Carbon dioxide storage capacity calculation method, device and equipment and storage medium

Abstract

The embodiment of the invention relates to a carbon dioxide storage capacity calculation method and device, equipment and a storage medium. The method comprises the following steps: acquiring a capacity calculation model matched with sealing state parameters; wherein the capacity calculation model is composed of at least one grading evaluation model; and inputting the sequestration state parameters into the capacity calculation model to obtain a target sequestration capacity. According to the technical scheme of the embodiment of the invention, high-precision calculation of the carbon dioxide storage capacity can be realized, and the reliability of a calculation result is improved under the conditions of complex geological conditions, fluctuation of engineering parameters and high data uncertainty.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a carbon dioxide storage capacity calculation method, device, equipment and storage medium. BACKGROUND

[0002] Under the global carbon neutralization background, CCS (Carbon Dioxide Geological Storage) / CCUS (Carbon Capture, Utilization and Storage) is one of the core technical paths for reducing industrial carbon emissions. Based on the ECBM (Enhanced Coal Bed Methane Recovery) technology, the coal bed has dual functions of adsorption storage and energy replacement, and the accuracy and reliability of the calculation of the carbon dioxide storage capacity directly affect the storage site selection, emission reduction project planning and implementation efficiency.

[0003] The commonly used coal bed carbon dioxide geological storage capacity calculation method at present includes a calculation model proposed according to the storage type, geological characteristics and other factors for carbon dioxide address storage site selection grading. However, the coal bed in China has strong heterogeneity, and the coal bed permeability, porosity, coal rank and other parameters change sharply in space, so that the traditional grading is difficult to clearly divide the boundary, resulting in capacity calculation deviation. Therefore, a targeted calculation model is needed to improve the calculation accuracy and avoid the limitations caused by the single existing model algorithm. SUMMARY

[0004] The present application provides a carbon dioxide storage capacity calculation method, device, equipment and storage medium, aiming to improve the accuracy of carbon dioxide storage capacity calculation and obtain high reliability calculation results under the condition of complex geological conditions, engineering parameter fluctuation and high data uncertainty.

[0005] In a first aspect, the present application embodiment provides a carbon dioxide storage capacity calculation method, comprising:

[0006] obtaining a capacity calculation model matched with the storage state parameter; wherein the capacity calculation model is composed of at least one grading evaluation model;

[0007] inputting the storage state parameter into the capacity calculation model to obtain a target storage capacity.

[0008] Optionally, the obtaining of the capacity calculation model matched with the storage state parameter comprises:

[0009] obtaining a set grading evaluation model matched with the storage state parameter;

[0010] determine the capacity calculation model as the set hierarchical evaluation model;

[0011] The set hierarchical evaluation model is a basin-level resource evaluation model, a target area-level reservoir model, a site-level facies calculation model, or a perfusion-level dynamic displacement model.

[0012] Optionally, the capacity calculation model matched with the sealing state parameter comprises:

[0013] determining at least two hierarchical evaluation models matched with the sealing state parameter and a level weight coefficient;

[0014] obtaining a multi-level weighted model of the at least two hierarchical evaluation models according to the level weight coefficient;

[0015] determining the multi-level weighted model as the capacity calculation model.

[0016] Optionally, the capacity calculation model matched with the sealing state parameter comprises:

[0017] inputting the sealing state parameter into a hierarchical matching model to obtain a level matching result output by the hierarchical matching model;

[0018] generating the capacity calculation model according to the level matching result;

[0019] The capacity calculation model is a set hierarchical evaluation model or a multi-level weighted model.

[0020] Optionally, before the sealing state parameter is input into the capacity calculation model, the method further comprises:

[0021] dynamically correcting the sealing state parameter according to real-time monitoring data.

[0022] Optionally, the dynamic correction of the sealing state parameter according to real-time monitoring data comprises:

[0023] obtaining sensor data stream;

[0024] performing data preprocessing on the sensor data stream to obtain state measurement parameters and field calibration data;

[0025] performing the dynamic correction of the sealing state parameter according to the state measurement parameters and the field calibration data based on a Kalman filter model.

[0026] Optionally, the data preprocessing on the sensor data stream to obtain state measurement parameters and field calibration data comprises:

[0027] performing data anomaly detection on the sensor data stream;

[0028] in a case where it is determined that the sensor data stream is abnormal, performing a sensor self-calibration operation;

[0029] in a case where it is determined that the sensor data stream is normal, performing a parameter conversion process on the sensor data stream to obtain the state measured parameter and the field calibration data.

[0030] In a second aspect, an embodiment of the present application provides a carbon dioxide storage capacity calculation device, comprising:

[0031] a model acquisition module configured to acquire a capacity calculation model matched with the storage state parameter, wherein the capacity calculation model is composed of at least one hierarchical evaluation model;

[0032] a capacity calculation module configured to input the storage state parameter into the capacity calculation model to obtain a target storage capacity.

[0033] In a third aspect, an embodiment of the present application provides a carbon dioxide storage capacity calculation device, comprising:

[0034] one or more processors;

[0035] a memory configured to store one or more programs;

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the carbon dioxide storage capacity calculation method provided by any embodiment of the present application.

[0037] In a fourth aspect, an embodiment of the present application provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to perform the carbon dioxide storage capacity calculation method provided by any embodiment of the present application.

