Shale gas well productivity potential assessment method, device and equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of shale gas exploration and development, and provides a shale gas well productivity potential assessment method, device and equipment and a storage medium, and the method comprises the steps: obtaining shale characteristic attribute data of a target shale gas well area and a corresponding recovery ratio; eliminating redundant data in the shale characteristic attribute data to obtain shale characteristic attribute data after elimination; on the basis of a deep learning model, feature reconstruction is carried out on the shale feature attribute data after elimination according to a preset feature extraction number, and shale features and corresponding shale feature values are obtained; forming a feature matrix by the shale feature value and the recovery ratio, and inputting the feature matrix into a pre-trained clustering model to obtain a clustering result of the target shale gas well block; and evaluating the shale gas productivity potential of each shale gas well in the target shale gas well area according to the clustering result and the shale characteristic value. According to the embodiment of the invention, the reliability and accuracy of shale gas productivity potential evaluation can be improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of shale gas exploration and development, and particularly to a shale gas well productivity potential evaluation method, device, equipment and storage medium. BACKGROUND

[0002] With the increasing demand for energy and the pursuit of clean energy worldwide, shale gas, as a key unconventional natural gas resource, is attracting unprecedented attention for its development and utilization. Due to the low porosity, low permeability and high heterogeneity of shale gas reservoirs, these characteristics greatly increase the complexity of shale gas exploitation, far exceeding the difficulty of conventional oil and gas reservoirs. Under such circumstances, accurate evaluation of the productivity potential of shale gas wells is particularly critical, as it is directly related to the optimization of exploitation schemes, the improvement of resource utilization efficiency and the maximization of economic benefits.

[0003] However, the current evaluation methods, such as geological interpretation, numerical simulation and empirical inference, all have certain limitations. The geological interpretation method, although relying on rich field data and expert knowledge, is affected by subjective judgment uncertainty and data incompleteness, and may not fully reveal the true productivity potential of shale gas wells. This subjectivity may lead to biased evaluation results, affecting the accuracy of exploitation decisions and the effective use of resources. The numerical simulation method, although capable of simulating the complex dynamics of the reservoir, is tedious and time-consuming in calculation and extremely sensitive to initial parameters, making it difficult to quickly adapt to rapid changes in field conditions, which may lead to delays in exploitation schemes and losses in economic benefits. The method based on empirical inference is limited by the representativeness of historical data and the limitations of expert experience, and may not accurately predict the productivity of new wells or unknown wells. This limitation may lead to overestimation or underestimation of the productivity of new wells, affecting investment decisions and the rational allocation of resources. Therefore, there is an urgent need for a shale gas well productivity potential evaluation method to solve the problems of low evaluation accuracy and high calculation cost in the prior art. SUMMARY

[0004] In view of the above problems of the prior art, the purpose of the embodiments of the present specification is to provide a shale gas well productivity potential evaluation method, device, equipment and storage medium to solve the problems of low evaluation accuracy and high calculation cost of shale gas well productivity potential in the prior art.

[0005] To solve the above technical problems, the specific technical solutions of the embodiments of the present specification are as follows:

[0006] On the one hand, the embodiments of the present specification provide a shale gas well productivity potential evaluation method, which comprises:

[0007] obtaining shale characteristic attribute data and corresponding recovery factor of a target shale gas well area;

[0008] The redundant data in the shale characteristic attribute data is removed to obtain removed shale characteristic attribute data;

[0009] The removed shale characteristic attribute data is reconstructed according to a preset feature extraction number based on a deep learning model to obtain shale characteristics and corresponding shale characteristic values;

[0010] The shale characteristic values and the recovery factor form a feature matrix which is input into a pre-trained clustering model to obtain a clustering result of the target shale gas well block;

[0011] The shale gas production potential of each shale gas well in the target shale gas well block is evaluated according to the clustering result and the shale characteristic values.

[0012] Preferably, the shale characteristics include geological characteristics, drilling characteristics and fracturing characteristics;

[0013] The geological characteristics include vertical depth data, TOC data, porosity data, 1 sublayer thickness data, gas saturation data and brittle mineral amount data;

[0014] The drilling characteristics include fracturing segment length data and I-class reservoir drilling length data;

[0015] The fracturing characteristics include average segment spacing data, fluid intensity data, sand intensity data and average displacement data.

[0016] Preferably, the removed shale characteristic attribute data is reconstructed according to a preset feature extraction number based on a deep learning model to obtain shale characteristics and corresponding shale characteristic values, including:

[0017] The removed shale characteristic attribute data is convoluted by a convolution layer to obtain a first shale feature map and corresponding feature weights;

[0018] The first shale feature map is input into a pooling layer for down-sampling to obtain a second shale feature map;

[0019] The second shale feature map and the corresponding feature weights are input into a fully connected layer for regression to output corresponding shale characteristic values.

