Inter-well connectivity analysis method for asymmetric time data alignment

Abstract

The invention provides an asymmetric time data alignment inter-well connectivity analysis method, which comprises the following steps of: S1, constructing preliminary representation of an original one-dimensional injection-production time sequence based on graph convolution, and constructing a graph structure framework of an inter-well connectivity analysis model; s2, according to different time window settings in the airspace, the one-dimensional injection-production time sequence structure is remodeled into a two-dimensional injection-production time sequence structure, so that inter-well communication relation feature extraction is carried out; s3, performing inter-well correlation degree characterization of the two-dimensional injection-production time sequence data in the frequency domain through Fourier transform; and S4, training a graph neural network inter-well connectivity model after feature extraction, and carrying out inter-well connectivity representation by using a reconstruction error of an injection-production time sequence rule. According to the method, the complex and subtle time sequence dependency relationship in the asymmetric injection-production time sequence data can be more accurately captured; information carried by each frequency component can be independently described and analyzed, and inaccuracy and misleading possibly caused by noise smoothing and overfitting problems are effectively avoided.

Description

Technical Field

[0001] The present invention belongs to the field of petroleum engineering, and in particular, relates to an inter-well connectivity analysis method for asymmetric time data alignment. Background Art

[0002] When the reservoir is running low on energy after a period of natural energy development and enters the second phase of development, water injection is an important way to increase oil recovery. However, in order to ensure that oil is transferred from injection wells to production wells, managers must analyze the connectivity of the wells. In water-driven reservoirs, underground flow is invisible and is affected by heterogeneous geophysical properties such as porosity, compressibility, and especially permeability. Interwell connectivity analysis is an important part of reservoir characterization, which aims to quantify the contribution of injection wells to production wells, thereby reflecting the relative permeability strength of the flow channel. Based on the analysis of interwell connectivity, the oil field makes hydrodynamic adjustments such as water plugging, profile adjustment, and well network optimization.

[0003] Traditional connectivity identification methods include well testing, tracer methods, and numerical simulation methods. These traditional methods have the disadvantages of high cost, limited application, and long time consumption. Oil fields have a large amount of production and water injection data, which are essentially related to inter-well connectivity. Data-driven methods provide a useful solution to the problem of calculating inter-well connectivity characteristics, aiming to calculate point-by-point similarities without considering the impact of time series, but the processing of multi-well interference is still a difficult problem. CRM is a common method for dealing with the impact of history on the current timestamp, which is derived from the material balance equation and the linear productivity model. The current inter-well connectivity analysis has the problem of poor accuracy. Summary of the invention

[0004] The embodiment of the present application provides an inter-well connectivity analysis method with asymmetric time data alignment, which can independently depict and analyze the information carried by each frequency component, thereby effectively avoiding the inaccuracy and misleading caused by noise smoothing and overfitting problems in the inter-well connectivity analysis.

[0005] The present application embodiment provides a well connectivity analysis method for asymmetric time data alignment, including:

[0006] S1, constructs a preliminary representation of the original one-dimensional injection-production time series based on graph convolution, and builds a graph structure framework for the well connectivity analysis model;

[0007] S2, in the spatial domain, according to different time window settings, the one-dimensional injection-production time series structure is reshaped into a two-dimensional injection-production time series structure to extract the features of the well-to-well connectivity relationship;

[0008] S3, characterize the inter-well correlation degree of two-dimensional injection-production time series data in the frequency domain by Fourier transform;

[0009] S4, the graph neural network well connectivity model after training feature extraction, uses the reconstruction error of the injection and production timing law to characterize the well connectivity.

[0010] Wherein, step S1 comprises:

[0011] S1.1, obtain the injection and production dynamic data of the block to be studied from the monitoring system of the oil reservoir block, and construct the original one-dimensional injection and production time series data with asymmetry in the time dimension; obtain the geological data of the block to be studied;

[0012] S1.2, when using graph convolutional networks for well connectivity analysis, feature embedding is performed on the original one-dimensional time series data; through the combined effect of graph convolutional mapping and position encoding, the original one-dimensional injection and production time series that is asymmetric in the time dimension is input into the embedding module for processing and feature conversion, thereby obtaining a preliminary representation of the injection and production data time series;

