Coal rock gas reservoir fracturing flowback fluid prediction method and device

Abstract

This invention discloses a method and apparatus for predicting fracturing flowback fluid in coal-rock gas reservoirs. The method includes: constructing a fracturing fluid flowback data matrix; obtaining a flowback fluid volume per unit length data matrix based on the fracturing fluid flowback data matrix, wherein the flowback fluid volume per unit length data matrix represents the flowback fluid volume per unit length of each coal-rock gas well in each effective production day; determining standard curve data for each effective production day in the flowback fluid volume per unit length data matrix; fitting a standard curve based on the standard curve data; and predicting flowback fluid volume using the standard curve. This invention uses a flowback fluid volume per unit length index and a dynamic median-average algorithm to continuously utilize fracturing fluid flowback data from already-produced wells to obtain standard water production curves for coal-rock gas wells. It then uses these standard water production curves to predict future fracturing flowback fluid volumes from already-produced wells in batches, providing a basis for fracturing fluid reuse and hydraulic fracturing implementation planning.

Description

Technical Field

[0001] This invention relates to the field of coal gas development technology, and in particular to a method and apparatus for predicting hydraulic flowback fluid in coal gas reservoirs. Background Technology

[0002] Coal shale gas is a hydrocarbon gas generated by medium- to high-rank coal or transported from other gas sources within coal reservoirs. Through reservoir stimulation, it can be rapidly produced and extracted on a large scale. Similar to shale gas development, coal shale gas development typically requires horizontal wells and volumetric fracturing to establish "artificial oil and gas reservoirs" for industrial development. Single wells are characterized by high initial production, rapid decline rates, and long periods of stable low-production. Horizontal well staged fracturing reservoir stimulation technology is one of the two key technologies for achieving large-scale shale gas development. It typically utilizes packers or bridge plugs to perform staged fracturing, creating multiple fractures within the horizontal wellbore, thereby effectively stimulating the reservoir and increasing single-well production. The different hydrocarbon generation, pore structure, permeability, and mechanical properties of coal reservoirs of different ranks determine their different development methods. Taking the high-rank coal-gas resources on the eastern edge of the Ordos Basin as an example, the coal reservoirs have good structure, high brittleness index, and strong roof and floor shielding. A multi-stage fracturing process mode for horizontal wells, characterized by "ultra-large discharge capacity + ultra-large fluid volume + ultra-high sand volume + rapid flowback," has been gradually developed. This effectively improves reservoir connectivity, maximizes reserve control, and allows gas wells to be extracted based on formation energy depletion. However, the "ultra-large fluid volume" staged fracturing development mode for horizontal wells consumes a large amount of water resources, typically ranging from tens of thousands to hundreds of thousands of cubic meters of fracturing fluid per well, leading to water consumption and environmental problems.

[0003] In order to effectively reduce water consumption, the common practice is to reuse fracturing fluid. The fracturing fluid returned from production wells is treated and reused. This not only saves a lot of water consumption, but also further reduces development costs.

[0004] Therefore, dynamic real-time prediction of the flowback fluid volume of gas wells, well groups, well areas, blocks, and the overall gas reservoir during the large-scale development of coal-rock gas reservoirs can provide a data basis for the overall development optimization of gas reservoirs, maximize the reuse of gas well flowback fluid, and thus achieve the goal of reducing water resource consumption and development costs, and improving development efficiency. Summary of the Invention

[0005] This invention provides a method and apparatus for predicting fracturing flowback fluid in coal and rock gas reservoirs, which can predict fracturing flowback fluid in coal and rock gas reservoirs.

[0006] According to one aspect of the present invention, a method for predicting fracturing flowback fluid in coal and rock gas reservoirs is provided, comprising:

[0007] A fracturing fluid flowback data matrix is ​​constructed, which represents the flowback fluid volume of each coal gas well in each effective production day; the fracturing fluid flowback data matrix is ​​obtained from the fracturing fluid flowback fluid volume data of the coal gas wells that have been put into production in each effective production day;

[0008] Based on the fracturing fluid flowback data matrix, a flowback fluid volume data matrix per unit length is obtained, wherein the flowback fluid volume per unit length of each coal and gas well is represented in each effective production day.

[0009] Determine the standard curve data for each effective production day in the unit segment length return liquid volume data matrix;

[0010] A standard curve is fitted based on the standard curve data, and the backflow fluid is predicted using the standard curve.

