generate bottom hole pressure response data; this method applies back pressure excitation at the wellhead, combines ground measurement data and annulus data calculated by a simplified two-phase flow model, and inverts the formation pressure; the bottom hole pressure response data is numerically extracted, and the pressure response value is numerically calculated to obtain bottom hole pressure numerical information; the bottom hole pressure numerical information is subjected to pressure gradient The pressure gradient is divided into three levels to obtain the bottom hole pressure gradient data; through the bottom hole pressure gradient data, the permanent optoelectronic composite cable monitoring technology is used to perform real-time bottom hole pressure monitoring on the bottom hole pressure distribution simulation data to obtain the bottom hole pressure change data; the bottom hole pressure state is identified on the bottom hole pressure change data, and the bottom hole pressure state mode is specifically identified, such as the high pressure state and the low pressure state, to obtain the bottom hole pressure state information; for the bottom hole pressure state information, the real-time formation pressure inversion method based on the back pressure excitation response is used to perform bottom hole pressure anomaly detection, specifically to detect the abnormal state of the bottom hole pressure being too high or too low, to obtain the bottom hole pressure anomaly data; according to the bottom hole pressure anomaly data, the pressure stability of the bottom hole pressure distribution simulation data is evaluated to obtain the bottom hole pressure stability data; based on the bottom hole pressure stability data, the bottom hole pressure measurement technology is used to measure the bottom hole pressure of the standard fracturing horizontal well data to obtain the bottom hole pressure data.

[0043] Preferably, step S4 comprises the following steps: Step S41: performing boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; Step S42: identifying the oil and gas flow state of the oil and gas characteristic data according to the boundary fracture relationship data to obtain the oil and gas flow state data; Step S43: calculating the oil and gas non-steady-state production capacity index for the standard fractured horizontal well data by using the oil and gas flow state data to generate the oil and gas non-steady-state production capacity index; Step S44: constructing a non-steady-state capacity prediction model according to the non-steady-state capacity index of oil and gas to obtain a non-steady-state capacity prediction pre-model; and training the non-steady-state capacity prediction pre-model using the non-steady-state capacity index of oil and gas to obtain a non-steady-state capacity prediction training model; Step S45: performing a model cross-validation evaluation on the non-steady-state capacity prediction training model to obtain model evaluation data; adjusting model parameters of the non-steady-state capacity prediction training model using the model evaluation data to obtain a non-steady-state capacity prediction model; Step S46: Perform non-steady-state capacity prediction on the standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0044] In the embodiment of the present invention, the bottom hole pressure data is monitored in real time by using the distributed fiber acoustic sensing technology (DAS), and the mutual influence and coupling relationship between the fractures are specifically analyzed to generate boundary fracture relationship data; the optical signal is converted into a seismic vibration signal by using a machine learning algorithm, such as a heterodyne demodulation algorithm, and then the signal is subjected to noise reduction processing to obtain fracture network information and generate boundary fracture relationship data; the semi-supervised learning fluid prediction and reservoir identification method based on physical guidance is used to specifically analyze the oil and gas characteristic data, identify the oil and gas flow state, and obtain the oil and gas flow state data; the new technology of permanent optoelectronic composite cable monitoring is used to specifically monitor the real-time dynamic pressure of the whole wellbore, identify the oil and gas flow state, and obtain the oil and gas flow state data; the production capacity analysis technology under the non-steady-state conditions of the vertical fracturing horizontal well is applied to derive the pressure drop formula and establish the coupling relationship between the wellbore and the reservoir; the seepage characteristic analysis technology is used to obtain the bottom hole pressure index through the pressure drop superposition technology to generate the oil and gas non-steady-state production capacity index; according to the oil and gas non-steady-state production capacity index, a non-steady-state production capacity prediction and forecasting system is constructed. Model; specifically, the infinite conductivity model and the finite conductivity model in the capacity analysis of vertically fractured horizontal wells under non-steady-state conditions are adopted; based on the Green function and the Newman product principle, the pressure drop formula of the vertically fractured horizontal wells under non-steady-state production is derived, and a non-steady-state capacity prediction pre-model is established; the point source solution theory, Pedrosa transformation, perturbation transformation, Laplace transformation, finite cosine transformation, numerical discretization and superposition principle in the non-steady-state capacity prediction pre-model are used to solve the established mathematical model; the typical production decline curve is drawn by the Stehfest numerical inversion technology, and it is divided into different flow stages according to the characteristics of the curve, and the model is verified and compared at the same time; the non-steady-state capacity prediction training model is cross-validated and evaluated; the K-fold cross-validation method is used to divide the data set into K subsets, and each subset is used as a test set in turn, and the rest are used as training sets, and the performance indicators of the model on each subset are calculated to obtain model evaluation data; the model parameters of the non-steady-state capacity prediction training model are adjusted through the model evaluation data. The adjustment parameters include sensitivity parameters such as permeability modulus, branch well length and number of branch wells, so as to summarize the influence of different parameters on production dynamics; with the increase of stress sensitivity coefficient, the oil production and cumulative oil production of the oil well decrease; or when the total number of fractures is small, the segment cluster ratio of the fractures has a greater impact on the cumulative oil production. Under the same number of fractures, the larger the segment cluster ratio, the greater the cumulative oil production; based on the non-steady-state capacity prediction model, the non-steady-state capacity prediction of standard fracturing horizontal well data is performed to generate a non-steady-state capacity prediction report; using the trained model, the new bottom hole pressure data is input, the predicted non-steady-state capacity index is output, and a non-steady-state capacity prediction report is generated.

