A method, device, equipment and medium for quantitatively dividing a coalbed methane well production stage

Abstract

The present application relates to the field of coalbed methane well production dynamic analysis, and discloses a coalbed methane well production stage quantitative division method, device, equipment and medium, the original production sequence of the coalbed methane well in the target period is smoothed to obtain the smoothed production sequence, the smoothed production sequence is segmented into multiple optimal segmented data based on the optimal segmentation algorithm and the principle of minimizing segmentation error, and the corresponding sub-period of each optimal segmented data is determined in the target period, each optimal segmented data is fitted respectively to obtain the decline rate of each optimal segmented data, and the production stage category corresponding to each sub-period is determined according to the decline rate of each optimal segmented data and the set stage classification threshold. The present application can realize the division of the production stage of the coalbed methane well only by using the production data of the coalbed methane well, and realize a more flexible, more adaptable and lower data quality requirement coalbed methane well production stage division mode.

Description

Technical Field

[0001] This invention relates to the field of dynamic analysis of coalbed methane well production, and in particular to a method, apparatus, equipment and medium for quantitatively dividing the production stages of coalbed methane wells. Background Technology

[0002] With the development of science and technology, the technology for developing and increasing production in coalbed methane wells has been continuously improved.

[0003] The relevant technologies for classifying the production stages of coalbed methane wells mainly rely on several key parameters, such as production rate, pressure, and water cut. However, as oil and gas development extends into unconventional and low-permeability areas, the limitations of these technologies are becoming increasingly apparent, particularly the growing contradiction between the high requirements for data quality and the scarcity of actual data. For example, in actual production, the monitoring facilities in some older wells or marginal blocks are inadequate, resulting in missing or low-quality data on bottom hole pressure, water cut, and other parameters.

[0004] Therefore, there is an urgent need to explore a more flexible, adaptable, and data quality-required method for dividing the production stages of coalbed methane wells. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and medium for quantitatively dividing the production stages of coalbed methane wells, which solves the defects of related technologies in dividing the production stages of coalbed methane wells with high requirements for data quality but insufficient actual data, and realizes a more flexible, adaptable, and lower data quality requirement for dividing the production stages of coalbed methane wells.

[0006] In a first aspect, the present invention provides a method for quantitatively dividing the production stages of a coalbed methane well, comprising:

[0007] The original production sequence of coalbed methane wells within the target time period is smoothed to obtain a smoothed production sequence. Based on the optimal segmentation algorithm and the principle of minimizing segmentation error, the smoothed production sequence is divided into multiple optimal segment data, and the sub-period corresponding to each of the optimal segment data is determined in the target time period; Each of the optimal segment data is fitted separately to obtain the decrease rate of each of the optimal segment data; Based on the decrease rate of each optimal segment data and the set stage classification threshold, the production stage category corresponding to each sub-time period is determined.

[0008] Optionally, the smoothing of the original production sequence of the coalbed methane well within the target time period to obtain a smoothed production sequence includes: The original production sequence is input into the created data processing model, so that the data processing model smooths the original production sequence based on the moving average method and the set moving window length to obtain the smoothed production sequence; The data processing model is as follows: ; in, For data order, The order of the smoothed production sequence is as follows: Data, To move the window length, The data in the original production sequence arranged in the target order are... and The sum of .

[0009] Optionally, based on the principle of optimal segmentation algorithm and minimizing segmentation error, the smoothed output sequence is segmented into multiple optimal segment data, including: Based on the total number of data in the smoothed production sequence, determine the range of values ​​for the number of change points; Select the number of variable points within the range of variable point values. K And based on the selected number of variable points K Selecting from the smoothed production sequence includes K The set of variable point positions; Based on the set of variable point locations, the smoothed production sequence is divided into... K +1 consecutive segmented data; Calculate the sample mean of each segment of data based on each segment of data; The deviation of each segment of data is calculated based on the sample mean of each segment. The total error is calculated based on the deviation of each segment of data and the created penalty term; wherein the penalty term is the number of selected variable points. K Proportional; Based on the PLET algorithm with precise linear time for pruning, the number of change points is calculated. K The set of variable points and the total error are iteratively optimized until the optimal number of variable points with the minimum total error is determined. K and the optimal set of change points; The smoothed production sequence is segmented based on the optimal change point location set to obtain multiple optimal segmented data.