[0038] The carbon dioxide storage capacity calculation method, device, equipment and storage medium provided by the embodiment of the present application, according to the storage state parameter, acquire the capacity calculation model composed of at least one hierarchical evaluation model, input the storage state parameter into the matched capacity calculation model to obtain the target storage capacity, solve the problem of low precision and single algorithm of the existing carbon dioxide storage capacity calculation model, realize the high-precision calculation of the carbon dioxide storage capacity, and improve the reliability of the calculation result in the case of complex geological conditions, engineering parameter fluctuation and high data uncertainty. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 A flowchart of a carbon dioxide storage capacity calculation method provided by the embodiment of the present application;

[0040] Figure 2 A flow chart of a carbon dioxide storage capacity calculation method provided for the second embodiment of the present application;

[0041] Figure 3 A data mapping relationship diagram provided for the second embodiment of the present application;

[0042] Figure 4 A flow chart of a dynamic correction processing based on Kalman filtering provided for the second embodiment of the present application;

[0043] Figure 5 An engineering control flow chart of a carbon dioxide storage capacity calculation method provided for the second embodiment of the present application;

[0044] Figure 6 A structural schematic diagram of a carbon dioxide storage capacity calculation device provided for the third embodiment of the present application;

[0045] Figure 7 A structural schematic diagram of a carbon dioxide storage capacity calculation device provided for the fourth embodiment of the present application. DETAILED DESCRIPTION

[0046] The present application will be further described below in conjunction with the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. In addition, it should be noted that, for the convenience of description, only the parts related to the present application are shown in the drawings, but not all the structures.

[0047] Embodiment one

[0048] Figure 1 A flow chart of a carbon dioxide storage capacity calculation method provided for the first embodiment of the present application, the present embodiment can be applicable to the case of calculating the capacity of carbon dioxide storage in coal seams under any geological conditions, the method can be executed by a carbon dioxide storage capacity calculation device, the device can be realized by hardware and / or software, and generally can be integrated in an electronic device, such as a computer device, the method specifically includes:

[0049] Step 110, obtaining a capacity calculation model matched with the storage state parameter.

[0050] The storage state parameter can be data describing the carbon dioxide storage condition, and can include parameters describing the geological condition of the carbon dioxide storage coal seam, parameters of the carbon dioxide storage engineering setup, and parameters describing the actual condition of the carbon dioxide storage, etc. Optionally, the storage state parameter can include the coal seam geological parameter, the engineering parameter, and the engineering monitoring data. Specifically, the coal seam geological parameter can include the coal rank, the permeability, and the hydrological condition of the coal seam, the engineering parameter can include the injection pressure and the displacement efficiency, and the engineering monitoring data can include the pressure and the temperature.

[0051] The capacity calculation model is composed of at least one hierarchical assessment model. The capacity calculation model can be a model for calculating the carbon dioxide storage capacity of the coal seam according to the carbon dioxide storage condition of the coal seam. The hierarchical assessment model can include a capacity calculation model of the coal seam applicable to each assessment level divided according to the carbon dioxide storage condition. Optionally, the assessment level can include a basin level, a target area level, a site level, and a perfusion level. The basin level is applicable to the macroscopic resource potential assessment of the coal seam of the entire basin, the target area level is applicable to the assessment of the coal seam in a specific area in the basin, the site level is applicable to the engineering storage capacity assessment of the coal seam of a specific storage site, and the perfusion level is applicable to the dynamic displacement efficiency assessment of the coal seam during the carbon dioxide injection process.

[0052] According to the carbon dioxide storage coal seam and the engineering condition, the storage state parameter can be obtained. According to the storage state parameter, the assessment level applicable to the assessment of the coal seam can be determined. For any coal seam, only one applicable assessment level can be determined, or multiple assessment levels to which the coal seam can be applicable can be determined. Each assessment level uses a different hierarchical assessment model to calculate the carbon dioxide storage capacity of the coal seam. Therefore, according to the assessment level, at least one hierarchical assessment model can be determined, and the capacity calculation model for calculating the carbon dioxide storage capacity of the coal seam is composed of all the determined hierarchical assessment models.

[0053] Optionally, obtaining the capacity calculation model matching the storage state parameter can include: obtaining a set hierarchical assessment model matching the storage state parameter; and determining the set hierarchical assessment model as the capacity calculation model.

[0054] The set hierarchical assessment model is a basin level resource assessment model, a target area level reservoir model, a site level facies calculation model, or a perfusion level dynamic displacement model.

[0055] The set hierarchical evaluation model can be a hierarchical evaluation model adopted by the only evaluation grade applicable to the coal seam. The basin-level resource evaluation model can be a model for calculating the carbon dioxide storage capacity of the coal seam applicable to the basin-level evaluation grade. The target area-level reservoir model can be a model for calculating the carbon dioxide storage capacity of the coal seam applicable to the target area-level evaluation grade. The site-level sub-phase calculation model can be a model for calculating the carbon dioxide storage capacity of the coal seam applicable to the site-level evaluation grade. The perfusion-level dynamic displacement model can be a model for calculating the carbon dioxide storage capacity of the coal seam applicable to the perfusion-level evaluation grade.

[0056] When the only evaluation grade applicable to the coal seam can be determined according to the description of the storage state parameter, the set hierarchical evaluation model adopted by the only evaluation grade can be obtained, and then the set hierarchical evaluation model can be directly determined as the capacity calculation model for calculating the carbon dioxide storage capacity of the coal seam.

