A method, device, equipment, medium and product for predicting halogen discharge crystallization of a pipe column in a salt cavern gas storage

Abstract

The application discloses a kind of salt cavern gas storage pipe string halogen discharge crystallization prediction method, device, equipment, medium and product, comprising: determining halogen discharge crystallization dataset and obtaining prediction model based on the halogen discharge crystallization dataset, the halogen discharge crystallization dataset includes at least one of experimental dataset, simulation dataset and monitoring dataset;The current brine parameter corresponding to the deep salt cavern gas storage is obtained;The current brine parameter is input into the prediction model, and the prediction result of the halogen discharge crystallization of the salt cavern gas storage pipe string is determined.The above technical solution realizes the diagnosis and prediction of the halogen discharge process of the deep salt cavern gas storage pipe string internal brine crystallization.

Description

Technical Field

[0001] This invention relates to the field of salt cavern gas analysis technology, and in particular to a method, apparatus, equipment, medium and product for predicting brine crystallization in the tubular column of a salt cavern gas storage facility. Background Technology

[0002] Salt cavern gas storage facilities utilize thick underground salt layers or salt domes, forming artificial cavern storage spaces through water-soluble cavity construction to store substances such as oil, natural gas, and carbon dioxide. Salt cavern gas storage facilities offer advantages such as large gas injection and extraction volumes, simple surface processes, and high capacity utilization. However, during the gas injection and brine discharge process in salt cavern gas storage facilities, changes in brine temperature and pressure can lead to crystal precipitation. These precipitated crystals adhere to the inner wall of the discharge pipe and continuously thicken, potentially causing blockages if not cleaned promptly. Deep salt cavern gas storage facilities are characterized by high temperature and pressure, and long discharge pipes. The deeper the burial depth, the longer the discharge pipe, resulting in a longer brine flow time within the pipe. The brine, primarily composed of sodium chloride, also contains other inorganic salt minerals and impurities, making crystallization in the discharge pipe more complex. Crystallization is the result of the combined effects of multiple factors, including the inorganic salt composition of the brine, the concentration of inorganic salt ions, the impurity content, temperature, pressure, flow rate, and the pipe material.

[0003] The ability to accurately diagnose and predict brine crystallization in the tubing of deep salt cavern gas storage wells directly affects the effective implementation of measures to prevent and control tubing blockage. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for predicting brine crystallization in tubing within a salt cavern gas storage facility, enabling the diagnosis and prediction of brine crystallization within the tubing during the brine discharge process in deep salt cavern gas storage wells.

[0005] In a first aspect, embodiments of this disclosure provide a method for predicting brine crystallization in tubular columns within a salt cavern gas storage facility, comprising:

[0006] A brine crystallization dataset is determined and a prediction model is trained based on the brine crystallization dataset, wherein the brine crystallization dataset includes at least one of an experimental dataset, a simulation dataset, and a monitoring dataset;

[0007] Obtain the current brine parameters corresponding to the deep salt cavern gas storage facility;

[0008] The current brine parameters are input into the prediction model to determine the prediction results of brine discharge and crystallization in the tubular column of the salt cavern gas storage.

[0009] Secondly, embodiments of this disclosure provide a predictive device for brine crystallization in a tubular column of a salt cavern gas storage facility, comprising:

[0010] A dataset determination module is used to determine a brine crystallization dataset and train a prediction model based on the brine crystallization dataset, wherein the brine crystallization dataset includes at least one of an experimental dataset, a simulation dataset, and a monitoring dataset.

[0011] The brine parameter acquisition module is used to acquire the current brine parameters corresponding to the deep salt cavern gas storage.

[0012] The crystallization prediction module is used to input the current brine parameters into the prediction model to determine the prediction result of brine crystallization in the tubing of the salt cavern gas storage.

[0013] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the method for predicting brine crystallization in the tubular column of a salt cavern gas storage facility provided in the first aspect embodiment above.

[0017] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility provided in the first aspect of the embodiments above.

[0018] Fifthly, this disclosure provides a computer program product, which includes a computer program that, when executed by a processor, implements a method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility as provided in the first aspect embodiment.

[0019] This invention discloses a method, apparatus, equipment, medium, and product for predicting brine crystallization during brine discharge from tubing in a salt cavern gas storage facility. The method includes determining a brine crystallization dataset and training a prediction model based on the dataset. The dataset includes at least one of experimental, simulated, and monitoring datasets. The method also involves acquiring current brine parameters corresponding to the deep salt cavern gas storage facility, inputting these parameters into the prediction model, and determining the prediction result for brine crystallization during brine discharge from the tubing within the salt cavern gas storage facility. This technical solution enables the diagnosis and prediction of brine crystallization within the tubing during the brine discharge process in deep salt cavern gas storage facilities.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility, provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is an example diagram of brine parameters provided in Embodiment 1 of the present invention;

[0024] Figure 3 This is an example diagram of a prediction result provided in Embodiment 1 of the present invention;

[0025] Figure 4a This is an example diagram illustrating the change in the amount of crystallization of a brine object under a first set environment, as provided in Embodiment 1 of the present invention.