[0010] Optionally, the stage classification threshold includes an increase threshold and a decrease threshold, wherein the increase threshold is greater than the decrease threshold, and the production stage category corresponding to the sub-period is an increase stage, a stable production stage, or a decrease stage.

[0011] Optionally, determining the production stage category corresponding to each sub-period based on the decrease rate of each optimal segment data and a set stage classification threshold includes: For any of the optimal segmented data, if the decrease rate of the optimal segmented data is greater than the production increase threshold, then the production stage category corresponding to the target sub-period is determined to be the production increase stage, where the target sub-period is the sub-period corresponding to the optimal segmented data. If the decrease rate of the optimal segmented data is less than the decrease threshold, then the production stage category corresponding to the target sub-period is determined to be the decrease stage. If the decrease rate of the optimal segmented data is not less than the decrease threshold and not greater than the production increase threshold, then the production stage category corresponding to the target sub-period is determined to be the stable production stage.

[0012] Optionally, after determining the production stage category corresponding to each sub-period based on the decrease rate of each optimal segment data and a set stage classification threshold, the method further includes: Based on the production stage category corresponding to each sub-period, the characteristic parameters of the coalbed methane well within the target period are determined to quantitatively characterize the development characteristics of the coalbed methane well.

[0013] Optionally, the characteristic parameters include the initial production period, the stable production period, the declining production period, and the stable gas production volume; The step of determining the characteristic parameters of the coalbed methane well within the target time period based on the production stage category corresponding to each sub-time period includes: The multiple sub-periods in which all production stages are classified as "up production stage" and are continuous in time are defined as the "up production period", the multiple sub-periods in which all production stages are classified as "stable production stage" and are continuous in time are defined as the "stable production period", and the multiple sub-periods in which all production stages are classified as "decreasing production stage" and are continuous in time are defined as the "decreasing period". The stable production volume is obtained by summing the production volumes of each individual product within the stable production period in the original production sequence.

[0014] Secondly, the present invention provides a device for quantitatively dividing the production stage of a coalbed methane well, comprising: The smoothing unit is used to smooth the original production sequence of coalbed methane wells within the target time period to obtain a smoothed production sequence. A segmentation unit is used to divide the smoothed production sequence into multiple optimal segment data based on the optimal segmentation algorithm and the principle of minimizing segmentation error; The first determining unit is configured to determine the sub-time period corresponding to each of the optimal segmented data within the target time period; A fitting unit is used to fit each of the optimal segment data to obtain the decrease rate of each of the optimal segment data. The second determining unit is used to determine the production stage category corresponding to each sub-time period based on the decrease rate of each optimal segment data and the set stage classification threshold.

[0015] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the quantitative division method for coalbed methane well production stages described in the first aspect or any corresponding embodiment thereof.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for quantitatively dividing the production stages of a coalbed methane well according to the first aspect or any corresponding embodiment described above.

[0017] This invention provides a method, apparatus, equipment, and medium for quantitatively dividing the production stages of coalbed methane wells. The method smooths the original production sequence of a coalbed methane well within a target time period to obtain a smoothed production sequence. Based on the optimal segmentation algorithm and the principle of minimizing segmentation error, the smoothed production sequence is divided into multiple optimal segment data. Within the target time period, a sub-time period corresponding to each optimal segment data is determined. Each optimal segment data is fitted to obtain its decrease rate. Based on the decrease rate of each optimal segment data and a set stage classification threshold, the production stage category corresponding to each sub-time period is determined. This invention only requires the production data of the coalbed methane well to achieve the division of coalbed methane well production stages, realizing a more flexible, adaptable, and data quality-restricted method for dividing coalbed methane well production stages.

