Geothermal well heat energy extraction data simulation deduction method based on digital twinning

Abstract

The present application relates to the technical field of data processing, in particular to a geothermal well heat energy extraction data simulation deduction method based on digital twinning, comprising: constructing a three-dimensional geological digital twinning model of a target geothermal well based on well structure parameters and formation thermal physical property parameters, correcting the three-dimensional geological digital twinning model according to measured temperature data and measured pressure data of monitoring points to obtain a corrected digital twinning geological body model; taking the corrected digital twinning geological body model as an initial heat storage model, and determining the heat conduction initial state parameters of multiple spatial nodes in the initial heat storage model by using the measured temperature data of the monitoring points. The present application can correct a layered local grid model recursively by using measured temperature and pressure data, can independently correct material properties for different lithology and porosity sections, can make the digital twinning geological body model accurately match field observation values in space, and can reduce the heat storage dynamic prediction error caused by geological parameter uncertainty.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins. Background Technology

[0002] With the continuous development of geothermal reservoir numerical simulation technology, layered grid modeling, heat-fluid coupling simulation, and multi-scenario iterative deduction have been widely used in well design, production capacity prediction, and production and irrigation scheme selection. Current simulation methods have gradually transitioned from homogeneous equivalent models to fine attribute assignment based on well logging interpretation and geostatistics, which can characterize reservoir heterogeneity and fracture distribution characteristics to a certain extent. However, in actual geothermal development, the lithology, porosity, and permeability of different strata vary significantly, and field temperature and pressure monitoring data are often not fully integrated into the model construction and correction process, resulting in a large deviation between the initial temperature and pressure fields and the actual reservoir state. Especially in complex strata with alternating lithologies, static models cannot automatically adjust the material properties of each layer based on measured feedback, leading to the accumulation of dynamic prediction errors of the geothermal reservoir and seriously affecting the engineering credibility of subsequent simulation results.

[0003] In related technologies, geothermal well heat extraction strategies are often formulated with maximizing cumulative heat production as the sole optimization objective. Typically, a limited number of trials are conducted using a fixed heat extraction rate and reinjection temperature scheme. This lacks comprehensive consideration of equipment lifespan constraints, unit heat production costs, and wellbore heat loss. Furthermore, no optimization mechanism has been established that couples multi-indicator weighted scoring with comprehensive ranking. Simultaneously, existing optimization results are mostly presented as theoretical curves or overall indicators, lacking specific executable scheduling instructions broken down by production cycle. This leads to a disconnect between theoretical solutions and actual field operation, making it difficult to achieve optimal economic efficiency throughout the entire lifecycle while ensuring equipment safety and the sustainability of the geothermal reservoir. Once the well condition or reservoir response deviates from the preset trajectory, management personnel cannot adjust operating parameters in a timely manner based on clear periodic control criteria, thereby increasing the risk of thermal breakthrough and subsequent maintenance costs. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins, comprising: Obtain the wellbore structural parameters and formation thermal properties parameters of the target geothermal well, as well as the measured temperature and pressure data of multiple pre-set monitoring points in the area surrounding the target geothermal well; A three-dimensional geological digital twin model of the target geothermal well is constructed based on wellbore structural parameters and formation thermal properties. The three-dimensional geological digital twin model is then corrected based on measured temperature and pressure data from monitoring points to obtain a corrected digital twin geological body model. The corrected digital twin geological model is used as the initial thermal reservoir model. The measured temperature data of the monitoring points are used to determine the initial state parameters of heat conduction of multiple spatial nodes in the initial thermal reservoir model. Based on the initial thermal reservoir model and the initial state parameters of heat conduction, a thermo-fluid coupling simulation is performed to obtain the temperature evolution data and pressure evolution data of each spatial node within a preset time period. Based on temperature and pressure evolution data, the thermal energy extraction potential value of each spatial node is determined. Based on the thermal energy extraction potential value, the thermal energy extraction sections in the digital twin geological model are divided into regions to obtain thermal energy extraction zone identification data. Based on the heat extraction zone identification data and the temperature evolution data corresponding to each spatial node, the heat extraction scheme of the target geothermal well is simulated and deduced in multiple scenarios to obtain the cumulative heat production data under different combinations of heat extraction parameters. Based on the accumulated heat production data, the long-term heat recovery strategy of the target geothermal well is optimized and evaluated to obtain an optimized scheme for heat energy extraction from the target geothermal well.