[0045] Preferably, step S41 includes the following steps: Step S411: extracting the pressure distribution characteristics of the bottom hole pressure data to obtain the bottom hole pressure distribution characteristics; identifying the pressure peak area of ​​the bottom hole pressure distribution characteristics to generate the bottom hole pressure peak area; Step S412: Identify the fracture concentration area of ​​the boundary fracture characteristic information according to the fracture space density data to obtain the boundary fracture concentration area; map and match the boundary fracture concentration area with the bottom hole pressure peak area to generate fracture pressure mapping data; Step S413: Calculate the degree of fracture pressure influence on the bottom hole pressure data through the fracture pressure mapping data to obtain fracture pressure influence data; perform fracture sensitivity measurement on the boundary fracture characteristic information according to the fracture pressure influence data to generate fracture sensitivity data; Step S414: using the fracture connectivity data to extract boundary fracture constraint features from the fracture sensitivity data to obtain boundary fracture constraint action data; using the fracture permeability data to extract boundary fracture permeability synergistic features from the boundary fracture constraint action data to generate boundary fracture synergistic action data; based on the boundary fracture constraint action data and the boundary fracture synergistic action data, boundary fracture mutual coupling identification is performed on the boundary fracture feature information to obtain boundary fracture relationship data.

[0046] In the embodiment of the present invention, an adaptive threshold technology is used to perform image processing on the bottom hole pressure data. Specifically, the optimal threshold is automatically obtained through the adaptive thresholding method to realize the extraction of the bottom hole pressure distribution characteristics and obtain the bottom hole pressure distribution characteristics; the image processing technology is used, combined with the directionality and continuity characteristics of the fracture image, to specifically analyze the bottom hole pressure distribution characteristics, identify the pressure peak area, and generate the bottom hole pressure peak area; according to the fracture space density data, an irregular micro-fracture network quantitative characterization method is used, and the seepage capacity of the porous medium is measured, and the boundary fracture characteristic information is specifically used to identify the fracture concentration area to obtain the boundary fracture concentration area; the boundary fracture concentration area is mapped and matched with the bottom hole pressure peak area, and the fracture pressure is obtained through numerical simulation methods, such as finite difference or computational fluid dynamics (CFD) methods. Mapping data; calculate the degree of fracture pressure influence on bottom hole pressure data through fracture pressure mapping data to obtain fracture pressure influence data; based on fracture pressure influence data, use fracture sensitivity determination technology to determine fracture sensitivity of boundary fracture feature information to obtain fracture sensitivity data; use fracture connectivity data and structural fracture depth inversion technology to extract boundary fracture constraint features from fracture sensitivity data to obtain boundary fracture constraint effect data; use fracture permeability data and synergistic analysis technology to extract boundary fracture permeability synergistic features from boundary fracture constraint effect data to obtain boundary fracture synergistic effect data; based on boundary fracture constraint effect data and boundary fracture synergistic effect data, use capacity analysis technology to identify boundary fracture mutual coupling on boundary fracture feature information to obtain boundary fracture relationship data.