[0018] This invention presents a quantitative segmentation method for coalbed methane well production stages based on the PELT algorithm. It requires only production data and introduces a linear penalty term proportional to the number of variable points. This balances model fit and complexity, robustly identifying multiple truly significant variable points in the data. Based on these variable points, it determines the segments and calculates the decline rate for each segment. Finally, it analyzes and classifies typical coalbed methane well production stages based on the decline rate pattern. This invention can quantitatively characterize the development features of coalbed methane wells, providing guidance and support for conducting production dynamic analysis and assessing marketable reserves. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for quantitatively dividing the production stages of a coalbed methane well, as provided in an embodiment of the present invention; Figure 2 A schematic diagram of raw yield sequence provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a smoothed production sequence provided in an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the division of production stages in a coalbed methane well, as provided in an embodiment of the present invention. Figure 5 This is a schematic diagram of a quantitative division device for the production stage of a coalbed methane well, provided in an embodiment of the present invention. Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] The following is combined with Figures 1-4 This invention describes a method for quantitatively dividing the production stages of coalbed methane wells.

[0023] like Figure 1 As shown in the figure, this embodiment proposes a first method for quantitatively dividing the production stage of a coalbed methane well, which may include the following steps: S101. Smooth the original production sequence of coalbed methane wells within the target time period to obtain the smoothed production sequence.

[0024] The target period can be multiple consecutive months. The original production sequence can include the oil production for each unit period within the target period. For example... Figure 2 As shown, the target period can be from March 27, 2021 to July 1, 2025, and the original production sequence can include the oil production for each month during the period.

[0025] Specifically, this embodiment can preprocess the original production sequence to improve the accuracy of production stage division.

[0026] Optionally, step S101 includes: The original production sequence is input into the created data processing model so that the data processing model can smooth the original production sequence based on the moving average method and the set moving window length to obtain the smoothed production sequence. The data processing model is as follows: ; in, For data order, The order of the output sequence after smoothing is as follows Data, To move the window length, It is an odd number. This refers to the data in the original production sequence arranged in the target order, where the target order is... and The sum of .

[0027] It should be noted that this embodiment uses the moving average method to smooth the original production data. Smoothing and noise reduction without affecting the data characteristics can better extract the dynamic trend of production, thereby improving the accuracy of production stage division.

[0028] by Figure 2 Taking the original production sequence shown as an example, this embodiment sets the moving window length to 7, and uses a data processing model to smooth the oil production of each month in the original production sequence. The smoothed production for the 4th month is: ; The smoothed output for month 5 is: ; Similarly, the monthly oil production in the original production sequence is smoothed to obtain, as shown below. Figure 3 The smoothed output sequence is shown.

[0029] S102. Based on the principle of optimal segmentation algorithm and minimizing segmentation error, the smoothed production sequence is segmented into multiple optimal segment data.

[0030] Specifically, in this embodiment, the smoothed production sequence can be divided into multiple segments, and the error of each segment and the sum of errors of all segments can be calculated. With the goal of minimizing the sum of errors, the optimal segmentation algorithm is used to divide the smoothed production sequence into multiple non-overlapping optimal segments.

[0031] Optionally, step S102 includes: Based on the total number of data points in the smoothed production sequence, determine the range of values ​​for the number of change points; Select the number of variable points within the range of variable point values. K And based on the selected number of variable points K Selecting from the smoothed production sequence includes K The set of variable point positions; Based on the set of change points, the smoothed production sequence is divided into K +1 consecutive segmented data; Calculate the sample mean of each data segment based on the data segment for each segment. Calculate the deviation of each data segment based on the sample mean of each segment; The total error is calculated based on the deviation of each data segment and the created penalty term; where the penalty term is the number of selected variable points. K Proportional; Based on the PLET algorithm with precise linear time for pruning, the number of change points is calculated. K The set of variable points and the total error are iteratively optimized until the optimal number of variable points with the minimum total error is determined. K and the optimal set of change points; The smoothed production sequence is segmented based on the optimal change point location set to obtain multiple optimal segmented data.

[0032] Specifically, this embodiment can initially segment typical coalbed methane well production data, and for the smoothed production sequence... y [n] exists K There are several unknown variable points that divide the data into... K +1 consecutive segments, denoted by the change point position τ = (τ1, τ2, ..., τ) K ), and it is agreed that τ0=0, τ K+1 = N Then the data for each segment is , … , .