[0057] Optionally, a set hierarchical evaluation model matched with the storage state parameter is obtained, wherein the storage state parameter can include the regional coalbed methane resource amount, the displacement ratio, and the basin effectiveness factor; the matched set hierarchical evaluation model can be a basin-level resource evaluation model, and specifically can be:

[0058] M CO2 = G 煤层气 × ρ g × ER 置换 × F 有效盆地

[0059] In the formula, M CO2 is the carbon dioxide storage capacity. G 煤层气 is the total basin coalbed methane resource amount determined by the regional coalbed methane resource amount, which refers to the total amount of recoverable coalbed methane, and the unit is m 3 (cubic meters), which is obtained through a regional coalbed methane resource evaluation report, drilling data, and coalbed methane content testing, such as desorption method. ρ g is the density of carbon dioxide under reservoir conditions, which is related to temperature and pressure, and is about 500-800 kg / m 3 (kilograms per cubic meter) in a supercritical state, which is determined according to the injection depth to query the physical property parameter table, such as when the burial depth is greater than 800 m (meters), the carbon dioxide is in a supercritical state, or is determined through PVT (Pressure-Volume-Temperature Experiment). ER 置换 is the displacement ratio of carbon dioxide to methane, which is dimensionless, and is determined through isothermal adsorption experiment, such as CO2 / CH4 mixed gas adsorption testing, or reference is made to the regional geological analogy data in Table 1. F 有效盆地The basin effectiveness factor, i.e. the basin available coefficient, ranges from 0.2 to 0.6, the comprehensive structural stability, i.e. the seismic activity, and the hydrological sealing, i.e. the aquifer barrier, wherein the structural stability can be determined by seismic history data and geostress simulation, and the hydrological sealing can be determined according to aquifer permeability test, such as pumping test, and cap rock lithology analysis.

[0060] Table 1 Coalbed methane recoverable coefficient (RF) and CO2 / CH4 replacement ratio (ER) of each coal rank in China

[0061]

[0062] Optionally, a set of grading evaluation models matching the sequestration state parameters is obtained, wherein the sequestration state parameters can include a coal rank correction coefficient, an adsorption capacity, and a fracture porosity; the set of grading evaluation models matching the sequestration state parameters can be a target area level reservoir model, and specifically can be:

[0063] M CO2 = A x h x p 煤 x (K coal-rank x V 吸附 + V 游离 x f 裂缝 ) x E

[0064] In the formula, M CO2 is the carbon dioxide sequestration capacity. A is the planar projection area of the target area coal seam, in units of m 2 (square meters), calculated by geological mapping, drilling control point spatial interpolation, such as Kriging method. h is the average net thickness of the coal seam excluding the parting layer, in units of m (meters), measured by drilling core and interpreted from well logging curves, including gamma, density. p 煤 is the apparent density of the coal, in units of t / m 3 (tons per cubic meter), tested in the laboratory by helium displacement method, or calibrated from the density curve of well logging. K coal-rank is the coal rank correction coefficient, dimensionless, divided according to the vitrinite reflectance Ro% of the coal, and an empirical relationship is established: K coal-rank = 0.5 x Ro + 0.6. V 吸附 is the carbon dioxide adsorption capacity of unit mass of coal, in units of m 3 / t (cubic meters per ton), obtained by high-pressure isothermal adsorption experiment, such as volumetric method, at a pressure of 0-20 MPa (megapascals). V 游离 is the volume fraction of free state carbon dioxide in the fracture system, dimensionless, determined by coal seam fracture rate, including CT (Computed Tomography Scan, computed tomography scan) and image analysis, or mercury intrusion method. f 裂缝Fracture porosity, unit %, calculated by core fracture statistics observed by microscope or logging interval transit time. E is the effectiveness factor, dimensionless, dynamically assigned by the relationship curve (K=f(σ)) of stress analysis through pulse decay permeability test and hydraulic fracturing test, and the value range of E is 0.1-0.3 in low permeability area (K<1 mD).

[0065] Optionally, a set of hierarchical evaluation models matching the sealing state parameters is obtained, wherein the sealing state parameters can include phase separation sealing capacity, including free phase, dissolved phase and adsorbed phase, and sealing efficiency; the set of matching hierarchical evaluation models can be a site-level phase separation calculation model, which can be specifically:

[0066] M CO2 = (M 自由 + M 溶解 + M 吸附 ) x R 封存

[0067] M 自由 = A x h x φ 裂缝 x (1-S 水 )

[0068] M 溶解 = A x h x φ 煤 x S 水 x C CO2，水

[0069] M 吸附 = A x h x ρg x V 吸附 x (1-R CH4 )

[0070] In the formula, M CO2 is the carbon dioxide sealing capacity. M 自由 is the free phase carbon dioxide sealing capacity. M 溶解 is the dissolved phase carbon dioxide sealing capacity. M 吸附 is the adsorbed phase carbon dioxide sealing capacity. φ 裂缝 is the fracture porosity, unit %, calculated by core fracture statistics observed by microscope or logging interval transit time. φ 煤 is the coal matrix porosity, unit %, obtained by BET (Brunauer-Emmett-Teller method of low-temperature nitrogen adsorption) or NMR (Nuclear Magnetic Resonance) test. ρ g is the density of carbon dioxide under reservoir conditions, related to temperature and pressure, about 500-800 kg / m 3, determined according to the injection depth and the physical property parameter table, or determined by PVT measurement. 水 is the water saturation, determined by core centrifugation or logging resistivity inversion. CO2，水 is the carbon dioxide solubility in water, unit kg / m 3 (kilogram per cubic meter), determined by PHREEQC (Program for Reaction Path, Equilibrium, and Mass Transport Modeling in Aquatic Systems) or laboratory high-pressure reactor. CH4 is the methane recovery rate, dimensionless, determined based on the production dynamic data of the coalbed methane well, such as production decline curve analysis or numerical simulation. 封存 is the site storage efficiency, dimensionless, determined by numerical simulation optimization of the injection-production well pattern or reference to similar engineering cases.