[0047] Preferably, step S42 includes the following steps: Step S421: performing fracture-oil and gas flow effect correspondence on the oil and gas characteristic data according to the boundary fracture relationship data to obtain fracture-oil and gas flow effect data; Step S422: marking the oil and gas characteristic data for oil and gas flow characteristics to generate oil and gas flow marking data; dividing the oil and gas characteristic data into flow units according to the oil and gas flow marking data to obtain flow unit division data; extracting flow characteristics from the flow unit division data to generate oil and gas flow characteristic data; Step S423: constructing a fracture oil and gas flow network for the oil and gas flow characteristic data based on the fracture-oil and gas flow action data to obtain a fracture oil and gas flow network; identifying the oil and gas flow path for the fracture oil and gas flow network to generate oil and gas flow path data; and calculating the oil and gas flow flow rate for the fracture oil and gas flow network based on the oil and gas flow path data to obtain oil and gas flow flow rate data; Step S424: performing flow state abnormality detection on the fracture oil and gas flow network through the oil and gas flow direction flow data to generate oil and gas flow state abnormality data; performing flow state stability evaluation on the fracture oil and gas flow network to obtain flow state stability data; Step S425: Integrate the oil and gas flow direction flow data, the oil and gas flow state abnormality data and the flow state stability data to obtain the oil and gas flow state data.

[0048] In the embodiment of the present invention, according to the boundary fracture relationship data, the numerical simulation technology in the progress of numerical simulation research on fluid flow in fractured reservoirs is used to perform a fracture-oil and gas flow effect correspondence analysis on the oil and gas characteristic data to obtain fracture-oil and gas flow effect data. Specifically, by simulating the reservoir fluid flow dominated by the fracture network, the influence of fractures on oil and gas flow is identified, thereby obtaining fracture-oil and gas flow effect data; the bottom hole pressure distribution characteristics are analyzed, and the bottom hole pressure peak area is identified by using the bottom hole pressure technology; the pressure peak area is determined by analyzing the fluid flow state at the pore scale, and the bottom hole pressure peak area is generated; the oil and gas characteristic data are marked with oil and gas flow characteristics, and oil and gas flow technology is used to generate oil and gas flow marking data; the flow characteristics of the remaining oil, such as droplet, columnar and film, are identified and classified, and the oil and gas flow characteristics are marked; the oil and gas flow marking data is used to The oil and gas characteristic data are divided into flow units using fracture network simulation technology to obtain flow unit division data; the reservoir is divided into different flow units according to the connectivity of the fracture network and the fluid flow characteristics; the flow unit division data is analyzed, and the oil and gas flow state analysis method is used to extract the oil and gas flow characteristic data; the fluid flow characteristics in each flow unit, such as flow velocity, flow direction and flow path, are specifically analyzed to generate oil and gas flow characteristic data; based on the fracture-oil and gas flow action data, a fracture oil and gas flow network is constructed using fracture oil and gas flow simulation technology, and a fracture oil and gas flow network is constructed by simulating the fluid flow in the fracture network. The fracture oil and gas flow network is analyzed, and the flow path analysis method is used to identify the oil and gas flow path and obtain the oil and gas flow path data; the flow direction of the oil and gas is specifically determined by tracing the flow path of the fluid in the fracture network; based on the oil and gas flow path data, the oil and gas flow simulation technology is used to specifically calculate the oil and gas flow flow rate of the fracture oil and gas flow network; the oil and gas flow flow data is obtained by simulating the flow on different flow paths; the flow state anomaly analysis method is used to detect the flow state anomaly of the fracture oil and gas flow network based on the oil and gas flow flow data; the flow state anomaly is identified by comparing the actual flow with the expected flow; the flow state stability of the fracture oil and gas flow network is evaluated by the stability analysis method, and the flow state stability data is obtained; the flow state stability is evaluated by analyzing the stability of the fluid flow in the fracture network; the data fusion technology is used to integrate the oil and gas flow flow data, the oil and gas flow state anomaly data and the flow state stability data to obtain the oil and gas flow state data.