[0026] Figure 4b This is an example diagram illustrating the change in the amount of crystallization of another brine object under a first set environment, as provided in Embodiment 1 of the present invention.

[0027] Figure 5 This is an example diagram of the coupling between a temperature field and a seepage field provided in Embodiment 1 of the present invention;

[0028] Figure 6a This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, provided in Embodiment 1 of the present invention.

[0029] Figure 6b This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, as provided in Embodiment 1 of the present invention.

[0030] Figure 6c This is another example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, provided in Embodiment 1 of the present invention;

[0031] Figure 6d This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, as provided in Embodiment 1 of the present invention.

[0032] Figure 7This is a schematic diagram of the structure of a predictive device for brine crystallization in a tubular column of a salt cavern gas storage facility, provided in Embodiment 2 of the present invention.

[0033] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," and "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] Example 1

[0037] Figure 1 This is a flowchart of a method for predicting brine crystallization during brine discharge from a tubular column in a salt cavern gas storage facility, provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the internal crystallization situation needs to be analyzed and predicted during the brine discharge process in a salt cavern gas storage facility. This method can be executed by a brine crystallization prediction device for tubular column brine discharge in a salt cavern gas storage facility, which can be implemented in hardware and / or software.

[0038] like Figure 1 As shown, the method includes:

[0039] S101. Determine the brine crystallization dataset and train a prediction model based on the brine crystallization dataset. The brine crystallization dataset includes at least one of the experimental dataset, simulation dataset, and monitoring dataset.

[0040] In this embodiment, the brine crystallization dataset can be understood as a dataset related to brine crystallization (brine crystallization) in the tubing of a brine wellbore, including at least one of experimental datasets, simulation datasets, and monitoring datasets. The dataset includes brine parameters as input data and brine crystallization information as output data. Specifically, the experimental dataset is obtained under controlled experimental conditions, the simulation dataset is obtained under a simulation environment coupled with temperature and seepage fields, and the monitoring dataset is collected from the tubing of an actual deep salt cavern gas storage brine wellbore. The prediction model can be understood as a model used to predict brine crystallization in the tubing of a deep salt cavern gas storage brine wellbore.

[0041] Specifically, firstly, brine objects with different brine parameters are identified, and then the crystallization of these brine objects under controlled variable conditions is determined to obtain corresponding brine discharge crystallization information. These brine parameters and corresponding brine discharge crystallization information are then compiled into an experimental dataset. Secondly, the brine composition within the discharge wellbore of a deep salt cavern gas storage facility is extracted, and corresponding brine parameters are determined. Based on these parameters, a corresponding brine object is simulated, and the crystallization of this simulated brine object under a coupled temperature and flow field environment is further determined to obtain corresponding brine discharge crystallization information. The brine parameters and corresponding brine discharge crystallization information of this simulated brine object are then compiled into a simulation dataset. Finally, brine within a deep salt cavern gas storage facility is extracted as the brine object, its brine parameters are analyzed, and the crystallization of the brine object within the deep salt cavern gas storage facility is dynamically monitored to obtain corresponding brine discharge crystallization information. The brine parameters and corresponding brine discharge crystallization information of this actual brine object are then compiled into a monitoring dataset.

[0042] A deep learning network model is established. The brine crystallization dataset is divided into training and test sets according to a certain ratio. The deep learning network model is trained based on the input and output sample sets in the training set. After training is complete, the deep learning network model is validated based on the input and output samples in the test set. If the validation is successful, the deep learning network model is determined to be a fully trained prediction model. If the validation fails, the deep learning network model is retrained based on the training set, or the brine crystallization dataset is redefined, and then the subsequent process is executed iteratively until the model passes the test on the validation set, indicating that the model is fully trained and the output is accurate.

[0043] S102. Obtain the current brine parameters corresponding to the deep salt cavern gas storage tank.

