Shale gas hydrops batch production well matching method

Abstract

The invention belongs to the technical field of shale gas well production, and particularly relates to a shale gas hydrops intermittent production well matching method, which comprises the following steps: firstly, acquiring multi-dimensional production data of a target shale gas well in a current preset time period, and acquiring historical production data of a shale gas well matched with the target shale gas well; then constructing a time sliding window, and generating a plurality of groups of window data according to the historical production data of the matched shale gas well according to the constructed time sliding window; and then constructing an intermittent production well matching model, inputting the obtained multi-dimensional production data and the plurality of groups of window data of the target shale gas well in the current preset time period into the intermittent production well matching model, and outputting matched shale gas well information meeting intermittent production requirements with the target shale gas well. The problem that in the prior art, an intermittent production well matching mode for a shale gas well due to the liquid accumulation problem is low in efficiency can be solved.

Description

Technical Field

[0001] The invention belongs to the technical field of shale gas well production, and in particular relates to a method for matching shale gas liquid accumulation intermittent production wells. Background Art

[0002] In the process of shale gas extraction, liquid accumulation inside the gas well is one of the important factors affecting production efficiency. Specifically, the liquid accumulation problem will lead to a decrease in the production capacity of the gas well and may even cause production stagnation. Therefore, in order to meet this challenge, an intermittent production strategy is usually adopted, that is, periodically shutting down the gas well, allowing the accumulated liquid to be naturally discharged before reopening the gas well to resume production.

[0003] At present, in the shale gas mining industry, in order to solve the problems caused by liquid accumulation, intermittent production is generally adopted. This operation mode closes the gas well for a period of time, allowing the accumulated liquid to flow out naturally or be discharged through auxiliary means, thereby reducing the impact of liquid accumulation on production efficiency. However, the timing of executing this intermittent production mainly depends on the operator's experience or is based on some simple rules, such as a fixed closing interval.

[0004] Therefore, the existing intermittent production methods have some problems or defects, including:

[0005] 1. The switching time is not determined accurately enough. The reason is that due to the lack of scientific decision-making support, the current intermittent production strategy often cannot accurately grasp the best time for the gas well to enter intermittent production, which may lead to excessive or insufficient closure, thus affecting the overall production efficiency.

[0006] 2. Insufficient use of historical data. The reason is that the existing methods do not effectively utilize the production experience and data from other gas wells under similar conditions, which limits the possibility of further optimizing production strategies.

[0007] Therefore, in order to solve the problems existing in the prior art, a new shale gas well liquid loading intermittent production matching method is needed. Summary of the invention

[0008] The technical problem solved by the present invention is to provide a method for matching shale gas intermittent production wells with liquid accumulation, so as to solve the problem of low efficiency in the prior art of matching intermittent production wells with shale gas wells due to liquid accumulation.

[0009] The basic solution provided by the present invention is a method for matching shale gas liquid accumulation intermittent production wells, comprising:

[0010] S1: Obtain multi-dimensional production data of the target shale gas well in the current preset time period, and obtain historical production data of the shale gas wells matching the target shale gas well;

[0011] S2: construct a time sliding window, and generate several groups of window data from the historical production data of the matching shale gas wells according to the constructed time sliding window;

[0012] S3: Construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well.

[0013] Furthermore, in S1, the multi-dimensional production data of the target shale gas well in the current preset time period includes tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data.

[0014] Further, the S2 includes:

[0015] S2-1: construct a time sliding window according to the preset time period of the target shale gas well in S1;

[0016] S2-2: Use the time sliding window to slide and collect in sequence along the timeline of the historical production data of the matching shale gas wells to obtain several groups of window data, expressed as:

[0017] X=[x1,…,x i ]

[0018] Where i is the number of windows;

[0019] S2-3: Preprocessing the acquired window data sets, obtaining each window data set including tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data, the expression is:

[0020] x i =[d i ,c i ,o i ,g i ,w i ,p i ]

[0021] Among them, d i represents the inner diameter data of the oil pipe in the i-th window, c i represents the casing pressure data in the i-th window, o i represents the oil pressure data in the i-th window, g i represents the gas production data in the i-th window, w i represents the water production data in the i-th window, p i Represents the production pressure difference data in the i-th window.