[0020] Preferably, the clustering model is a K-means++ clustering model, and the shale characteristic values and the recovery factor form a feature matrix which is input into a pre-trained clustering model to obtain a clustering result of the target shale gas well block, including:

[0021] S1: randomly select a sample from the input data as a first initial clustering center;

[0022] S2: calculating the shortest distance between each remaining sample in the input data and the first initial clustering center, and determining the probability of each remaining sample being selected as the next clustering center according to the shortest distance;

[0023] S3: selecting the next clustering center by roulette method according to the probability, and repeating steps S1-S2 until a preset number of second initial clustering centers is determined;

[0024] S4: calculating the distance between each sample in the input data except the second initial clustering center and each second initial clustering center, and dividing it into the class corresponding to the second initial clustering center with the smallest distance, to obtain a first clustering result;

[0025] S5: re-determining the clustering center according to the first clustering result;

[0026] S6: repeating steps S4-S5 until the change of the clustering center meets a preset convergence condition, to obtain a final clustering result.

[0027] Preferably, the shale gas production potential of each shale gas well in the target shale gas well area is evaluated according to the clustering result and shale characteristic values, including:

[0028] According to the clustering result, the target shale gas well area is divided into a number of productivity potential categories corresponding to the clustering clusters;

[0029] According to the shale characteristic values, the geological feature mean value, drilling feature mean value and fracturing feature mean value in each productivity potential category are calculated;

[0030] The productivity potential of each productivity potential category is evaluated according to the geological feature mean value, drilling feature mean value and fracturing feature mean value.

[0031] Preferably, the productivity potential of each productivity potential category is evaluated according to the geological feature mean value, drilling feature mean value and fracturing feature mean value, including:

[0032] According to the geological feature mean value, the geological condition is evaluated to obtain a geological condition evaluation result;

[0033] According to the drilling feature mean value and the fracturing feature mean value, the fracturing effect is evaluated to obtain a fracturing effect evaluation result;

[0034] According to the geological condition evaluation result and the fracturing effect evaluation result, the productivity potential is evaluated to obtain a productivity potential evaluation result.

[0035] In another aspect, the embodiments of the present specification provide a shale gas well productivity potential evaluation device, the device comprising:

[0036] The acquisition module is configured to acquire shale characteristic attribute data and corresponding recovery rates of a target shale gas well area.

[0037] The characteristic attribute elimination module is configured to eliminate redundant data in the shale characteristic attribute data to obtain eliminated shale characteristic attribute data.

[0038] The characteristic reconstruction module is configured to reconstruct the eliminated shale characteristic attribute data based on a deep learning model according to a preset number of characteristic extraction to obtain shale characteristics and corresponding shale characteristic values.

[0039] The clustering module is configured to input the shale characteristic values and the recovery rates into a pre-trained clustering model to obtain a clustering result of the target shale gas well area.

[0040] The evaluation module is configured to evaluate shale gas production potential of each shale gas well in the target shale gas well area according to the clustering result and the shale characteristic values.

[0041] In another aspect, the embodiments of the present specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory, when the computer program is run by the processor, instructions of any one of the above methods are executed.

[0042] In another aspect, the embodiments of the present specification also provide a computer readable storage medium, having a computer program stored thereon, when the computer program is run by a processor of a computer device, instructions of any one of the above methods are executed.

[0043] In another aspect, the embodiments of the present specification also provide a computer program product, when the computer program product is run by a processor of a computer device, instructions of any one of the above methods are executed.

[0044] The one or more technical solutions provided by some embodiments of the present specification have at least the following technical effects:

[0045] The embodiments of the present specification first automatically extract and filter key features by using a deep learning model, solve the problems of subjectivity and incomplete data in traditional evaluation methods, ensure the objectivity and accuracy of the evaluation results, and then use a clustering algorithm to cluster according to the extracted features, so that the clustering process can automatically adapt to the actual characteristics of the data, improve the accuracy and adaptability of the classification. Finally, the shale gas production potential of the shale gas well is evaluated according to the clustering result and the shale characteristic value, thereby improving the objectivity and accuracy of the evaluation. In addition, compared with the numerical simulation method in the prior art, the embodiments of the present specification can quickly process and analyze a large amount of data, meet the needs of real-time or near real-time production evaluation, and provide timely decision support for rapidly changing exploitation environments.

