Digital twinborn monitoring method for underground salt cavern gas storage of compressed air energy storage power station

Abstract

The invention relates to the technical field of underground salt cavern gas storage monitoring, in particular to a digital twinborn monitoring method for an underground salt cavern gas storage of a compressed air energy storage power station, which comprises the following steps of: performing pressure monitoring on each pressure monitoring point of the underground salt cavern gas storage based on a pressure sensor; performing temperature monitoring on each temperature monitoring point of the underground salt cavern gas storage based on a temperature sensor; and performing flow monitoring on each flow monitoring point of the underground salt cavern gas storage based on a flow sensor, and performing stress-strain monitoring on each stress monitoring point of the underground salt cavern gas storage based on a stress sensor. Pressure, temperature, flow, stress and humidity are monitored through multiple sensors, the state of the underground environment can be obtained in real time, it is ensured that potential risks are reflected in time, the abnormal state can be effectively recognized by utilizing the trained risk early warning model, early warning can be given out in advance, and therefore safe operation of the gas storage is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of underground salt cavern gas storage monitoring, and in particular to a digital twin monitoring method for an underground salt cavern gas storage of a compressed gas energy storage power station. Background Art

[0002] An underground salt cavern gas storage is an underground facility used to store and manage compressed air. It is mainly used in compressed air energy storage systems. Underground salt cavern gas storage uses natural salt caverns formed by underground salt layers to store compressed air. These salt caverns are artificially excavated or use holes formed by natural salt layers to inject and store high-pressure gas.

[0003] Traditional methods usually rely on limited monitoring parameters and cannot fully reflect the complexity of the underground environment, making it difficult to detect potential risks in a timely manner. Traditional monitoring technologies often rely on manual inspection and data analysis, with a slow response speed, and cannot achieve real-time monitoring and rapid response, which increases the difficulty of risk management. Traditional methods may not have advanced models to identify abnormal conditions, resulting in the inability to provide early warnings, increasing the possibility of accidents. Traditional monitoring data are usually presented in digital or tabular form, lacking intuitive visualization tools, making it difficult to help decision makers quickly understand the condition of underground structures. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a digital twin monitoring method for an underground salt cavern gas storage reservoir of a compressed gas energy storage power station.

[0005] The technical solution adopted to solve the above technical problems is: a digital twin monitoring method for underground salt cavern gas storage in a compressed gas energy storage power station, comprising:

[0006] Performing pressure monitoring at each pressure monitoring point of the underground salt cavern gas storage reservoir based on a pressure sensor, and performing temperature monitoring at each temperature monitoring point of the underground salt cavern gas storage reservoir based on a temperature sensor;

[0007] Based on the flow sensor, flow monitoring is performed on each flow monitoring point of the underground salt cavern gas storage reservoir, based on the stress sensor, stress strain monitoring is performed on each stress monitoring point of the underground salt cavern gas storage reservoir, and based on the humidity sensor, humidity monitoring is performed on each humidity monitoring point of the underground salt cavern gas storage reservoir;

[0008] Extracting features of the pressure at each pressure monitoring point, the temperature at each temperature monitoring point, the flow rate at each flow monitoring point, the stress change at each stress monitoring point, and the humidity at each humidity monitoring point of the underground salt cavern gas storage to obtain data features;

[0009] Performing risk warning on the data features based on the trained risk warning model to obtain a risk warning label for the underground salt cavern gas storage;

[0010] Based on BIM technology, the underground and above-ground geometric modeling of salt cavity + gas well + gas tree is constructed to obtain the geometric model of underground salt cavern gas storage;

[0011] The pressure of each pressure monitoring point of the underground salt cavern gas storage, the temperature of each temperature monitoring point, the flow rate of each flow monitoring point, the stress change of each stress monitoring point, the humidity of each humidity monitoring point and the risk warning label map are mapped to the corresponding geometric model of the underground salt cavern gas storage to obtain a digital twin model of the underground salt cavern gas storage.