[0011] Optionally, constructing the fracturing fluid flowback data matrix includes:

[0012] Obtain fracturing fluid flowback data for each of the coal and gas wells on different natural days;

[0013] The effective production days are determined based on the dates during which wells are not shut in within the natural days, and zero values ​​in the fracturing fluid flowback data are removed and continuously processed.

[0014] The fracturing fluid flowback data is aligned based on the effective production days, and the fracturing fluid flowback data matrix is ​​constructed using the longest effective production time of each coal and gas well.

[0015] Optionally, obtaining the flowback fluid volume data matrix per unit length based on the fracturing fluid flowback data matrix includes:

[0016] Divide each fracturing fluid flowback data in the fracturing fluid flowback data matrix by the length of the fracturing section of the corresponding coal-rock gas well to obtain the flowback fluid volume data matrix per unit section length.

[0017] Optionally, determining the standard curve data for each effective production day in the unit segment length return liquid volume data matrix includes:

[0018] Determine the number of valid data points for each valid production day in the unit segment length return liquid volume data matrix;

[0019] The data selection interval for each effective production day is determined based on the number of effective samples, and the average value of the effective data within the data selection interval is used as the standard curve data for each effective production day.

[0020] Optionally, the step of determining the data selection interval for each effective production day based on the number of effective samples, and using the average value of the effective data within the data selection interval as the standard curve data for each effective production day, includes:

[0021] Divide the numerical ranges of different valid data, and set a first correspondence between each numerical range and the dynamic median average, and a second correspondence between each numerical range and the data selection range;

[0022] Based on the target value range in which the number of valid data for each valid production day falls, the target dynamic median average value for each valid production day is determined according to the first correspondence.

[0023] Based on the second correspondence, the target data selection interval for each effective production day is determined, and the standard curve data for each effective production day is determined based on the effective data within the target data selection interval and the target dynamic median average.

[0024] Optionally, fitting a standard curve based on the standard curve data includes:

[0025] The standard curve data is fitted using at least one alternative curve fitting prediction model, and the coefficient of determination and the adjusted coefficient of determination are determined. The alternative curve fitting prediction model with the highest coefficient of determination and the adjusted coefficient of determination is taken as the target curve fitting prediction model.

[0026] Based on the preset production time upper limit, the standard curve data is fitted using the target curve fitting prediction model to obtain the standard curve.

[0027] Optionally, the prediction of flowback fluid using the standard curve includes:

[0028] Determine the category of the target coal and gas well to be predicted;

[0029] Based on the categories and corresponding fitting rules, the flowback volume of the target coal and rock gas well is predicted using the standard curve.

[0030] According to another aspect of the present invention, a device for predicting fracturing flowback fluid in coal and rock gas reservoirs is provided, comprising:

[0031] The first matrix determination unit is used to construct a fracturing fluid flowback data matrix, which represents the flowback fluid volume of each coal gas well in each effective production day; the fracturing fluid flowback data matrix is ​​obtained from the fracturing fluid flowback fluid volume data of the coal gas wells that have been put into production in each effective production day;

[0032] The second matrix determination unit is used to obtain a unit segment length flowback fluid volume data matrix based on the fracturing fluid flowback data matrix, wherein the unit segment length flowback fluid volume data matrix represents the unit segment length flowback fluid volume of each coal gas well in each effective production day.

[0033] A standard curve data determination unit is used to determine the standard curve data for each effective production day in the unit segment length return liquid volume data matrix.

[0034] The standard curve fitting unit is used to fit a standard curve based on the standard curve data, and to predict the backflow liquid using the standard curve.

[0035] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0036] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the coal and rock gas reservoir fracturing flowback fluid prediction method according to any embodiment of the present invention.

[0037] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the coal and rock gas reservoir fracturing flowback fluid prediction method according to any embodiment of the present invention.

[0038] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the method for predicting hydraulic flowback fluid in coal and rock gas reservoirs according to any embodiment of the present invention.

[0039] The technical solution of this invention uses the unit section length flowback fluid volume index and dynamic median average algorithm to continuously utilize the fracturing fluid flowback data of already produced wells to obtain the standard water production curve of coal and rock gas wells. The standard water production curve is then used to predict the future fracturing flowback fluid volume of already produced wells in batches, providing a basis for the reuse of fracturing fluid and the implementation of hydraulic fracturing.