[0046] The above description is only a summary of some technical solutions of the embodiments of the present specification. In order to enable a clearer understanding of the technical means of some embodiments of the present specification, the technical means can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the present specification more obvious and easy to understand, the preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present specification or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present specification, and those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0048] Figure 1 An implementation environment schematic diagram of a shale gas well productivity potential evaluation method in some embodiments of the present specification is shown;

[0049] Figure 2 A flowchart schematic diagram of a shale gas well productivity potential evaluation method in some embodiments of the present specification is shown;

[0050] Figure 3 A flowchart schematic diagram of reconstructing features of shale feature attribute data after elimination based on a deep learning model according to a preset feature extraction number to obtain shale features and corresponding shale feature values in some embodiments of the present specification is shown;

[0051] Figure 4 A flowchart schematic diagram of inputting the shale feature values and recovery efficiency into a pre-trained clustering model to obtain a clustering result of the target shale gas well block in some embodiments of the present specification is shown;

[0052] Figure 5 A profile coefficient trend graph with the number of clustering clusters k in some embodiments of the present specification is shown;

[0053] Figure 6 A CH value trend graph with the number of clustering clusters k in some embodiments of the present specification is shown;

[0054] Figure 7 A flowchart schematic diagram of evaluating shale gas productivity potential of each shale gas well in the target shale gas well block according to the clustering result and shale feature value in some embodiments of the present specification is shown;

[0055] Figure 8This specification illustrates a flowchart of an evaluation process for each of the described production potential categories based on the mean values ​​of the geological features, drilling features, and fracturing features, in some embodiments of this specification.

[0056] Figure 9 This specification shows a schematic diagram of the structure of a shale gas well production potential assessment device in some embodiments;

[0057] Figure 10 A schematic diagram of the structure of a computer device is shown in this specification.

[0058] Explanation of symbols in the attached drawings:

[0059] 901. Acquisition Module;

[0060] 902. Feature Attribute Removal Module;

[0061] 903. Feature Reconstruction Module;

[0062] 904, Clustering Module;

[0063] 905. Evaluation Module;

[0064] 1002. Computer equipment;

[0065] 1004, Processor;

[0066] 1006. Memory;

[0067] 1008. Drive mechanism;

[0068] 1010. Input / Output Module;

[0069] 1012. Input devices;

[0070] 1014. Output devices;

[0071] 1016. Presentation device;

[0072] 1018. Graphical User Interface;

[0073] 1020. Network interface;

[0074] 1022. Communication link;

[0075] 1024. Communication bus. Detailed Implementation

[0076] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0077] It should be noted that the terms "first," "second," etc., used in this specification, claims, and the foregoing drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0078] like Figure 1The diagram shown illustrates the implementation environment of a shale gas well production potential assessment method according to an embodiment of this specification. It may include a terminal 101 and a server 102. The terminal 101 and the server 102 communicate with each other through a network. The network may include a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof, and is connected to a website, user equipment (e.g., computing devices), and a backend system. The server 102 can be used to acquire shale characteristic attribute data and corresponding recovery rates of the target shale gas well area; to remove redundant data from the shale characteristic attribute data to obtain the removed shale characteristic attribute data; to reconstruct features of the removed shale characteristic attribute data based on a deep learning model according to a preset number of feature extractions to obtain shale features and corresponding shale feature values; to input the shale feature values ​​and recovery rates into a feature matrix and input it into a pre-trained clustering model to obtain the clustering results of the target shale gas well block; and to evaluate the shale gas production potential of each shale gas well in the target shale gas well area based on the clustering results and shale feature values. Optionally, the server 102 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0079] In an optional embodiment, the terminal 101 may be an electronic device, including but not limited to self-service terminal equipment, desktop computers, tablet computers, laptops, smart wearable devices, etc. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, Windows, etc. Of course, the terminal 101 is not limited to the aforementioned physical electronic devices; it may also be software running on the aforementioned electronic devices.

[0080] It should be noted that, Figure 1 This is merely one implementation environment for the shale gas well production potential assessment method provided in this application embodiment. In practical applications, other implementation environments may also be included.