[0044] In this embodiment, the current brine parameters can be understood as brine-related parameters related to the crystallization information to be predicted, collected in real time. The current brine parameters include at least one of the following: brine composition, ion concentration, brine temperature, brine pH, brine salinity, brine conductivity, formation depth, formation temperature, formation pressure, tubing depth, tubing discharge intensity, tubing wall material, wellhead discharge intensity, wellhead pressure, and cavity pressure. Brine composition refers to the chemical components dissolved in the brine, typically including inorganic salts such as sodium ions, potassium ions, calcium ions, magnesium ions, carbonate ions, sulfate ions, chloride ions, and bicarbonate ions. The brine composition directly affects the industrial utilization value of the brine. Ion concentration is the content of specific ions in the brine. Brine salinity is the total mass of dissolved salts per unit volume of brine, reflecting the salinity of the brine. Brine conductivity is a parameter measuring the electrical conductivity of the brine, positively correlated with ion concentration and type, and often used for rapid estimation of salinity. Brine temperature is the temperature of the brine at the time of extraction. The pH value of brine reflects its acidity or alkalinity; acidic brine easily corrodes metal pipes. Formation depth is the vertical depth of the brine layer from the surface, usually positively correlated with pressure and temperature. Formation temperature is the in-situ temperature of the brine layer. Formation pressure is the pressure exerted on the fluid in the brine layer. Pipeline depth is the depth to which the downhole tubing (production casing or tubing) penetrates the formation. Pipeline discharge intensity characterizes the volume of brine discharged per unit time through the tubing, related to production capacity and pump power. Wellhead discharge intensity is the brine flow rate discharged at the wellhead, affected by formation permeability and pump efficiency. Pipeline wall material is the metal material of the tubing, such as carbon steel, stainless steel, or titanium alloy, and must be resistant to brine corrosion and high pressure. Wellhead pressure is the residual pressure of the brine at the wellhead, reflecting formation energy. Cavity pressure is the pressure within the artificial cavity or reservoir of a deep salt cavern gas storage well; the cavity pressure must be kept stable to prevent formation collapse or brine leakage. Figure 2 This is an example diagram of brine parameters provided in Embodiment 1 of the present invention, as shown below. Figure 2 As shown, the main components of brine in deep salt cavern gas storage include sodium ions, potassium ions, calcium ions, magnesium ions, suspended solids, carbonate ions, sulfate ions, chloride ions, and bicarbonate ions. Each ion has its corresponding concentration (mass). The table also includes brine mineralization, brine density, and brine type. Brine type is the reference solution type of the brine, such as sodium chloride solution.

[0045] Specifically, the geological environment parameters (deep formation, temperature, pressure), mining engineering parameters (tubing depth, brine discharge intensity, tubing wall material, wellhead brine discharge intensity, wellhead pressure, cavity pressure), and brine property parameters (brine composition, ion concentration, temperature, pH, salinity, conductivity) corresponding to the deep salt cavern gas storage under the current actual working conditions are obtained.

[0046] S103. Input the current brine parameters into the prediction model to determine the prediction results of brine discharge and crystallization in the tubular column of the salt cavern gas storage.

[0047] In this embodiment, the prediction result can be understood as predictive information related to brine crystallization in deep salt cavern gas storage pipelines, including at least one of the following: crystallization type, crystallization amount, and crystallization location. The crystallization type is related to the chemical composition, such as sodium chloride (NaCl) crystallization, calcium sulfate (CaSO4) crystallization, and complex salt crystallization. The crystallization amount refers to the physical quantity of salt deposition per unit time or space. The crystallization location refers to the spatial distribution of crystals within the pipeline.

[0048] Specifically, the current brine parameters are input into the prediction model to predict brine crystallization in the tubing of the brine discharge wellbore of the deep salt cavern gas storage. The prediction model is then used to perform calculations and output the prediction results. The prediction results indicate whether there will be brine crystallization in the tubing of the brine discharge wellbore of the deep salt cavern gas storage. If so, the prediction results also include the crystallization type, amount, and location of the brine crystallization.

[0049] For example, Figure 3 This is an example diagram of a prediction result provided in Embodiment 1 of the present invention, such as... Figure 3 As shown, the predicted results corresponding to the current brine parameters include crystallization types such as sodium chloride crystallization, barium sulfate crystallization, calcium carbonate crystallization, and calcium sulfate crystallization. The crystallization locations include surface facilities, choke valves, wellhead, midhead (vertical well section 500-1500m downhole), downhole (generally referring to the well section above the top of the salt cavern), bottomhole, and salt cavern body. The specific predictions include: calcium sulfate crystals are present at 26 mg / L in the salt cavern itself, with no crystals found in other locations; barium sulfate crystals are present at all locations between 2 mg / L and 3 mg / L; calcium carbonate crystals gradually increase from 7 mg / L to 28 mg / L in the locations of surface facilities, choke valves, wellheads, intermediate sections, downhole, bottom of the salt cavern, and the salt cavern itself, meaning that the deeper the depth, the more calcium carbonate crystals are produced; sodium chloride crystals gradually decrease from 13000 mH / L to 3000 mH / L in the locations of surface facilities, choke valves, wellheads, intermediate sections, downhole, bottom of the salt cavern, and the salt cavern itself, meaning that the deeper the depth, the less sodium chloride crystals are produced.

