Safety monitoring and optimizing method and device for peak regulation process of gas storage

Abstract

The invention relates to a safety monitoring and optimizing method and device for a peak regulation process of a gas storage. The method comprises the following steps: acquiring a pre-trained radial basis function neural network model; constructing a target function model and safety constraint conditions of the gas storage; substituting the radial basis function neural network model into the target function model to obtain a peak regulation optimization model of the gas storage; obtaining inherent gas storage information of the target gas storage, and substituting the inherent gas storage information of the target gas storage into the peak regulation optimization model to obtain a peak regulation optimization model of the target gas storage; and the peak regulation optimization model of the target gas storage is optimized under the safety constraint condition, and the target gas production amount of each injection-production well of the target gas storage is obtained when the safety constraint condition is met and the peak regulation optimization model outputs the minimum. According to the scheme provided by the invention, various data of the gas storage can be monitored, so that the optimal gas production amount of each injection-production well in the gas storage is obtained, and the safety of the peak regulation process of the gas storage is improved.

Description

Technical Field

[0001] The present application relates to the technical field of gas storage peak-shaving optimization, and in particular to a method and device for safety monitoring and optimization of a gas storage peak-shaving process. Background Art

[0002] A gas storage is a facility used to store natural gas. It mainly refers to an underground gas storage, which is a natural gas reservoir formed by re-injecting natural gas into an underground space that can store gas. A gas storage has multiple functions such as seasonal peak regulation, emergency gas supply, and national energy strategic reserve. As an important part of my country's natural gas storage and peak regulation, the normal and stable peak regulation of gas storage is an important guarantee for the stable supply of natural gas during my country's peak gas consumption period.

[0003] Underground gas storage is built in conjunction with long-distance natural gas pipelines. During the off-season, the surplus natural gas in the long-distance pipeline is injected into underground storage, and during the peak season, the natural gas is extracted to supplement the gas demand during the peak season. However, in the event of an emergency, such as an accident that causes a shortage of natural gas supply, the gas storage also needs to temporarily change the injection and extraction process to perform emergency peak load regulation. However, how to set safety constraints for the peak load regulation process of the gas storage and optimize the peak load regulation gas supply to ensure the smooth operation of the gas storage peak load regulation is an important issue currently facing the peak load regulation process of the gas storage. Summary of the invention

[0004] In order to solve or partially solve the problems existing in the related technology, the present application provides a method and device for safety monitoring and optimization of the peak-shaving process of a gas storage reservoir, which can monitor various data of the gas storage reservoir to obtain the optimal gas production volume of each injection and production well in the gas storage reservoir, thereby improving the safety of the peak-shaving process of the gas storage reservoir.

[0005] The first aspect of the present application provides a method for safety monitoring and optimization of a gas storage peak-shaving process, comprising obtaining a pre-trained radial basis function neural network model, wherein the radial basis function neural network model is used to indicate the relationship between the gas production volume of an injection-production well and the status data of the injection-production well;

[0006] Constructing an objective function model and safety constraints of a gas storage facility; wherein the objective function model of the gas storage facility is the difference between the total gas production of each injection and production well of the gas storage facility and the target gas production; the safety constraints include at least one of the following: an oil pressure constraint of each injection and production well in the gas storage facility, a casing pressure constraint of the injection and production well, an oil / technical casing pressure constraint of the injection and production well, a wellhead temperature constraint of the injection and production well, a well opening number constraint of the gas storage facility, a gas production constraint of the injection and production well, and an outlet pressure constraint of the gas storage facility;

[0007] Substituting the radial basis neural network model into the objective function model, a peak-shaving optimization model of the gas storage is obtained, wherein the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage;

[0008] Acquire inherent gas storage reservoir information of a target gas storage reservoir, and substitute the inherent gas storage reservoir information of the target gas storage reservoir into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage reservoir;

[0009] The peak-shaving optimization model of the target gas storage is optimized under the safety constraint conditions to obtain the target gas production volume of each injection and production well of the target gas storage when the safety constraint conditions are met and the output of the peak-shaving optimization model is minimized.

[0010] In combination with the first aspect, in a possible implementation of the first aspect, the peak-shaving optimization model of the target gas storage reservoir is optimized under the safety constraint conditions to obtain the target gas production of each injection and production well of the target gas storage reservoir when the safety constraint conditions are satisfied and the output of the peak-shaving optimization model is minimized, including: initializing the variable gas storage reservoir information of the target gas storage reservoir according to the safety constraint conditions, wherein the variable gas storage reservoir information satisfies the safety constraint conditions; executing the optimization process: substituting the variable gas storage reservoir information of the target gas storage reservoir into the peak-shaving optimization model of the target gas storage reservoir to obtain a current optimization value, wherein the current optimization value is used to indicate the target gas production of each injection and production well of the target gas storage reservoir. the difference between the total gas production of the well and the target gas production; if the current optimization value does not meet the preset convergence condition, then under the safety constraint condition, adjust the variable gas storage information of the target gas storage, and return to the step of substituting the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain the current optimization value, until the current optimization value meets the preset convergence condition; when the current optimization value meets the preset convergence condition, determine the target gas production of each injection and production well of the target gas storage according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model.