[0081] Figure 2This is a flowchart illustrating a method for assessing the production potential of shale gas wells, as provided in the embodiments of this specification. This specification provides the operational steps of the methods described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or accompanying drawings can be executed sequentially or in parallel. Specifically, as shown in the embodiments or accompanying drawings... Figure 2 As shown, the method includes:

[0082] S201: Obtain shale characteristic attribute data and corresponding recovery rate of the target shale gas well area;

[0083] S202: Redundant data in the shale characteristic attribute data are removed to obtain the shale characteristic attribute data after removal;

[0084] S203: Based on a deep learning model, feature reconstruction is performed on the removed shale feature attribute data according to a preset number of feature extractions to obtain shale features and corresponding shale feature values;

[0085] S204: Input the shale feature values ​​and recovery rate into a feature matrix and then into a pre-trained clustering model to obtain the clustering results of the target shale gas well block;

[0086] S205: Evaluate the shale gas production potential of each shale gas well in the target shale gas well area based on the clustering results and shale characteristic values.

[0087] This specification's embodiments first utilize a deep learning model to automatically extract and filter key features, addressing the subjectivity and data incompleteness issues of traditional evaluation methods and ensuring the objectivity and accuracy of the evaluation results. Then, a clustering algorithm is used to cluster based on the extracted features, allowing the clustering process to automatically adapt to the actual characteristics of the data, improving the accuracy and adaptability of the classification. Finally, the shale gas production potential of shale gas wells is evaluated based on the clustering results and shale characteristic values, thereby improving the objectivity and accuracy of the evaluation. Furthermore, compared to existing numerical simulation methods, this specification's embodiments can quickly process and analyze large amounts of data, meeting the needs of real-time or near-real-time production capacity evaluation and providing timely decision support for rapidly changing mining environments.

[0088] This specification's embodiments use shale characteristic attribute data and recovery rate (EUR) from 287 fractured shale gas wells in the target shale gas well area as experimental data for evaluation. The EUR is estimated in advance based on the shale characteristic attribute data and can be directly obtained from the petroleum system. In some embodiments, the shale characteristic attribute data mainly includes vertical depth data, TOC data, porosity data, fracture section length data, gas saturation data, brittle mineral content data, and proppant strength data. To reduce feature redundancy and subsequent low computational efficiency, it is necessary to extract strongly correlated characteristic attributes from the shale characteristic attribute data. Optionally, this can be achieved by calculating the Pearson correlation coefficient between shale characteristic attribute data and removing any shale characteristic attribute from two shale characteristic attributes with a Pearson correlation coefficient greater than a preset threshold, resulting in the removed shale characteristic attribute data. In the embodiments of this specification, the shale characteristic attribute data after rejection consists of 12 items, including vertical depth data, TOC data, porosity data, thickness of the first sublayer data, gas saturation data, brittle mineral content data, fracturing section length data, drilling length of Class I reservoir data, average interval data, fluid intensity data, sand addition intensity data, and average displacement data. Among them, the thickness of the first sublayer refers to the Longmaxi first sublayer, which can also be called the Long 1 sublayer. Its gas content and organic carbon content are generally the highest, making it the optimal target for shale gas. Theoretically, the thicker its thickness, the more reserves it can control. The drilling length of Class I reservoir data refers to the length of Class I reservoir encountered and traversed during the drilling process.

[0089] To ensure the quality and accuracy of the acquired data, the removed shale characteristic attribute data needs to be normalized. This scaling process brings feature variables with different scales and ranges to the same range, eliminating the influence of differences in units and dimensions. This allows different feature variables to be compared and analyzed on the same scale. Normalization improves the performance, training speed, and convergence of subsequent deep learning models, reduces the risk of overfitting, and enhances generalization ability. It also facilitates computation and understanding. Optionally, in the embodiments of this specification, the removed shale characteristic attribute data is normalized using the following formula:

[0090]

[0091] Where, x ij Let x represent the characteristic attribute data of the j-th shale in the i-th sample. i ′ j This represents the data after normalization. σ represents the mean of the characteristic attribute data of the j-th shale. j This represents the standard deviation of the characteristic attribute data of the j-th shale.

[0092] In this embodiment, the deep learning model is a Convolutional Neural Network (CNN). CNN is a type of deep neural network based on convolutional feature extraction. Unlike deep neural networks with simple nonlinear processing, it uses a hierarchical extraction method, no longer connecting all input and hidden layers, but instead using a filter weight sharing method to simplify the number of parameters and improve the efficiency of feature extraction. When used as a feature extraction tool, CNN extracts and merges the original feature attribute data into interpretable and strong features based on the weights obtained from deep learning, according to the set number of features to be extracted. In this embodiment, the preset number of features to be extracted is set to three categories: geological features, fracturing features, and drilling features, based on the shale characteristic attributes. By using CNN to automatically extract key features from the preprocessed shale characteristic attribute data, the dimensionality of clustering features is reduced, thereby improving the clustering analysis effect.