[0050] This invention provides a method for predicting brine crystallization during brine discharge from tubing in a salt cavern gas storage facility. The method includes determining a brine crystallization dataset and training a prediction model based on this dataset. The brine crystallization dataset includes at least one of experimental, simulated, and monitoring datasets. The method also involves obtaining the current brine parameters corresponding to the deep salt cavern gas storage facility, inputting these parameters into the prediction model, and determining the predicted result for brine crystallization during brine discharge from the tubing within the salt cavern gas storage facility. This technical solution establishes a prediction model that integrates multiple information sources for multi-angle comprehensive diagnosis, enabling more accurate diagnosis and prediction of brine crystallization during brine discharge from the wellbore in deep salt cavern gas storage facilities.

[0051] In one embodiment, determining the brine crystallization dataset includes:

[0052] a1. Determine multiple brine objects and the first brine parameter for each brine object.

[0053] In this embodiment, the brine object can be understood as a brine solution prepared based on core analysis and brine chemical analysis, such as a solution with different inorganic salt components added to a sodium chloride solution as a reference. The first brine parameter can be understood as the relevant parameters corresponding to these brine objects, including at least the brine components and ion concentrations, and may also include the pH, salinity, and conductivity of the brine object. Different brine objects may differ not only in brine components and ion concentrations, but also in pH, salinity, and conductivity. Each brine object has the same formation depth, formation temperature, formation pressure, tubing depth, tubing discharge intensity, tubing wall material, wellhead discharge intensity, wellhead pressure, and cavity pressure.

[0054] Specifically, brine samples are taken primarily from the target deep salt cavern gas storage facility to obtain corresponding brine samples. The geological characteristics of the stratigraphic layer where the target deep salt cavern gas storage facility is located and the results of core analysis (i.e., the formation environmental parameters and mining engineering parameters of the brine samples) are determined. The original brine components and ion concentrations of the brine samples are identified, and different component solutions are prepared for the brine samples to form corresponding brine objects with different components and ion concentrations. Furthermore, for the same brine object, tubing walls of different materials are installed within the brine object.

[0055] The process of preparing different component solutions for brine samples to form brine objects with different brine components and ion concentrations includes: adding at least one reference solution to the reference sodium chloride solution corresponding to the brine sample. The reference solution is an inorganic salt solution that is different from the sodium chloride solution and has different components and concentrations than the reference sodium chloride solution.

[0056] For example, brine solutions of different concentrations of inorganic salts are added to a NaCl solution to form a corresponding brine object, and the corresponding first brine parameters are identified and analyzed; brine solutions of two different concentrations of inorganic salts are added to a NaCl solution to form a corresponding brine object, and the corresponding first brine parameters are identified and analyzed; brine solutions of three different concentrations of inorganic salts are added to a NaCl solution to form a corresponding brine object, and the corresponding first brine parameters are identified and analyzed; brine solutions of multiple concentrations of inorganic salts are added to a NaCl solution to form a corresponding brine object, and the corresponding first brine parameters are identified and analyzed.

[0057] b1. For each brine object, determine the first brine crystallization information of the brine object under the first set environment. The first set environment is a control variable environment based on temperature or pressure.

[0058] In this embodiment, the first set environment can be understood as a pre-set experimental environment, which is a controlled variable environment based on temperature or pressure. The first brine crystallization information can be understood as relevant information on the precipitation and crystallization of brine in the brine object under the first set environment, including at least the crystallization information of brine on different column wall materials under the condition of changes in environmental variables. The crystallization information includes at least the crystallization type, crystallization location, and crystallization amount, and may also include the crystallization rate. The crystallization amount can be presented in the form of a change curve to reflect the crystallization law. The first brine crystallization information may also include changes in the pH, conductivity, and mineralization of the brine object.

[0059] Specifically, when the initial environment is at atmospheric pressure and subject to temperature variations (different starting temperatures, different temperature variations, or different temperature gradients), the crystallization of each brine sample on the corresponding material of the brine discharge column is monitored under the initial environment. This yields the crystallization location, corresponding crystallization rate, crystallization amount, and crystallization type of the brine sample on different material discharge columns under varying temperature parameters. A curve showing the effect of temperature changes on the amount of crystallization is then generated, i.e., a curve showing the change in the amount of crystallization. Taking a specific brine sample as an example... Figure 4a This is an example diagram illustrating the change in the amount of crystallization of a brine sample under a first set environment, as provided in Embodiment 1 of the present invention. Figure 4aAs shown, under normal pressure, the amount of sodium chloride crystallization decreases rapidly to zero with increasing temperature; while the amount of calcium carbonate crystallization increases uniformly and rapidly with increasing temperature. When the first set environment is at room temperature with varying pressure (different starting pressures, different pressure changes, or different pressure gradients), the crystallization of each brine object on the corresponding material of the brine discharge column under the first set environment is monitored. The crystallization position, corresponding crystallization rate, crystallization amount, and crystallization type of the brine object on the brine discharge column of different materials under pressure parameter changes are obtained. A pressure change effect curve for brine crystallization is generated for the crystallization amount, i.e., the crystallization change curve. Figure 4b This is an example diagram illustrating the change in the amount of crystallization of another brine object under a first set environment, as provided in Embodiment 1 of the present invention. Figure 4b As shown, under normal temperature conditions, the amount of calcium carbonate crystals increases slowly with increasing pressure; the amount of sodium chloride crystals decreases at a near-uniform rate until it reaches zero with increasing pressure; the amount of barium sulfate crystals decreases slowly with increasing pressure; and the amount of calcium sulfate crystals decreases until it reaches zero with increasing pressure.