[0071] Optionally, a set of grading evaluation models matched with the storage state parameters is obtained, wherein the storage state parameters can include a carbon dioxide injection rate, a displacement efficiency, and a pressure breakthrough threshold; and the matched set of grading evaluation models can be a perfusion level dynamic displacement model, which can be specifically:

[0072] M CO2 = Q 注入 × t × η 驱替 × (1-P 注入 P 突破 )

[0073] In the formula, M CO2 is the carbon dioxide storage capacity. Q 注入 is the carbon dioxide injection rate, unit m 3 / d (cubic meter per day), determined by field injection pump measured data or engineering design value. t is the injection time, unit d (day), engineering planning period or actual running time. η 驱替 is the carbon dioxide displacement efficiency, dimensionless, determined by core displacement experiment or estimated based on the coal wettability empirical formula. P 注入 is the injection pressure breakthrough threshold, which refers to the minimum pressure at which carbon dioxide breaks through the caprock, generally greater than 8 MPa in deep coal seams, determined by caprock breakthrough pressure experiment or geostress field simulation. P 突破 is the actual injection pressure, unit MPa, obtained by real-time monitoring of the injection wellhead pressure sensor.

[0074] Optionally, the capacity calculation model matched with the sealing state parameter can comprise: determining at least two hierarchical evaluation models and level weight coefficients matched with the sealing state parameter; obtaining a multi-level weighted model of the at least two hierarchical evaluation models according to the level weight coefficients; and determining the multi-level weighted model as the capacity calculation model.

[0075] The level weight coefficient can be a coefficient describing the applicability of each evaluation level in a plurality of evaluation levels possibly applicable to the coal seam according to the sealing state parameter. The multi-level weighted model can be a model obtained by superimposing and fusing the plurality of evaluation levels possibly applicable to the coal seam according to the sealing state parameter according to the level weight coefficients of the respective evaluation levels.

[0076] When the sealing state parameter cannot be used to determine a unique evaluation level applicable to the coal seam, but the coal seam is between different evaluation levels, a hierarchical evaluation model used in each evaluation level can be obtained according to a plurality of evaluation levels possibly applicable to the coal seam. Correspondingly, a level weight coefficient of each hierarchical evaluation model can be obtained according to the applicability of the coal seam to each evaluation level. The multi-level weighted model can be obtained by superimposing and fusing the determined hierarchical evaluation levels according to the respective level weight coefficients. For example, a high-permeability coal seam can be focused on using a perfusion level dynamic displacement model, and a low-permeability coal seam can be focused on using a site level phase separation calculation model. Optionally, a fuzzy logic algorithm can be used to dynamically adjust the evaluation grading boundary of the coal seam, for example, by using Monte Carlo simulation or Bayesian optimization to probabilistically fuse the evaluation grading results obtained by multiple algorithms. Therefore, the multi-level weighted model can be determined as the capacity calculation model for calculating the carbon dioxide sealing capacity of the coal seam.

[0077] The above embodiments can set a level weight coefficient to weight and fuse hierarchical evaluation models used in a plurality of evaluation levels when the sealing state parameter cannot be used to determine an evaluation level applicable to the coal seam, thereby obtaining a multi-level weighted model, compensating for the limitations of a single algorithm applied to complex geological conditions and engineering situations, and improving the accuracy and reliability of the calculation results.

[0078] Optionally, the at least two hierarchical evaluation models and the level weight coefficient matched with the sealing state parameter can comprise: a basin level resource evaluation model and a target area level reservoir model; and the level weight coefficient can be determined according to the coal seam homogeneity in the sealing state parameter. Correspondingly, the obtained multi-level weighted model is:

[0079] M CO2 = α · M 盆地 + (1-α) · M 目标区

[0080] In the formula, MCO2 M is the carbon dioxide storage capacity, M 盆地 M is the basin-level resource assessment model, and a is the level weight coefficient of the basin-level resource assessment model, the higher the coal seam homogeneity, the closer a is to 1, M 目标区 M is the target area-level reservoir model, and (1-a) is the level weight coefficient of the target area-level reservoir model.

[0081] Optionally, at least two hierarchical assessment models and level weight coefficients matched with the storage state parameters are determined, wherein the at least two hierarchical assessment models can include a site-level phase calculation model and a perfusion-level dynamic displacement model; and the level weight coefficients can be determined according to the storage efficiency and the displacement efficiency in the storage state parameters. Correspondingly, the obtained multi-level weighted model is:

[0082] M CO2 = β · M 分相 + (1-β) · M 动态

[0083] M is the carbon dioxide storage capacity, M CO2 M is the basin-level resource assessment model, and a is the level weight coefficient of the basin-level resource assessment model, the higher the coal seam homogeneity, the closer a is to 1, M 分相 M is the site-level phase calculation model, and β is the level weight coefficient of the site-level phase calculation model, β is the ratio of the storage efficiency to the displacement efficiency, M 动态 M is the perfusion-level dynamic displacement model, and (1-β) is the level weight coefficient of the perfusion-level dynamic displacement model.

[0084] Step 120, input the storage state parameters into the capacity calculation model to obtain the target storage capacity.

[0085] The target storage capacity can be the carbon dioxide storage capacity of the coal seam that needs to be calculated.

[0086] After obtaining the capacity calculation model suitable for the coal seam according to the storage state parameters, the storage state parameters can be input into the capacity calculation model to obtain the target storage capacity by performing corresponding calculation on the storage state parameters according to the capacity calculation model.