[0049] Preferably, step S43 includes the following steps: Step S431: performing unit oil and gas volume statistics on the oil and gas flow data to obtain unit oil and gas volume data; performing instantaneous oil and gas production calculation on the unit oil and gas volume data to generate instantaneous oil and gas production data; Step S432: Identify the abnormal state type of the abnormal oil and gas flow state data to obtain the abnormal flow state type; record the abnormal instantaneous production of the instantaneous oil and gas production data according to the abnormal flow state type to generate abnormal state instantaneous production data; accumulate the oil and gas production of the abnormal state instantaneous production data to obtain abnormal state cumulative production data; Step S433: recording the instantaneous oil and gas production data in a stable state based on the flow state stability data to generate the instantaneous production data in a stable state; accumulating the oil and gas production in the instantaneous production data in a stable state to obtain the cumulative production data in a stable state; Step S434: Subtract the production value of the steady-state cumulative production data from the abnormal-state cumulative production data to obtain the oil and gas non-steady-state production capacity index.

[0050] In the embodiment of the present invention, the oil and gas flow data are statistically analyzed per unit oil and gas volume, and the production calculation method in the pressure recovery test of the oil and water well test project is used; the crude oil production is calculated by the single well steady-state flow method based on the dynamic data of the oil well fluid; the instantaneous oil and gas production data of the unit oil and gas volume data are calculated by simulating the mapping relationship between various influencing factors and the natural gas well production; the abnormal state type of the oil and gas flow state abnormal data is identified by using the abnormal state identification technology; by analyzing the moving object flow data, the abnormal traffic state is quickly identified and the flow abnormal state type is determined; according to the flow abnormal state type, the abnormal instantaneous production data is recorded for the abnormal instantaneous production to generate the abnormal state instantaneous production data; the abnormal state instantaneous production data is accumulated to obtain the abnormal state cumulative production data; the oil and gas production accumulation method is used to calculate the abnormal state type of the oil and gas flow state abnormal data by analyzing the moving object flow data The instantaneous production within the period is accumulated to calculate the cumulative oil and gas production under abnormal conditions; based on the flow state stability data, the instantaneous production of the instantaneous oil and gas production data is recorded in a stable state to generate the instantaneous production data in a stable state; the fracturing oil well production method in the oil and gas production calculation formula is used, and the formula is to calculate the crude oil production based on the known fracturing fluid volume, inflow pressure and abortion pressure; the oil and gas production data in the stable state are accumulated to obtain the cumulative production data in a stable state; the oil and gas production accumulation method is used to accumulate the instantaneous production in different time periods to calculate the cumulative oil and gas production in a stable state; the stable state cumulative production data and the abnormal state cumulative production data are subtracted to obtain the oil and gas non-steady-state capacity index; the oil and gas production numerical difference calculation method is used to calculate the oil and gas non-steady-state capacity index by numerically subtracting the cumulative production data in a stable state and an abnormal state.

[0051] In this specification, a closed boundary fractured horizontal well unsteady-state capacity prediction device is provided, including a prediction system for executing the above-mentioned closed boundary fractured horizontal well unsteady-state capacity prediction method, the prediction system comprising: The data acquisition module is used to collect data from closed boundary fractured horizontal wells to generate fractured horizontal well data; pre-process the fractured horizontal well data to obtain standard fractured horizontal well data; The boundary fracturing oil and gas simulation module is used to identify the closed boundary fracturing characteristics of the standard fracturing horizontal well data to obtain the closed boundary fracturing data; extract the crack characteristics of the closed boundary fracturing data to generate the boundary crack characteristic information; determine the fracturing porosity of the standard fracturing horizontal well data according to the boundary crack characteristic information to obtain the fracturing porosity data; simulate the oil and gas characteristics of the standard fracturing horizontal well data based on the boundary crack characteristic information and the fracturing porosity data to generate the oil and gas characteristic data; The fracturing horizontal well bottom pressure measurement module is used to extract fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identify the wellbore position of standard fracturing horizontal well data according to the boundary fracture parameter information to obtain wellbore position data; associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of standard fracturing horizontal well data based on the fracture wellbore associated data to obtain bottom hole pressure data; The oil and gas non-steady-state capacity index calculation module is used to perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state of oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index of standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