[0022] Further, the S3 includes:

[0023] S3-1: Constructing intermittent production well matching model based on VAE model;

[0024] S3-2: Divide several groups of window data into training sets and validation sets, input the training sets into the intermittent production well matching model for training, validate the trained intermittent production well matching model through the validation set and retain the model parameter settings that have passed the validation;

[0025] S3-3: Input several groups of window data into the intermittent production well matching model, and output the two-dimensional characteristic standard data of each group of window data after dimension reduction. The expression is:

[0026] w i =[μ i ,σ i ]

[0027] S3-4: input the multi-dimensional production data of the target shale gas well in the current preset time period into the intermittent production well matching model, and output the two-dimensional feature matching data [μ, σ] after dimensionality reduction;

[0028] S3-5: Calculate the absolute value distance between the two-dimensional feature matching data and the two-dimensional feature standard data. The expression is:

[0029] e i =|μ-μ i |+|σ-σ i |

[0030] Output the well number information of the corresponding matching shale gas well with the smallest absolute value distance and the corresponding time sliding window date information.

[0031] Furthermore, the S3 further includes:

[0032] 3-6: According to the well number information of the corresponding matching shale gas well with the smallest absolute value distance obtained in S3-5 and the corresponding time sliding window date information, obtain the intermittent time information and intermittent operation information of the shale gas well after the corresponding time sliding window date information ends;

[0033] S3-7: Generate the intermittent time and intermittent operation of the target shale gas well according to the acquired intermittent time information and intermittent operation information of the shale gas well.

[0034] A system for matching shale gas liquid accumulation intermittent production wells, applied to the above-mentioned method for matching shale gas liquid accumulation intermittent production wells, comprises:

[0035] A data acquisition module, used to acquire multi-dimensional production data of a target shale gas well in a current preset time period, and to acquire historical production data of a shale gas well matching the target shale gas well;

[0036] A data preprocessing module is used to divide the historical production data of the matching shale gas wells into several groups of window data by constructing a time sliding window;

[0037] The intermittent production matching module is used to construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well.

[0038] An electronic device includes a processor and a memory, wherein the memory stores programs or instructions, and the processor executes the above-mentioned method for matching shale gas liquid accumulation intermittent production wells by calling the programs or instructions stored in the memory.

[0039] A computer-readable storage medium stores a program or instruction, wherein the program or instruction enables a computer to execute a method for matching shale gas liquid accumulation intermittent production wells as described above.

[0040] The principles and advantages of the present invention are as follows: In this application, in view of the problem that shale gas wells in the prior art rely heavily on manual judgment and have poor optimization of production strategies when executing intermittent production, the overall solution of the present application combines the advantages of existing big data models to match the operating data of the target shale gas well with the historical operating data of other shale gas wells of the same type to obtain an intermittent production method that is scientific, effective, and maximizes the benefits of the production strategy. In the entire technical solution, the innovation of this application lies in the type of target shale gas well data acquisition and the matching method of production data. In the existing big data model field, network models such as neural networks and deep learning are usually used as the basis. After the historical operating data is input into the model for training, the real-time data of the target shale gas well is input into the model. In order to predict or generate intermittent production of shale gas wells, this method has the defect that a lot of sample data is required for model training. The sample data collected in this application is the operation data since the establishment of the shale gas well. If such a huge amount of data is used to train the model, the required computing power is very large. In this regard, in the scheme of this application, the historical operation data obtained is divided by a time sliding window, for example, according to a time sliding window of every 7 days, the historical operation data is divided into several groups of window data, and then processed by the intermittent production well matching model. Therefore, the data processed by the intermittent production well matching model each time is the historical operation data of every 7 days, rather than a large amount of historical operation data of the shale gas well since the start of operation, which solves the problem of high computing power required for model processing in the prior art.