[0060] Understandably, during the crystallization process, it is also possible to predict the brine crystallization of the brine object under the first set environment within a historical period. The currently fitted change curve is compared with the change curve under the same conditions within a historical period. If the similarity is greater than a set threshold (e.g., 95%), the current change curve can be fitted based on the change curve of the historical period to predict the brine crystallization situation at future times.

[0061] c1. An experimental dataset is established based on the parameters of each first brine and the corresponding first brine crystallization information.

[0062] In this embodiment, an empty experimental dataset is created, and the first brine parameters and corresponding first brine crystallization information of each brine object are added to the experimental dataset. The first brine parameters are divided into input data, and the first brine crystallization information is divided into output data.

[0063] In one embodiment, determining the brine crystallization dataset includes:

[0064] a2. Determine the target object for simulation and the second brine parameters of the target object.

[0065] In this embodiment, the simulated target object can be understood as the brine solution inside the brine draining well of a simulated deep salt cavern gas storage facility, which is a brine solution prepared based on the brine parameters of the actual brine. The second brine parameter can be understood as the relevant parameters corresponding to the simulated target object, including at least the brine components and ion concentration, and may also include the acidity, alkalinity, and conductivity of the brine object, as well as the formation depth, formation temperature, formation pressure, tubing depth, tubing draining intensity, tubing wall material, wellhead draining intensity, wellhead pressure, and cavity pressure of the simulated actual brine solution.

[0066] Specifically, brine parameters are extracted from the brine within the deep salt cavern gas storage chamber, and a corresponding brine solution is prepared based on these parameters as the simulation target. Second brine parameters for the simulation target are then determined.

[0067] b2. Determine the second row of halogen crystallization information of the simulated target object under the second set environment. The second set environment is a simulation environment that couples the temperature field and the permeation field.

[0068] In this embodiment, the second set environment can be understood as a pre-set simulation environment, which is a coupled environment of temperature field and seepage field. The second brine crystallization information can be understood as relevant information on the precipitation of brine crystals by the target object under the second set environment. It includes at least the crystallization information of the target object precipitating crystals on different column wall materials under the seepage field environment with the change of temperature field. The crystallization information includes at least the crystallization type, crystallization location and crystallization amount, and may also include the crystallization rate. The crystallization amount can be presented in the form of a change curve to reflect the crystallization law.

[0069] Figure 5 This is an example diagram illustrating the coupling of a temperature field and a seepage field according to Embodiment 1 of the present invention, as shown below. Figure 5 As shown, the temperature increases with depth; that is, the deeper the depth, the higher the temperature of the brine discharge column and the brine.

[0070] Specifically, the distribution of temperature, pressure, flow velocity, and shear force within the brine discharge column of a deep salt cavern gas storage facility is simulated through the coupling of temperature and flow fields. The target object is placed in a second, pre-defined environment coupled with the temperature and flow fields to obtain corresponding second-stage brine crystallization information; alternatively, the second-stage brine parameters of the target object are input into a pre-defined coupling model to obtain the second-stage brine crystallization information output by the coupling model, where the coupling model is a prediction model associated with the second-stage environment. Through numerical simulation of brine discharge within the column based on the coupling of temperature and flow fields, the spatial distribution of temperature, pressure, flow velocity, and shear force under different discharge intensities is obtained. The temperature and pressure distribution within the column are used to analyze the crystallization sites of the brine inside the column, while the flow velocity and shear force are used to analyze changes in brine concentration and the forces acting on crystal particles.

