Method and device for predicting productivity of oil and gas reservoirs

Abstract

An embodiment of the present invention discloses a method and device for predicting the productivity of an oil and gas reservoir. The method includes: preprocessing logging data and reservoir productivity data to construct a standardized sample set; constructing and training a constrained neural network according to the sample set, and adding neurons as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network; the input of the constraint element is calculated by a rock mechanics seepage model; obtaining the logging data of the reservoir to be predicted and inputting it into the constrained neural network to obtain the reservoir productivity under unit pressure difference. By adding constraint elements to the constrained neural network and establishing a constrained neural network under the constraint of a rock mechanics seepage model, the present invention can complete the prediction of reservoir productivity at the logging resolution, thereby improving the accuracy of the prediction.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing in oil exploration, and particularly to a method and device for predicting the productivity of oil and gas reservoirs. Background Art

[0002] Productivity refers to the ability of an oil and gas reservoir to produce fluids under formation conditions. It is the basic data for reservoir productivity evaluation and development plan formulation, and also an important parameter for determining the lower limit of reservoir physical properties. The productivity of a reservoir is jointly determined by the reservoir's own conditions, engineering factors, and oil and gas properties. The factors affecting reservoir geological characteristics are complex and multi-faceted. It is very difficult to predict reservoir productivity using complex parameters. Methods such as productivity comprehensive index and reservoir category index have their limitations and one-sidedness in reservoir productivity prediction, and it is impossible to accurately quantify reservoir productivity with a precise mathematical method, resulting in inaccurate prediction results and unreliable comprehensive evaluation. Formation testing is currently the most direct and effective method for verifying reservoir fluid properties and obtaining formation productivity in oil and gas exploration. However, due to the high difficulty and cost of downhole operations, it is limited to local reservoir operations. Therefore, a conclusion of productivity prediction is required as data support for formation testing before formation testing. Summary of the Invention

[0003] In view of the above problems, the embodiments of the present invention are proposed to provide a method and device for predicting the productivity of oil and gas reservoirs that overcome the above problems or at least partially solve the above problems.

[0004] According to one aspect of the embodiments of the present invention, a method for predicting the productivity of an oil and gas reservoir is provided. The method includes:

[0005] Preprocess the logging data and reservoir productivity data to construct a standardized sample set;

[0006] Construct and train a constrained neural network based on the sample set, and add neurons as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network; the input of the constraint elements is calculated by a rock mechanics seepage model;

[0007] Obtain the logging data of the reservoir to be predicted, input it into the constrained neural network, and obtain the reservoir productivity under unit pressure difference.

[0008] According to another aspect of the embodiments of the present invention, a device for predicting the productivity of an oil and gas reservoir is provided, which includes:

[0009] A sample construction module, adapted to preprocess the logging data and reservoir productivity data to construct a standardized sample set;

[0010] A training module is adapted to construct and train a constrained neural network based on a sample set, and add neurons as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network; the input of the constraint elements is calculated by a rock mechanics seepage model.

[0011] A prediction module is adapted to obtain well logging data of a reservoir to be predicted and input it into the constrained neural network to obtain the reservoir productivity under a unit pressure difference.

[0012] According to another aspect of an embodiment of the present invention, a computing device is provided, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface complete communication with each other through the communication bus;

[0013] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned oil and gas reservoir productivity prediction method.

[0014] According to still another aspect of an embodiment of the present invention, a computer storage medium is provided, and at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to execute the operations corresponding to the above-mentioned oil and gas reservoir productivity prediction method.

[0015] According to the oil and gas reservoir productivity prediction method and device provided by the embodiment of the present invention, by adding constraint elements to the constrained neural network and establishing a constrained neural network under the constraint of a rock mechanics seepage model, the prediction of reservoir productivity at well logging resolution can be completed, thereby improving the prediction accuracy.