[0011] In combination with the first aspect, in a possible implementation of the first aspect, the target gas production of each injection and production well of the target gas storage is determined according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model, including: extracting the status data of each injection and production well in the target gas storage from the variable gas storage information and the inherent gas storage information of the target gas storage; inputting the status data of each injection and production well in the target gas storage into the radial basis neural network model to obtain the target gas production of each injection and production well.

[0012] In combination with the first aspect, in a possible implementation of the first aspect, the training process of the radial basis neural network model includes: constructing an initialized radial basis neural network model; obtaining a sample set, the sample set including a preset number of samples, each of the samples including: a sample gas production volume of a sample injection and production well, and sample status data obtained by monitoring the sample injection and production well; splitting the sample set into a training set, a validation set, and a test set; training the radial basis neural network model through the training set, and optimizing the radial basis neural network model through a particle swarm algorithm during the training process; the calculation formula of the particle dimension in the particle swarm algorithm is as follows:

[0013] D = I × J + J + J × K;

[0014] Wherein, D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model.

[0015] In combination with the first aspect, in a possible implementation of the first aspect, the status data includes at least one of the following: oil pressure, casing pressure, oil / technical casing pressure and wellhead temperature of the injection and production well.

[0016] In combination with the first aspect, in a possible implementation of the first aspect, the oil pressure constraint condition of the injection and production well is: the oil pressure of the injection and production well is less than or equal to the maximum oil pressure of the injection and production well; the casing pressure constraint condition of the injection and production well is: the casing pressure of the injection and production well is less than or equal to the maximum casing pressure of the injection and production well; the oil / technical suite pressure constraint condition of the injection and production well is: the oil / technical suite pressure of the injection and production well is less than or equal to the maximum oil / technical suite pressure of the injection and production well; the wellhead temperature constraint condition of the injection and production well is: the wellhead temperature of the injection and production well is less than or equal to the Maximum wellhead temperature; the constraint condition for the number of wells opened in the gas storage reservoir is: the number of wells opened in the gas storage reservoir is less than or equal to the maximum number of wells that can be opened on the same day, and the maximum number of wells that can be opened on the same day is less than or equal to the number of injection and production wells in the gas storage reservoir; the constraint condition for the gas production volume of the injection and production well is: the gas production volume of the injection and production well is less than or equal to the maximum gas production volume of the injection and production well, and the maximum gas production volume of the injection and production well is positively correlated with the formation pressure of the injection and production well; the constraint condition for the outlet pressure of the injection and production well is: the outlet pressure of the injection and production well is less than or equal to the bearing capacity of the ground equipment of the injection and production well.

[0017] The second aspect of the present application provides a gas storage peak-shaving process safety monitoring and optimization device, comprising a first acquisition module, for acquiring a pre-trained radial basis function neural network model, wherein the radial basis function neural network model is used to indicate the relationship between the gas production volume of an injection-production well and the state data of the injection-production well;

[0018] A construction module is used to construct an objective function model and safety constraints of a gas storage facility; wherein the objective function model of the gas storage facility is the difference between the total gas production of each injection and production well of the gas storage facility and the target gas production; the safety constraints include at least one of the following: an oil pressure constraint of each injection and production well in the gas storage facility, a casing pressure constraint of the injection and production well, an oil / technical casing pressure constraint of the injection and production well, a wellhead temperature constraint of the injection and production well, a well opening number constraint of the gas storage facility, a gas production constraint of the injection and production well, and an outlet pressure constraint of the gas storage facility;

[0019] A processing module, used for substituting the radial basis neural network model into the objective function model to obtain a peak-shaving optimization model of the gas storage, wherein the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage;

[0020] A second acquisition module is used to acquire inherent gas storage information of a target gas storage, and substitute the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage;

[0021] The optimization module is used to optimize the peak-shaving optimization model of the target gas storage reservoir under the safety constraint conditions to obtain the target gas production volume of each injection and production well of the target gas storage reservoir when the safety constraint conditions are met and the output of the peak-shaving optimization model is minimized.

[0022] In combination with the second aspect, in a possible implementation of the second aspect, the optimization module is further used to initialize the variable gas storage reservoir information of the target gas storage reservoir according to the safety constraint condition, and the variable gas storage reservoir information satisfies the safety constraint condition; execute the optimization process: substitute the variable gas storage reservoir information of the target gas storage reservoir into the peak-shaving optimization model of the target gas storage reservoir to obtain the current optimization value, and the current optimization value is used to indicate the difference between the total gas production of each injection and production well of the target gas storage reservoir and the target gas production; if the current optimization value does not meet the preset convergence condition , then under the safety constraint condition, the variable gas storage information of the target gas storage is adjusted, and the step of substituting the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain the current optimization value is returned until the current optimization value satisfies the preset convergence condition; when the current optimization value satisfies the preset convergence condition, the target gas production of each injection and production well of the target gas storage is determined according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model.

[0023] In combination with the second aspect, in a possible implementation of the second aspect, the optimization module is also used to extract the status data of each injection and production well in the target gas storage from the variable gas storage information and the inherent gas storage information of the target gas storage; the status data of each injection and production well in the target gas storage is input into the radial basis neural network model to obtain the target gas production of each injection and production well.