[0052] The present invention uses a data acquisition module and a sensor to collect data from closed boundary fracturing horizontal wells, ensuring that original and direct information about the fracturing horizontal wells is obtained, which can provide basic information for subsequent analysis; pre-processing the fracturing horizontal well data helps to eliminate noise and outliers in the data, ensure the consistency and accuracy of the data, and provide key data input for subsequent fracturing porosity determination and oil and gas characteristic simulation. Through the boundary fracturing oil and gas simulation module, the closed boundary fracturing feature identification of the standard fracturing horizontal well data can evaluate the key of fracture network and reservoir connectivity; the fracture feature extraction of the closed boundary fracturing data can clarify the boundary fracture feature information; the fracturing porosity of the standard fracturing horizontal well data is determined according to the boundary fracture feature information, which can accurately reflect the pore structure of the fracturing area, which is crucial for evaluating the reservoir characteristics of the oil and gas reservoir; the oil and gas feature simulation of the standard fracturing horizontal well data based on the boundary fracture feature information and the fracturing porosity data can simulate the distribution and flow of oil and gas in the fracturing horizontal well. Through the fracturing horizontal well bottom pressure measurement module, the fracture parameters are extracted from the boundary fracture characteristic information through the oil and gas characteristic data, so that the geometric characteristics and distribution characteristics of the fractures can be described in detail; the wellbore position of the standard fracturing horizontal well data is identified according to the boundary fracture parameter information, so that the accurate position of the wellbore in the oil and gas reservoir can be determined; the boundary fracture parameter information and the wellbore position data are correlated and mapped, so that the fracture parameters can be correlated with the wellbore position, providing data support for the bottom hole pressure measurement; the bottom hole pressure of the standard fracturing horizontal well data is measured based on the fracture wellbore correlation data, so that the bottom hole pressure data can be clarified. Through the oil and gas non-steady-state capacity index calculation module, the boundary crack mutual coupling analysis is performed on the boundary crack characteristic information according to the bottom hole pressure data, which can reveal the interaction and influence between the cracks; the oil and gas flow state is identified on the oil and gas characteristic data according to the boundary crack relationship data, which can identify the flow state of oil and gas in the crack network; the oil and gas non-steady-state capacity index is calculated on the standard fracturing horizontal well data through the oil and gas flow state data, which can provide the dynamic change information of oil and gas production; the non-steady-state capacity prediction model is constructed by using the oil and gas non-steady-state capacity index to obtain the non-steady-state capacity prediction model; the non-steady-state capacity prediction is performed on the standard fracturing horizontal well data based on the non-steady-state capacity prediction model, and the non-steady-state capacity prediction report is generated. Therefore, the present invention realizes the identification of the mutual relationship between the bottom hole pressure and the boundary crack characteristics through data processing technology, pattern recognition technology, and deep learning technology; and realizes the oil and gas flow state detection of the oil and gas characteristics according to the boundary crack relationship, thereby improving the accuracy of the non-steady-state capacity prediction.