[0071] In the second row of halogen crystallization information, the amount of crystallization can form a variation curve. For example, Figure 6a This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, as provided in Embodiment 1 of the present invention. Figure 6a As shown, under the coupled environment of temperature field and seepage field, the amount of crystallization of calcium carbonate gradually increases with the increase of temperature. Figure 6b This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, as provided in Embodiment 1 of the present invention. Figure 6b As shown, under the coupled environment of temperature field and seepage field, the amount of crystallization of calcium sulfate crystallization shows a trend of first rapidly decreasing and then slowly increasing when the temperature increases and the ion concentration is greater than or equal to 5525 mg / L. When the ion concentration is less than 5525 mg / L, the amount of crystallization gradually decreases until it becomes zero. Figure 6c This is another example diagram illustrating the change in the amount of crystallization of a simulated target object under a second set environment, provided in Embodiment 1 of the present invention. Figure 6c As shown, under the coupled environment of temperature field and seepage field, the amount of crystallization of barium sulfate gradually decreases with increasing temperature until it reaches zero. Figure 6d This is an example diagram illustrating the change in the amount of crystallization of a target object under a second set environment, as provided in Embodiment 1 of the present invention. Figure 6d As shown, under the coupled temperature and permeation field conditions, the amount of strontium sulfate crystallization initially decreases and then rapidly increases with increasing temperature. The ion concentration in the second brine parameters is directly proportional to the amount of crystallization in the second brine crystallization information; at the same temperature, the higher the ion concentration corresponding to the crystallization type, the greater the amount of that type of crystal precipitated.

[0072] c2. Establish a simulation dataset based on the second brine parameters and the crystallization information of the second brine.

[0073] In this embodiment, an empty simulation dataset is created, and the second brine parameters and the corresponding second brine crystallization information of the simulated target object are added to the simulation dataset. The second brine parameters are classified as input data, and the second brine crystallization information is classified as output data.

[0074] In one embodiment, determining the brine crystallization dataset includes:

[0075] a3. Determine the monitoring target and the third brine parameter of the monitoring target.

[0076] In this embodiment, the monitoring target can be understood as the brine solution extracted from the brine discharge wellbore of a real-world deep salt cavern gas storage facility. The third brine parameter can be understood as the relevant parameters corresponding to the monitoring target, including at least brine components, ion concentration, formation depth, formation temperature, formation pressure, tubing depth, tubing discharge intensity, tubing wall material, wellhead discharge intensity, wellhead pressure, and cavity pressure. It may also include the acidity, alkalinity, and conductivity of the brine.

[0077] Specifically, brine is extracted from the cavity of a deep salt cavern gas storage tank as the monitoring target, and the corresponding third brine parameters are determined.

[0078] b3. Determine the third row of brine crystallization information of the monitoring target object in the salt cavern gas storage environment.

[0079] In this embodiment, the third brine crystallization information can be understood as relevant information on the precipitation of brine crystals on the brine discharge pipe column in the actual deep salt cavern gas storage, including at least the crystallization type, crystallization location and crystallization amount, and may also include the crystallization rate. The crystallization amount can be presented in the form of a change curve to reflect the crystallization pattern.

[0080] Specifically, after identifying the target object for monitoring, the brine discharge situation of the target object in the brine discharge well of the deep salt cavern gas storage is obtained. The wellhead pressure, discharge intensity, brine salinity, brine pH value, and brine conductivity of the discharge well are monitored and recorded. A relationship curve between the changes of real-time dynamic monitoring parameters of the discharge well and the brine crystallization in the tubing is established to obtain the third brine crystallization information.

[0081] c3. Establish a monitoring dataset based on the third brine parameters and the third brine crystallization information.

[0082] In this embodiment, an empty monitoring dataset is established, and the third brine parameter and the corresponding third brine crystallization information of the monitoring target object are added to the monitoring dataset. The third brine parameter is divided into input data, and the third brine crystallization information is divided into output data.

[0083] In one embodiment, a prediction model is trained based on a brine crystallization dataset, including:

[0084] a4. Divide the brine crystallization dataset into a training sample set and a validation sample set.

[0085] In this embodiment, the training sample set can be understood as the dataset used to train the prediction model. The validation sample set can be understood as the dataset used to verify whether the performance of the prediction model meets the requirements.

[0086] Specifically, the brine discharge dataset undergoes normalization preprocessing. The preprocessed dataset is then divided into training and validation sets according to a set ratio. For example, 80% of the data in the brine discharge crystallization dataset is allocated to the training set, and 20% to the validation set. Within both the training and validation sets, brine parameters are classified as input data, and brine discharge crystallization information is classified as output data.

[0087] b4. Establish a deep learning network model, train the deep learning network model based on the training sample set and the validation sample set, and obtain a fully trained prediction model.