[0024] In combination with the second aspect, in a possible implementation of the second aspect, the processing module is further used to construct an initialized radial basis neural network model; obtain a sample set, the sample set includes a preset number of samples, each of the samples includes: a sample gas production volume of a sample injection and production well, and sample status data obtained by monitoring the sample injection and production well; split the sample set into a training set, a validation set, and a test set; train the radial basis neural network model through the training set, and optimize the radial basis neural network model through a particle swarm algorithm during the training process. The calculation formula of the particle dimension in the particle swarm algorithm is as follows:

[0025] D = I × J + J + J × K;

[0026] Wherein, D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model.

[0027] A third aspect of the present application provides an electronic device, including:

[0028] Processor; and

[0029] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0030] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0031] A fifth aspect of the present application provides a computer program product, comprising a computer program / instruction, which implements the method described above when executed by a processor.

[0032] The technical solution provided by this application may have the following beneficial effects:

[0033] The present invention discloses a method for monitoring and optimizing the peak-shaving process of a gas storage reservoir, comprising obtaining a pre-trained radial basis function neural network model, the radial basis function neural network model being used to indicate the relationship between the gas production of an injection-production well and the state data of the injection-production well; constructing an objective function model and safety constraint conditions of the gas storage reservoir; wherein the objective function model of the gas storage reservoir is the difference between the total gas production of each injection-production well of the gas storage reservoir and the target gas production; the safety constraint conditions include at least one of the following: an oil pressure constraint condition of each injection-production well in the gas storage reservoir, a casing pressure constraint condition of the injection-production well, an oil / technical casing pressure constraint condition of the injection-production well, a wellhead temperature constraint condition of the injection-production well, a constraint condition on the number of wells opened in the gas storage reservoir, a constraint condition on the gas production of the injection-production well, and a constraint condition on the outlet pressure of the gas storage reservoir; and Substituting the objective function model into the base neural network model, a peak-shaving optimization model of the gas storage is obtained, and the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage; obtaining the inherent gas storage information of the target gas storage, and substituting the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage; optimizing the peak-shaving optimization model of the target gas storage under safety constraints, and obtaining the target gas production of each injection and production well of the target gas storage when the safety constraints are met and the output of the peak-shaving optimization model is minimized, and various data of the gas storage can be monitored to obtain the optimal gas production of each injection and production well in the gas storage, thereby improving the safety of the peak-shaving process of the gas storage.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0036] Figure 1 It is a flow chart of a method for safety monitoring and optimization of a gas storage peak-shaving process shown in an embodiment of the present application;

[0037] Figure 2 It is a structural schematic diagram of a gas storage peak-shaving process safety monitoring and optimization device shown in an embodiment of the present application;

[0038] Figure 3 is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application;

[0039] Figure 4 It is a scenario diagram of a method for safely monitoring and optimizing a gas storage peak-shaving process shown in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0041] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "a", "an" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0042] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0043] In the related technology, during the peak-shaving process, gas storage facilities currently ignore some possible influencing factors or injection-production well status data such as oil pressure, casing pressure, injection-production well temperature and other parameters during the peak-shaving process, which makes it easy for gas storage facilities to have safety problems during the peak-shaving process. Once a major safety accident occurs during the peak-shaving process of the gas storage facility, it will directly affect the peak-shaving and emergency peak-shaving capabilities.

[0044] In response to the above problems, an embodiment of the present application provides a method for safely monitoring and optimizing the peak-shaving process of a gas storage reservoir, which can monitor various data of the gas storage reservoir to obtain the optimal gas production of each injection and production well in the gas storage reservoir, thereby improving the safety of the peak-shaving process of the gas storage reservoir.

[0045] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0046] Figure 1 It is a flow chart of a method for safely monitoring and optimizing a gas storage peak-shaving process according to an embodiment of the present application.

[0047] See also Figure 1 and Figure 4 , a method for safety monitoring and optimization of gas storage peak load regulation process, comprising:

[0048] S110: Acquire a pre-trained radial basis function neural network model, where the radial basis function neural network model is used to indicate the relationship between the gas production volume of the injection and production well and the status data of the injection and production well.

[0049] Specifically, a pre-trained radial basis function neural network model can be obtained. The radial basis function neural network model is used to indicate the relationship between the gas production of the injection and production wells and the status data of the injection and production wells. The radial basis function neural network model contains an input layer, a hidden layer and an output layer. The status data of the injection and production wells can be input into the pre-trained radial basis function neural network model. The pre-trained radial basis function neural network model can output the gas production of the injection and production wells. Different gas productions of the injection and production wells can be obtained according to the input of different status data of the injection and production wells.

[0050] In a possible implementation, an initialized radial basis neural network model is constructed; a sample set is obtained, the sample set includes a preset number of samples, each sample includes: a sample gas production of a sample injection and production well, and sample status data obtained by monitoring the sample injection and production well; the sample set is split into a training set, a validation set, and a test set; the radial basis neural network model is trained using the training set, and the radial basis neural network model is optimized using a particle swarm algorithm during the training process; the calculation formula for the particle dimension in the particle swarm algorithm is as follows: D=I×J+J+J×K; wherein D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model.