[0041] On this basis, this application does not adopt the method of directly outputting intermittent production strategies using existing big data models. Instead, it performs absolute value calculations on the reduced-dimensional data of several groups of window data output by the intermittent production well matching model and the reduced-dimensional data of the real-time operating data of the target shale gas well, thereby obtaining the comparison results of each window with the real-time operating data of the target shale gas well, and taking the shale gas well information and intermittent production strategy corresponding to the result with the smallest absolute value as the reference object for the intermittent production strategy of the target shale gas well. In this way, the optimal intermittent production strategy for the target shale gas well is obtained, which effectively solves the problem of liquid accumulation and greatly improves the production efficiency of the target shale gas well. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flowchart of an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the processing logic of an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of VAE model training in an embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram of the output results of the intermittent production well matching model in an embodiment of the present invention;

[0046] Figure 5 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following is further described in detail through specific implementation methods:

[0048] The symbols in the drawings of the specification include: electronic device 400 , processor 401 , memory 402 , input device 403 , and output device 404 .

[0049] Liquid accumulation in shale gas wells is caused by the fact that in the late stage of gas well production, due to the decrease in formation pressure and gas well production capacity, the temperature gradient of the gas cylinder increases, and due to the temperature drop, some components of the natural gas condense in the wellbore to form condensate. When the gas well production is not enough to bring out part of the condensate, the condensate falls back to the bottom of the well, resulting in liquid accumulation in the wellbore. The generation of liquid accumulation will aggravate the decline in the production capacity of the gas well. For this, intermittent production is required to drain the liquid accumulation. For this, the technical solution of the present application is basically as shown in the attached embodiment. Figure 1 and Figure 2 A method for matching shale gas liquid accumulation intermittent production wells, comprising:

[0050] S1: Obtain multi-dimensional production data of the target shale gas well in the current preset time period, and obtain historical production data of the shale gas wells matching the target shale gas well;

[0051] In this embodiment, the multi-dimensional production data of the target shale gas well obtained include tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data, and the preset time period is 7 days, that is, the tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data of the target shale gas well in the 7 days before the current time are obtained. The type of multi-dimensional production data selected for this application is selected according to different types of shale gas wells, so that the shale gas wells can ensure the highest adaptability during data matching and type matching.

[0052] At the same time, in step S1 of the present application, the multi-dimensional production data of the target shale gas well obtained is continuously updated as the target shale gas well operates, that is, the multi-dimensional production data obtained is the real-time production data of the current target shale gas well within a preset time period. For example, taking the preset time period as 7 days as an example, the multi-dimensional production data obtained uses 7 days as a time window, and continuously fills the latest production data of the target shale gas well into the time window, and production data older than 7 days is eliminated.

[0053] S2: construct a time sliding window, and generate several groups of window data from the historical production data of the matching shale gas wells according to the constructed time sliding window; wherein S2 includes:

[0054] S2-1: construct a time sliding window according to the preset time period of the target shale gas well in S1;

[0055] S2-2: Use the time sliding window to slide and collect in sequence along the timeline of the historical production data of the matching shale gas wells to obtain several groups of window data, expressed as:

[0056] X=[x1,…,x i ]

[0057] Where i is the number of windows;

[0058] S2-3: Preprocessing the acquired window data sets, obtaining each window data set including tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data, the expression is:

[0059] x i =[d i ,c i ,o i ,g i ,w i ,p i ]

[0060] Among them, d i represents the inner diameter data of the oil pipe in the i-th window, c irepresents the casing pressure data in the i-th window, o i represents the oil pressure data in the i-th window, g i represents the gas production data in the i-th window, w i represents the water production data in the i-th window, p i Represents the production pressure difference data in the i-th window.