[0040] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a method for predicting flowback fluid in fracturing of coal-rock gas reservoirs provided in Embodiment 1 of the present invention;

[0043] Figure 2 This is a schematic diagram illustrating the calculation of standard curve data applicable to Embodiment 1 of the present invention;

[0044] Figure 3 This is a schematic diagram of a standard curve fitting method applicable to Embodiment 1 of the present invention;

[0045] Figure 4 This is a schematic diagram of a fitting and prediction method for a continuous smooth standard curve applicable to Embodiment 1 of the present invention;

[0046] Figure 5 This is a schematic diagram of the structure of a coal and rock gas reservoir fracturing flowback fluid prediction device provided in Embodiment 2 of the present invention;

[0047] Figure 6 This is a schematic diagram of the electronic device used to implement the method for predicting flowback fluid from fracturing in coal and rock gas reservoirs according to embodiments of the present invention. Detailed Implementation

[0048] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0049] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0050] Example 1

[0051] Figure 1 This is a flowchart of a method for predicting fracturing flowback fluid in coal and rock gas reservoirs according to Embodiment 1 of the present invention. This embodiment is applicable to the prediction of fracturing flowback fluid in coal and rock gas reservoirs. This method can be executed by a coal and rock gas reservoir fracturing flowback fluid prediction device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0052] S110. Construct a fracturing fluid flowback data matrix. The fracturing fluid flowback data matrix represents the flowback fluid volume of each coal and gas well in each effective production day. The fracturing fluid flowback data matrix is ​​obtained from the fracturing fluid flowback fluid volume data of the coal and gas wells that have been put into production in each effective production day.

[0053] Data on fracturing fluid flowback from operational coal and gas wells is collected. Simultaneously, labels are added to the wells indicating their oilfield company, reservoir, block, well area, well group, well type, and year of commissioning. This facilitates subsequent iterative calculations and standard curve fitting based on predetermined attributes. Dynamic production data for a single coal and gas well typically includes date, daily gas production, flowback fluid volume, oil pressure, casing pressure, and transmission pressure. This embodiment uses date and flowback fluid volume data for coal and gas wells. Dynamic production data is typically acquired using a data platform and real-time data acquisition methods to ensure the frequency and quality of data updates. Typical production curves for coal and gas wells are usually calculated based on dimensions such as oilfield company, reservoir, block, well area, well group, and well type.

[0054] In this embodiment of the invention, constructing a fracturing fluid flowback data matrix includes:

[0055] Obtain fracturing fluid flowback data for each coal gas well on different natural days;

[0056] Valid production days are determined based on the dates during which wells are not shut in, and zero values ​​in the fracturing fluid flowback data are removed and processed continuously.

[0057] The fracturing fluid flowback data were aligned based on the effective production days, and a fracturing fluid flowback data matrix was constructed based on the longest effective production time of each coal and gas well.

[0058] Standard curves are typically derived from daily fracturing fluid flowback data of coal and rock gas wells. Daily data usually consists of the calendar date and flowback fluid volume. However, in actual production, wells are shut down due to workover and other process measures, resulting in zero flowback fluid volume for calendar dates. Fracturing fluid flowback data processing converts calendar dates to actual production days, removes zero values ​​due to well shutdowns, and performs continuous processing on the flowback fluid data. After data preprocessing, fracturing fluid flowback data from all sample wells in the database are aligned using the longest effective production time (t) of all coal and rock gas wells in the sample database. max To ensure accuracy, a fracturing fluid flowback data matrix is ​​constructed. The first row of the data matrix represents the effective production time, and zeroing is applied to gas wells with insufficient effective production time. The constructed fracturing fluid flowback data matrix is ​​shown in the following formula:

[0059]

[0060] In equation (1), t max The longest effective production time of coal-rock gas wells in the sample database is d; Let m be the daily fluid production of the nth well in the sample database at time t. 3 / d.

[0061] S120. Based on the fracturing fluid flowback data matrix, a flowback fluid volume data matrix per unit length is obtained. The flowback fluid volume data matrix per unit length represents the flowback fluid volume per unit length of each coal and gas well in each effective production day.

[0062] In this embodiment of the invention, a flowback volume data matrix per unit length is obtained based on the fracturing fluid flowback data matrix, including:

[0063] Divide each fracturing fluid flowback data in the fracturing fluid flowback data matrix by the length of the fracturing section of the corresponding coal-rock gas well to obtain the flowback fluid volume data matrix per unit section length.

[0064] The fracturing fluid flowback data matrix and the fracturing section length of the gas well are used to calculate the flowback fluid volume per unit section length, as shown in Equation (2). Finally, the daily fracturing fluid flowback data matrix per unit fracturing section length is obtained as shown in Equation (3).