[0033] initial K = 1, then the original production sequence is divided into 2 segments, and the initial change point position is τ 1 = 9, meaning the 9th month of the original production sequence is the turning point, and τ 0 = 0, τ 2=53, then a segment of data is Another segment of data is Subsequently, this embodiment can calculate the statistical attributes and segmentation deviation of each segment, including: For each segment of data Calculate its sample mean: ; Then the first segment data S The sample mean of 1 is: ; Then the second segment data S The sample mean of 1 is: ; Furthermore, this embodiment can calculate the deviation within each data segment separately, using the squared error loss as a deviation metric for each segment. All data points within it are equal to the mean of that segment. The total deviation is: ; Then the first segment S The deviation of 1 is: ; Then the second segment S The deviation of 2 is: ; Furthermore, calculate the total deviation, and then... K Add the deviations of the +1 segmented data to obtain the total deviation under this specific segmentation scheme: ; The total deviation is: ; This embodiment then optimizes the location of the change points and determines the optimal segmented data. Specifically, to prevent overfitting, this embodiment adds a factor related to the number of change points to the total residual in the objective function. K Proportional penalty βK The final objective function is: ; Traverse all possible τ 1 value, calculate the corresponding J Value. Make J smallest τ 1 is K The optimal change point position when =1.

[0034] Increase K value( K =2,3,...), repeat the above process, and the optimization objective is to find the value that makes... J ( K , τ Minimum number of optimal change pointsK and optimal change point position τ This process can be automated using the Pruned Exact Linear Time (PLET) algorithm to find the optimal set of change points. Ultimately, the optimal number of change points for dividing the coalbed methane well production data is determined. K =5, the optimal change point position is τ =(6,9,21,33,42).

[0035] S103. Determine the sub-time period corresponding to each optimal segment of data within the target time period.

[0036] Specifically, this embodiment can determine the sub-time period corresponding to any optimal segment of data within the target time period.

[0037] It is understandable that each sub-time period is a non-overlapping and continuous time period within the target time period.

[0038] S104. Fit each optimal segment of data to obtain the decrease rate of each optimal segment.

[0039] Specifically, in this embodiment, for any optimal segment of data, an exponentially decreasing method can be used to fit the optimal segment of data to obtain the decrease rate of each optimal segment of data. D = ( D 1, D 2,… D K+1 ).

[0040] S105. Based on the decrease rate of each optimal segment data and the set stage classification threshold, determine the production stage category corresponding to each sub-period.

[0041] The stage classification threshold can be set by technicians according to the actual situation, and this embodiment does not limit it.

[0042] Optionally, the stage classification thresholds include an increase threshold and a decrease threshold. If the increase threshold is greater than the decrease threshold, the production stage category corresponding to the sub-period is the increase stage, the stable production stage, or the decrease stage.

[0043] Optionally, step S105 above includes: For any optimal segmented data, if the decline rate of the optimal segmented data is greater than the production threshold, then the production stage category corresponding to the target sub-period is determined to be the production stage, and the target sub-period is the sub-period corresponding to the optimal segmented data. If the decline rate of the optimal segmented data is less than the decline threshold, then the production stage category corresponding to the target sub-period is determined to be the decline stage. If the decline rate of the optimal segmented data is not less than the decline threshold and not greater than the production threshold, then the production stage category corresponding to the target sub-period is determined to be the stable production stage.

[0044] Specifically, this embodiment can divide the target time period into different categories of production stages based on the decrease rate of each optimal segment data and the set stage classification threshold.

[0045] This embodiment presents a quantitative segmentation method for coalbed methane well production stages based on the PELT algorithm. It requires only production data and introduces a linear penalty term proportional to the number of variable points. This balances model fit and complexity, robustly identifying multiple truly significant variable points in the data. Based on these variable points, it determines the segments and calculates the decline rate for each segment. Finally, it analyzes and segments typical coalbed methane well production stages based on the decline rate pattern. This embodiment can quantitatively characterize the development features of coalbed methane wells, providing guidance and support for conducting production dynamic analysis and assessing marketable reserves.

[0046] The quantitative segmentation method for coalbed methane well production stages proposed in this embodiment smooths the original production sequence of the coalbed methane well within a target time period to obtain a smoothed production sequence. Based on the optimal segmentation algorithm and the principle of minimizing segmentation error, the smoothed production sequence is divided into multiple optimal segment data. A sub-time period corresponding to each optimal segment data is determined within the target time period. Each optimal segment data is fitted to obtain its decline rate. Based on the decline rate of each optimal segment data and a set stage classification threshold, the production stage category corresponding to each sub-time period is determined. This embodiment only requires coalbed methane well production data to achieve the segmentation of coalbed methane well production stages, realizing a more flexible, adaptable, and data quality-restricted method for segmenting coalbed methane well production stages.