[0051] Specifically, the state data of each injection and production well in the gas storage reservoir can be obtained. The state data of the injection and production wells may include the oil pressure, casing pressure, oil / technical casing pressure and wellhead temperature of the injection and production wells, and may be the state data of each injection and production well at different times. By normalizing the state data of the injection and production wells and eliminating null values ​​and state data that deviate too much from the numerical value, a sample set is obtained. Each sample in the sample set may include the gas production of the sample injection and production well and the sample state data of the sample injection and production well. The sample injection and production well may be any injection and production well in the gas storage reservoir, and the sample state data may be the state data of any injection and production well in the gas storage reservoir at any time. The sample set is split into a training set, a validation set and a test set according to a preset ratio. For example, the state data of the injection and production wells may be used to construct a training set, a validation set and a test set according to a ratio of 8:1:1. The radial basis neural network model may be trained through the training set. During the training process, the radial basis neural network model is optimized through a particle swarm algorithm. The calculation formula of the particle dimension in the particle swarm algorithm is as follows:

[0052] D = I × J + J + J × K;

[0053] Wherein, D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model; the number of input layer nodes can be set to 1, the number of hidden layer nodes to 12, and the number of output layer nodes to 1. At this time, the particle dimension D=72, and the particle dimension includes the center point position and basis width information. The training set and the verification set are input into the radial basis neural network model, and the particle swarm algorithm is used to obtain the optimal basis width information and center point position in the radial basis neural network to obtain the trained radial basis neural network model; after obtaining the trained radial basis neural network model, the test set can be input into the trained radial basis neural network model to verify whether the trained radial basis neural network model can pass the verification.

[0054] S120: Constructing an objective function model and safety constraints of a gas storage facility; wherein the objective function model of the gas storage facility is the difference between the total gas production of each injection and production well of the gas storage facility and the target gas production; the safety constraints include at least one of the following: the oil pressure constraint of each injection and production well in the gas storage facility, the casing pressure constraint of the injection and production well, the oil / technical casing pressure constraint of the injection and production well, the wellhead temperature constraint of the injection and production well, the well opening number constraint of the gas storage facility, the gas production constraint of the injection and production well, and the outlet pressure constraint of the gas storage facility.

[0055] Specifically, an objective function model of a gas storage is constructed. The objective function model is the difference between the total gas production of each injection and production well of the gas storage and the target gas production. During the peak shaving process, it is necessary to set a planned amount of natural gas required for peak shaving, that is, the target gas production. The objective function model can be:

[0056]

[0057] Q is the target gas production volume, Q i is the gas production of the ith well, n is the number of wells opened, and F is the fitness. The smaller the fitness, the smaller the difference between the total gas production of each injection and production well and the target gas production, that is, the total gas production of each injection and production well is closer to the target gas production.

[0058] Specifically, safety constraints can be set to avoid dangers in the peak-shaving process when adjusting the gas production of each injection and production well. The safety constraints may include: oil pressure constraints of each injection and production well in the gas storage reservoir, casing pressure constraints of the injection and production wells, oil / technical casing pressure constraints of the injection and production wells, wellhead temperature constraints of the injection and production wells, constraints on the number of wells opened in the gas storage reservoir, gas production constraints of the injection and production wells, and outlet pressure constraints of the gas storage reservoir.

[0059] In a possible implementation, the oil pressure constraint of the injection-production well is: the oil pressure of the injection-production well is less than or equal to the maximum oil pressure of the injection-production well; the casing pressure constraint of the injection-production well is: the casing pressure of the injection-production well is less than or equal to the maximum casing pressure of the injection-production well; the oil / technical casing pressure constraint of the injection-production well is: the oil / technical casing pressure of the injection-production well is less than or equal to the maximum oil / technical casing pressure of the injection-production well; the wellhead temperature constraint of the injection-production well is: the wellhead temperature of the injection-production well is less than or equal to the maximum wellhead temperature of the injection-production well. degree; the constraint condition of the number of wells opened in the gas storage reservoir is: the number of wells opened in the gas storage reservoir is less than or equal to the maximum number of wells that can be opened on the same day, and the maximum number of wells that can be opened on the same day is less than or equal to the number of injection and production wells in the gas storage reservoir; the constraint condition of the gas production volume of the injection and production well is: the gas production volume of the injection and production well is less than or equal to the maximum gas production volume of the injection and production well, and the maximum gas production volume of the injection and production well is positively correlated with the formation pressure of the injection and production well; the constraint condition of the outlet pressure of the injection and production well is: the outlet pressure of the injection and production well is less than or equal to the bearing capacity of the ground equipment of the injection and production well.

[0060] Specifically, the oil pressure of the injection and production well should be less than or equal to the maximum oil pressure of the injection and production well. For example, the maximum oil pressure of the injection and production well can be set to 36MPa. In actual operation, the oil pressure of the injection and production well should be less than or equal to 36MPa. The casing pressure of the injection and production well should be less than or equal to the maximum casing pressure of the injection and production well. For example, the maximum casing pressure of the injection and production well is 36MPa. In actual operation, the casing pressure of the injection and production well should be less than or equal to 36MPa. The oil / technical casing pressure of the injection and production well should be less than or equal to the maximum oil / technical casing pressure of the injection and production well. Suite pressure, for example, the maximum oil / technical suite pressure of the injection and production well is 21MPa. In actual operation, the oil / technical suite pressure of the injection and production well should be less than or equal to 21MPa; the wellhead temperature of the injection and production well should be less than or equal to the maximum wellhead temperature of the injection and production well. For example, the maximum wellhead temperature of the injection and production well is 90 degrees. In actual operation, the wellhead temperature of the injection and production well should be less than or equal to 90 degrees. By constraining the various status data of the above-mentioned injection and production wells, accidents in the injection and production wells can be avoided during the peak regulation process.