[0065]

[0066] In equations (2) and (3), Let m be the actual fracturing section length of the nth well in the database; Let m be the flow-back fluid volume per unit fracturing section length corresponding to time t in the nth well in the database. 3 / (d·m).

[0067] S130. Determine the standard curve data for each effective production day in the unit section length return liquid volume data matrix.

[0068] In this embodiment of the invention, the number of valid data for each valid production day in the unit section length return liquid volume data matrix is ​​determined;

[0069] The data selection interval for each effective production day is determined based on the number of valid samples, and the average value of the valid data within the data selection interval is used as the standard curve data for each effective production day.

[0070] Standard curve data is an important foundation for data-driven methods of predicting flowback fluid in coal and gas reservoirs. It is obtained by processing and analyzing daily flowback fluid data per unit fracturing section length and is used to construct a standard curve that reflects the variation law of flowback fluid volume in coal and gas wells, providing a key basis for subsequent flowback fluid volume prediction.

[0071] The standard curve data of fracturing flowback fluid is obtained by using the daily data matrix of fracturing flowback fluid per unit fracturing section length. Specifically, the calculation method is to calculate the dynamic median average of all valid daily data (non-zero data) of fracturing flowback fluid per unit fracturing section length for each day, and then obtain the corresponding standard curve data.

[0072] In this embodiment of the invention, the data selection interval for each effective production day is determined based on the number of effective samples, and the average value of the effective data within the data selection interval is used as the standard curve data for each effective production day, including:

[0073] Divide the numerical intervals of different valid data, and set a first correspondence between each numerical interval and the dynamic median average, and a second correspondence between each numerical interval and the data selection interval;

[0074] Based on the target value range where the number of valid data for each valid production day falls, the target dynamic median average value for each valid production day is determined according to the first correspondence relationship.

[0075] Based on the second correspondence, the target data selection interval for each effective production day is determined, and the standard curve data for each effective production day is determined based on the effective data within the target data selection interval and the average of the target dynamic median.

[0076] Specifically, the dynamic median mean is calculated by sorting the fracturing flowback fluid volume per unit fracturing section length of all sample wells corresponding to a given production time, and then calculating it based on the number of valid samples (S). tThe final number of valid samples is calculated (as shown in Formula 4 below). Finally, the corresponding number of samples is taken from the middle of the sorted data of the flowback fluid volume per unit fracturing section length, and the arithmetic mean is calculated as the standard curve data. This method can not only remove outlier data in the flowback fluid volume per unit fracturing section length at a given time, but also make use of more sample data to obtain the standard curve data. Figure 2 This is a schematic diagram illustrating the calculation of standard curve data applicable to Embodiment 1 of the present invention.

[0077]

[0078] In equation (4), is the number of valid samples selected for the final dynamic median average calculation, which is dimensionless; the content in parentheses represents the numerical range of valid data. For example, if the number of valid data, St, is 30, then in equation (4), it falls within the range of 20-100 (excluding 100). In equation (4), the coefficient before the numerical range is used to reflect the first correspondence. Taking St as an example of 30, multiplying it by the coefficient 0.5 yields the dynamic median average of 15.

[0079]

[0080] Equation (5) is the formula for calculating the dynamic median average. The data for the flowback fluid per unit fracturing section length at time t is calculated based on the dynamic median average. (m) 3 / (d·m). The second correspondence refers to selecting a range based on the numerical interval and its corresponding valid data. For example, when the number of valid data is 20≤S t When P < 100, 25 ~P 75 The standard curve data is obtained by using the arithmetic mean of the sample data in the interval (i.e., the 25th to the 75th data point) as the dynamic median mean; when the number of valid data points is 100 ≤ S t When <200, P 20 ~P 70 The standard curve data is obtained by using the arithmetic mean of the sample data in the interval as the dynamic median mean; when the number of valid data is 200 ≤ S t When P < 400, 15 ~P 75 The standard curve data is obtained by using the arithmetic mean of the interval sample data as the dynamic median mean; when the number of valid data is 400 ≤ S t When <800, P 10 ~P 90 The standard curve data is obtained by using the arithmetic mean of the interval sample data as the dynamic median mean; when the number of valid data S t When ≥800, P5~P 95The standard curve data is obtained by using the arithmetic mean of the interval sample data as the dynamic median mean.