[0087] The technical scheme of the embodiment, according to the storage state parameters, obtains a capacity calculation model composed of at least one hierarchical assessment model, inputs the storage state parameters into the matched capacity calculation model to obtain the target storage capacity, solves the problem of low precision and single algorithm of the existing carbon dioxide storage capacity calculation model, and realizes high-precision calculation of the carbon dioxide storage capacity, thereby improving the reliability of the calculation results in the case of complex geological conditions, engineering parameter fluctuation, and high data uncertainty.

[0088] Embodiment Two

[0089] Figure 2A flowchart of a carbon dioxide storage capacity calculation method provided for the second embodiment of the present application, the present embodiment further refines the above technical solution, and can be the capacity calculation model matched with the storage state parameters, including: inputting the storage state parameters into a hierarchical matching model to obtain a level matching result output by the hierarchical matching model; generating the capacity calculation model according to the level matching result; wherein the capacity calculation model is a set hierarchical evaluation model or a multi-level weighted model. The method specifically includes:

[0090] Step 210, input the storage state parameters into the hierarchical matching model to obtain the level matching result output by the hierarchical matching model.

[0091] The hierarchical matching model can be a classification model pre-trained based on machine learning, which can automatically match the evaluation level suitable for the coal seam according to the input storage state parameters and output. The level matching result can be the evaluation level suitable for the coal seam, which can be the optimal hierarchical result or the multi-level weighted result.

[0092] According to the evaluation model suitable for the coal seam in the carbon dioxide storage situation described by the determined storage state parameters, the hierarchical matching model can be pre-trained by machine learning technology. The trained hierarchical matching model can automatically match the evaluation level suitable for the coal seam in the situation described by the input storage state parameters and output the corresponding level matching result.

[0093] Optionally, the level matching result can be the optimal hierarchical result output by the hierarchical matching model, that is, when the storage state parameters are within the explicit hierarchical standard, the optimal hierarchical suitable for the coal seam can be obtained, for example, it can be a basin level, a target area level, a site level or a perfusion level.

[0094] Optionally, the level matching result can be a multi-level weighted result output by the hierarchical matching model, that is, when the storage state parameters are in a fuzzy state between the explicit hierarchical standards, it is not possible to directly and explicitly match to a certain evaluation level. Optionally, it can be determined that the state is fuzzy by checking whether the storage state parameters are in the overlapping interval of the hierarchical standards, such as the boundary values of permeability and coal rank, according to the result difference rate greater than the threshold value 15% or the model confidence less than the threshold value 80% obtained by multiple algorithms. Therefore, the hierarchical matching model can output a multi-level weighted result, for example, it can be a weighted result of a basin level weight of 30% and a target area level weight of 70%.

[0095] Step 220, generating the capacity calculation model according to the level matching result.

[0096] The capacity calculation model is a set hierarchical evaluation model or a multi-level weighted model.

[0097] When the level matching result output by the level matching model is a determined optimal level, which can be an optional optimal level, the setting level evaluation model adopted by the optimal level can be obtained as the capacity calculation model. When the level matching result output by the level matching model contains a plurality of weighted results of levels, which can be optional multi-level weighted results, a plurality of level evaluation models adopted by the plurality of evaluation levels can be obtained, and the weight of each level evaluation model can be determined according to the weight of each evaluation level in the multi-level weighted result to generate a multi-level weighted model as the capacity calculation model.

[0098] The above embodiment trains the level matching model by using the machine learning technology, automatically matches the evaluation level suitable for the coal seam through the level matching model, reduces the degree of manual intervention, and further improves the reliability of the calculation result under the complex condition of carbon dioxide storage.

[0099] Step 230, input the storage state parameter into the capacity calculation model to obtain the target storage capacity.

[0100] Optionally, before inputting the storage state parameter into the capacity calculation model, the method can further include: performing dynamic correction processing on the storage state parameter according to real-time monitoring data.

[0101] The real-time monitoring data can be data monitored in the implementation process of the carbon dioxide storage project, and can describe the actual situation of carbon dioxide storage. The dynamic correction processing can be to optimize the storage state parameter according to the actual situation of carbon dioxide storage described by the real-time monitoring data, so that the carbon dioxide storage situation described by the storage state parameter is consistent with the actual situation.

[0102] Optionally, the real-time monitoring data can include carbon dioxide injection pressure, temperature, carbon dioxide concentration, flow rate and formation microseismic data.

[0103] Optionally, the real-time monitoring data can be obtained through sensors deployed in advance in the carbon dioxide storage project. Specifically, the carbon dioxide injection pressure data can be monitored through piezoresistive pressure sensors installed at the wellhead and key layer positions downhole, and the optional sampling frequency is 1 Hz (Hertz) and the accuracy is ±0.1 MPa; the temperature can be monitored through PT100 thermocouples installed in the wellbore and fracture monitoring wells, and the optional sampling frequency is 1 Hz and the accuracy is ±0.5°C (Celsius); the carbon dioxide concentration can be monitored through NDIR (Non-Dispersive Infrared) optical gas sensors installed at the exhaust port of the production well and the monitoring well, and the optional sampling frequency is 0.1 Hz and the accuracy is ±100 ppm (parts per million); the flow rate can be monitored through ultrasonic flow meters installed in the injection pipeline, and the optional sampling frequency is 1 Hz and the accuracy is ±1% FS (Full Scale); and the formation microseismic data can be detected through an accelerometer array installed in the borehole around the coal seam, and the optional sampling frequency is 19 kHz and the positioning accuracy is ±1 m.