[0016] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to be able to understand the technical means of the embodiments of the present invention more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of the embodiments of the present invention more obvious and understandable, the following specifically describes the specific embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the embodiments of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0018] Figure 1 The flowchart of the oil and gas reservoir productivity prediction method according to an embodiment of the present invention is shown;

[0019] Figure 2 The structural schematic diagram of the oil and gas reservoir productivity prediction device according to an embodiment of the present invention is shown;

[0020] Figure 3 Shows a schematic structural diagram of a computing device according to an embodiment of the present invention. Detailed implementation manners

[0021] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0022] Figure 1 Shows a flowchart of a method for predicting the productivity of an oil and gas reservoir according to an embodiment of the present invention, as Figure 1 shown, the method includes the following steps:

[0023] Step S101, preprocess the logging data and reservoir productivity data to construct a standardized sample set.

[0024] The productivity of a reservoir is jointly determined by the reservoir's own conditions, engineering factors, and oil and gas properties, etc. The factors affecting the reservoir geological characteristics are complex and multi-faceted. It is very difficult to predict the productivity of a reservoir using complex parameters. Existing technologies have their limitations and one-sidedness in predicting the productivity of oil and gas reservoirs using methods such as the productivity comprehensive index and reservoir category index, and cannot accurately quantitatively characterize the reservoir productivity with a fine mathematical method, resulting in inaccurate prediction results and unreliable comprehensive evaluation.

[0025] In this embodiment, a sample set is constructed according to the logging data and the measured reservoir productivity data for subsequent training of the constructed productivity prediction neural network. Since the dynamic change laws of each phase fluid in the reservoir are different, the reservoir productivity is divided into oil productivity and gas productivity according to the reservoir fluid properties. When constructing the sample set, the oil productivity and gas productivity need to be divided into different categories of data respectively to construct the sample set. For example, a sample set is constructed with the logging data and the reservoir oil productivity data for the productivity prediction neural network for predicting oil productivity, and a sample set is constructed with the logging data and the reservoir gas productivity data for the productivity prediction neural network for predicting gas productivity.

[0026] Since the testing conditions vary when testing the formation productivity, and the formation testing reservoir productivity data are all the productivity of a certain section of the formation, it is also necessary to standardize the constructed sample set to remove the limitations and one-sidedness of the constructed sample set. Specifically, considering that the logging data of different logging operations are obtained by different acquisition methods, different well conditions, different instruments used for acquisition, etc., resulting in different logging data standards, the logging data is normalized. The normalization is performed according to the maximum and minimum values of the logging data to make their response differences within the same order of magnitude, thereby unifying the measurement units of the logging data and enabling better discovery of its regularity during training. During normalization, if the value of a certain logging data is m, the maximum value is x, and the minimum value is y, the normalization can be performed using the method of (m - y) / (x - y). The normalization can be set according to the actual situation to normalize the logging data to the 0-1 interval, etc. The specific calculation method of the normalization is not limited here. When performing data preprocessing on the logging data, one or more of the above methods can be selected according to the actual situation to make the logging data more regular and facilitate accurate training of the neural network. In addition, outliers in the logging data are removed, such as determining outliers according to technical means such as crossplot plates and removing them. Considering that the logging data has depth points at specified intervals, if the depth points corresponding to the reservoir productivity data are not included in the logging data, the logging data corresponding to the depth points of the reservoir productivity data are interpolated using the interpolation method based on the adjacent upper and lower depths of the logging data to fill in the required missing values. The above methods for calculating the logging data are for illustrative purposes, and the logging data of the required depth points are specifically calculated according to the actual situation, which is not limited here. For the reservoir productivity data, the reservoir productivity data is normalized, and the reservoir productivity under unit pressure difference is calculated. The reservoir productivity is divided by the production pressure difference to obtain the reservoir productivity under unit pressure difference. Then, according to the specified unit average permeability, the specified unit reservoir productivity is calculated. For example, if the specified unit average permeability is the average permeability in meters, the average permeability in meters is used as the weight coefficient. Considering that the permeabilities of different formations are different, the reservoir productivity is taken as an example of oil productivity. For example, a reservoir with a thickness of x meters produces y cubic meters of oil per day. The ratio of the unit average permeability to the total permeability of the reservoir is used as the weight coefficient and multiplied by the reservoir productivity to calculate the reservoir productivity per unit meter, that is, the specified unit reservoir productivity. Using the logging data of the specified unit reservoir as the input data of the sample set and the specified unit reservoir productivity as the output data of the sample set, a standardized sample set is constructed to ensure the accuracy of the data in the sample set. For ease of understanding, the above is described by taking oil productivity as an example. The construction of the standardized sample sets for oil productivity and gas productivity can both be constructed with reference to the above description, which is not limited here.