[0061] Specifically, the constraints also include the number of wells opened in the gas storage. The number of injection and production wells in each gas storage may be different, and the maximum number of wells that can be opened on the same day may also be different. During the peak load regulation process, the number of wells opened in the gas storage should be less than or equal to the maximum number of wells that can be opened on the same day. The maximum gas production of each injection and production well may be different. During the peak load regulation process, the gas production of the injection and production well should be less than or equal to the maximum gas production of the injection and production well. The maximum gas production of the injection and production well is positively correlated with the formation pressure of the injection and production well. For example, the relationship between the maximum gas production of each injection and production well and the formation pressure can be expressed by Table 1:

[0062] Table 1 Maximum gas production of each injection and production well

[0063]

[0064]

[0065] In the current gas storage, there are 20 injection and production wells. The maximum gas production of each injection and production well is different and is positively correlated with the formation pressure. Each injection and production well also has an outlet pressure during the gas production process. The outlet pressure of the injection and production well is related to the bearing capacity of the ground equipment of the injection and production well. The outlet pressure of the injection and production well should be less than or equal to the bearing capacity of the ground equipment of the injection and production well. The ground equipment can be equipment with rated working pressure such as natural gas dehydration and dehydrocarbonization equipment, compressors, pipelines and other ground equipment of the gathering and injection station.

[0066] S130: Substitute the radial basis neural network model into the objective function model to obtain a peak-shaving optimization model for the gas storage reservoir. The peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage reservoir and the relationship between the status data of each injection and production well of the gas storage reservoir.

[0067] Specifically, a peak-shaving optimization model of a gas storage reservoir is obtained through a radial basis neural network model and an objective function model, and the total gas production of each injection and production well of the gas storage reservoir can be obtained by inputting the status data of each injection and production well of the gas storage reservoir into the peak-shaving optimization model.

[0068] S140: Acquire inherent gas storage information of the target gas storage, and substitute the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage.

[0069] Specifically, the inherent gas storage information of the target gas storage may include the maximum number of injection and production wells of the target gas storage, the ground equipment carrying capacity of the injection and production wells of the target gas storage, the maximum oil pressure of each injection and production well of the target gas storage, the maximum casing pressure, the maximum oil / technical casing pressure, the maximum wellhead temperature and other status data. By substituting the gas storage information of the target gas storage into the peak-shaving optimization model, the peak-shaving optimization model of the target gas storage can be obtained.

[0070] S150: Optimizing the peak-shaving optimization model of the target gas storage under safety constraints to obtain the target gas production of each injection and production well of the target gas storage when the safety constraints are met and the output of the peak-shaving optimization model is minimized.

[0071] Specifically, it is possible to optimize the peak-shaving optimization model of the target gas storage reservoir under safety constraints, and continuously adjust the status data of each injection and production well so that when the safety constraints are met and the output of the peak-shaving optimization model is minimized, the target gas production of each injection and production well of the target gas storage reservoir is achieved, so as to maximize the gas production of each injection and production well required in the peak-shaving process.

[0072] In a possible implementation, variable gas storage information of a target gas storage is initialized according to safety constraints, and the variable gas storage information satisfies the safety constraints; an optimization process is performed: the variable gas storage information of the target gas storage is substituted into a peak-shaving optimization model of the target gas storage to obtain a current optimization value, and the current optimization value is used to indicate the difference between the total gas production of each injection and production well of the target gas storage and the target gas production; if the current optimization value does not meet a preset convergence condition, the variable gas storage information of the target gas storage is adjusted under the safety constraints, and the step of substituting the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain the current optimization value is returned until the current optimization value meets the preset convergence condition; when the current optimization value meets the preset convergence condition, the target gas production of each injection and production well of the target gas storage is determined according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model.

[0073] Specifically, the variable gas storage reservoir information may include the number of wells opened on the day of the target gas storage reservoir and the status data such as the casing pressure of each injection and production well of the target gas storage reservoir, the oil / technical suite pressure, the wellhead temperature, the outlet pressure, the gas production volume, etc.; in the process of executing the peak-shaving optimization model, the variable gas storage reservoir information of the target gas storage reservoir may be substituted into the peak-shaving optimization model of the target gas storage reservoir, that is, the number of wells opened on the day of the target gas storage reservoir and the status data such as the casing pressure of each injection and production well of the target gas storage reservoir, the oil / technical suite pressure, the wellhead temperature, the outlet pressure, the gas production volume, etc. are substituted into the peak-shaving optimization model of the target gas storage reservoir, and the current optimization value can be obtained. If the current optimization value does not meet the preset convergence conditions If the gas production of each injection and production well is not the optimal gas production at this time, and the difference between the total gas production of each injection and production well of the target gas storage reservoir and the target gas production cannot be minimized, the variable gas storage reservoir information of the target gas storage reservoir is adjusted, and the adjusted variable gas storage reservoir information of the target gas storage reservoir is brought into the peak-shaving optimization model again to obtain the current optimization value, until the current optimization value meets the preset convergence condition, that is, the gas production of the injection and production well is the optimal gas production at this time, and the difference between the total gas production of each injection and production well of the target gas storage reservoir and the target gas production can be minimized. When the current optimization value meets the preset convergence condition, the target gas production of each injection and production well of the target gas storage reservoir is obtained.