[0093] In some embodiments, reference is made to Figure 3 The deep learning model reconstructs the shale feature attribute data after removal based on a preset number of feature extractions to obtain shale features and corresponding shale feature values, including:

[0094] S301: Use a convolutional layer to perform a convolution operation on the removed shale feature attribute data to obtain the first shale feature map and the corresponding feature weights;

[0095] S302: Input the first shale feature map into the pooling layer for downsampling to obtain the second shale feature map;

[0096] S303: Input the second shale feature map and the corresponding feature weights into the fully connected layer for regression, and output the corresponding shale feature values.

[0097] Specifically, geological features are designated as C1, fracturing features as C2, and drilling features as C3. Through automatic extraction using a CNN, 12 shale characteristic attribute data are reconstructed into three new features: C1, C2, and C3. The geological features include vertical depth data, TOC data, porosity data, first-layer thickness data, gas saturation data, and brittle mineral content data. The drilling features include fracturing section length data and Class I reservoir encounter length data. The fracturing features include average interval data, fluid intensity data, proppant addition intensity data, and average displacement data. The feature attribute data weight matrix obtained after CNN processing is as follows:

[0098] W=[0.079,0.100,0.093,0.070,0.066,0.150,0.063,0.071,0.060,0.081,0.110,0.059] T ;

[0099] in,

[0100]

[0101] Therefore, we can calculate that:

[0102] Geological characteristics are:

[0103] Fracturing characteristic values ​​are:

[0104] Drilling characteristic values ​​are:

[0105] Therefore, the feature values ​​of the three types of shale characteristics can be calculated. Then, the feature matrix composed of the three types of shale feature values ​​and EUR is input into a pre-trained clustering model to obtain the clustering results of the target shale gas well block. The size of the feature matrix is ​​4×287. In the embodiments of this specification, the clustering model is a K-means++ clustering model. K-means++ selects initial cluster centers in a specific way, making the distance between initial centers as large as possible, thereby dispersing the centers in the initial stage and reducing the risk of getting trapped in local optima. Compared with the K-means model that randomly selects initial centers, the initialization method of K-means++ can select better initial centers, thereby improving the accuracy and stability of the clustering results, accelerating the model's convergence speed, and having a better ability to handle large amounts of data. The K-means++ clustering model automatically classifies shale gas wells into corresponding categories based on geological characteristics, fracturing characteristics, and drilling characteristics for use in assessing production potential.

[0106] In some embodiments, reference is made to Figure 4 The step of inputting a feature matrix composed of the shale feature values ​​and recovery rates into a pre-trained clustering model to obtain the clustering results of the target shale gas well block includes the following steps:

[0107] S1: Randomly select a sample from the input data as the first initial cluster center;

[0108] S2: Calculate the shortest distance between each remaining sample in the input data and the first initial cluster center, and determine the probability that each remaining sample will be selected as the next cluster center based on the shortest distance;

[0109] S3: Select the next cluster center using the roulette wheel method according to the probability, and repeat steps S1-S2 until the preset number of second initial cluster centers are determined;

[0110] S4: Calculate the distance from each sample in the input data (excluding the second initial cluster center) to each second initial cluster center and assign it to the class corresponding to the second initial cluster center with the smallest distance, to obtain the first clustering result;

[0111] S5: Based on the first clustering result, redetermine its cluster center;

[0112] S6: Repeat steps S4-S5 until the changes in the cluster centers satisfy the preset convergence condition to obtain the final clustering result.

[0113] Specifically, to obtain the optimal number of clusters k, this specification sets k∈[2,9] for sensitivity analysis. Clustering is performed with different k values, and the trends of silhouette coefficient and CH value with the number of clusters k are shown below. Figure 5 and Figure 6 As shown in the figure, when k=5, both the profile coefficient and the CH value are at their maximum values. Therefore, the optimal number of clusters is determined to be 5. This can be understood as classifying shale gas wells in the target shale gas well area into five categories based on geological characteristics, drilling characteristics, fracturing characteristics, and EUR.

[0114] In some embodiments, reference is made to Figure 7 The shale gas production potential of each shale gas well in the target shale gas well area is evaluated based on the clustering results and shale characteristic values, including:

[0115] S401: Based on the clustering results, the target shale gas well area is divided into several clusters with production potential categories;

[0116] S402: Calculate the mean geological characteristics, mean drilling characteristics, and mean fracturing characteristics for each of the aforementioned production potential categories based on the shale characteristic values;

[0117] S403: Assess the production potential of each of the aforementioned production potential categories based on the average geological characteristics, average drilling characteristics, and average fracturing characteristics.