[0012] Preferably, the pressure monitoring points include the bottom of the well, the wellhead of the injection and production pipe, the A annulus, the B annulus and the plugging well, the temperature monitoring points include the protective wellbore, the salt cavity and the A annulus, the flow monitoring points include the straight pipe section at the wellhead of the injection and production well, the stress monitoring points include the cement ring of the injection and production well casing, and the humidity monitoring points include the wellhead of the injection and production well.

[0013] Preferably, the data characteristics include pressure characteristics, temperature characteristics, flow characteristics, stress characteristics and humidity characteristics, wherein the pressure characteristics include the average pressure of each pressure monitoring point, the pressure fluctuation range and the pressure change rate, the temperature characteristics include the average temperature of each temperature monitoring point, the temperature change rate and the temperature fluctuation amplitude, the flow characteristics include the average flow of each flow monitoring point, the flow change trend and the flow fluctuation amplitude, the stress characteristics include the average stress of each stress monitoring point, the stress change rate and the stress fluctuation range, and the humidity characteristics include the average humidity of each humidity monitoring point, the humidity change trend and the humidity fluctuation amplitude.

[0014] Preferably, the risk warning model adopts an improved support vector machine, and optimizes the parameters of the support vector machine based on the slime mold optimization algorithm to obtain an improved support vector machine, wherein the parameters of the support vector machine include a penalty coefficient and a kernel function.

[0015] Preferably, the parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, including:

[0016] Initializing the parameters of the slime mold optimization algorithm, wherein the parameters of the slime mold optimization algorithm include a population size N, a problem dimension D, a maximum number of iterations T, an upper bound ub of a search space, and a lower bound lb of a search space;

[0017] An initial particle population is generated in the search space, the fitness value of each individual particle in the particle population is calculated, and the fitness value of each individual particle in the particle population is sorted to update the best fitness value bF and the worst fitness value wF under the current number of iterations.

[0018] Preferably, the parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, and further includes:

[0019] The position of each individual particle in the particle population is disturbed, and the fitness value of the individual particle is recalculated. The disturbance formula is as follows:

[0020]

[0021] Among them, X(t+1) represents the position of the individual particle at the t+1th iteration, X b (T) represents the position of the best individual at the tth iteration, X A (t) and X B (t) represents two individuals randomly selected from the particle population at the tth iteration, vb represents a random number in [―a,a], a represents a dynamically updated parameter, and vc represents a parameter that decreases linearly from 1 to 0 as the number of iterations increases, r represents a random number in [0,1], p represents a dynamic threshold, and p = tanh(S(i)-DF), S(i) represents the fitness value of the individual particle, DF represents the currently obtained optimal fitness value of the individual particle, W represents the dynamic weight of the individual particle, and

[0022] Repeat the above steps until the maximum number of iterations is reached to output the optimal individual particle position, which is the optimal combination of the parameters of the support vector machine. The support vector machine is improved based on the optimal combination of the parameters of the support vector machine to obtain an improved support vector machine.

[0023] The beneficial effects of the present invention are as follows: (1) The present invention monitors pressure, temperature, flow, stress and humidity through a variety of sensors, and can obtain the status of the underground environment in real time to ensure timely response to potential risks; (2) The present invention can effectively identify abnormal conditions and issue early warnings by utilizing trained risk warning models, thereby ensuring the safe operation of the gas storage facility; (3) The present invention provides an intuitive visualization tool by mapping monitoring data into a geometric model, thereby enhancing the understanding and monitoring capabilities of underground structures, and through real-time data feedback, it can better formulate maintenance strategies, extend the service life of the gas storage facility and improve operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1A schematic flow chart of the steps of an overall method in an embodiment of the present invention;

[0025] Figure 2 This is a schematic diagram of the sensor installation position in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] Embodiment 1, as Figure 1 - Figure 2 As shown, the present invention proposes a digital twin monitoring method for underground salt cavern gas storage of a compressed gas energy storage power station, comprising:

[0027] S1. Performing pressure monitoring at each pressure monitoring point of the underground salt cavern gas storage reservoir based on a pressure sensor, and performing temperature monitoring at each temperature monitoring point of the underground salt cavern gas storage reservoir based on a temperature sensor;

[0028] S2. Perform flow monitoring at each flow monitoring point of the underground salt cavern gas storage based on a flow sensor, perform stress strain monitoring at each stress monitoring point of the underground salt cavern gas storage based on a stress sensor, and perform humidity monitoring at each humidity monitoring point of the underground salt cavern gas storage based on a humidity sensor;

[0029] S3, extracting features of the pressure at each pressure monitoring point of the underground salt cavern gas storage, the temperature at each temperature monitoring point, the flow rate at each flow monitoring point, the stress change at each stress monitoring point, and the humidity at each humidity monitoring point to obtain data features;

[0030] S4. Perform risk warning on data features based on the trained risk warning model to obtain risk warning labels for underground salt cavern gas storage;

[0031] S5. Construct the underground and above-ground geometric modeling of salt cavity + gas well + gas tree based on BIM technology to obtain the geometric model of underground salt cavern gas storage;

[0032] S6. Map the pressure of each pressure monitoring point of the underground salt cavern gas storage, the temperature of each temperature monitoring point, the flow rate of each flow monitoring point, the stress change of each stress monitoring point, the humidity of each humidity monitoring point and the risk warning label map to the corresponding underground salt cavern gas storage geometric model to obtain a digital twin model of the underground salt cavern gas storage.

[0033] In the present invention, BIM technology is a digital modeling technology used for construction and engineering projects. Through BIM technology, a geometric model of a target underground salt cavern gas storage reservoir can be created and managed, including structure, equipment and space information; the geometric model is a three-dimensional digital model of the target underground salt cavern gas storage reservoir, showing its geometric shape and structure; the gas storage cavity refers to a cavity in an underground salt cavern gas storage reservoir for storing gas, and the cavity stores gas by injecting gas and releases the gas when needed.

[0034] Embodiment 2, the present invention proposes a digital twin monitoring method for an underground salt cavern gas storage reservoir of a compressed gas energy storage power station. Compared with Embodiment 1, this embodiment also includes: pressure monitoring points include the bottom of the well, the wellhead of the injection and production pipe, the A annulus, the B annulus and the plugging well, the temperature monitoring points include the protective wellbore, the salt cavity and the A annulus, the flow monitoring points include the straight pipe section at the wellhead of the injection and production well, the stress monitoring points include the cement ring of the injection and production well casing, and the humidity monitoring points include the wellhead of the injection and production well.

[0035] In this embodiment, A annulus / B annulus: the space between the inside and outside casing of the wellbore, usually used to monitor the pressure and fluid status of the wellbore wall; plugging well: a well used to seal or isolate the wellbore to ensure that the fluid does not leak or be contaminated; protecting the wellbore: used to protect the structure of the main wellbore and prevent damage to the wellbore by external factors; salt cavity: a cavity excavated in the underground salt layer for storing gas or liquid; straight pipe section at the wellhead of the injection and production well: the straight pipe section of the injection and production well, directly connecting the wellhead with the ground facilities; cement ring of the injection and production well casing: a cement ring surrounding the wellbore, used to fix the casing and prevent fluid leakage, thereby ensuring the integrity of the well.

[0036] In an optional embodiment, the data characteristics include pressure characteristics, temperature characteristics, flow characteristics, stress characteristics and humidity characteristics, wherein the pressure characteristics include the average pressure, pressure fluctuation range and pressure change rate of each pressure monitoring point, the temperature characteristics include the average temperature, temperature change rate and temperature fluctuation amplitude of each temperature monitoring point, the flow characteristics include the average flow, flow change trend and flow fluctuation amplitude of each flow monitoring point, the stress characteristics include the average stress, stress change rate and stress fluctuation range of each stress monitoring point, and the humidity characteristics include the average humidity, humidity change trend and humidity fluctuation amplitude of each humidity monitoring point.