[0074] In a possible implementation, the status data of each injection and production well in the target gas storage is extracted from the variable gas storage information and the inherent gas storage information of the target gas storage; the status data of each injection and production well in the target gas storage is input into a radial basis neural network model to obtain the target gas production of each injection and production well.

[0075] Specifically, after obtaining the current optimization value, the status data of each injection and production well in the target gas storage is extracted from the variable gas storage information and the inherent gas storage information corresponding to the current optimization value, and the status data of each injection and production well in the target gas storage is input into the radial basis neural network model, so as to obtain the target gas production of each injection and production well.

[0076] The present invention discloses a method for monitoring and optimizing the peak-shaving process of a gas storage reservoir, comprising obtaining a pre-trained radial basis function neural network model, the radial basis function neural network model being used to indicate the relationship between the gas production of an injection-production well and the state data of the injection-production well; constructing an objective function model and safety constraint conditions of the gas storage reservoir; wherein the objective function model of the gas storage reservoir is the difference between the total gas production of each injection-production well of the gas storage reservoir and the target gas production; the safety constraint conditions include at least one of the following: an oil pressure constraint condition of each injection-production well in the gas storage reservoir, a casing pressure constraint condition of the injection-production well, an oil / technical casing pressure constraint condition of the injection-production well, a wellhead temperature constraint condition of the injection-production well, a constraint condition on the number of wells opened in the gas storage reservoir, a constraint condition on the gas production of the injection-production well, and a constraint condition on the outlet pressure of the gas storage reservoir; and Substituting the objective function model into the base neural network model, a peak-shaving optimization model of the gas storage is obtained, and the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage; obtaining the inherent gas storage information of the target gas storage, and substituting the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage; optimizing the peak-shaving optimization model of the target gas storage under safety constraints, and obtaining the target gas production of each injection and production well of the target gas storage when the safety constraints are met and the output of the peak-shaving optimization model is minimized, and various data of the gas storage can be monitored to obtain the optimal gas production of each injection and production well in the gas storage, thereby improving the safety of the peak-shaving process of the gas storage.

[0077] Corresponding to the aforementioned application function realization method embodiment, the present application also provides a gas storage peak-shaving process safety monitoring and optimization device, electronic equipment and corresponding embodiments.

[0078] Figure 2 It is a schematic diagram of the structure of a gas storage peak-shaving process safety monitoring and optimization device shown in an embodiment of the present application.

[0079] See also Figure 2 A gas storage peak load regulation process safety monitoring and optimization device 200 includes a first acquisition module 210, a construction module 220, a processing module 230, a second acquisition module 240, and an optimization module 250.

[0080] The first acquisition module 210 is used to acquire a pre-trained radial basis function neural network model, and the radial basis function neural network model is used to indicate the relationship between the gas production volume of the injection and production well and the status data of the injection and production well.

[0081] Specifically, a pre-trained radial basis function neural network model can be obtained. The radial basis function neural network model is used to indicate the relationship between the gas production of the injection and production wells and the status data of the injection and production wells. The radial basis function neural network model contains an input layer, a hidden layer and an output layer. The status data of the injection and production wells can be input into the pre-trained radial basis function neural network model. The pre-trained radial basis function neural network model can output the gas production of the injection and production wells. Different gas productions of the injection and production wells can be obtained according to the input of different status data of the injection and production wells.

[0082] Construction module 220 is used to construct the objective function model and safety constraints of the gas storage reservoir; wherein the objective function model of the gas storage reservoir is the difference between the total gas production of each injection and production well of the gas storage reservoir and the target gas production; the safety constraints include at least one of the following: the oil pressure constraint of each injection and production well in the gas storage reservoir, the casing pressure constraint of the injection and production well, the oil / technical casing pressure constraint of the injection and production well, the wellhead temperature constraint of the injection and production well, the well opening number constraint of the gas storage reservoir, the gas production constraint of the injection and production well, and the outlet pressure constraint of the gas storage reservoir.

[0083] Specifically, safety constraints are set to avoid danger in the peak-shaving process when adjusting the gas production of each injection and production well. The safety constraints may include: oil pressure constraints of each injection and production well in the gas storage, casing pressure constraints of the injection and production wells, oil / technical casing pressure constraints of the injection and production wells, wellhead temperature constraints of the injection and production wells, constraints on the number of wells opened in the gas storage, constraints on the gas production of the injection and production wells, and constraints on the outlet pressure of the gas storage.

[0084] The processing module 230 is used to substitute the radial basis neural network model into the objective function model to obtain the peak-shaving optimization model of the gas storage reservoir. The peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage reservoir and the relationship between the status data of each injection and production well of the gas storage reservoir.