[0061] In this embodiment, the historical operation data of the shale gas well obtained for intermittent production matching with the target shale gas well includes all historical operation data since the matching shale gas well started to operate, and the number of matching shale gas wells is more than one. Therefore, the amount of historical operation data is very large. In order to better process and calculate the data, the present application constructs a time sliding window, the size of which is the same as the preset time period in S1, for example, 7 days, and then divides the historical operation data into several window data through the time sliding window. Each window data is preprocessed so that the data type and data dimension in each window data include the multi-dimensional production data of the target shale gas well obtained, specifically including tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data. For cases of missing data, data errors, etc., data cleaning, data supplementation and other preprocessing methods are used to improve the data to ensure that each window data contains the data type required to match the target shale gas well.

[0062] S3: construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well; wherein S3 includes:

[0063] S3-1: Constructing intermittent production well matching model based on VAE model;

[0064] S3-2: Divide several groups of window data into training sets and validation sets, input the training sets into the intermittent production well matching model for training, validate the trained intermittent production well matching model through the validation set and retain the model parameter settings that have passed the validation;

[0065] S3-3: Input several groups of window data into the intermittent production well matching model, and output the two-dimensional characteristic standard data of each group of window data after dimension reduction. The expression is:

[0066] w i =[μ i ,σ i ]

[0067] S3-4: input the multi-dimensional production data of the target shale gas well in the current preset time period into the intermittent production well matching model, and output the two-dimensional feature matching data [μ, σ] after dimensionality reduction;

[0068] S3-5: Calculate the absolute value distance between the two-dimensional feature matching data and the two-dimensional feature standard data. The expression is:

[0069] e i =|μ-μ i |+|σ-σ i |

[0070] Output the well number information of the corresponding matching shale gas well with the smallest absolute value distance and the corresponding time sliding window date information;

[0071] 3-6: According to the well number information of the corresponding matching shale gas well with the smallest absolute value distance obtained in S3-5 and the corresponding time sliding window date information, obtain the intermittent time information and intermittent operation information of the shale gas well after the corresponding time sliding window date information ends;

[0072] S3-7: Generate the intermittent time and intermittent operation of the target shale gas well according to the acquired intermittent time information and intermittent operation information of the shale gas well.

[0073] In this embodiment, the intermittent production well matching model constructed is based on the VAE model. First, the model is trained through a number of window data, such as Figure 3 As shown, the tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data of continuous time periods in the window data are input into the VAE model, and the VAE model outputs data of the same type. When the difference between the output value of the same type of data and the input value of the same type of data is within the preset threshold, it means that the training effect of the VAE model meets the requirements, and the parameter settings of the model are retained as the processing result of the multi-dimensional operation data of the target shale gas well.

[0074] In the intermittent production well matching model, the VAE model is used to reduce the dimension of the input window data and multi-dimensional feature data. For example, each window data of the input matching shale gas well includes six-dimensional data, namely, tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data, and production pressure difference data. After the VAE model reduces the dimension, the output is two-dimensional feature data [μ i ,σ i ]; Each window data of the input target shale gas well includes six-dimensional data, including tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data. After dimension reduction by VAE model, two-dimensional feature data [μ, σ] is output;

[0075] Then calculate the 2D feature data [μ,σ] and each 2D feature data [μ i ,σ i ], and the subsequent intermittent production strategy of the matching shale gas well corresponding to the window data with the smallest absolute value distance in the time period corresponding to the window data is taken as the intermittent production strategy of the target shale gas well.

[0076] To more clearly describe the present application scheme, take well A and well B as an example, where well A is the target shale gas well, well B is the matching shale gas well, and the operation time of well A is greater than the preset time period, for example, the operation time of well A is greater than 7 days, then the multi-dimensional production data of well A within 7 days before the current time is obtained;

[0077] Assume that well B has been producing for 10 days since its start of operation. Therefore, we need to find a window of data in well B (the window length is 7 days) that is closest to the production situation of well A in the past 7 days.