[0037] In an optional embodiment, the risk warning model adopts an improved support vector machine, and optimizes the parameters of the support vector machine based on the slime mold optimization algorithm to obtain an improved support vector machine, wherein the parameters of the support vector machine include a penalty coefficient and a kernel function.

[0038] It should be noted that support vector machine (SVM): a supervised learning model mainly used for classification and regression analysis, which distinguishes different categories of data by finding the best hyperplane; penalty coefficient: in SVM, it is used to control the classifier's tolerance for misclassification. A larger penalty coefficient will cause the model to pay more attention to the accuracy of the training data, which may lead to overfitting; kernel function: used to map input data to a high-dimensional space in order to better separate different categories of data. Common kernel functions include linear kernels, radial basis functions (RBF), etc.; slime mold optimization algorithm: a heuristic optimization algorithm that imitates the behavior of slime mold and finds the optimal solution through exploration and utilization mechanisms. It is suitable for complex parameter optimization problems.

[0039] In an optional embodiment, the parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, including:

[0040] A1. Initialize the parameters of the slime mold optimization algorithm, where the parameters of the slime mold optimization algorithm include the population size N, the problem dimension D, the maximum number of iterations T, the upper bound ub of the search space, and the lower bound lb of the search space;

[0041] A2. Generate an initial particle population in the search space, calculate the fitness value of each individual particle in the particle population, and sort the fitness value of each individual particle in the particle population to update the best fitness value bF and the worst fitness value wF under the current number of iterations.

[0042] In an optional embodiment, the parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, further comprising:

[0043] A3. Perturb the position of each individual particle in the particle population and recalculate the fitness value of the individual particle. The perturbation formula is as follows:

[0044]

[0045] Among them, X(t+1) represents the position of the individual particle at the t+1th iteration, X b (t) represents the position of the best individual at the tth iteration, X A (t) and X B (t) represents two individuals randomly selected from the particle population at the tth iteration, vb represents a random number in [―a,a], a represents a dynamically updated parameter, and vc represents a parameter that decreases linearly from 1 to 0 as the number of iterations increases, r represents a random number in [0,1], p represents a dynamic threshold, and p = tanh(S(i)-DF), S(i) represents the fitness value of the individual particle, DF represents the currently obtained optimal fitness value of the individual particle, W represents the dynamic weight of the individual particle, and

[0046] A4. Repeat the above steps until the maximum number of iterations is reached to output the optimal individual particle position, which is the optimal combination of support vector machine parameters. The support vector machine is improved based on the optimal combination of support vector machine parameters to obtain an improved support vector machine.

[0047] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A digital twin monitoring method for underground salt cavern gas storage in a compressed gas energy storage power station, characterized in that: include: Performing pressure monitoring at each pressure monitoring point of the underground salt cavern gas storage reservoir based on a pressure sensor, and performing temperature monitoring at each temperature monitoring point of the underground salt cavern gas storage reservoir based on a temperature sensor; Based on the flow sensor, flow monitoring is performed on each flow monitoring point of the underground salt cavern gas storage reservoir, based on the stress sensor, stress strain monitoring is performed on each stress monitoring point of the underground salt cavern gas storage reservoir, and based on the humidity sensor, humidity monitoring is performed on each humidity monitoring point of the underground salt cavern gas storage reservoir; Extracting features of the pressure at each pressure monitoring point, the temperature at each temperature monitoring point, the flow rate at each flow monitoring point, the stress change at each stress monitoring point, and the humidity at each humidity monitoring point of the underground salt cavern gas storage to obtain data features; Performing risk warning on the data features based on the trained risk warning model to obtain a risk warning label for the underground salt cavern gas storage; Based on BIM technology, the underground and above-ground geometric modeling of salt cavity + gas well + gas tree is constructed to obtain the geometric model of underground salt cavern gas storage; The pressure of each pressure monitoring point of the underground salt cavern gas storage, the temperature of each temperature monitoring point, the flow rate of each flow monitoring point, the stress change of each stress monitoring point, the humidity of each humidity monitoring point and the risk warning label map are mapped to the corresponding geometric model of the underground salt cavern gas storage to obtain a digital twin model of the underground salt cavern gas storage.