[0013] S1.3, building a graph structure framework of the well-to-well connectivity analysis model; based on the geological data obtained in step S1.1, establishing a graph neural network well-to-well connectivity analysis model using different nodes to represent each production well and each water injection well; wherein, when the first node represents the first production well, the first node is characterized by the liquid production of the first production well formation; when the second node represents the second water injection well, the second node is characterized by the water injection of the second water injection well formation; the edges of the graph neural network model are used for the distance and relative position between the third well point and other well points; the third well point is a production well or a water injection well, and the other well points are production wells or water injection wells;

[0014] The input end of the graph neural network well-to-well connectivity analysis model is used to input the liquid production of each production well and the water injection volume of each water injection well; the output end of the graph neural network well-to-well connectivity analysis model is used to output the predicted liquid production of each production well.

[0015] Among them, the geological data include the number of injection wells, the number of production wells, the distance between each production well and each injection well, the distance between each production well and each production well, the distance between each injection well and each injection well, the relative position between each production well and each injection well, the relative position between each production well and each production well, and the relative position between each injection well and each injection well, as well as perforation parameters, layer depth, effective thickness, permeability and porosity.

[0016] Wherein, step S2 comprises:

[0017] S2.1, according to the collection frequency characteristics of the production and water injection data of the block to be studied, select multiple different time windows as the period P of the two-dimensional injection-production time series structure to be reshaped;

[0018] S2.2, for each selected period P, the original one-dimensional injection-production time series data is segmented with a time length of P and reshaped into a two-dimensional matrix of P×S, where S represents the number of periods contained in this time length. In this way, the inter-well connectivity relationship features in the spatial domain are extracted.

[0019] The period P is 1 hour, 6 hours or 12 hours.

[0020] Wherein, step S3 comprises:

[0021] S3.1, decomposing the two-dimensional injection-production time series structure in the frequency domain by Fourier transform to obtain a series of two-dimensional injection-production time series representations with different frequency characteristics;

[0022] S3.2, characterize the inter-well correlation degree of the one-dimensional structure Fourier component under each independent frequency component, and integrate the multi-scale information through fusion strategy;

[0023] S3.3, perform inverse Fourier transform on the data after information fusion in step S3.2 to restore the data to a two-dimensional structure. The formula is as follows:

[0024] X 2D * =iFFT(X 2D ')∈R P×S×c

[0025] Where, X 2D * is the reshaped two-dimensional original data obtained in step S2.2, iFFT is the inverse Fourier transform process, X 2D ′ is the data after information fusion in step S3.2;

[0026] S3.4, based on the multiple reconstructed two-dimensional data sets obtained, these two-dimensional injection and production data structures based on different time modes are restored one by one to their original one-dimensional states, and through fusion, they are integrated into new one-dimensional injection and production time series data, and the new one-dimensional injection and production time series data conforms to a symmetrical relationship in space.

[0027] Among them, step S3.1 includes: applying Fourier transform technology to the two-dimensional injection-production time series structure obtained in step S2.2 to realize Fourier decomposition of the signal, thereby obtaining a series of different Fourier components, which contain the detailed details and overall trend characteristics of the original sequence.

[0028] Wherein, step S4 comprises:

[0029] S4.1, using the new one-dimensional injection-production time series data obtained in step S3.4, training a graph neural network well connectivity analysis model;

[0030] S4.2, by finally obtaining the new one-dimensional injection-production time series data in step S3.4 and the reconstruction error of its original injection-production, construct the learning criteria for model training, and perform gradient update on the parameters in the model until the training error meets the preset conditions; if the preset conditions of the model training error are not met, return to step 2 and retrain until the requirements are met;

[0031] S4.3, after the model training is completed, the well connectivity characterization results guided by the reconstruction error after data alignment are obtained, and the production dynamic data of the liquid production of each production well is output.

[0032] In step S4.2, a learning criterion for model training is constructed, and the parameters in the model are gradient updated until the training error is less than 10 -2 If the model training error is less than 10 -2 If the requirement is not met, return to step 2 and retrain until the requirement is met.

[0033] The well connectivity analysis method of asymmetric time data alignment in the embodiment of the present application has the following beneficial effects:

[0034] This application reconstructs the original one-dimensional injection-production time series data into two-dimensional injection-production time series data from the perspective of multiple time windows, so that the well connectivity analysis has a diverse time pattern. By deeply characterizing and analyzing such two-dimensional data, the complex and subtle time series dependencies in asymmetric injection-production time series data can be captured more accurately.