[0078] The multi-dimensional production data includes six-dimensional data, namely, tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data, and production pressure difference data. For the convenience of demonstration, taking gas production and water production as an example, there are a total of 10 sets of gas production data and water production data in Well B, as shown in Table 1 below:

[0079] Table 1 Well B production status

[0080]

[0081] Dividing the historical operating data in Table 1 above by a time sliding window of length 7 will generate 4 sets of exposure data, as shown in Table 2 below:

[0082] Table 2 Sliding window data of well B

[0083]

[0084] The production situation of Well A in the past 7 days is shown in Table 3 below:

[0085] Table 3 Production status of Well A in the past 7 days

[0086] date 2024.6.8 6.9 6.10 6.11 6.12 6.13 6.14 Gas production 1700 4000 3800 5000 5500 3100 4700 Water production 1 4 1 6 7 3 1

[0087] The above data are input into the intermittent production well matching model, and the VAE model is used to reduce the dimension of the above window data features and the real-time production data of well A, as shown in the following example: Figure 4 As shown, the two-dimensional feature data shown in Table 4 is obtained:

[0088] Table 4 μ and σ values ​​for all sliding windows and well A

[0089]

[0090]

[0091] Then, the sum of the absolute values ​​of μ and σ of all sliding windows and μ and σ of well A is calculated. In the final calculation result, the absolute value between sliding window 2 and well A is the smallest, which is 0.1, which means that sliding window 2 is closest to the production situation of well A in the past 7 days. The start date corresponding to sliding window 2 is January 12, 2024, which means that the production situation of well B in the 7 days from January 12, 2024 to January 18, 2024 is closest to the production situation of well A. The intermittent production strategy after January 18 is used as the intermittent production strategy of well A.

[0092] In this implementation, for the intermittent production strategy time node after the matching window data, every 7 days is set as a time node. If there is intermittent production within these 7 days, it will be used as the intermittent production strategy for the target shale gas well. If not, the target shale gas well will produce normally within 7 days, and the intermittent production well matching operation will be performed again after the end of 7 days.

[0093] Therefore, in the technical solution of the present application, compared with the existing technology, a data-driven approach is adopted, combined with the advantages of the existing big data model, by collecting and analyzing the historical production data of gas wells, to provide scientific decision-making support for intermittent production, effectively avoiding reliance on manual experience or simple rules, and improving the accuracy and reliability of intermittent production strategies.

[0094] In another embodiment of the present embodiment, a system for matching shale gas liquid accumulation intermittent production wells is also included, which is applied to the above-mentioned method for matching shale gas liquid accumulation intermittent production wells, including:

[0095] A data acquisition module, used to acquire multi-dimensional production data of a target shale gas well in a current preset time period, and to acquire historical production data of a shale gas well matching the target shale gas well;

[0096] A data preprocessing module is used to divide the historical production data of the matching shale gas wells into several groups of window data by constructing a time sliding window;

[0097] The intermittent production matching module is used to construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well.

[0098] Also included is an electronic device such as Figure 5 As shown, the electronic device 400 includes one or more processors 401 and a memory 402 .

[0099] The processor 401 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0100] The memory 402 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement a method for matching shale gas intermittent production wells with liquid accumulation in any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0101] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including early warning information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0102] Of course, to simplify, Figure 5 Only some of the components related to the present invention in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device 400 may also include any other appropriate components.

[0103] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of a method for matching shale gas liquid-filled intermittent production wells provided in any embodiment of the present invention.

[0104] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0105] In addition, an embodiment of the present invention may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of a method for matching shale gas liquid-filled intermittent production wells provided in any embodiment of the present invention.

[0106] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0107] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A method for matching shale gas liquid accumulation intermittent production wells, characterized in that: include: S1: Obtain multi-dimensional production data of the target shale gas well in the current preset time period, and obtain historical production data of the shale gas wells matching the target shale gas well; S2: construct a time sliding window, and generate several groups of window data from the historical production data of the matching shale gas wells according to the constructed time sliding window; S3: Construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well.