[0118] This can be understood as classifying shale gas wells into different production potential categories based on clustering results, and assessing the production potential of each category based on shale characteristic values. A higher mean geological characteristic value indicates better geological conditions, which are more conducive to later construction and stimulation. The fracturing characteristic value characterizes the scale of fracturing operations; a larger value indicates a greater amount of liquid or sand injected into the well, and theoretically, a larger scale of operations would yield better stimulation results. The drilling characteristic value characterizes the quality of drilling technology; a larger value indicates a better and more solid drilling of the shale gas well, reducing the likelihood of various problems during construction that could lead to reduced production later.

[0119] In some embodiments, reference is made toFigure 8 The assessment of the production potential of each of the aforementioned production potential categories based on the average geological characteristics, average drilling characteristics, and average fracturing characteristics includes:

[0120] S501: The geological conditions are evaluated based on the average value of the geological characteristics to obtain the geological condition evaluation results;

[0121] S502: Evaluate the fracturing effect based on the average drilling characteristics and the average fracturing characteristics to obtain the fracturing effect evaluation result;

[0122] S503: Based on the geological conditions assessment results and the fracturing effect assessment results, the production capacity potential is assessed to obtain the production capacity potential assessment results.

[0123] Specifically, this specification divides the 287 shale gas wells in the target shale gas well area into 5 categories, and the detailed characteristics and data statistics of each category are shown in Table 1.

[0124] Table 1

[0125]

[0126] Table 1 shows that the 136 wells in categories 1 and 2 have good geological conditions and high production potential in this shale gas well area. Among them, 33 wells in category 1 have the best fracturing effect, higher EUR (Earnings Per Second), and larger actual production. Wells in category 2, due to unreasonable fracturing parameter design or engineering problems such as sand blockage during fracturing, have lower EUR, and their production potential has not been fully realized. The average C1 value of wells in category 3 is slightly lower than that of wells in category 2, but their average EUR is higher. Therefore, it can be determined that the production potential of wells in category 3 is slightly lower than that of categories 2 and 1. However, due to their relatively successful fracturing operations, their actual production is higher. Wells in categories 4 and 5 have the lowest average EUR and geological characteristic values. Therefore, it can be determined that the geological conditions of these wells are poor, resulting in low production potential and low actual production. Although many factors contribute to low shale gas well production, if the reservoir conditions for shale gas formation are poor, both its production potential and actual output will be lower. Furthermore, it can be inferred from Table 1 that the value of C1 can indicate the quality of the geological conditions of the shale gas wells in this block, and the larger the C1 value, the better the geological conditions, and vice versa.

[0127] Therefore, the production potential categories of the target shale gas wells can be determined as follows:

[0128] Category 1: Excellent geological conditions, good fracturing effect, and huge production potential;

[0129] Category 2: Geological conditions are good, but the fracturing effect is average, and the production capacity potential is high;

[0130] Category 3: Moderate geological conditions, unstable fracturing effect, and moderate production potential;

[0131] Category 4: Poor geological conditions, limited fracturing effect, and low production potential;

[0132] Category 5: Poor geological conditions, poor fracturing effect, and the lowest production capacity potential.

[0133] By classifying shale gas block wells, the production potential of wells in the block was correctly evaluated. Therefore, based on the evaluation results, shale gas wells worth developing can be selected, and fracturing parameters can be formulated and optimized according to the characteristics of each category to develop a reasonable development strategy. Wells in categories 1 and 3 can be used as standard wells for the block. Wells in categories 1 and 2 have good geological conditions and high production potential in the target shale gas well area. However, wells in category 2 have lower EUR (Effective Potential) due to unreasonable fracturing parameter design or engineering problems such as sand blockage during fracturing, resulting in insufficient exploitation of their production potential. The average value of wells in category 3 is slightly lower than that of wells in category 2, but their average EUR is higher. Therefore, it can be determined that the production potential of wells in category 3 is slightly lower than that of categories 2 and 1. However, due to their relatively successful fracturing operations, their actual production capacity is higher. Therefore, the fracturing parameters for wells in category 2 need to be optimized, and the specific values ​​will vary depending on the different blocks. Specifically, for fracturing and stimulation of shale gas wells with favorable geological conditions, the drilling parameters and fracturing operation parameters of wells in Category 1 can be referenced. The specific parameter ranges are shown in Table 2.

[0134] Table 2

[0135]

[0136]

[0137] As shown in Table 2, the brittle mineral content of Category 1 wells ranges from 65.80% to 96%, with an average of 84.17%, and the thickness of the first sublayer ranges from 2.60m to 7.60m, with an average of 6.35m. For wells with general geological conditions, i.e., Category 2 wells, the engineering design parameters for Category 3 wells can be referenced, and the specific parameter ranges are shown in Table 3.