[0047] based on Figure 1 This embodiment proposes a second method for quantitatively dividing the production stages of coalbed methane wells. This method, after step S105, may further include: Based on the production stage category corresponding to each sub-period, the characteristic parameters of coalbed methane wells within the target period are determined to quantitatively characterize the development characteristics of coalbed methane wells.

[0048] Specifically, in this embodiment, characteristic parameters can be calculated based on the production stage category corresponding to each sub-period, and the characteristic parameters can be used to quantitatively characterize the development characteristics of coalbed methane wells.

[0049] Optionally, the characteristic parameters include the production period, stable production period, declining production period, and stable gas production volume. In this case, the characteristic parameters of the coalbed methane well within the target period are determined based on the production stage category corresponding to each sub-period, including: Multiple sub-periods in which all production stages are classified as "upward production stage" and are continuous in time are defined as the "upward production period," multiple sub-periods in which all production stages are classified as "stable production stage" and are continuous in time are defined as the "stable production period," and multiple sub-periods in which all production stages are classified as "decline stage" and are continuous in time are defined as the "decline period." The stable gas production volume is obtained by summing up the production volumes of each individual product within the stable production period in the original production sequence.

[0050] by Figure 2 and Figure 3 For example, the production data in the middle, such as Figure 4 As shown in the figure, this embodiment can calculate that the production period of the coalbed methane well is 9 months, the stable production period is 24 months, and the stable gas production is 12,140 cubic meters / month, etc., which quantitatively characterizes the development characteristics of the coalbed methane well and provides data support for subsequent production dynamic analysis and market reserve assessment.

[0051] The quantitative segmentation method for coalbed methane well production stages proposed in this embodiment only requires production data. By introducing a linear penalty term proportional to the number of variable points, a trade-off is made between model fit and model complexity, thereby robustly detecting multiple truly significant variable points in the data. Based on the variable points, the segmentation is determined and the decline rate of each segment is calculated. Finally, the production stages of typical coalbed methane wells are analyzed and segmented according to the decline rate law.

[0052] like Figure 5 As shown in the figure, this embodiment proposes a device for quantitatively dividing the production stage of a coalbed methane well. The device may include: Smoothing unit 101 is used to smooth the original production sequence of coalbed methane wells within the target time period to obtain a smoothed production sequence. The segmentation unit 102 is used to segment the smoothed production sequence into multiple optimal segment data based on the optimal segmentation algorithm and the principle of minimizing segmentation error; The first determining unit 103 is used to determine the sub-time period corresponding to each optimal segment of data in the target time period; Fitting unit 104 is used to fit each optimal segment of data separately to obtain the decrease rate of each optimal segment of data; The second determining unit 105 is used to determine the production stage category corresponding to each sub-period based on the decrease rate of each optimal segment data and the set stage classification threshold.

[0053] It should be noted that the processing procedures and beneficial effects of the smoothing unit 101, segmentation unit 102, first determining unit 103, fitting unit 104, and second determining unit 105 can be referred to respectively. Figure 1 Steps S101 to S105 are not described in detail here.

[0054] Optionally, the smoothing unit 101 is also used for: The original production sequence is input into the created data processing model so that the data processing model can smooth the original production sequence based on the moving average method and the set moving window length to obtain the smoothed production sequence. The data processing model is as follows: ; in, For data order, The order of the output sequence after smoothing is as follows Data, To move the window length, This refers to the data in the original production sequence arranged in the target order, where the target order is... and The sum of .

[0055] Optionally, the segmentation unit 102 is also used for: Based on the total number of data points in the smoothed production sequence, determine the range of values ​​for the number of change points; Select the number of variable points within the range of variable point values. K And based on the selected number of variable points K Selecting from the smoothed production sequence includes K The set of variable point positions; Based on the set of change points, the smoothed production sequence is divided into K +1 consecutive segmented data; Calculate the sample mean of each data segment based on the data segment for each segment. Calculate the deviation of each data segment based on the sample mean of each segment; The total error is calculated based on the deviation of each data segment and the created penalty term; where the penalty term is the number of selected variable points. K Proportional; Based on the PLET algorithm with precise linear time for pruning, the number of change points is calculated. K The set of variable points and the total error are iteratively optimized until the optimal number of variable points with the minimum total error is determined. K and the optimal set of change points; The smoothed production sequence is segmented based on the optimal change point location set to obtain multiple optimal segmented data.