[0081] Since the calculation of standard curve data is affected by the sample size and statistical method, the fracturing flowback fluid volume per unit fracturing section length obtained in equation (5) needs to be truncated and equivalently corrected. Because the production time of the sample gas wells is different, the number of effective production days of a given gas well on a given date varies, and the sample size in the standard curve data matrix shows a gradually decreasing trend. Therefore, the typical curve data needs to be truncated according to the sample size. In this embodiment of the invention, the sample size is preferably 20. Standard curve data with fewer than 20 samples are cleared, and the final standard curve data is obtained after data truncation, as shown in equation (6) below:

[0082]

[0083] S140. Fit a standard curve based on the standard curve data, and use the standard curve to predict the backflow liquid.

[0084] In this embodiment of the invention, fitting a standard curve based on standard curve data includes:

[0085] The standard curve data is fitted using at least one alternative curve fitting prediction model. The coefficient of determination and the adjusted coefficient of determination are determined after fitting. The alternative curve fitting prediction model with the highest coefficient of determination and the adjusted coefficient of determination is taken as the target curve fitting prediction model.

[0086] Based on the preset production time limit, the standard curve data is fitted by the target curve fitting prediction model to obtain the standard curve.

[0087] The flowback fluid volume of fracturing in coal-rock gas wells is characterized by large initial flowback volume, rapid decline rate, and small flowback volume over a long period. The standard data of flowback fluid volume per unit fracturing section length obtained in equation (6) are fitted. Since coal-rock gas is in its initial development stage, the actual production time of the wells in the sample database is generally short. Based on the fitting of the standard curve data, prediction is needed to obtain the final full-lifecycle standard curve of flowback fluid volume per unit fracturing section length. The obtained curves are fitted and predicted using the formulas ExpGro3, Boltzmann, Logistic5, ExpDec3, ExpDecay3, and HyperbolaGen. The model is optimized based on the fitting accuracy to obtain the final standard curve.

[0088] ExpGro3 formula:

[0089] Boltzmann formula:

[0090] Logistic5 model:

[0091] ExpDec3 formula:

[0092] ExpDecay3 formula:

[0093] HyperbolaGen formula:

[0094] In the above formulas, A1, A2, A3, A4, A5, A6, and A7 are dimensionless constants in the ExpGro3 fitting formula; B1, B2, B3, and B4 are dimensionless constants in the Boltzmann fitting formula; C1, C2, C3, C4, and C5 are dimensionless constants in the Logistic5 fitting formula; D1, D2, D3, D4, D5, D6, and D7 are dimensionless constants in the ExpDec3 fitting formula; E1, E2, E3, E4, E5, E6, E7, and E8 are dimensionless constants in the ExpDec3 fitting formula; and F1, F2, F3, and F4 are dimensionless constants in the HyperbolaGen fitting formula.

[0095] Figure 3 This is a schematic diagram of a standard curve fitting method applicable to Embodiment 1 of the present invention. Figure 4 This is a schematic diagram of a fitting prediction of a continuous smooth standard curve applicable to Embodiment 1 of the present invention. During the fitting process of fracturing flowback fluid data per unit fracturing section length, the fitting accuracy control parameters are the coefficient of determination and the adjusted coefficient of determination. The formula with the highest coefficient of determination and the adjusted coefficient of determination is preferred for interpolation extrapolation prediction. Attention is paid especially to the fitting accuracy of the final segment of the standard curve data during the fitting process. Where is the actual observed value; is the regression predicted value; is the average of all actual observed values; k is the number of data points in the dataset; and is the number of independent variables (including the constant term) in the regression equation. After determining the optimal fitting formula, extrapolation prediction is performed to obtain a continuous smooth standard curve of fracturing fluid flowback per unit fracturing section length corresponding to a production time of 1–6600 days (6600 days is a conventional upper limit of production time). This curve is used for iterative prediction of fracturing flowback fluid volume. The coefficient of determination, the adjusted coefficient of determination, and the continuous smooth standard curve of fracturing fluid flowback per unit fracturing section length from 1 to 6600 days are shown in the following formula.

[0096] Coefficient of determination (R-Square(COD)):

[0097] Adjusted coefficient of determination (Adj. R-Square):

[0098] In this embodiment of the invention, predicting backflow fluid using a standard curve includes:

[0099] Determine the category of the target coal and gas well to be predicted;

[0100] Based on the category and the corresponding fitting rules, the flowback volume of the target coal and rock gas well is predicted using a standard curve.