[0138] Table 3

[0139]

[0140] Table 3 shows that the brittle mineral content of wells in category 3 ranges from 69% to 90%, with an average of 81.71%, and the thickness of the first minor layer ranges from 2.50m to 7.30m, with an average of 5.32m. The comparison reveals that higher brittle mineral content and greater organic layer thickness indicate better geological conditions and higher shale gas well production potential. For wells in categories 4 and 5, due to their lowest average EUR and geological characteristic values, it can be concluded that these wells have poor geological conditions, low production potential, and low actual production. Development of these wells is recommended to be abandoned to reduce resource waste.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the acquisition, storage, use, and processing of data in the technical solutions described in the embodiments of this application all comply with relevant regulations.

[0142] Based on the shale gas well production potential assessment method described above, this specification also provides a shale gas well production potential assessment device. The device may include a system (including a distributed system), software (application), module, component, server, client, etc., using the method described in this specification, combined with necessary implementation hardware. Based on the same innovative concept, the devices in one or more embodiments provided in this specification are as described in the following embodiments. Since the implementation schemes and methods for solving the problem are similar, the implementation of specific devices in this specification can refer to the implementation of the aforementioned method, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0143] Specifically, Figure 9 This is a schematic diagram of the module structure of one embodiment of a shale gas well production potential assessment device provided in this specification. (Refer to...) Figure 9 As shown in the embodiments of this specification, a shale gas well production potential assessment device includes:

[0144] The acquisition module 901 is used to acquire shale characteristic attribute data and corresponding recovery rates of the target shale gas well area;

[0145] The feature attribute removal module 902 is used to remove redundant data from the shale feature attribute data to obtain the removed shale feature attribute data.

[0146] The feature reconstruction module 903 is used to reconstruct the features of the removed shale feature attribute data based on a deep learning model according to a preset number of feature extractions, so as to obtain shale features and corresponding shale feature values.

[0147] Clustering module 904 is used to input the shale feature values ​​and recovery rate into a feature matrix and then into a pre-trained clustering model to obtain the clustering results of the target shale gas well block.

[0148] The evaluation module 905 is used to evaluate the shale gas production potential of each shale gas well in the target shale gas well area based on the clustering results and shale characteristic values.

[0149] The beneficial effects obtained by the apparatus provided in the embodiments of this specification are consistent with the beneficial effects obtained by the methods described above, and will not be repeated here.

[0150] Reference Figure 10 As shown, based on the above-described method for assessing the production potential of shale gas wells, one embodiment of this specification also provides a computer device 1002, wherein the above-described method operates on the computer device 1002. The computer device 1002 may include one or more processors 1004, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The computer device 1002 may also include any memory 1006 for storing information of any kind, such as code, settings, data, etc. Non-limitingly, for example, the memory 1006 may include any one or more combinations of: any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1002. In one case, when the processor 1004 executes associated instructions stored in any memory or combination of memories, the computer device 1002 can perform any operation of the associated instructions. The computer device 1002 also includes one or more drive mechanisms 1008 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0151] Computer device 1002 may also include an input / output module 1010 (I / O) for receiving various inputs (via input device 1012) and providing various outputs (via output device 1014). A specific output mechanism may include a presentation device 1016 and an associated graphical user interface (GUI) 1018. In other embodiments, the input / output module 1010 (I / O), input device 1012, and output device 1014 may be omitted, and the device may function solely as a computer device within a network. Computer device 1002 may also include one or more network interfaces 1020 for exchanging data with other devices via one or more communication links 1022. One or more communication buses 1024 couple the components described above together.

[0152] The communication link 1022 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. The communication link 1022 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0153] Corresponding to, for example Figures 1 to 4 and Figures 7 to 8 In addition to the method shown, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described method.

[0154] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the following... Figures 1 to 4 and Figures 7 to 8 The method.

[0155] This specification also provides a computer program product, including at least one instruction or at least one program segment, wherein the at least one instruction or the at least one program segment is loaded and executed by a processor to achieve the following: Figures 1 to 4 and Figures 7 to 8 The method.

[0156] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0157] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this specification generally indicates that the preceding and following related objects have an "or" relationship.

[0158] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this specification.

[0159] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0160] In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0161] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0162] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0163] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0164] This specification uses specific embodiments to illustrate the principles and implementation methods of this specification. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this specification. Therefore, the content of this specification should not be construed as a limitation of this specification.