[0085] Specifically, a peak-shaving optimization model of a gas storage reservoir is obtained through a radial basis neural network model and an objective function model, and the total gas production of each injection and production well of the gas storage reservoir can be obtained by inputting the status data of each injection and production well of the gas storage reservoir into the peak-shaving optimization model.

[0086] In a possible implementation, the processing module is also used to construct an initialized radial basis neural network model; obtain a sample set, the sample set includes a preset number of samples, each sample includes: a sample gas production of a sample injection and production well, and sample status data obtained by monitoring the sample injection and production well; split the sample set into a training set, a verification set, and a test set; train the radial basis neural network model through the training set, and optimize the radial basis neural network model through a particle swarm algorithm during the training process. The calculation formula of the particle dimension in the particle swarm algorithm is as follows: D=I×J+J+J×K; wherein D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model.

[0087] The second acquisition module 240 is used to acquire the inherent gas storage information of the target gas storage, and substitute the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage.

[0088] Specifically, the inherent gas storage information of the target gas storage may include the maximum number of injection and production wells of the target gas storage, the ground equipment carrying capacity of the injection and production wells of the target gas storage, the maximum oil pressure of each injection and production well of the target gas storage, the maximum casing pressure, the maximum oil / technical casing pressure, the maximum wellhead temperature and other status data. By substituting the gas storage information of the target gas storage into the peak-shaving optimization model, the peak-shaving optimization model of the target gas storage can be obtained.

[0089] The optimization module 250 is used to optimize the peak-shaving optimization model of the target gas storage reservoir under safety constraints, and obtain the target gas production of each injection and production well of the target gas storage reservoir when the safety constraints are met and the output of the peak-shaving optimization model is minimized.

[0090] Specifically, it is possible to optimize the peak-shaving optimization model of the target gas storage reservoir under safety constraints, and continuously adjust the status data of each injection and production well so that when the safety constraints are met and the output of the peak-shaving optimization model is minimized, the target gas production of each injection and production well of the target gas storage reservoir is achieved, so as to maximize the gas production of each injection and production well required in the peak-shaving process.

[0091] In a possible implementation, the optimization module 250 is also used to initialize the variable gas storage information of the target gas storage according to the safety constraint condition, and the variable gas storage information satisfies the safety constraint condition; execute the optimization process: substitute the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain the current optimization value, and the current optimization value is used to indicate the difference between the total gas production of each injection and production well of the target gas storage and the target gas production; if the current optimization value does not meet the preset convergence condition, then under the safety constraint condition, adjust the variable gas storage information of the target gas storage, and return to the step of substituting the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain the current optimization value, until the current optimization value meets the preset convergence condition; when the current optimization value meets the preset convergence condition, determine the target gas production of each injection and production well of the target gas storage according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model.

[0092] In a possible implementation, the optimization module 250 is also used to extract the status data of each injection and production well in the target gas storage from the variable gas storage information and the inherent gas storage information of the target gas storage; the status data of each injection and production well in the target gas storage is input into the radial basis neural network model to obtain the target gas production of each injection and production well.

[0093] Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0094] Figure 3 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0095] See also Figure 3 , the electronic device 300 includes a memory 310 and a processor 320.

[0096] The processor 320 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0097] The memory 310 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 320 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 310 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 310 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0098] The memory 310 stores executable codes, and when the executable codes are processed by the processor 320 , the processor 320 can execute part or all of the methods described above.

[0099] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0100] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0101] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for safety monitoring and optimization of gas storage peak load regulation process, characterized in that: include: Acquire a pre-trained radial basis function neural network model, wherein the radial basis function neural network model is used to indicate the relationship between the gas production volume of the injection and production well and the state data of the injection and production well; Constructing an objective function model and safety constraints of a gas storage facility; wherein the objective function model of the gas storage facility is the difference between the total gas production of each injection and production well of the gas storage facility and the target gas production; the safety constraints include at least one of the following: an oil pressure constraint of each injection and production well in the gas storage facility, a casing pressure constraint of the injection and production well, an oil / technical casing pressure constraint of the injection and production well, a wellhead temperature constraint of the injection and production well, a well opening number constraint of the gas storage facility, a gas production constraint of the injection and production well, and an outlet pressure constraint of the gas storage facility; Substituting the radial basis neural network model into the objective function model, a peak-shaving optimization model of the gas storage is obtained, wherein the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage; Acquire inherent gas storage reservoir information of a target gas storage reservoir, and substitute the inherent gas storage reservoir information of the target gas storage reservoir into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage reservoir; The peak-shaving optimization model of the target gas storage is optimized under the safety constraint conditions to obtain the target gas production volume of each injection and production well of the target gas storage when the safety constraint conditions are met and the output of the peak-shaving optimization model is minimized.