[0101] Currently, the prediction of recoverable reserves in a single coal-rock gas well mainly draws on the prediction methods for unconventional natural gas such as shale gas. By fitting standard curve data and interpolating extrapolation, a set of continuous daily data on the flowback fluid volume per unit fracturing section length can be obtained. Using standard curve data, the flowback fluid volume data of wells already in production, deployed wells (wells under drilling, completed wells, and fracturing wells), and planned wells can be predicted.

[0102] 1. Prediction of fluid return from wells already in production.

[0103] Zero-value data on daily flowback fluid volume from already operational wells is removed to generate continuous single-well daily flowback fluid volume data. Future daily flowback fluid volume is predicted based on the cumulative flowback volume, effective production time, and a continuously smoothed standard curve of daily flowback fluid volume per unit fracture section length from already operational wells. Given a database, multiple continuously smoothed standard curves of daily flowback fluid volume per unit fracture section length with different dimensions may exist. Typically, the standard curve data with the smallest dimension belonging to the gas well is selected first for predicting daily flowback fluid volume. For example, if a gas well's tag includes standard curve data for oilfield company, gas reservoir, block, and well area, then the standard curve data for daily flowback fluid volume per unit fracture section length of the corresponding well area is selected first for prediction. Predicted daily flowback fluid volume for already operational wells:

[0104]

[0105] in, The effective production leave after clearing the "zero value" data of the daily flowback fluid volume of the nth well put into production is d; Let m be the predicted future daily flowback fluid volume for the nth well. 3 / d; m is the daily flowback volume per unit fracturing section on day t, obtained after fitting and predicting standard curve data. 3 / (d·m); The first one obtained after fitting and predicting the standard curve data. Daily flowback fluid volume per unit length of fracturing section per day, m 3 / (d·m). By fitting continuous smooth standard unit fracturing section length daily flowback fluid volume data, the future daily flowback fluid volume of wells already in production can be predicted in a rolling manner.

[0106] 2. Prediction of fluid return from deployed wells:

[0107] For a given oilfield company, gas reservoir, block, and well area, the deployed wells need to be further subdivided into wells currently being drilled, wells completed, and fracturing wells for prediction:

[0108] Drilling in progress:

[0109] Drilling completed:

[0110] Fracturing wells:

[0111]

[0112] in, To predict the daily flowback volume of fracturing fluid during well drilling, m 3 / d; To predict the daily flowback volume of fracturing fluid in well drilling, m 3 / d; To predict the daily flowback volume of fracturing fluid in a fracturing well, m 3 / d;L Design The design length of the horizontal section for drilling is given in meters (m); L Drilled The actual horizontal section length is in meters (m); L F R is the length of the horizontal section of the fracturing process, in meters (m); D-F The average horizontal section length fracturing utilization rate refers to the average horizontal section length fracturing utilization rate of all production wells in the sample library, which is dimensionless. Let n be the actual length of the fractured section in the nth well, in meters. Let be the actual horizontal section length of the nth well, in meters.

[0113] 3. Prediction of well flowback volume in planning and deployment.

[0114] In actual development, rolling development plans are continuously formulated for a given oilfield company, gas reservoir, block, or well area, and a large number of gas wells are deployed according to the plans. The daily flowback volume of the planned wells can be predicted based on the planned horizontal section length. At the same time, the predicted daily flowback volume of fracturing fluid is summarized by combining the minimum dimension well construction cycle, drilling cycle, waiting period for fracturing, and fracturing cycle.

[0115] Planned deployment wells:

[0116] in, To predict the daily flowback volume of fracturing fluid for well planning and deployment, m 3 / d;L P The length of the horizontal section of the well is determined by the planned deployment design, in meters (m).

[0117] Furthermore, the main purpose of the rolling iterative prediction of fracturing flowback fluid volume in coal and rock gas wells is to grasp the future flowback fluid volume of the platform, well area, block, gas reservoir, oilfield company, or basin in real time, optimize the design based on the predicted flowback fluid volume to maximize the full reuse of fracturing flowback fluid volume, and at the same time, grasp the water resource preparation volume based on the reuse of fracturing flowback fluid volume, and continuously optimize the implementation arrangement of fracturing measures. Equation (22) gives the matrix of daily fracturing fluid flowback volume of production wells, deployed wells (drilled wells, completed wells, and fracturing wells), and planned deployment wells, where t A This refers to the current prediction time, d; T D For drilling cycles, d; T AF For coal and gas platform well group development, fracturing measures can usually be implemented only after the wellhead or half of the platform has been fully drilled. Therefore, there is a waiting period for fracturing after the well is completed; T F For fracturing cycle, d; T P Given the planning and deployment period of an oil and gas field company, reservoir, block, well area, or well group, d. The future daily fracturing fluid flowback volume for a given oil and gas field company, reservoir, block, well area, or well group can be obtained by superimposing the predicted future daily fracturing fluid flowback volumes of producing wells, drilling wells, completed wells, fractured wells, and planned wells, as shown in the following formula: R W The well opening rate is the actual fracturing fluid flowback volume prediction process, which needs to take into account the gas well production rate. The gas well production rate is usually in the range of 95% to 100%, and it is necessary to determine whether to use a constant well opening rate or a dynamic well opening rate based on the specific circumstances.