[0104] Optionally, the dynamic correction processing of the storage state parameters based on the real-time monitoring data can include: obtaining a sensor data stream; performing data preprocessing on the sensor data stream to obtain state measurement parameters and field calibration data; and performing dynamic correction processing on the storage state parameters based on the Kalman filter model according to the state measurement parameters and the field calibration data.

[0105] The sensor data stream can be a data stream obtained by a sensor deployed in the carbon dioxide storage project to collect signals. The data preprocessing can be an operation of obtaining valid data from the sensor data stream. The state measurement parameters can be actual values of the storage state parameters obtained by the sensor in the actual carbon dioxide storage project. The field calibration data can be data obtained by a sensor through a calibration operation in the field of the carbon dioxide storage project.

[0106] The sensor deployed in the carbon dioxide storage project can collect signals in real time to generate a sensor data stream. The data preprocessing on the sensor data stream can obtain state measurement parameters and field calibration data therefrom, which can be effectively utilized based on the Kalman filter to achieve dynamic correction processing of the storage state parameters. The specific content of the state measurement parameters and the field calibration data can be determined according to the data required by the storage state parameters and the Kalman filter. Optionally, the sensor data stream can be preprocessed by an edge computing node.

[0107] Optionally, the data preprocessing of the sensor data stream to obtain the state measured parameter and the field calibration data can include: performing data anomaly detection on the sensor data stream; performing sensor self-calibration operation in the case of determining that the sensor data stream is abnormal; performing parameter conversion processing on the sensor data stream to obtain the state measured parameter and the field calibration data in the case of determining that the sensor data stream is normal.

[0108] The data anomaly detection can be an operation of judging whether the sensor is working normally according to the sensor data stream. The sensor self-calibration operation can be an operation of re-entering the normal working state for the sensor in the abnormal working state. The parameter conversion processing can be an operation of extracting and converting data from the sensor data stream to obtain the effective state measured parameter and the field calibration data.

[0109] The sensor deployed in the carbon dioxide storage project can be abnormal, so the data anomaly detection can be performed on the sensor data stream in the data preprocessing to timely find the abnormal case of the sensor data stream and perform the sensor self-calibration operation. If it is determined that the sensor data stream is normal, the effective state measured parameter and the field calibration data can be obtained through the parameter conversion processing.

[0110] Optionally, based on the Kalman filter model, the dynamic correction processing of the storage state parameter according to the state measured parameter and the field calibration data can include: establishing state equation and observation equation based on the Kalman filter, wherein the state equation is specifically as follows:

[0111] x k =Ax k-1 +Bu k +w k

[0112] The observation equation is specifically as follows:

[0113] z k =Hx k +V k

[0114] In the formula, x k is a state vector corresponding to the storage state parameter, which can be [pressure, saturation, adsorption amount] for example. u k is an operation variable artificially controlled in the carbon dioxide storage project, which can be the manually adjusted carbon dioxide injection rate for example. z k is an actual observation value of the sensor, which is data from the sensor. w k and v k are process noise and observation noise, which are obtained through field calibration. A is a state transition matrix, which describes the evolution law of the system itself, and x k-1Mapped to the current moment. B is the control input matrix, which can be used to manipulate the variable u k Converting to state effects can be done by converting the injection rate adjustment into pressure / saturation changes. H is the observation matrix, and the state vector x k Mapping to observation space z k , extracting directly observable states.

[0115] Among them, the first state vector x k-1 Initialization relies on geological exploration data and pre-injection sensor baseline monitoring. Geological exploration data includes initial pressure and coal rank parameters obtained through well logging and core analysis; initial adsorption Langmuir parameters and saturation based on porosity models are calibrated through laboratory measurements; and pre-injection monitoring involves activating the sensor network and collecting baseline data, such as pre-injection formation pressure.

[0116] In the field calibration data, the process noise w k Refers to the uncertainty of the system model. The interference sources may include simplified errors of geological parameters and unforeseen dynamic changes of coal seam fractures; observation noise v k Refers to sensor measurement error. Interference sources can include sensor accuracy limitations and signal transmission interference. Calibration can be performed using conventional industry methods, including static and dynamic calibration steps. Static calibration involves shutting down the injection process, collecting sensor data in a stable state, and calculating the observed noise variance, R. For example, this can include the variance of pressure sensor reading fluctuations. Model errors are then inverted from historical data to estimate the process noise covariance, Q. Dynamic calibration involves injecting a step signal, such as a sudden pressure increase of 0.5 MPa, comparing the model prediction with the measured value, and updating Q using maximum likelihood estimation.

[0117] Figure 3 A data mapping relationship diagram provided in the second embodiment of the present invention is as follows: Figure 3 As shown, the state vector calculation depends on the underlying physical quantities monitored by the sensor in real time, such as pressure, temperature, concentration and flow rate. For example, in the state vector [pressure, saturation, adsorption amount], the saturation is dynamically calculated through the real-time carbon dioxide concentration, flow rate and geological porosity model; the adsorption amount is inverted by the Langmuir adsorption equation through pressure and temperature input, where the adsorption constant needs to be pre-calibrated. Furthermore, the state vector forms a closed-loop feedback with the sensor observation value. The Kalman filter uses the sensor raw data as the observation value, for example, it can be z k = [pressure, temperature, carbon dioxide concentration, flow rate], and the state vector prediction value x k =[pressure, saturation, adsorption amount] for weighted fusion, and the mapping of physical quantities to state space is realized through the observation matrix H.