2. According to claim 1, a digital twin monitoring method for underground salt cavern gas storage of a compressed gas energy storage power station is characterized in that: The pressure monitoring points include the bottom of the well, the wellhead of the injection and production pipe, the A annulus, the B annulus and the plugging well; the temperature monitoring points include the protective wellbore, the salt cavity and the A annulus; the flow monitoring points include the straight pipe section at the wellhead of the injection and production well; the stress monitoring points include the cement ring of the casing of the injection and production well; and the humidity monitoring points include the wellhead of the injection and production well.

3. A digital twin monitoring method for underground salt cavern gas storage of a compressed gas energy storage power station according to claim 1, characterized in that: The data characteristics include pressure characteristics, temperature characteristics, flow characteristics, stress characteristics and humidity characteristics, wherein the pressure characteristics include the average pressure, pressure fluctuation range and pressure change rate of each pressure monitoring point, the temperature characteristics include the average temperature, temperature change rate and temperature fluctuation amplitude of each temperature monitoring point, the flow characteristics include the average flow, flow change trend and flow fluctuation amplitude of each flow monitoring point, the stress characteristics include the average stress, stress change rate and stress fluctuation range of each stress monitoring point, and the humidity characteristics include the average humidity, humidity change trend and humidity fluctuation amplitude of each humidity monitoring point.

4. A digital twin monitoring method for underground salt cavern gas storage of a compressed gas energy storage power station according to claim 1, characterized in that: The risk warning model adopts an improved support vector machine, and optimizes the parameters of the support vector machine based on a slime mold optimization algorithm to obtain an improved support vector machine, wherein the parameters of the support vector machine include a penalty coefficient and a kernel function.

5. A digital twin monitoring method for underground salt cavern gas storage of a compressed gas energy storage power station according to claim 4, characterized in that: The parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, including: Initializing the parameters of the slime mold optimization algorithm, wherein the parameters of the slime mold optimization algorithm include a population size N, a problem dimension D, a maximum number of iterations T, an upper bound ub of a search space, and a lower bound lb of a search space; An initial particle population is generated in the search space, the fitness value of each individual particle in the particle population is calculated, and the fitness value of each individual particle in the particle population is sorted to update the best fitness value bF and the worst fitness value wF under the current number of iterations.

6. A digital twin monitoring method for underground salt cavern gas storage in a compressed gas energy storage power station according to claim 5, characterized in that: The parameters of the support vector machine are optimized based on the slime mold optimization algorithm to obtain an improved support vector machine, which also includes: The position of each individual particle in the particle population is disturbed, and the fitness value of the individual particle is recalculated. The disturbance formula is as follows: Among them, X(t+1) represents the position of the individual particle at the t+1th iteration, X b (t) represents the position of the best individual at the tth iteration, X A (t) and X B (t) represents two individuals randomly selected from the particle population at the tth iteration, vb represents a random number in [―a,a], a represents a dynamically updated parameter, and vc represents a parameter that decreases linearly from 1 to 0 as the number of iterations increases, r represents a random number in [0,1], p represents a dynamic threshold, and p = tanh(S(i)-DF), S(i) represents the fitness value of the individual particle, DF represents the currently obtained optimal fitness value of the individual particle, W represents the dynamic weight of the individual particle, and Repeat the above steps until the maximum number of iterations is reached to output the optimal individual particle position, which is the optimal combination of the parameters of the support vector machine. The support vector machine is improved based on the optimal combination of the parameters of the support vector machine to obtain an improved support vector machine.

Images