[0118]

[0119] The above process completes the prediction of fracturing fluid volume for a given oil and gas field company, reservoir, block, well area, or well group. During the calculation and fitting of the standard curve for the daily flowback fluid volume per unit fracturing section length in coal-rock gas wells, the data volume and number of samples in the gas well sample database exhibit a continuous increasing characteristic. The gas well production dynamic sample data shows data updates in three dimensions: First, the daily flowback fluid volume data of old wells in the sample database continuously increases over time, increasing the number of columns in the production dynamic data matrix, i.e., the maximum production time in the sample database continuously increases. Second, data from newly commissioned wells continuously enters the sample database, increasing the number of rows in the daily flowback fluid volume data matrix, i.e., the number of valid sample data corresponding to a given time continuously increases. Third, as the number of wells in the sample database increases, it is necessary to further subdivide dimensions based on tag attributes to more accurately predict the fracturing flowback fluid volume. As the number of wells already in production and the daily flowback volume continue to increase, it is necessary to set a given cycle to repeat the above process. When repeating, it is necessary to recalculate the standard curve data of the daily flowback volume per unit fracturing section length. By curve fitting and linear extrapolation, 6600 days of smooth and continuous standard curve data are obtained, and finally, prediction is made.

[0120] Predicting the flowback fluid volume for a given oil and gas field company, reservoir, block, well area, and well group based on a standard curve of the daily flowback fluid volume per unit fracturing section requires iterative rolling fitting of the standard curve for flowback fluid volume prediction. To achieve real-time rolling prediction of future fracturing flowback fluid volume, the database needs to be updated daily to re-obtain and predict the standard curve. As the number of producing wells in a given oil and gas field company, reservoir, block, well area, and well group continues to increase, this method requires a data system to achieve automatic data updates and iterative calculations. This method constructs a fracturing flowback fluid volume prediction system workflow. The data-driven method and system for predicting fracturing flowback fluid in coal and rock gas reservoirs can provide a basis for fracturing fluid reuse and hydraulic fracturing implementation planning.

[0121] Example 2

[0122] Figure 5 This is a schematic diagram of a coal and rock gas reservoir fracturing flowback fluid prediction device provided in Embodiment 2 of the present invention. Figure 5 As shown, the device includes:

[0123] The first matrix determination unit 510 is used to construct the fracturing fluid flowback data matrix, which represents the flowback fluid volume of each coal and gas well in each effective production day; the fracturing fluid flowback data matrix is ​​obtained from the fracturing fluid flowback fluid volume data of the coal and gas wells that have been put into production in each effective production day;

[0124] The second matrix determination unit 520 is used to obtain the unit section length flowback fluid volume data matrix based on the fracturing fluid flowback data matrix. The unit section length flowback fluid volume data matrix represents the unit section length flowback fluid volume of each coal and gas well in each effective production day.

[0125] Standard curve data determination unit 530 is used to determine the standard curve data for each effective production day in the unit segment length return liquid volume data matrix;

[0126] The standard curve fitting unit 540 is used to fit a standard curve based on the standard curve data and to predict the backflow liquid using the standard curve.

[0127] The coal and rock gas reservoir fracturing flowback fluid prediction device provided in the embodiments of the present invention can execute the coal and rock gas reservoir fracturing flowback fluid prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0128] Example 3

[0129] Figure 6A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0130] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0132] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the coal and gas reservoir fracturing flowback fluid prediction method.

[0133] In some embodiments, the coal gas reservoir fracturing flowback fluid prediction method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the coal gas reservoir fracturing flowback fluid prediction method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the coal gas reservoir fracturing flowback fluid prediction method by any other suitable means (e.g., by means of firmware).