[0118] Accordingly, according to the optimal estimation state vector x k-1 at the last moment k , the prior predictive state vector X k is obtained by estimating the parameters at the current moment k , and combined with the sensor observation value z k , the Kalman gain K is calculated, so that the sealed state parameters can be updated according to the following formula:

[0119] x k =X k +K(z k -HX k )

[0120] The x k obtained in the above formula is the optimized parameter value after fusing the measured data of the sensor, which is the correction value. HX k is the mapping of the predictive state X k to the predictive observation value through the observation matrix H, which is used to calculate the residual by comparing with the actual observation value z k .

[0121] Exemplarily, Figure 4 a flowchart of a dynamic correction processing based on Kalman filtering provided by Embodiment Two of the present application is shown. As shown in the figure, the prior state estimation X k is the predictive value, which is only dependent on the current state value predicted by the state equation in the system model, does not fuse the latest sensor data, and contains model uncertainty; the posterior state estimation x is the correction value, which is the optimal state estimation corrected by the Kalman gain K using the latest sensor observation value z

[0001] , and realizes error minimization.

[0122] Exemplarily, Figure 5 a flowchart of an engineering control method based on the carbon dioxide sealing capacity calculation method provided by Embodiment Two of the present application is shown. As shown in the figure, the sensor data stream obtained on the engineering site is input to the edge computing node for data calculation and processing, and the data collected by the sensor is detected for abnormality according to the obtained result. In the case where it is detected that there is an abnormality, the sensor is self-calibrated. In the case where it is determined that it is normal, the effective observation value is obtained through the parameter conversion module, and the Kalman filtering / RLS (Recursive Least Squares Optimization) is performed according to the observation value to dynamically correct the state parameters, so that the optimized state parameters are input to the matched capacity calculation model, and the dynamic weight adjustment is performed according to the dynamically corrected parameters. Finally, the output is performed through the visual instrument panel, and the engineering control is performed through the corresponding engineering control instruction.

[0123] The technical scheme of the embodiment obtains a capacity calculation model composed of at least one hierarchical evaluation model according to the storage state parameter, inputs the storage state parameter into the matched capacity calculation model, and obtains the target storage capacity, thereby solving the problems of low precision and single algorithm of the existing carbon dioxide storage capacity calculation model, and realizing high-precision calculation of the carbon dioxide storage capacity and improving the reliability of the calculation result in the case of complex geological conditions, engineering parameter fluctuation and high data uncertainty.

[0124] Embodiment three

[0125] Figure 6 A structure diagram of a carbon dioxide storage capacity calculation device provided for the third embodiment of the application is shown in the figure. Figure 6 The carbon dioxide storage capacity calculation device comprises a model acquisition module 310 and a capacity calculation module 320, wherein,

[0126] The model acquisition module 310 is configured to acquire a capacity calculation model matched with the storage state parameter, wherein the capacity calculation model is composed of at least one hierarchical evaluation model.

[0127] The capacity calculation module 320 is configured to input the storage state parameter into the capacity calculation model to obtain a target storage capacity.

[0128] The carbon dioxide storage capacity calculation method, device, equipment and storage medium provided by the embodiment of the application acquire a capacity calculation model composed of at least one hierarchical evaluation model according to the storage state parameter, input the storage state parameter into the matched capacity calculation model, and obtain the target storage capacity, thereby solving the problems of low precision and single algorithm of the existing carbon dioxide storage capacity calculation model, realizing high-precision calculation of the carbon dioxide storage capacity, and improving the reliability of the calculation result in the case of complex geological conditions, engineering parameter fluctuation and high data uncertainty.

[0129] Optionally, the model acquisition module 310 can comprise a set hierarchical model acquisition unit configured to acquire a set hierarchical evaluation model matched with the storage state parameter, and a first capacity model determination unit configured to determine the set hierarchical evaluation model as the capacity calculation model, wherein the set hierarchical evaluation model is a basin-level resource evaluation model, a target area-level reservoir model, a site-level facies calculation model or a perfusion-level dynamic displacement model.

[0130] Optionally, the model acquisition module 310 can comprise a model weight determination unit configured to determine at least two hierarchical evaluation models matched with the storage state parameter and a level weight coefficient, a weighted model acquisition unit configured to acquire a multi-level weighted model of the at least two hierarchical evaluation models according to the level weight coefficient, and a first capacity model determination unit configured to determine the multi-level weighted model as the capacity calculation model.

[0131] Optionally, the model obtaining module 310 can comprise: a parameter input unit configured to input the storage state parameters into the hierarchical matching model to obtain a level matching result output by the hierarchical matching model; and a capacity model generating unit configured to generate a capacity calculation model according to the level matching result, wherein the capacity calculation model is a set hierarchical evaluation model or a multi-level weighted model.

[0132] Optionally, the device can further comprise a dynamic correction module configured to perform dynamic correction processing on the storage state parameters according to real-time monitoring data before inputting the storage state parameters into the capacity calculation model.

[0133] Optionally, the dynamic correction module can comprise: a data stream obtaining unit configured to obtain a sensor data stream; a preprocessing unit configured to perform data preprocessing on the sensor data stream to obtain state measurement parameters and field calibration data; and a Kalman filter unit configured to perform dynamic correction processing on the storage state parameters according to the state measurement parameters and the field calibration data based on a Kalman filter model.

[0134] Optionally, the preprocessing unit can comprise: an anomaly detection subunit configured to perform data anomaly detection on the sensor data stream; a self-calibration subunit configured to perform a sensor self-calibration operation in a case where it is determined that the sensor data stream is abnormal; and a parameter conversion subunit configured to perform parameter conversion processing on the sensor data stream to obtain the state measurement parameters and the field calibration data in a case where it is determined that the sensor data stream is normal.