[0088] In this embodiment, the deep learning network model can be a deep residual network model ResNet50, with ReLU selected as the activation function, Adam optimizer and mean squared error function as the loss function, and the number of training iterations set; the input data x in the training sample set is used. i Input to deep learning network model y * In F(x,α), the amount of inorganic salt crystallization y output by the model is obtained. i * In the formula, F(x,α) represents the nonlinear complex expression corresponding to the deep learning network model. This is based on the output data yi from the training sample set and the model output y. i * The loss function L is calculated to obtain the deviation between the forward propagation output and the sample label values ​​in the network model, thereby enabling the reverse modification of the network model parameters. Based on Calculate the model update parameters In the formula, y is a physical quantity used to characterize the crystallization of inorganic salts. The deep learning network model is updated by continuously updating the network model parameters using an optimizer, completing the model training for the current iteration. This process gradually brings the output result closer to the expected output. Then, the next iteration of model training is performed, with new input data from the training sample set being fed back into the deep learning network model. This iterative cycle continues until the required number of iterations is reached. Through learning from the training sample set, the internal parameters of the ResNet network model automatically fit to the values ​​that minimize the residual function, ultimately determining the deep learning network model parameters and obtaining a relatively complete deep learning network model. The validation sample set is used to verify the accuracy of the deep learning network model parameters. The input data from the validation sample set is fed into the trained deep learning network model, and the test output is compared with the output data from the corresponding validation sample set. If the difference is significant, the network model parameters need to be retrained and updated until the error between the output and the actual value is within the allowable range. If the output obtained after inputting the data from the validation sample set is close to the expected output and the error is within the allowable range, it indicates that the deep learning network model parameters have passed the accuracy test and are confirmed as a fully trained test model. During training, brine-related data outside of the training and validation sample sets can also be selected to determine the generalization ability of the deep learning network model.

[0089] The above technical solution, this invention, integrates information from multiple aspects such as lithology and brine analysis of salt cavern gas storage, indoor brine crystallization physical experiments, brine crystallization prediction calculations, and tubing crystallization diagnosis based on dynamic parameters of the brine discharge well. Through deep learning based on big data, it determines network model parameters and ultimately achieves the diagnosis and prediction of brine crystallization location within the brine discharge tubing of deep salt cavern gas storage. Based on data such as the formation depth, formation pressure, core sample composition analysis, and brine composition analysis of the salt cavern gas storage, the brine type, inorganic salt composition, ion concentration, mineralization, pH value, and suspended solids are determined. Indoor physical experiments are used to analyze the crystallization status under different conditions, and the changes in brine mineralization, pH value, and conductivity during the crystallization process are analyzed. Numerical simulation analysis is used to obtain the temperature and pressure distribution within the wellbore during brine discharge. Brine crystallization trend curves are obtained through brine crystallization prediction. Dynamic monitoring of discharge intensity, wellhead pressure, brine pH value, and mineralization during the discharge process establishes a correlation between brine crystallization distribution within the tubing. Based on a comprehensive evaluation of brine crystallization and its distribution within the tubing, including geological data, brine analysis, indoor physical experiments, numerical simulations, and brine discharge dynamics, a dataset was established for training and testing a deep learning network model. The ResNet50 deep residual network model was selected and trained using the dataset to determine its optimal parameters. Relevant known information about the brine discharge well to be predicted was input into the deep learning network model to predict and diagnose the crystallization status within the well. This invention employs a deep learning-based big data processing method to diagnose and predict the location of brine crystallization within the tubing during brine discharge from deep salt cavern gas storage facilities.

[0090] Example 2

[0091] Figure 7 This is a schematic diagram of the structure of a predictive device for brine crystallization in a tubular column of a salt cavern gas storage facility, provided in Embodiment 2 of the present invention. Figure 7 As shown, the device includes:

[0092] The dataset determination module 21 is used to determine the brine crystallization dataset and train a prediction model based on the brine crystallization dataset. The brine crystallization dataset includes at least one of the experimental dataset, the simulation dataset, and the monitoring dataset.

[0093] The brine parameter acquisition module 22 is used to acquire the current brine parameters corresponding to the deep salt cavern gas storage tank;

[0094] The crystallization prediction module 23 is used to input the current brine parameters into the prediction model to determine the prediction result of brine crystallization in the tubular column of the salt cavern gas storage.

[0095] The technical solution employs a predictive device for brine crystallization during the discharge of brine from the tubing in a salt cavern gas storage facility, enabling the diagnosis and prediction of brine crystallization inside the tubing during the discharge process in a deep salt cavern gas storage facility.

[0096] Optionally, the dataset determination module 21 is specifically used for:

[0097] Determine multiple brine objects and a first brine parameter for each of the brine objects;

[0098] For each of the brine objects, determine the first brine crystallization information of the brine object under a first set environment, wherein the first set environment is a control variable environment based on temperature or pressure;

[0099] An experimental dataset was established based on each of the first brine parameters and the corresponding first brine crystallization information.

[0100] Optionally, the dataset determination module 21 is specifically used for:

[0101] Determine the simulated target object and the second brine parameters of the simulated target object;

[0102] Determine the second brine crystallization information of the simulated target object under a second set environment, wherein the second set environment is a simulation environment coupled with a temperature field and a percolation field;

[0103] A simulation dataset is established based on the second brine parameters and the second brine crystallization information.