[0027] Step S102, construct and train a constrained neural network according to the sample set.

[0028] The input layer of the constrained neural network is specified unit reservoir logging data, and the output layer is the productivity of the specified unit reservoir. Based on the conventional neural network structure, the constrained neural network consists of an input layer, a constraint layer, a hidden layer, and an output layer. Among them, the constraint layer is a network layer with specified additional constraint elements, and the constrained neural network is constructed by adding neurons as constraint elements in the constraint layer. Specifically, neurons are added as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network. Among them, the input of the constraint element is calculated by the rock mechanics seepage model and is in a non-connected state with the neurons in the input layer, and the other neurons in the constraint layer are in a fully connected state with the neurons in the input layer. The input of the constraint element of the constrained neural network is provided by the rock mechanics seepage model, and the output is fully connected to the next hidden layer. The weights and biases of the constraint element are jointly adjusted with other neurons. Compared with the conventional model, the constrained neural network has a wider application range and higher calculation accuracy, and can well solve the limitations and one-sidedness of the current oil and gas reservoir productivity prediction methods.

[0029] Specifically, the constrained neural network has a specified number of layers. For example, the constrained neural network has a five-layer neural network structure, and the second specified layer is a fully connected layer. For example, the first two layers are fully connected layers, and the number of neurons in the first layer is twice that of the second layer, which is used for feature extraction. The number of neurons in the third layer is halved on the basis of the second layer, and at the same time, one neuron is added as a constraint element for input. This constraint element is calculated by the rock mechanics seepage model, and the rock mechanics seepage model can adopt the following formula:

[0030]

[0031] Among them, q is the constraint element, k is the absolute permeability contained in the logging data, k r is the relative permeability, μ is the viscosity, B is the volume coefficient, r e is the equivalent radius, r w is the wellbore radius, and S′ is the apparent skin factor. The constraint element is calculated by the rock mechanics seepage model. Among them, k is the absolute permeability contained in the logging data in the sample set and can be directly input in the input layer, and the other parameters are directly input when constructing the constrained neural network. The number of neurons in the fourth layer is twice that of the third layer and is fully connected to the neurons in the third layer, which is used for data refinement; the last layer is the output layer, which is used to output the productivity of the specified unit reservoir. The above formula is for illustrative purposes, and in specific implementation, the formula corresponding to the appropriate rock mechanics seepage model can be selected according to the implementation situation, and no limitation is made here.

[0032] The sample set adopted by the constrained neural network biases towards the formations with better productivity. If no constraint elements are added to the constraint layer, using a conventional neural network can accurately predict the formations with better productivity, but poorly predict the formations with poor productivity. The formula treats both the formations with good or poor productivity in a regular way. Combining the reservoir productivity calculated by the formula with the constrained neural network makes the regularity of the constrained neural network more accurate and applicable to various formations.

[0033] During training, the sample set can be divided by means of K-Fold cross-validation and divided into a test sample set and a validation sample set for training. Input the sample set into the constrained neural network. At the third layer, according to the permeability contained in the well logging data of the sample set and each parameter, the reservoir productivity calculated by the formula is used as the added constraint element and input into the third layer to train and adjust the training parameters of the constrained neural network, completing the training of the constrained neural network.

[0034] The models of the constrained neural network include, for example, regional models, general models, etc., and the type is determined according to the quantity size, distribution range, etc. of the sample set. Select and construct a constrained neural network of a suitable type according to the implementation situation.

[0035] Step S103: Obtain the well logging data of the reservoir to be predicted and input it into the constrained neural network to obtain the reservoir productivity under unit pressure difference.

[0036] Obtain the well logging data to be predicted and input it into the trained constrained neural network to obtain the prediction result. The prediction result includes the reservoir productivity curve under the well logging resolution of unit pressure difference. The energy storage productivity of the formation is related to the production pressure difference. Under different production pressure differences, the reservoir productivity is different. When actually applied, according to the production pressure difference and the depth range of the layer to be predicted, perform an accumulation process on the reservoir productivity curve under the well logging resolution of unit pressure difference, and multiply the accumulated result by the actual production pressure difference to calculate the reservoir productivity of the layer to be predicted.