[0005] Preferably, the target geothermal well comprises multiple layer units; A three-dimensional geological digital twin model of the target geothermal well is constructed based on wellbore structural parameters and formation thermal property parameters. The three-dimensional geological digital twin model is then corrected using measured temperature and pressure data from monitoring points to obtain a corrected digital twin geological body model, including: Acquire logging curve data and geological exploration data of the target geothermal well, and determine the rock type and porosity properties of each layer unit based on the logging curve data and geological exploration data; Select one of the multiple segment units as the target segment unit, and generate a local mesh model of the target segment unit based on the rock type and porosity properties of the target segment unit; Based on the deviation values ​​between the measured temperature and pressure data at the monitoring points and the corresponding nodes in the local mesh model, the material properties of the local mesh model are corrected. The corrected local mesh models are then stitched together to obtain the corrected digital twin geological model.

[0006] Preferably, the initial state parameters of heat conduction at multiple spatial nodes within the initial thermal reservoir model are determined using measured temperature data from monitoring points. Based on the initial thermal reservoir model and the initial state parameters of heat conduction, a thermofluid coupling simulation is performed to obtain temperature evolution data and pressure evolution data for each spatial node within a preset time period, including: Obtain the injection flow rate and injection temperature data of the target geothermal well, and use the injection flow rate and injection temperature data as the heat source boundary conditions; Using the rock type and porosity properties of each spatial node in the corrected digital twin geological model as permeability constraints, the initial thermal conduction initialization process of the initial thermal reservoir model is performed based on the heat source boundary conditions and permeability constraints to obtain the initial state parameters of thermal conduction. The initial state parameters of heat conduction are input into the thermo-fluid coupling simulation engine, and the heat diffusion process and fluid transport process of each spatial node within a preset time period are jointly simulated to obtain temperature evolution data and pressure evolution data.

[0007] Preferably, the thermal energy extraction potential value of each spatial node is determined based on temperature evolution data and pressure evolution data. Based on the thermal energy extraction potential value, the thermal energy extraction zones in the digital twin geological model are divided into regions to obtain thermal energy extraction zone identification data, including: For each spatial node, obtain the temperature drop value of the temperature evolution data of the current spatial node and the pressure change rate value of the pressure evolution data within a preset time period; The thermal response intensity value of the space node is calculated based on the weighted combination of the temperature drop value and the pressure change rate value. The thermal response intensity value of each spatial node is compared with the preset potential threshold. The spatial nodes with values ​​higher than the potential threshold are marked as high-efficiency heating zones, and the spatial nodes with values ​​lower than the potential threshold are marked as low-efficiency heating zones, thus obtaining heating zone identification data.

[0008] Preferably, based on the heat extraction zone identification data and the temperature evolution data corresponding to each spatial node, multi-scenario simulation and extrapolation are performed on the heat extraction scheme of the target geothermal well to obtain cumulative heat production data under different combinations of heat extraction parameters, including: Multiple sets of candidate heat harvesting parameter combinations are obtained, wherein each set of candidate heat harvesting parameter combinations includes heat harvesting rate parameters and reinjection temperature parameters; For each candidate combination of heating parameters, the range of the corresponding high-efficiency heating section is determined based on the heating zone identification data, and the remaining heat energy reserve value within each high-efficiency heating section is determined based on the temperature evolution data. Based on the remaining thermal energy reserves and the thermal recovery rate and reinjection temperature parameters in the candidate thermal recovery parameter combinations, the thermal balance state of the target geothermal well in multiple consecutive production cycles is iteratively extrapolated to obtain the cumulative heat production data corresponding to each candidate thermal recovery parameter combination.