[0104] Optionally, the dataset determination module 21 is specifically used for:

[0105] Determine the target object for monitoring and the third brine parameter of the target object;

[0106] Determine the third brine crystallization information of the monitored target object in the salt cavern gas storage environment;

[0107] A monitoring dataset is established based on the third brine parameters and the third brine crystallization information.

[0108] Optionally, the dataset determination module 21 is specifically used for:

[0109] The brine crystallization dataset is divided into a training sample set and a validation sample set;

[0110] A deep learning network model is established, and the deep learning network model is trained based on the training sample set and the validation sample set to obtain a fully trained prediction model.

[0111] Optionally, the current brine parameters include at least one of the following: brine composition, ion concentration, brine temperature, brine pH, brine salinity, brine conductivity, formation depth, formation temperature, formation pressure, tubing depth, tubing discharge intensity, tubing wall material, wellhead discharge intensity, wellhead pressure, and cavity pressure.

[0112] The prediction results include at least one of the following: crystallization type, crystallization amount, and crystallization location.

[0113] The predictive device for brine crystallization in the tubing of a salt cavern gas storage facility provided in this embodiment of the invention can execute the predictive method for brine crystallization in the tubing of a salt cavern gas storage facility provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0114] Example 3

[0115] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0116] like Figure 8 As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 or a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0117] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0118] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as the predictive method for brine crystallization in tubular columns within a salt cavern gas storage facility.

[0119] In some embodiments, the method for predicting brine crystallization in a tubing within a salt cavern gas storage facility can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the method for predicting brine crystallization in a tubing within a salt cavern gas storage facility described above can be performed. Alternatively, in other embodiments, processor 31 can be configured to perform the method for predicting brine crystallization in a tubing within a salt cavern gas storage facility by any other suitable means (e.g., by means of firmware).

[0120] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0124] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0125] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0126] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0127] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility, characterized in that, include: A brine crystallization dataset is determined and a prediction model is trained based on the brine crystallization dataset, wherein the brine crystallization dataset includes at least one of an experimental dataset, a simulation dataset, and a monitoring dataset; Obtain the current brine parameters corresponding to the deep salt cavern gas storage facility; The current brine parameters are input into the prediction model to determine the prediction results of brine discharge and crystallization in the tubular column of the salt cavern gas storage.

2. The method according to claim 1, characterized in that, The determination of the brine crystallization dataset includes: Determine multiple brine objects and a first brine parameter for each of the brine objects; For each of the brine objects, determine the first brine crystallization information of the brine object under a first set environment, wherein the first set environment is a control variable environment based on temperature or pressure; An experimental dataset was established based on each of the first brine parameters and the corresponding first brine crystallization information.

3. The method according to claim 1, characterized in that, The determination of the brine crystallization dataset includes: Determine the simulated target object and the second brine parameters of the simulated target object; Determine the second brine crystallization information of the simulated target object under a second set environment, wherein the second set environment is a simulation environment coupled with a temperature field and a percolation field; A simulation dataset is established based on the second brine parameters and the second brine crystallization information.

4. The method according to claim 1, characterized in that, The determination of the brine crystallization dataset includes: Determine the target object for monitoring and the third brine parameter of the target object; Determine the third brine crystallization information of the monitored target object in the salt cavern gas storage environment; A monitoring dataset is established based on the third brine parameters and the third brine crystallization information.

5. The method according to claim 1, characterized in that, The prediction model trained based on the brine crystallization dataset includes: The brine crystallization dataset is divided into a training sample set and a validation sample set; A deep learning network model is established, and the deep learning network model is trained based on the training sample set and the validation sample set to obtain a fully trained prediction model.

6. The method according to claim 1, characterized in that, The current brine parameters include at least one of the following: brine composition, ion concentration, brine temperature, brine pH, brine salinity, brine conductivity, formation depth, formation temperature, formation pressure, tubing depth, tubing discharge intensity, tubing wall material, wellhead discharge intensity, wellhead pressure, and cavity pressure. The prediction results include at least one of the following: crystallization type, crystallization amount, and crystallization location.

7. A predictive device for brine crystallization in a tubular column of a salt cavern gas storage facility, characterized in that, include: A dataset determination module is used to determine a brine crystallization dataset and train a prediction model based on the brine crystallization dataset, wherein the brine crystallization dataset includes at least one of an experimental dataset, a simulation dataset, and a monitoring dataset. The brine parameter acquisition module is used to acquire the current brine parameters corresponding to the deep salt cavern gas storage. The crystallization prediction module is used to input the current brine parameters into the prediction model to determine the prediction result of brine crystallization in the tubing of the salt cavern gas storage.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement a method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility, as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements a method for predicting brine crystallization in a tubular column of a salt cavern gas storage facility according to any one of claims 1-6.

Images