[0037] According to the oil and gas reservoir productivity prediction method provided by the embodiment of the present invention, by adding constraint elements to the constrained neural network and establishing a constrained neural network under the constraint of the rock mechanics seepage model, the prediction of the reservoir productivity under well logging resolution can be completed, thereby improving the prediction accuracy.

[0038] Figure 2 The structural schematic diagram of the oil and gas reservoir productivity prediction device provided by the embodiment of the present invention is shown. As Figure 2 shown, the device includes:

[0039] A sample construction module 210, suitable for preprocessing the well logging data and reservoir productivity data to construct a standardized sample set;

[0040] A construction training module 220, which is adapted to construct and train a constrained neural network according to a sample set, and add neurons as constraint elements in a first specified layer of the constrained neural network to constrain the calculation of the constrained neural network; the input of the constraint elements is calculated by a rock mechanics seepage model;

[0041] A prediction module 230, which is adapted to obtain well logging data of a reservoir to be predicted, input it into the constrained neural network, and obtain the reservoir productivity under a unit pressure difference.

[0042] Optionally, the construction sample module 210 is further adapted to:

[0043] Perform normalization processing on the well logging data, eliminate outliers, and use the interpolation method to complete the missing values;

[0044] Perform normalization processing on the reservoir productivity data, and calculate the reservoir productivity under a unit pressure difference;

[0045] Calculate the specified unit reservoir productivity according to the specified unit average permeability;

[0046] Use the well logging data of the specified unit reservoir as the input data of the sample set, and use the specified unit reservoir productivity as the output data of the sample set to construct a standardized sample set.

[0047] Optionally, the constrained neural network structure consists of an input layer, a constraint layer, a hidden layer, and an output layer, where the constraint layer is the network layer where the constraint elements are specified to be added.

[0048] Optionally, the constraint elements of the constraint layer are not connected to the neurons of the input layer, and the other neurons of the constraint layer are fully connected to the neurons of the input layer.

[0049] Optionally, the constraint layer is constrained by a rock mechanics seepage model, and the rock mechanics seepage model is used to calculate the constraint elements of the constraint layer.

[0050] Optionally, the input of the constraint elements of the constrained neural network is provided by a rock mechanics seepage model, and the output is fully connected to the next hidden layer; the weights and biases of the constraint elements are jointly adjusted with other neurons.

[0051] Optionally, the model of the constrained neural network includes a regional model and / or a general model; the type is determined according to the quantity size and / or distribution range of the sample set.

[0052] The descriptions of the above modules refer to the corresponding descriptions in the method embodiments and will not be elaborated here.

[0053] An embodiment of the present invention also provides a non-volatile computer storage medium, and the computer storage medium stores at least one executable instruction, and the executable instruction can execute the oil and gas reservoir productivity prediction method in any of the above method embodiments.

[0054] Figure 3 FIG. 2 shows a schematic structural diagram of a computing device according to an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0055] As Figure 3 shown, the computing device may include: a processor 302, a communications interface 304, a memory 306, and a communication bus 308.

[0056] It is characterized in that:

[0057] The processor 302, the communications interface 304, and the memory 306 communicate with each other through the communication bus 308.

[0058] The communications interface 304 is used to communicate with network elements of other devices such as clients or other servers.

[0059] The processor 302 is used to execute the program 310, and specifically may execute the relevant steps in the above-mentioned embodiments of the oil and gas reservoir productivity prediction method.

[0060] Specifically, the program 310 may include program code, and the program code includes computer operation instructions.

[0061] The processor 302 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0062] The memory 306 is used to store the program 310. The memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0063] The program 310 is specifically used to cause the processor 302 to execute the oil and gas reservoir productivity prediction method in any of the above method embodiments. For the specific implementation of each step in the program 310, reference may be made to the corresponding steps and units in the above-mentioned embodiments of the oil and gas reservoir productivity prediction, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, which will not be repeated here.

[0064] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. A variety of general-purpose systems can also be used in conjunction with the teachings provided herein. The structure required to construct such systems will be apparent from the above description. In addition, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the embodiments of the present invention described herein can be implemented using a variety of programming languages, and the descriptions made above regarding specific languages are for the purpose of disclosing the preferred embodiments of the present invention.