[0134] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0139] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0140] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0141] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A coal rock gas reservoir fracturing flowback fluid prediction method, characterized in that, include: Construct a fracturing fluid flowback data matrix, wherein the fracturing fluid flowback data matrix represents the flowback fluid volume of each coal and gas well in each effective production day; The fracturing fluid flowback data matrix is ​​obtained by using the fracturing fluid flowback volume data of the coal and rock gas wells that have been put into production for each effective production day; Based on the fracturing fluid flowback data matrix, a flowback fluid volume data matrix per unit length is obtained, wherein the flowback fluid volume data matrix per unit length represents the flowback fluid volume per unit length of each coal and gas well in each effective production day; Determine the standard curve data for each effective production day in the unit segment length return liquid volume data matrix; A standard curve is fitted based on the standard curve data, and the backflow fluid is predicted using the standard curve.

2. The method of claim 1, wherein, The construction of the fracturing fluid flowback data matrix includes: Obtain fracturing fluid flowback data for each of the coal and gas wells on different natural days; The effective production days are determined based on the dates during which wells are not shut in within the natural days, and zero values ​​in the fracturing fluid flowback data are removed and continuously processed. The fracturing fluid flowback data is aligned based on the effective production days, and the fracturing fluid flowback data matrix is ​​constructed using the longest effective production time of each coal and gas well.

3. The method of claim 1, wherein, The process of obtaining a flowback volume data matrix per unit length based on the fracturing fluid flowback data matrix includes: Divide each fracturing fluid flowback data in the fracturing fluid flowback data matrix by the length of the fracturing section of the corresponding coal-rock gas well to obtain the flowback fluid volume data matrix per unit section length.

4. The method of claim 1, wherein, The determination of the standard curve data for each effective production day in the unit segment length return liquid volume data matrix includes: Determine the number of valid data points for each valid production day in the unit segment length return liquid volume data matrix; The data selection interval for each effective production day is determined based on the number of effective samples, and the average value of the effective data within the data selection interval is used as the standard curve data for each effective production day.

5. The method of claim 4, wherein, The step of determining the data selection interval for each effective production day based on the number of effective samples, and using the average value of the effective data within the data selection interval as the standard curve data for each effective production day, includes: Divide the numerical ranges of different valid data, and set a first correspondence between each numerical range and the dynamic median average, and a second correspondence between each numerical range and the data selection range; Based on the target value range in which the number of valid data for each valid production day falls, the target dynamic median average value for each valid production day is determined according to the first correspondence relationship. Based on the second correspondence, the target data selection interval for each effective production day is determined, and the standard curve data for each effective production day is determined based on the effective data within the target data selection interval and the target dynamic median average.

6. The method of claim 1, wherein, The fitting of the standard curve based on the standard curve data includes: The standard curve data is fitted using at least one alternative curve fitting prediction model, and the coefficient of determination and the adjusted coefficient of determination are determined. The alternative curve fitting prediction model with the highest coefficient of determination and the adjusted coefficient of determination is taken as the target curve fitting prediction model. Based on the preset production time upper limit, the standard curve data is fitted using the target curve fitting prediction model to obtain the standard curve.

7. The method of claim 1, wherein, The prediction of flowback fluid using the standard curve includes: Determine the category of the target coal and gas well to be predicted; Based on the categories and corresponding fitting rules, the flowback volume of the target coal and rock gas well is predicted using the standard curve.

8. A coal rock gas reservoir fracturing flowback fluid prediction device, characterized in that, include: The first matrix determination unit is used to construct a fracturing fluid flowback data matrix, which represents the flowback fluid volume of each coal gas well in each effective production day; the fracturing fluid flowback data matrix is ​​obtained from the fracturing fluid flowback fluid volume data of the coal gas wells that have been put into production in each effective production day; The second matrix determination unit is used to obtain a unit segment length flowback fluid volume data matrix based on the fracturing fluid flowback data matrix, wherein the unit segment length flowback fluid volume data matrix represents the unit segment length flowback fluid volume of each coal gas well in each effective production day. A standard curve data determination unit is used to determine the standard curve data for each effective production day in the unit segment length return liquid volume data matrix. The standard curve fitting unit is used to fit a standard curve based on the standard curve data, and to predict the backflow liquid using the standard curve.

9. An electronic device, comprising: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the coal and rock gas reservoir fracturing flowback fluid prediction method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for predicting flowback fluid from fracturing in coal and rock gas reservoirs as described in any one of claims 1-7.

11. A computer program product, characterised in that, The computer program product includes a computer program that, when executed by a processor, implements the method for predicting flowback fluid from fracturing in coal and rock gas reservoirs according to any one of claims 1-7.

Images