[0035] This application uses the frequency domain analysis method and introduces Fourier decomposition technology to finely divide the original reservoir injection and production data into multiple component data with different frequency characteristics. This can independently depict and analyze the information carried by each frequency component, thereby effectively avoiding the inaccuracy and misleading caused by noise smoothing and overfitting problems in the well connectivity analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the flow chart of the well connectivity analysis method for asymmetric time data alignment according to an embodiment of the present application;

[0037] Figure 2 Another schematic diagram of the flow chart of the well connectivity analysis method for asymmetric time data alignment according to an embodiment of the present application;

[0038] Figure 3 Schematic diagram of the overall structure of the asymmetric time-aligned well connectivity analysis method. DETAILED DESCRIPTION

[0039] The present application is further described below in conjunction with the accompanying drawings and embodiments.

[0040] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present invention, and different embodiments can be replaced or combined, so this application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more of all other possible combinations of features A, B, C, and D, even though the embodiment may not be clearly recorded in the following text.

[0041] Embodiment 1

[0042] In the complex process of oil reservoir production, all links are closely connected to form a huge data network. Among them, injection and production dynamic data is a crucial link in this network. During the injection and production process, various devices and sensors will record a large amount of data in real time, which reflects the dynamic changes inside the reservoir. These data include injection volume, production volume, pressure changes, temperature fluctuations, etc., which are constantly changing over time, so they can form a series of time series. These time series data are not just a pile of numbers, they contain rich information. First, they can intuitively show the production status of the reservoir at different time points and provide decision-making basis for engineers and technicians. Secondly, these data are essentially closely related to inter-well connectivity. Therefore, the time series in the injection and production dynamic data should be fully considered and applied in the work of connectivity analysis.

[0043] When forming time series, injection and production data often show complex multi-time patterns, which lead to data asymmetry in the time dimension. Specifically, different types of injection and production data may have different acquisition frequencies and regularities. For example, liquid production data is usually collected on a daily basis, because for daily reservoir management, the acquisition frequency of once a day is sufficient to meet the needs. However, water injection data is different. Since water injection operations require more sophisticated control and monitoring, the data collection frequency is often higher, sometimes even every half an hour. When trying to apply these time series data to connectivity analysis, this asymmetry will directly affect the accuracy and reliability of the analysis and processing. In addition, data with multiple time patterns may also complicate the analysis model and reduce the efficiency and real-time performance of the analysis.

[0044] In order to process these injection and production data that are asymmetric in the time dimension, the present invention proposes an inter-well connectivity analysis method for asymmetric time data alignment, such as Figure 1As shown, it includes: S1, constructing a preliminary representation of the original one-dimensional injection-production time series based on graph convolution, and building a graph structure framework for the well-to-well connectivity analysis model; S2, reshaping the one-dimensional injection-production time series structure into a two-dimensional injection-production time series structure according to different time window settings in the spatial domain to extract the features of the well-to-well connectivity relationship; S3, characterizing the well-to-well correlation degree of the two-dimensional injection-production time series data in the frequency domain through Fourier transform; S4, training the well-to-well connectivity model of the graph neural network after feature extraction, and using the reconstruction error of the injection-production time series law to characterize the well-to-well connectivity.

[0045] This application uses the frequency domain analysis method and introduces Fourier decomposition technology to finely divide the original reservoir injection and production data into multiple component data with different frequency characteristics. This can independently depict and analyze the information carried by each frequency component, thereby effectively avoiding the inaccuracy and misleading caused by noise smoothing and overfitting problems in the well connectivity analysis.

[0046] Embodiment 2

[0047] In the process of exploration and development of a certain oil reservoir block, in order to accurately evaluate the connectivity between wells, it is necessary to analyze the production and water injection data of the block. Considering that the production data is collected every 10 minutes, and the water injection data is collected once a day, these two different data collection frequencies bring challenges to the analysis. This embodiment will use a method based on graph convolution, multi-scale time window reconstruction and Fourier transform to extract the inter-well connectivity relationship features of the injection and production data, and finally obtain the representation of the inter-well connectivity.

[0048] Step 1: Construct a preliminary representation of the original one-dimensional injection-production time series based on graph convolution, and build a graph structure framework for the well-to-well connectivity analysis model.