[0009] Preferably, the long-term heat recovery strategy of the target geothermal well is optimized and evaluated based on the accumulated heat production data to obtain an optimized scheme for heat energy extraction from the target geothermal well, including: Obtain equipment life data and economic assessment data for the target geothermal well, and determine the maximum allowable production life parameters based on the equipment life data; The unit heat production cost and wellbore heat loss rate of each candidate heat production parameter combination are calculated based on cumulative heat production data and economic evaluation data. The unit heat production cost, wellbore heat loss rate, and maximum allowable production years are comprehensively evaluated. The candidate heat extraction parameter combination with the highest comprehensive score is selected as the recommended scheme, and an optimized heat extraction scheme is generated based on the recommended scheme.

[0010] Preferably, a comprehensive score is calculated based on the unit heat production cost, wellbore heat loss rate, and maximum allowable production years. The candidate heat extraction parameter combination with the highest comprehensive score is selected as the recommended scheme, and an optimized heat extraction scheme is generated based on the recommended scheme, including: The comprehensive score of the candidate heat production parameter combination is obtained by superimposing the unit heat production cost value, the wellbore heat loss rate value, and the sub-item scores corresponding to the maximum allowable production years parameter. The comprehensive scores of all candidate heat harvesting parameter combinations are ranked, and the candidate heat harvesting parameter combination ranked first is selected as the recommended scheme. An optimized heat extraction scheme is generated based on the heat extraction rate parameters and reinjection temperature parameters in the recommended scheme; the optimized heat extraction scheme includes scheduling instructions for each production cycle.

[0011] Compared with the prior art, the beneficial effects of the present invention are: This invention uses measured temperature and pressure data to recursively correct a layered local grid model, enabling independent correction of material properties for different lithologies and porosities. This allows the digital twin geological model to accurately match field observations in space, reducing the dynamic prediction error of the reservoir caused by the uncertainty of geological parameters. It also ensures that the initial temperature and pressure fields in subsequent simulations are highly consistent with the actual reservoir state, thereby improving the engineering credibility and prediction accuracy of temperature and pressure evolution data. This invention introduces equipment lifespan data as a hard constraint on the maximum production lifespan and weights and ranks the unit heat production cost, wellbore heat loss rate, and lifespan indicators. This effectively avoids the economic risks of simply pursuing heat production while ignoring equipment depreciation, heat loss, and subsequent maintenance costs. It achieves quantitative joint optimization of heat extraction rate and reinjection temperature, and finally generates specific scheduling instructions covering each production cycle. This makes the optimized scheme directly executable on-site, avoids the disconnect between theoretical schemes and actual operation, and ensures the optimal synergy between economic efficiency and safety of geothermal wells throughout their entire lifespan. Attached Figure Description

[0012] Figure 1 This is a schematic flowchart of the overall method in one embodiment of the present invention; Figure 2 This is a schematic diagram of the steps involved in creating a digital twin geological model according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the steps involved in the evolution of data in one embodiment of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0014] Example 1, please refer to Figures 1-3 This invention provides a technical solution: a method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins, comprising: S1. Obtain the wellbore structural parameters and formation thermal properties of the target geothermal well, as well as the measured temperature and pressure data of multiple preset monitoring points in the area surrounding the target geothermal well.

[0015] Among them, wellbore structural parameters refer to various indicators describing the geometry and completion method of geothermal wells, including the diameter of each drill bit, casing specifications, running depth, cement return height, and well deviation trajectory, which are used to clarify the spatial constraints of fluid flow channels and heat exchange interfaces; formation thermal property parameters cover physical properties such as thermal conductivity, specific heat capacity, thermal diffusivity, and porosity of the core at the target stratum, reflecting the intrinsic ability of the formation to conduct and store heat; preset monitoring points refer to temperature and pressure sensing nodes that are fixed in advance according to geological design at a certain radial distance and different depths around the well, and their spatial distribution takes into account both reservoir heterogeneity and geothermal gradient direction; measured temperature data and pressure data are the formation temperature values ​​and pore fluid pressure values ​​recorded by each monitoring node in a continuous time series, which are used to characterize the real-time state of thermal front advancement and pressure decay during geothermal extraction.