2. The method for matching shale gas liquid accumulation intermittent production wells according to claim 1, characterized in that: In S1, the multi-dimensional production data of the target shale gas well in the current preset time period includes tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data.

3. The method for matching shale gas liquid accumulation intermittent production wells according to claim 2, characterized in that: The S2 includes: S2-1: construct a time sliding window according to the preset time period of the target shale gas well in S1; S2-2: Use the time sliding window to slide and collect in sequence along the timeline of the historical production data of the matching shale gas wells to obtain several groups of window data, expressed as: X=[x1,…,x i ] Where i is the number of windows; S2-3: Preprocessing the acquired window data sets, obtaining each window data set including tubing inner diameter data, casing pressure data, oil pressure data, gas production data, water production data and production pressure difference data, the expression is: x i =[d i ,c i ,o i ,g i ,w i ,p i ] Among them, d i represents the inner diameter data of the oil pipe in the i-th window, c i represents the casing pressure data in the i-th window, o i represents the oil pressure data in the i-th window, g i represents the gas production data in the i-th window, w i represents the water production data in the i-th window, p i Represents the production pressure difference data in the i-th window.

4. The method for matching shale gas liquid accumulation intermittent production wells according to claim 3, characterized in that: The S3 includes: S3-1: Constructing intermittent production well matching model based on VAE model; S3-2: Divide several groups of window data into training sets and validation sets, input the training sets into the intermittent production well matching model for training, validate the trained intermittent production well matching model through the validation set and retain the model parameter settings that have passed the validation; S3-3: Input several groups of window data into the intermittent production well matching model, and output the two-dimensional characteristic standard data of each group of window data after dimension reduction. The expression is: w i =[μ i ,s i ] S3-4: input the multi-dimensional production data of the target shale gas well in the current preset time period into the intermittent production well matching model, and output the two-dimensional feature matching data [μ, σ] after dimensionality reduction; S3-5: Calculate the absolute value distance between the two-dimensional feature matching data and the two-dimensional feature standard data. The expression is: e i =|μ-μ i |+|s-s i | Output the well number information of the corresponding matching shale gas well with the smallest absolute value distance and the corresponding time sliding window date information.

5. The method for matching shale gas liquid accumulation intermittent production wells according to claim 4, characterized in that: The S3 further includes: 3-6: According to the well number information of the corresponding matching shale gas well with the smallest absolute value distance obtained in S3-5 and the corresponding time sliding window date information, obtain the intermittent time information and intermittent operation information of the shale gas well after the corresponding time sliding window date information ends; S3-7: Generate the intermittent time and intermittent operation of the target shale gas well according to the acquired intermittent time information and intermittent operation information of the shale gas well.

6. A system for matching shale gas liquid accumulation intermittent production wells, applied to a method for matching shale gas liquid accumulation intermittent production wells as described in any one of claims 1 to 5 above, characterized in that: include: A data acquisition module, used to acquire multi-dimensional production data of a target shale gas well in a current preset time period, and to acquire historical production data of a shale gas well matching the target shale gas well; A data preprocessing module is used to divide the historical production data of the matching shale gas wells into several groups of window data by constructing a time sliding window; The intermittent production matching module is used to construct an intermittent production well matching model, input the multi-dimensional production data of the target shale gas well in the current preset time period and several groups of window data into the intermittent production well matching model, and output the matching shale gas well information that meets the intermittent production requirements of the target shale gas well.

7. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores programs or instructions, and the processor executes a method for matching shale gas liquid accumulation intermittent production wells as described in any one of claims 1 to 5 by calling the programs or instructions stored in the memory.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and the programs or instructions enable a computer to execute a method for matching shale gas liquid accumulation intermittent production wells as described in any one of claims 1 to 5.

Images