[0049] Step 1.1, from the monitoring system of the reservoir block, obtain the injection and production dynamic data of the block to be studied. Since the injection and production sampling time intervals are different, the original one-dimensional injection and production time series data with asymmetry in the time dimension is formed. At the same time, obtain the geological data of the block to be studied; wherein, the geological data include the number of injection wells, the number of production wells, the distance between each production well and each injection well, the distance between each production well and each production well, the distance between each injection well and each injection well, the relative position between each production well and each injection well, the relative position between each production well and each production well, and the relative position between each injection well and each injection well, as well as perforation parameters, layer depth, effective thickness, permeability and porosity and other data.

[0050] Step 1.2, when using Graph Convolutional Networks (GCN) for well connectivity analysis, feature embedding is performed on the original one-dimensional time series data. Through the combined effect of graph convolutional mapping and position encoding, the original one-dimensional injection and production time series, which is asymmetric in the time dimension, is input into the embedding module for processing and feature transformation, thereby obtaining a preliminary representation of the injection and production data time series. Here, we assume that the convolution kernel of GCN is k and the output dimension is d. At the same time, in order to deal with the asymmetry in the time dimension, position encoding is introduced. Through the combined effect of GCN and position encoding, the original one-dimensional time series data is input into the embedding module, feature transformation is performed, and a preliminary time series representation is obtained.

[0051] Step 1.3, build a graph structure framework of the well-to-well connectivity analysis model; based on the geological data obtained in step 1.1, establish a graph neural network well-to-well connectivity analysis model using different nodes to represent each production well and each water injection well; wherein, when the node represents a production well, the characteristic of the node is the liquid production of the production well in the formation, and when the node represents a water injection well, the characteristic of the node is the water injection volume of the water injection well in the formation; the edges of the graph neural network model are used for the distance and relative position between a well point and other well points; one well point is a production well or a water injection well, and the other well points are production wells or water injection wells.

[0052] The input end of the graph neural network well-to-well connectivity analysis model is used to input the liquid production of each production well and the water injection volume of each water injection well; the output end of the graph neural network well-to-well connectivity analysis model is used to output the predicted liquid production of each production well.

[0053] Step 2: In the spatial domain, according to different time window settings, the one-dimensional injection-production time series structure is reshaped into a two-dimensional injection-production time series structure to extract the features of the well-to-well connectivity relationship.

[0054] Step 2.1, according to the acquisition frequency characteristics of the production and injection data of the block to be studied, select multiple different time windows as the period P of the two-dimensional injection-production time series structure to be reshaped. For example, 1 hour, 6 hours, 12 hours, etc. can be selected as the period P.

[0055] Step 2.2, for each selected period P, the original one-dimensional injection-production time series data is segmented with P as the time length and reshaped into a two-dimensional matrix of P×S. Where S represents the number of periods contained in the time length. In this way, the well connectivity relationship features in the spatial domain are extracted.

[0056] This structure is designed to simultaneously show the changing trend of data within a single cycle, as well as the changes and relationships between data across S cycles. This conversion method not only retains the temporal characteristics of time series data, but also enables injection and production data with different periodic attributes to blend and interact with each other in two-dimensional space through spatial display, further mining and revealing the deep information of injection and production time series data.

[0057] Step 3: Characterize the inter-well correlation degree of two-dimensional injection-production time series data in the frequency domain through Fourier transform.

[0058] Step 3.1, decompose the two-dimensional injection-production time series structure in the frequency domain through Fourier transform to obtain a series of two-dimensional injection-production time series representations with different frequency characteristics.

[0059] Specifically, for the two-dimensional injection-production time series structure obtained in step 2.2, the Fourier transform technology is applied to realize the Fourier decomposition of the signal, thereby obtaining a series of different Fourier components. These components contain the detailed details and overall trend characteristics of the original sequence, and can accurately capture the local changes of the signal in the two dimensions of time and frequency.

[0060] The specific working principle of Fourier transform is that, first, a one-dimensional fast Fourier transform operation is performed on each row of two-dimensional data to obtain the low-frequency component L and high-frequency component H of each row in the horizontal direction. Then, a one-dimensional fast Fourier transform operation is performed again on each column of the data after row transformation to obtain four different frequency component combinations.