[0056] Optionally, the stage classification thresholds include an increase threshold and a decrease threshold. If the increase threshold is greater than the decrease threshold, the production stage category corresponding to the sub-period is the increase stage, the stable production stage, or the decrease stage.

[0057] Optionally, the second determining unit 105 is also used for: For any optimal segmented data, if the decline rate of the optimal segmented data is greater than the production threshold, then the production stage category corresponding to the target sub-period is determined to be the production stage, and the target sub-period is the sub-period corresponding to the optimal segmented data. If the decline rate of the optimal segmented data is less than the decline threshold, then the production stage category corresponding to the target sub-period is determined to be the decline stage. If the decline rate of the optimal segmented data is not less than the decline threshold and not greater than the production threshold, then the production stage category corresponding to the target sub-period is determined to be the stable production stage.

[0058] Optionally, the above-mentioned device further includes: The characterization unit is used to determine the production stage category corresponding to each sub-period based on the decline rate of each optimal segment data and the set stage classification threshold, and then to determine the characteristic parameters of the coalbed methane well in the target period based on the production stage category corresponding to each sub-period, so as to quantitatively characterize the development characteristics of the coalbed methane well.

[0059] Optional, the characteristic parameters include the initial production period, the stable production period, the declining period, and the stable gas production volume; The characterization unit is also used for: Multiple sub-periods in which all production stages are classified as "upward production stage" and are continuous in time are defined as the "upward production period," multiple sub-periods in which all production stages are classified as "stable production stage" and are continuous in time are defined as the "stable production period," and multiple sub-periods in which all production stages are classified as "decline stage" and are continuous in time are defined as the "decline period." The stable gas production volume is obtained by summing up the production volumes of each individual product within the stable production period in the original production sequence.

[0060] The quantitative segmentation device for coalbed methane well production stages proposed in this embodiment smooths the original production sequence of coalbed methane wells within a target time period, obtaining a smoothed production sequence. Based on the optimal segmentation algorithm and the principle of minimizing segmentation error, the smoothed production sequence is divided into multiple optimal segment data. Within the target time period, a sub-time period corresponding to each optimal segment data is determined. Each optimal segment data is fitted to obtain its decrease rate. Based on the decrease rate of each optimal segment data and a set stage classification threshold, the production stage category corresponding to each sub-time period is determined. This embodiment only requires coalbed methane well production data to achieve the segmentation of coalbed methane well production stages, realizing a more flexible, adaptable, and data quality-restricted method for segmenting coalbed methane well production stages.

[0061] In this embodiment, the quantitative division device for the production stage of a coalbed methane well is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0062] This invention also provides a computer device having the above-described features. Figure 5 The device shown is a quantitative division device for the production stage of a coalbed methane well.

[0063] Please see Figure 6 The present invention provides a schematic diagram of the structure of a computer device according to an optional embodiment. The computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0064] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0065] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0066] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function. The data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0067] Memory 20 may include volatile memory, such as random access memory. Memory may also include non-volatile memory, such as flash memory, hard disk, or solid-state drive. Memory 20 may also include combinations of the above types of memory.

[0068] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0069] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for quantitatively dividing the production stages of a coalbed methane well, characterized in that, include: The original production sequence of coalbed methane wells within the target time period is smoothed to obtain a smoothed production sequence. Based on the optimal segmentation algorithm and the principle of minimizing segmentation error, the smoothed production sequence is divided into multiple optimal segment data, and the sub-period corresponding to each of the optimal segment data is determined in the target time period; Each of the optimal segment data is fitted separately to obtain the decrease rate of each of the optimal segment data; Based on the decrease rate of each optimal segment data and the set stage classification threshold, the production stage category corresponding to each sub-time period is determined.