Claims

1. A method for assessing the production potential of shale gas wells, characterized in that, The method includes: Acquire shale characteristic attribute data and corresponding recovery rates for the target shale gas well area; Redundant data is removed from the shale characteristic attribute data to obtain the shale characteristic attribute data after removal. Based on a deep learning model, the feature attributes of the removed shale feature data are reconstructed according to a preset number of feature extractions to obtain shale features and corresponding shale feature values. The shale feature values ​​and recovery rates are used to construct a feature matrix, which is then input into a pre-trained clustering model to obtain the clustering results of the target shale gas well block. The shale gas production potential of each shale gas well in the target shale gas well area is evaluated based on the clustering results and shale characteristic values.

2. The method according to claim 1, characterized in that, The shale characteristics include geological features, drilling features, and fracturing features; The geological features mentioned include vertical depth data, TOC data, porosity data, sublayer thickness data, gas saturation data, and brittle mineral content data; The drilling characteristics include data on the length of the fractured section and the length of Class I reservoir encountered. The fracturing characteristics include average segment spacing data, fluid intensity data, sand addition intensity data, and average displacement data.

3. The method according to claim 1, characterized in that, The deep learning model reconstructs the features of the removed shale feature attribute data according to a preset number of feature extractions, obtaining shale features and corresponding shale feature values, including: The discarded shale feature attribute data are convolved using a convolutional layer to obtain the first shale feature map and the corresponding feature weights. The first shale feature map is input into the pooling layer for downsampling to obtain the second shale feature map; The second shale feature map and its corresponding feature weights are input into the fully connected layer for regression, and the corresponding shale feature values ​​are output.

4. The method according to claim 1, characterized in that, The clustering model is a K-means++ clustering model. The shale feature values ​​and recovery rates are used to construct a feature matrix, which is then input into the pre-trained clustering model to obtain the clustering results for the target shale gas well block, including: S1: Randomly select a sample from the input data as the first initial cluster center; S2: Calculate the shortest distance between each remaining sample in the input data and the first initial cluster center, and determine the probability that each remaining sample will be selected as the next cluster center based on the shortest distance; S3: Select the next cluster center using the roulette wheel method according to the probability, and repeat steps S1-S2 until the preset number of second initial cluster centers are determined; S4: Calculate the distance from each sample in the input data (excluding the second initial cluster center) to each second initial cluster center and assign it to the class corresponding to the second initial cluster center with the smallest distance, to obtain the first clustering result; S5: Based on the first clustering result, redetermine its cluster center; S6: Repeat steps S4-S5 until the changes in the cluster centers satisfy the preset convergence condition to obtain the final clustering result.

5. The method according to claim 2, characterized in that, The assessment of the shale gas production potential of each shale gas well in the target shale gas well area based on the clustering results and shale characteristic values ​​includes: Based on the clustering results, the target shale gas well area is divided into several clusters with production potential categories. Calculate the mean geological features, mean drilling features, and mean fracturing features for each of the aforementioned production potential categories based on the shale characteristic values; The production potential of each of the aforementioned production potential categories is assessed based on the mean values ​​of geological features, drilling features, and fracturing features.

6. The method according to claim 5, characterized in that, The assessment of the production potential of each of the aforementioned production potential categories based on the average geological characteristics, average drilling characteristics, and average fracturing characteristics includes: The geological conditions are assessed based on the average value of the geological characteristics, and the geological condition assessment results are obtained. The fracturing effect is evaluated based on the average values ​​of the drilling characteristics and the average values ​​of the fracturing characteristics, and the fracturing effect evaluation results are obtained. Based on the geological condition assessment results and the fracturing effect assessment results, the production capacity potential is evaluated to obtain the production capacity potential assessment results.

7. A device for assessing the production potential of shale gas wells, characterized in that, The device includes: The acquisition module is used to acquire shale characteristic attribute data and corresponding recovery rates for the target shale gas well area; The feature attribute removal module is used to remove redundant data from the shale feature attribute data to obtain the removed shale feature attribute data. The feature reconstruction module is used to reconstruct the features of the removed shale feature attribute data based on a deep learning model according to a preset number of feature extractions, so as to obtain shale features and corresponding shale feature values. The clustering module is used to input the shale feature values ​​and recovery rates into a feature matrix and then into a pre-trained clustering model to obtain the clustering results of the target shale gas well block. An evaluation module is used to assess the shale gas production potential of each shale gas well in the target shale gas well area based on the clustering results and shale characteristic values.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes at least one instruction or at least one program segment, said at least one instruction or said at least one program segment being loaded and executed by a processor to implement the method as claimed in any one of claims 1 to 6.

Images