[0061] Step 3.2, characterize the inter-well correlation degree of the one-dimensional structural Fourier component under each independent frequency component, and integrate the multi-scale information through a fusion strategy. This helps to more comprehensively understand the inter-well connectivity related characteristics contained in the injection and production data.

[0062] Step 3.3, perform inverse Fourier transform on the data after information fusion in step 3.2 to restore the data to a two-dimensional structure. The formula is as follows:

[0063] X 2D * =iFFT(X 2D ')∈R P×S×c

[0064] Where, X 2D * is the reshaped two-dimensional original data obtained in step 2.2, iFFT is the inverse Fourier transform process, X 2D ' is the data after information fusion in step 3.2.

[0065] Step 3.4, based on the multiple reconstructed two-dimensional data sets obtained, these two-dimensional injection and production data structures based on different time modes are restored one by one to their original one-dimensional state, and through fusion, they are integrated into a complete and more meaningful new one-dimensional injection and production time series data. At this time, the injection and production data conform to the symmetric relationship in space. Here is feature extraction and integration, in order to better reflect the correlation between the data.

[0066] Step 4: Train the graph neural network well connectivity model after feature extraction, and use the reconstruction error of the injection and production time sequence to characterize the well connectivity.

[0067] Step 4.1, using the new one-dimensional injection-production time series data obtained in step 3.4, train the graph neural network well connectivity analysis model.

[0068] Step 4.2: Based on the reconstruction error between the new one-dimensional injection-production time series data and its original injection-production data finally obtained in step 3.4, the learning criteria for model training are constructed, and the parameters in the model are gradient updated until the training error is less than 10 -2 If the model training error is less than 10 -2 If the requirements are met, return to step 2 to reselect the time scale, reconstruct the data, and retrain until the requirements are met.

[0069] Step 4.3, after the model training is completed, the well connectivity characterization results guided by the reconstruction error after data alignment are obtained, and the production dynamic data of the liquid production of each production well is output.

[0070] This example successfully processed production and water injection data with different sampling frequencies by combining graph convolution, multi-scale time window reconstruction, and Fourier transform, and obtained the characterization of well connectivity. This method not only improves the understanding of fluid flow inside the reservoir block, but also provides strong technical support for the exploration and development of the reservoir block.

[0071] This application reconstructs the original one-dimensional injection-production time series data into two-dimensional injection-production time series data from the perspective of multiple time windows, so that the well connectivity analysis has a diverse time pattern. By deeply characterizing and analyzing such two-dimensional data, the complex and subtle time series dependencies in asymmetric injection-production time series data can be captured more accurately.

[0072] This application uses the frequency domain analysis method and introduces Fourier decomposition technology to finely divide the original reservoir injection and production data into multiple component data with different frequency characteristics. This can independently depict and analyze the information carried by each frequency component, thereby effectively avoiding the inaccuracy and misleading caused by noise smoothing and overfitting problems in the well connectivity analysis.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for well connectivity analysis based on asymmetric time data alignment, characterized in that: include: S1, constructs a preliminary representation of the original one-dimensional injection-production time series based on graph convolution, and builds a graph structure framework for the well connectivity analysis model; S2, in the spatial domain, according to different time window settings, the one-dimensional injection-production time series structure is reshaped into a two-dimensional injection-production time series structure to extract the features of the well-to-well connectivity relationship; S3, characterize the inter-well correlation degree of two-dimensional injection-production time series data in the frequency domain by Fourier transform; S4, the graph neural network well connectivity model after training feature extraction, uses the reconstruction error of the injection and production timing law to characterize the well connectivity.

2. The well connectivity analysis method of asymmetric time data alignment according to claim 1, characterized in that: Step S1 includes: S1.1, obtain the injection and production dynamic data of the block to be studied from the monitoring system of the oil reservoir block, and construct the original one-dimensional injection and production time series data with asymmetry in the time dimension; obtain the geological data of the block to be studied; S1.2, when using graph convolutional networks for well connectivity analysis, feature embedding is performed on the original one-dimensional time series data; through the combined effect of graph convolutional mapping and position encoding, the original one-dimensional injection and production time series that is asymmetric in the time dimension is input into the embedding module for processing and feature conversion, thereby obtaining a preliminary representation of the injection and production data time series; S1.3, building a graph structure framework of the well-to-well connectivity analysis model; based on the geological data obtained in step S1.1, establishing a graph neural network well-to-well connectivity analysis model using different nodes to represent each production well and each water injection well; wherein, when the first node represents the first production well, the first node is characterized by the liquid production of the first production well formation; when the second node represents the second water injection well, the second node is characterized by the water injection of the second water injection well formation; the edges of the graph neural network model are used for the distance and relative position between the third well point and other well points; the third well point is a production well or a water injection well, and the other well points are production wells or water injection wells; The input end of the graph neural network well-to-well connectivity analysis model is used to input the liquid production of each production well and the water injection volume of each water injection well; the output end of the graph neural network well-to-well connectivity analysis model is used to output the predicted liquid production of each production well.