[0135] The carbon dioxide storage capacity calculation device provided in the embodiments of the present application can perform the carbon dioxide storage capacity calculation method provided in any of the embodiments of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0136] Embodiment Four

[0137] Figure 7 A structural schematic diagram of a carbon dioxide storage capacity calculation device provided in Embodiment Four of the present application is shown in FIG. 4, which comprises a processor 410, a memory 420, an input device 430 and an output device 440; the number of processors 410 in the carbon dioxide storage capacity calculation device can be one or more, and one processor 410 is taken as an example in the embodiment; Figure 7 The processor 410, the memory 420, the input device 430 and the output device 440 in the carbon dioxide storage capacity calculation device can be connected through a bus or other means, and a connection through a bus is taken as an example in the embodiment. Figure 7 Figure 7

[0138] ​​The memory 420, as a computer readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the carbon dioxide storage capacity calculation method in the embodiments of the present application (for example, the model acquisition module 310 and the capacity calculation module 320 in the carbon dioxide storage capacity calculation device). The processor 410 performs various functional applications and data processing of the carbon dioxide storage capacity calculation device by running the software programs, instructions and modules stored in the memory 420, that is, implements the carbon dioxide storage capacity calculation method described above.

[0139] The memory 420 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the terminal and the like. In addition, the memory 420 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some examples, the memory 420 can further include a memory remotely arranged with respect to the processor 410, which can be connected to the carbon dioxide storage capacity calculation device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0140] The input device 430 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the carbon dioxide storage capacity calculation device. The output device 440 can include a display device such as a display screen.

[0141] Embodiment five

[0142] The embodiment five of the present application also provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to perform a carbon dioxide storage capacity calculation method, comprising:

[0143] Obtaining a capacity calculation model matched with the storage state parameter; wherein the capacity calculation model is composed of at least one hierarchical evaluation model;

[0144] Inputting the storage state parameter into the capacity calculation model to obtain a target storage capacity.

[0145] Of course, the computer executable instructions of the storage medium provided by the embodiment of the present application are not limited to the method operations as described above, but can also perform related operations in the carbon dioxide storage capacity calculation method provided by any embodiment of the present application.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary universal hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH memory, a hard disk, or an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments of the present application.

[0147] It is worth noting that in the above embodiments of the carbon dioxide storage capacity calculation device, each unit and module included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy mutual differentiation, and do not limit the protection scope of the present application.

[0148] Although the present application has been described in detail above with general description, specific embodiments and experiments, some modifications or improvements can be made on the basis of the present application, which is obvious to those skilled in the art. Therefore, these modifications or improvements made on the basis of not deviating from the spirit of the present application, all belong to the scope of protection required by the present application.

Claims

1. A method for calculating carbon dioxide storage capacity, characterized in that: include: Obtaining a capacity calculation model that matches the storage status parameters; wherein the capacity calculation model is composed of at least one hierarchical assessment model; The storage state parameters are input into the capacity calculation model to obtain the target storage capacity.

2. The method according to claim 1, characterized in that The obtaining of a capacity calculation model matching the storage status parameters includes: Obtaining a set grading assessment model that matches the storage status parameters; Determining the set hierarchical assessment model as the capacity calculation model; The set hierarchical evaluation model is a basin-level resource evaluation model, a target area-level reservoir model, a site-level phase calculation model or an injection-level dynamic displacement model.

3. The method according to claim 1, characterized in that The obtaining of a capacity calculation model matching the storage status parameters includes: determining at least two of the hierarchical assessment models and level weight coefficients that match the storage status parameters; Obtaining a multi-level weighted model of at least two of the hierarchical evaluation models according to the level weight coefficients; The multi-level weighted model is determined as the capacity calculation model.

4. The method according to claim 1, wherein The obtaining of a capacity calculation model matching the storage status parameters includes: Inputting the storage state parameter into a hierarchical matching model to obtain a level matching result output by the hierarchical matching model; generating the capacity calculation model according to the level matching result; The capacity calculation model is a set hierarchical evaluation model or a multi-level weighted model.

5. The method according to claim 1, wherein Before inputting the storage state parameter into the capacity calculation model, the method further includes: The storage status parameters are dynamically corrected according to real-time monitoring data.

6. The method according to claim 5, characterized in that The dynamically correcting the storage status parameters according to the real-time monitoring data includes: Get sensor data stream; Performing data preprocessing on the sensor data stream to obtain state measured parameters and on-site calibration data; Based on the Kalman filter model, the dynamic correction processing is performed on the storage state parameters according to the actual measured state parameters and the on-site calibration data.

7. The method according to claim 6, characterized in that The data preprocessing of the sensor data stream to obtain state measured parameters and field calibration data includes: performing data anomaly detection on the sensor data stream; When determining that the sensor data stream is abnormal, performing a sensor self-calibration operation; When it is determined that the sensor data stream is normal, parameter conversion processing is performed on the sensor data stream to obtain the state measured parameters and the on-site calibration data.

8. A device for calculating carbon dioxide storage capacity, characterized in that: include: A model acquisition module, configured to acquire a capacity calculation model that matches the storage status parameters; wherein the capacity calculation model is composed of at least one hierarchical assessment model; A capacity calculation module is used to input the storage state parameters into the capacity calculation model to obtain a target storage capacity.

9. A device for calculating carbon dioxide storage capacity, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the carbon dioxide storage capacity calculation method according to any one of claims 1 to 7.

10. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the carbon dioxide storage capacity calculation method according to any one of claims 1 to 7.

Images