[0053] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0054] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well, characterized in that: The following steps are involved: Step S1: collecting data from closed boundary fractured horizontal wells to generate fractured horizontal well data; preprocessing the fractured horizontal well data to obtain standard fractured horizontal well data; Step S2: performing closed boundary fracturing feature recognition on the standard fracturing horizontal well data to obtain closed boundary fracturing data; performing crack feature extraction on the closed boundary fracturing data to generate boundary crack feature information; performing fracturing porosity determination on the standard fracturing horizontal well data according to the boundary crack feature information to obtain fracturing porosity data; performing oil and gas feature simulation on the standard fracturing horizontal well data based on the boundary crack feature information and the fracturing porosity data to generate oil and gas feature data; Step S3: extracting fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identifying wellbore position of standard fractured horizontal well data according to boundary fracture parameter information to obtain wellbore position data; associating and mapping boundary fracture parameter information with wellbore position data to generate fracture wellbore associated data; measuring bottom hole pressure of standard fractured horizontal well data based on fracture wellbore associated data to obtain bottom hole pressure data; Step S4: perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state on oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index on standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

2. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing nonlinear feature decomposition on standard fracturing horizontal well data to generate nonlinear fracturing horizontal well features; performing fracturing feature enhancement on the nonlinear fracturing horizontal well features to obtain fracturing feature enhancement data; performing closed boundary fracturing feature extraction on the fracturing feature enhancement data to obtain closed boundary fracturing data; Step S22: extracting fracturing morphological features from closed boundary fracturing data to generate fracturing morphological feature data; quantifying geometric features from standard fracturing horizontal well data to obtain fracturing morphological geometric features; identifying fracture features from fracturing morphological geometric features to generate boundary fracture feature information; Step S23: determining the distribution range of the boundary crack feature information to obtain the boundary crack distribution range; identifying the crack space distribution characteristics of the boundary crack distribution range to generate the crack space distribution characteristics; performing crack space distribution morphological characteristics on the fracturing morphological geometric characteristics according to the crack space distribution characteristics to obtain the crack space distribution morphological characteristics; Step S24: Calculate the fracture density of the fracture space distribution morphology to generate fracture space density data; perform fracturing pore characteristics on the boundary fracture feature information based on the fracture space density data to obtain fracturing pore characteristics; perform fracturing porosity measurement on the standard fracturing horizontal well data through the fracturing pore characteristics to obtain fracturing porosity data; Step S25: Perform porosity gradient division on the fracturing porosity data to generate porosity gradient data; perform oil and gas characteristic simulation on the standard fracturing horizontal well data based on the porosity gradient data and boundary fracture characteristic information to generate oil and gas characteristic data.

3. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing fracture geometric feature recognition on the boundary fracture feature information to generate fracture geometric feature data; performing fracture geometric parameter extraction on the fracture geometric feature data according to the oil and gas feature data to obtain fracture geometric parameters; Step S32: performing fracture connectivity detection on the boundary fracture characteristic information by using fracture geometric parameters to generate fracture connectivity data; performing fracture permeability evaluation on the boundary fracture characteristic information based on the fracture connectivity data to obtain fracture permeability data; performing fracture fluid flow simulation on the oil and gas characteristic data according to the fracture permeability data to obtain fracture fluid flow simulation data; Step S33: Integrate the fracture connectivity data, fracture permeability data and fracture fluid flow simulation data to obtain boundary fracture parameter information; perform wellbore feature recognition on the standard fracturing horizontal well data to generate wellbore feature data; perform wellbore position detection on the wellbore feature data according to the boundary fracture parameter information to obtain wellbore position data; Step S34: associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of the standard fracturing horizontal well data based on the fracture wellbore associated data to obtain the bottom hole pressure data.

4. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 3, characterized in that: Step S34 includes the following steps: Step S341: quantifying the connectivity of the fracture connectivity data to obtain fracture connectivity quantitative data; associating the fracture connectivity quantitative data with the wellbore position data to generate fracture wellbore connectivity association data; Step S342: performing permeability parameterization on the fracture permeability data to obtain fracture permeability parameterized data; performing fracture permeability correlation on the fracture permeability parameterized data and the wellbore position data to generate fracture wellbore permeability correlation data; Step S343: extracting flow characteristics of fracture fluid flow simulation data to obtain fracture fluid flow characteristic data; correlating the fracture fluid flow characteristic data with wellbore position data to generate fracture wellbore fluidity correlation data; Step S344: Integrate the fracture wellbore connectivity correlation data, the fracture wellbore permeability correlation data and the fracture wellbore fluidity correlation data to obtain the fracture wellbore correlation data; Step S345: measuring the bottom hole pressure of the standard fractured horizontal well data based on the fracture wellbore correlation data to obtain the bottom hole pressure data.

5. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 4, characterized in that: Step S345 includes the following steps: Step S3451: extracting the bottom hole stress characteristics of the standard fractured horizontal well data based on the fracture wellbore correlation data to generate the bottom hole stress characteristics; simulating the bottom hole pressure distribution of the standard fractured horizontal well data according to the bottom hole stress characteristics to obtain the bottom hole pressure distribution simulation data; Step S3452: performing bottom hole pressure response identification on the bottom hole pressure distribution simulation data to generate bottom hole pressure response data; performing pressure numerical calculation on the bottom hole pressure response data to obtain bottom hole pressure numerical information; performing pressure gradient division on the bottom hole pressure numerical information to generate bottom hole pressure gradient data; Step S3453: performing real-time bottom hole pressure monitoring on the bottom hole pressure distribution simulation data through the bottom hole pressure gradient data to obtain bottom hole pressure change data; performing bottom hole pressure state identification on the bottom hole pressure change data to generate bottom hole pressure state information; Step S3454: perform bottom hole pressure anomaly detection on the bottom hole pressure status information to obtain bottom hole pressure anomaly data; perform pressure stability evaluation on the bottom hole pressure distribution simulation data based on the bottom hole pressure anomaly data to obtain bottom hole pressure stability data; perform bottom hole pressure measurement on the standard fracturing horizontal well data based on the bottom hole pressure stability data to obtain bottom hole pressure data.

6. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; Step S42: identifying the oil and gas flow state of the oil and gas characteristic data according to the boundary fracture relationship data to obtain the oil and gas flow state data; Step S43: calculating the oil and gas non-steady-state production capacity index for the standard fractured horizontal well data by using the oil and gas flow state data to generate the oil and gas non-steady-state production capacity index; Step S44: constructing a non-steady-state capacity prediction model according to the oil and gas non-steady-state capacity index to obtain a non-steady-state capacity prediction pre-model; and training the non-steady-state capacity prediction pre-model using the oil and gas non-steady-state capacity index to obtain a non-steady-state capacity prediction training model; Step S45: performing a model cross-validation evaluation on the non-steady-state capacity prediction training model to obtain model evaluation data; adjusting model parameters of the non-steady-state capacity prediction training model using the model evaluation data to obtain a non-steady-state capacity prediction model; Step S46: Perform non-steady-state capacity prediction on the standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

7. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 6, characterized in that: Step S41 includes the following steps: Step S411: extracting the pressure distribution characteristics of the bottom hole pressure data to obtain the bottom hole pressure distribution characteristics; identifying the pressure peak area of ​​the bottom hole pressure distribution characteristics to generate the bottom hole pressure peak area; Step S412: Identify the fracture concentration area of ​​the boundary fracture characteristic information according to the fracture space density data to obtain the boundary fracture concentration area; map and match the boundary fracture concentration area with the bottom hole pressure peak area to generate fracture pressure mapping data; Step S413: Calculate the degree of fracture pressure influence on the bottom hole pressure data through the fracture pressure mapping data to obtain fracture pressure influence data; perform fracture sensitivity measurement on the boundary fracture characteristic information according to the fracture pressure influence data to generate fracture sensitivity data; Step S414: using the fracture connectivity data to extract boundary fracture constraint features from the fracture sensitivity data to obtain boundary fracture constraint action data; using the fracture permeability data to extract boundary fracture permeability synergistic features from the boundary fracture constraint action data to generate boundary fracture synergistic action data; based on the boundary fracture constraint action data and the boundary fracture synergistic action data, boundary fracture mutual coupling identification is performed on the boundary fracture feature information to obtain boundary fracture relationship data.

8. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 6, characterized in that: Step S42 includes the following steps: Step S421: performing fracture-oil and gas flow effect correspondence on the oil and gas characteristic data according to the boundary fracture relationship data to obtain fracture-oil and gas flow effect data; Step S422: marking the oil and gas characteristic data for oil and gas flow characteristics to generate oil and gas flow marking data; dividing the oil and gas characteristic data into flow units according to the oil and gas flow marking data to obtain flow unit division data; extracting flow characteristics from the flow unit division data to generate oil and gas flow characteristic data; Step S423: constructing a fracture oil and gas flow network for the oil and gas flow characteristic data based on the fracture-oil and gas flow action data to obtain a fracture oil and gas flow network; identifying the oil and gas flow path for the fracture oil and gas flow network to generate oil and gas flow path data; and calculating the oil and gas flow flow rate for the fracture oil and gas flow network based on the oil and gas flow path data to obtain oil and gas flow flow rate data; Step S424: performing flow state abnormality detection on the fracture oil and gas flow network through the oil and gas flow direction flow data to generate oil and gas flow state abnormality data; performing flow state stability evaluation on the fracture oil and gas flow network to obtain flow state stability data; Step S425: Integrate the oil and gas flow direction flow data, the oil and gas flow state abnormality data and the flow state stability data to obtain the oil and gas flow state data.

9. The method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 6, characterized in that: Step S43 includes the following steps: Step S431: performing unit oil and gas volume statistics on the oil and gas flow data to obtain unit oil and gas volume data; performing instantaneous oil and gas production calculation on the unit oil and gas volume data to generate instantaneous oil and gas production data; Step S432: Identify the abnormal state type of the abnormal oil and gas flow state data to obtain the abnormal flow state type; record the abnormal instantaneous production of the instantaneous oil and gas production data according to the abnormal flow state type to generate abnormal state instantaneous production data; accumulate the oil and gas production of the abnormal state instantaneous production data to obtain abnormal state cumulative production data; Step S433: recording the instantaneous oil and gas production data in a stable state based on the flow state stability data to generate the instantaneous production data in a stable state; accumulating the oil and gas production in the instantaneous production data in a stable state to obtain the cumulative production data in a stable state; Step S434: Subtract the production value of the steady-state cumulative production data from the abnormal-state cumulative production data to obtain the oil and gas non-steady-state production capacity index.

10. A device for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well, characterized in that: A prediction system is included for executing the method for predicting the non-steady-state production capacity of a closed boundary fractured horizontal well according to claim 1, the prediction system comprising: The data acquisition module is used to collect data from closed boundary fractured horizontal wells to generate fractured horizontal well data; pre-process the fractured horizontal well data to obtain standard fractured horizontal well data; The boundary fracturing oil and gas simulation module is used to identify the closed boundary fracturing characteristics of the standard fracturing horizontal well data to obtain the closed boundary fracturing data; extract the crack characteristics of the closed boundary fracturing data to generate the boundary crack characteristic information; determine the fracturing porosity of the standard fracturing horizontal well data according to the boundary crack characteristic information to obtain the fracturing porosity data; simulate the oil and gas characteristics of the standard fracturing horizontal well data based on the boundary crack characteristic information and the fracturing porosity data to generate the oil and gas characteristic data; The fracturing horizontal well bottom pressure measurement module is used to extract fracture parameters from boundary fracture characteristic information through oil and gas characteristic data to obtain boundary fracture parameter information; identify the wellbore position of standard fracturing horizontal well data according to the boundary fracture parameter information to obtain wellbore position data; associate and map the boundary fracture parameter information with the wellbore position data to generate fracture wellbore associated data; and measure the bottom hole pressure of standard fracturing horizontal well data based on the fracture wellbore associated data to obtain bottom hole pressure data; The oil and gas non-steady-state capacity index calculation module is used to perform boundary fracture mutual coupling analysis on boundary fracture characteristic information according to bottom hole pressure data to generate boundary fracture relationship data; identify oil and gas flow state of oil and gas characteristic data according to boundary fracture relationship data to obtain oil and gas flow state data; calculate oil and gas non-steady-state capacity index of standard fractured horizontal well data through oil and gas flow state data to generate oil and gas non-steady-state capacity index; construct a non-steady-state capacity prediction model using oil and gas non-steady-state capacity prediction model; perform non-steady-state capacity prediction on standard fractured horizontal well data based on the non-steady-state capacity prediction model to generate a non-steady-state capacity prediction report.

Images