3. The well connectivity analysis method of asymmetric time data alignment according to claim 2, characterized in that: The geological data include the number of injection wells, the number of production wells, the distance between each production well and each injection well, the distance between each production well and each production well, the distance between each injection well and each injection well, the relative position between each production well and each injection well, the relative position between each production well and each production well, and the relative position between each injection well and each injection well, as well as perforation parameters, layer depth, effective thickness, permeability and porosity.

4. The well connectivity analysis method of asymmetric time data alignment according to any one of claims 1 to 3, characterized in that: Step S2 includes: S2.1, according to the collection frequency characteristics of the production and water injection data of the block to be studied, select multiple different time windows as the period P of the two-dimensional injection-production time series structure to be reshaped; S2.2, for each selected period P, the original one-dimensional injection-production time series data is segmented with a time length of P and reshaped into a two-dimensional matrix of P×S, where S represents the number of periods contained in this time length. In this way, the inter-well connectivity relationship features in the spatial domain are extracted.

5. The well connectivity analysis method of asymmetric time data alignment according to claim 4, characterized in that: The period P is 1 hour, 6 hours or 12 hours.

6. The well connectivity analysis method of asymmetric time data alignment according to claim 4, characterized in that: Step S3 includes: S3.1, decomposing the two-dimensional injection-production time series structure in the frequency domain by Fourier transform to obtain a series of two-dimensional injection-production time series representations with different frequency characteristics; S3.2, characterize the inter-well correlation degree of the one-dimensional structure Fourier component under each independent frequency component, and integrate the multi-scale information through fusion strategy; S3.3, perform inverse Fourier transform on the data after information fusion in step S3.2 to restore the data to a two-dimensional structure. The formula is as follows: X 2D * =iFFT(X 2D ')∈R P×S×c In the formula, X 2D * is the reshaped two-dimensional original data obtained in step S2.2, iFFT is the inverse Fourier transform process, X 2D ′ is the data after information fusion in step S3.2; S3.4, based on the multiple reconstructed two-dimensional data sets obtained, these two-dimensional injection and production data structures based on different time modes are restored one by one to their original one-dimensional states, and through fusion, they are integrated into new one-dimensional injection and production time series data, and the new one-dimensional injection and production time series data conforms to a symmetrical relationship in space.

7. The well connectivity analysis method of asymmetric time data alignment according to claim 6, characterized in that: Step S3.1 includes: applying Fourier transform technology to the two-dimensional injection-production time series structure obtained in step S2.2 to realize Fourier decomposition of the signal, thereby obtaining a series of different Fourier components, which contain detailed details and overall trend characteristics of the original sequence.

8. The well connectivity analysis method of asymmetric time data alignment according to claim 6 or 7, characterized in that: Step S4 includes: S4.1, using the new one-dimensional injection-production time series data obtained in step S3.4, training a graph neural network well connectivity analysis model; S4.2, by finally obtaining the new one-dimensional injection-production time series data in step S3.4 and the reconstruction error of its original injection-production, construct the learning criteria for model training, and perform gradient update on the parameters in the model until the training error meets the preset conditions; if the preset conditions of the model training error are not met, return to step 2 and retrain until the requirements are met; S4.3, after the model training is completed, the well connectivity characterization results guided by the reconstruction error after data alignment are obtained, and the liquid production dynamic data of each production well are output.

9. The well connectivity analysis method of asymmetric time data alignment according to claim 8, characterized in that: In step S4.2, the learning criteria for model training are constructed, and the parameters in the model are gradient updated until the training error is less than 10 -2 If the model training error is less than 10 -2 If the requirement is not met, return to step 2 and retrain until the requirement is met.

Images