2. The method according to claim 1, characterized in that, The smoothing process of the original production sequence of coalbed methane wells within the target time period to obtain the smoothed production sequence includes: The original production sequence is input into the created data processing model, so that the data processing model smooths the original production sequence based on the moving average method and the set moving window length to obtain the smoothed production sequence; The data processing model is as follows: ； in, For data order, The order of the smoothed production sequence is as follows: Data, To move the window length, The data in the original production sequence arranged in the target order are... and The sum of .

3. The method according to claim 1, characterized in that, Based on the principle of optimal segmentation algorithm and minimizing segmentation error, the smoothed output sequence is segmented into multiple optimal segment data, including: Based on the total number of data in the smoothed production sequence, determine the range of values ​​for the number of change points; Select the number of variable points within the range of variable point values. K And based on the selected number of variable points K Selecting from the smoothed production sequence includes K The set of variable point positions; Based on the set of variable point locations, the smoothed output sequence is divided into... K +1 consecutive segmented data; Calculate the sample mean of each segment of data based on each segment of data; The deviation of each segment of data is calculated based on the sample mean of each segment. The total error is calculated based on the deviation of each segment of data and the created penalty term; wherein the penalty term is the number of selected variable points. K Proportional; Based on the PLET algorithm with precise linear time for pruning, the number of change points is calculated. K The set of variable points and the total error are iteratively optimized until the optimal number of variable points with the minimum total error is determined. K and the optimal set of change points; The smoothed production sequence is segmented based on the optimal change point location set to obtain multiple optimal segmented data.

4. The method according to claim 1, characterized in that, The stage classification thresholds include an increase production threshold and a decrease production threshold. The increase production threshold is greater than the decrease production threshold. The production stage category corresponding to the sub-period is an increase production stage, a stable production stage, or a decrease production stage.

5. The method according to claim 4, characterized in that, The step of determining the production stage category corresponding to each sub-period based on the decrease rate of each optimal segment data and the set stage classification threshold includes: For any of the optimal segmented data, if the decrease rate of the optimal segmented data is greater than the production increase threshold, then the production stage category corresponding to the target sub-period is determined to be the production increase stage, where the target sub-period is the sub-period corresponding to the optimal segmented data. If the decrease rate of the optimal segmented data is less than the decrease threshold, then the production stage category corresponding to the target sub-period is determined to be the decrease stage. If the decrease rate of the optimal segmented data is not less than the decrease threshold and not greater than the production increase threshold, then the production stage category corresponding to the target sub-period is determined to be the stable production stage.

6. The method according to claim 5, characterized in that, After determining the production stage category corresponding to each sub-period based on the decrease rate of each optimal segment data and the set stage classification threshold, the method further includes: Based on the production stage category corresponding to each sub-period, the characteristic parameters of the coalbed methane well within the target period are determined to quantitatively characterize the development characteristics of the coalbed methane well.

7. The method according to claim 6, characterized in that, The characteristic parameters include the early production period, the stable production period, the declining period, and the stable gas production volume; The step of determining the characteristic parameters of the coalbed methane well within the target time period based on the production stage category corresponding to each sub-time period includes: The multiple sub-periods in which all production stages are classified as "up production stage" and are continuous in time are defined as the "up production period", the multiple sub-periods in which all production stages are classified as "stable production stage" and are continuous in time are defined as the "stable production period", and the multiple sub-periods in which all production stages are classified as "decreasing production stage" and are continuous in time are defined as the "decreasing period". The stable production volume is obtained by summing the production volumes of each individual product within the stable production period in the original production sequence.

8. A device for quantitatively dividing the production stages of a coalbed methane well, characterized in that, include: The smoothing unit is used to smooth the original production sequence of coalbed methane wells within the target time period to obtain a smoothed production sequence. A segmentation unit is used to divide the smoothed production sequence into multiple optimal segment data based on the optimal segmentation algorithm and the principle of minimizing segmentation error; The first determining unit is configured to determine the sub-time period corresponding to each of the optimal segmented data within the target time period; A fitting unit is used to fit each of the optimal segment data to obtain the decrease rate of each of the optimal segment data. The second determining unit is used to determine the production stage category corresponding to each sub-time period based on the decrease rate of each optimal segment data and the set stage classification threshold.

9. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for quantitatively dividing the production stages of a coalbed methane well as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the method for quantitatively dividing the production stages of a coalbed methane well as described in any one of claims 1 to 7.

Images