[0065] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies have not been shown in detail so as not to obscure the understanding of this specification.

[0066] Similarly, it should be understood that, in order to streamline the embodiments of the present invention and assist in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be construed as reflecting an intention that the claimed embodiments of the present invention require more features than are expressly recited in each claim. Rather, as reflected in the following claims, the inventive aspects lie in less than all of the features of the single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present invention.

[0067] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and disposed in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except for the fact that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose.

[0068] In addition, those skilled in the art can understand that although some embodiments herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

[0069] Each component embodiment of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. Embodiments of the present invention can also be implemented as a device or apparatus program (for example, a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the embodiments of the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0070] It should be noted that the above embodiments illustrate the embodiments of the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for predicting the productivity of an oil and gas reservoir, characterized in that the method include: Preprocess the well logging data and reservoir productivity data to construct a standardized sample set; A constrained neural network is constructed and trained according to the sample set, and neurons are added as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network; the constrained neural network is composed of an input layer, a constraint layer, a hidden layer, and an output layer, and the constraint layer is a network layer for specifying the addition of constraint elements; the constraint element input is calculated by a rock mechanics seepage model, the constraint element output is fully connected with the next hidden layer, and the weight and bias of the constraint element are adjusted together with other neurons; the constraint element of the constraint layer is in a non-connected state with the neurons of the input layer, and the other neurons of the constraint layer are in a fully connected state with the neurons of the input layer; The rock mechanics seepage model is as follows: where q is the constraint element, k is the absolute permeability included in the logging data, k r is the relative permeability, μ is the viscosity, B is the volume coefficient, r e is the equivalent radius, r w is the wellbore radius, and S′ is the apparent skin factor; The well logging data of the reservoir to be predicted is obtained and input into the constraint neural network to obtain the reservoir production capacity under unit pressure difference.

2. The method according to claim 1, wherein The preprocessing of the well logging data and the reservoir productivity data to construct a standardized sample set further includes: Normalizing the logging data, removing abnormal values, and filling in default values ​​using interpolation; Normalizing the reservoir capacity data to calculate the reservoir capacity under unit pressure difference; According to the specified unit average permeability, the specified unit reservoir capacity is calculated; The well logging data of the designated unit reservoir is used as the input data of the sample set, and the capacity of the designated unit reservoir is used as the output data of the sample set to construct a standardized sample set.

3. The method according to claim 1, wherein The constraint layer is constrained by a rock mechanics seepage model, and the rock mechanics seepage model is used to calculate the constraint elements of the constraint layer.

4. The method according to claim 1, wherein The model of the constrained neural network includes a regional model and / or a universal model; the type is determined according to the quantity and / or distribution range of the sample set.

5. A device for predicting oil and gas reservoir productivity, characterized in that the device comprises: Constructing sample modules, which are suitable for preprocessing well logging data and reservoir productivity data and constructing standardized sample sets; Constructing a training module, which is suitable for constructing and training a constrained neural network according to the sample set, and adding neurons as constraint elements in the constraint layer of the constrained neural network to constrain the calculation of the constrained neural network; the constrained neural network is composed of an input layer, a constraint layer, a hidden layer, and an output layer, and the constraint layer is a network layer for specifying the addition of constraint elements; the constraint element input is calculated by a rock mechanics seepage model, the constraint element output is fully connected with the next hidden layer, and the weight and bias of the constraint element are jointly adjusted with other neurons; the constraint element of the constraint layer is in a non-connected state with the neurons of the input layer, and the other neurons of the constraint layer are in a fully connected state with the neurons of the input layer; The rock mechanics seepage model is as follows: Among them, q is the constraint element, k is the absolute permeability contained in the logging data, and k r is the relative permeability, μ is the viscosity, B is the volume coefficient, r e is the equivalent radius, r w is the wellbore radius, and S′ is the apparent skin factor; The prediction module is suitable for obtaining the logging data of the reservoir to be predicted, inputting it into the constraint neural network, and obtaining the reservoir production capacity under unit pressure difference.

6. A computing device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the oil and gas reservoir productivity prediction method according to any one of claims 1-4.

7. A computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes a processor to perform operations corresponding to the oil and gas reservoir productivity prediction method according to any one of claims 1-4.

Images