2. The method according to claim 1, characterized in that The peak-shaving optimization model of the target gas storage is optimized under the safety constraint conditions to obtain the target gas production volume of each injection and production well of the target gas storage when the safety constraint conditions are met and the output of the peak-shaving optimization model is minimum, including: Initializing the variable gas storage reservoir information of the target gas storage reservoir according to the safety constraint condition, wherein the variable gas storage reservoir information satisfies the safety constraint condition; Execute the optimization process: substitute the variable gas storage information of the target gas storage into the peak-shaving optimization model of the target gas storage to obtain a current optimization value, wherein the current optimization value is used to indicate the difference between the total gas production of each injection and production well of the target gas storage and the target gas production; If the current optimized value does not meet the preset convergence condition, then under the safety constraint condition, the variable gas storage reservoir information of the target gas storage reservoir is adjusted, and the step of substituting the variable gas storage reservoir information of the target gas storage reservoir into the peak load optimization model of the target gas storage reservoir to obtain the current optimized value is returned until the current optimized value meets the preset convergence condition; When the current optimization value satisfies the preset convergence condition, the target gas production of each injection and production well of the target gas storage is determined according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model.

3. The method according to claim 2, characterized in that The step of determining the target gas production volume of each injection and production well of the target gas storage according to the variable gas storage information corresponding to the current optimization value, the inherent gas storage information of the target gas storage and the radial basis neural network model comprises: Extracting status data of each injection and production well in the target gas storage from the variable gas storage information and the inherent gas storage information of the target gas storage; The state data of each injection and production well in the target gas storage reservoir is input into the radial basis function neural network model to obtain the target gas production volume of each injection and production well.

4. The method according to any one of claims 1 to 3, characterized in that The training process of the radial basis neural network model includes: Construct an initialized radial basis neural network model; Acquire a sample set, wherein the sample set includes a preset number of samples, each of which includes: a sample gas production volume of a sample injection-production well, and sample status data obtained by monitoring the sample injection-production well; Splitting the sample set into a training set, a validation set, and a test set; The radial basis neural network model is trained by the training set, and the radial basis neural network model is optimized by a particle swarm algorithm during the training process; The calculation formula of the particle dimension in the particle swarm algorithm is as follows: D = I × J + J + J × K; Wherein, D is the particle dimension in the particle swarm algorithm, I is the number of input layer nodes of the radial basis neural network model, J is the number of hidden layer nodes of the radial basis neural network model, and K is the number of output layer nodes of the radial basis neural network model.

5. The method according to any one of claims 1 to 3, characterized in that The state data includes at least one of the following: oil pressure, casing pressure, oil / technical casing pressure and wellhead temperature of the injection and production well.

6. The method according to claim 1, characterized in that The oil pressure constraint condition of the injection-production well is: the oil pressure of the injection-production well is less than or equal to the maximum oil pressure of the injection-production well; The casing pressure constraint condition of the injection-production well is: the casing pressure of the injection-production well is less than or equal to the maximum casing pressure of the injection-production well; The oil / technical suite pressure constraint condition of the injection-production well is: the oil / technical suite pressure of the injection-production well is less than or equal to the maximum oil / technical suite pressure of the injection-production well; The wellhead temperature constraint condition of the injection-production well is: the wellhead temperature of the injection-production well is less than or equal to the maximum wellhead temperature of the injection-production well; The constraint condition of the number of wells to be opened in the gas storage is: the number of wells to be opened in the gas storage is less than or equal to the maximum number of wells that can be opened on the same day in the gas storage, and the maximum number of wells that can be opened on the same day is less than or equal to the number of injection and production wells in the gas storage; The gas production constraint condition of the injection-production well is: the gas production of the injection-production well is less than or equal to the maximum gas production of the injection-production well, and the maximum gas production of the injection-production well is positively correlated with the formation pressure of the injection-production well; The outlet pressure constraint condition of the injection-production well is: the outlet pressure of the injection-production well is less than or equal to the bearing capacity of the surface equipment of the injection-production well.

7. A gas storage peak load regulation process safety monitoring and optimization device, characterized in that: include: A first acquisition module is used to acquire a pre-trained radial basis function neural network model, wherein the radial basis function neural network model is used to indicate the relationship between the gas production volume of the injection and production well and the state data of the injection and production well; A construction module is used to construct an objective function model and safety constraints of a gas storage facility; wherein the objective function model of the gas storage facility is the difference between the total gas production of each injection and production well of the gas storage facility and the target gas production; the safety constraints include at least one of the following: an oil pressure constraint of each injection and production well in the gas storage facility, a casing pressure constraint of the injection and production well, an oil / technical casing pressure constraint of the injection and production well, a wellhead temperature constraint of the injection and production well, a well opening number constraint of the gas storage facility, a gas production constraint of the injection and production well, and an outlet pressure constraint of the gas storage facility; A processing module, used for substituting the radial basis neural network model into the objective function model to obtain a peak-shaving optimization model of the gas storage, wherein the peak-shaving optimization model is used to indicate: the total gas production of each injection and production well of the gas storage and the relationship between the status data of each injection and production well of the gas storage; A second acquisition module is used to acquire inherent gas storage information of a target gas storage, and substitute the inherent gas storage information of the target gas storage into the peak-shaving optimization model to obtain the peak-shaving optimization model of the target gas storage; The optimization module is used to optimize the peak-shaving optimization model of the target gas storage reservoir under the safety constraint conditions to obtain the target gas production volume of each injection and production well of the target gas storage reservoir when the safety constraint conditions are met and the output of the peak-shaving optimization model is minimized.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 6.

Images