[0016] For example, in a deep fractured geothermal field, after cementing a production well with a designed depth of 3500 meters, the operations team obtained detailed structural parameters of the 339.7 mm outer diameter surface casing in the second section, the 244.5 mm outer diameter technical casing in the third section, and the open-hole completion section using the drilling log and core test report. Simultaneously, using a steady-state flat plate heat flow meter and transient hot wire method, the thermal conductivity of the target granite reservoir was measured to be 2.8 Kelvin per meter, and the specific heat capacity to be 890 Joules per kilogram of Kelvin. At radial depths of 200 meters, 500 meters, and 800 meters, and at a depth of 1500 meters... Nine sets of quartz crystal pressure gauges and platinum resistance thermometers were deployed at depths of 1,500 meters, 2,500 meters, and 3,200 meters to continuously record downhole temperature and pressure data at a sampling frequency of once per minute. After obtaining all the above parameters, the analysts input the well structure, thermophysical property data, and the measured temperature and pressure change curves of the first week into the numerical simulation platform. They found that the pressure at the monitoring point 200 meters away from the well decreased at a rate about 20% faster than that at the far end in the initial stage of pumping, while the temperature decrease showed a significant lag effect. Based on this, it was determined that the thermal reservoir's heat generation mechanism is mainly fracture conduction and secondarily heat conduction, providing a quantitative basis for the formulation of subsequent reinjection strategies.

[0017] S2. Construct a three-dimensional geological digital twin model of the target geothermal well based on the wellbore structural parameters and formation thermal properties parameters. Correct the three-dimensional geological digital twin model according to the measured temperature data and measured pressure data of the monitoring points to obtain the corrected digital twin geological body model.

[0018] Among them, the three-dimensional geological digital twin model refers to a three-dimensional digital equivalent body that can virtually reproduce the geothermal reservoir geometry, thermodynamic properties, and fluid flow channels by constructing a discretized grid model and initial temperature and pressure field assignment based on static data such as well trajectory, casing sequence, lithological stratification, and spatial distribution of thermal properties. The correction process refers to using the continuously recorded temperature and pressure time series at the monitoring points as the observation target, and using an iterative inversion algorithm to adjust key parameters such as thermal conductivity, permeability, and heat storage coefficient in the model step by step, so that the deviation between the simulated output and the measured value at each monitoring point converges to an acceptable range for engineering. The corrected digital twin geological body model refers to a modified model that maintains the original geological framework and has consistent dynamic response after being constrained by measured data and optimized by parameters. It can more realistically reflect the migration of the reservoir thermal front and the evolution of the pressure field, and can serve as a benchmark for subsequent production capacity prediction, inter-well interference analysis, and reinjection scheme optimization.

[0019] For example, after the completion of a 3200-meter-deep geothermal production well, the operators established an initial three-dimensional geological digital twin model based on drilling logging curves and core experimental data. This model included four sets of casing programs, three main fracture zones, and thermal property zoning of the granite basement. The total number of grids in the model was approximately 2.5 million. The initial temperature field was assigned based on the geothermal gradient, and the pressure field was calculated based on hydrostatic pressure. Subsequently, temperature and pressure data collected continuously for 48 hours from monitoring points at depths of 300 meters, 600 meters, and 1000 meters radially around the well were imported into the calibration process. By adjusting the thermal conductivity and porosity elastic coefficient of each layer, the simulated temperature error of the calibrated model at the nine monitoring points was controlled within 0.5 degrees Celsius, and the pressure error did not exceed 0.2 MPa. The calibrated digital twin geological model not only accurately reproduced the current reservoir temperature and pressure distribution but also successfully indicated the existence of a high-permeability fracture channel in the northeast direction, improving the overall development efficiency of the geothermal field.

[0020] For example, the target geothermal well includes multiple layer units; S201, acquire logging curve data and geological exploration data of the target geothermal well, and determine the rock type and porosity properties of each layer unit based on the logging curve data and geological exploration data; S202, select one of the multiple layer units as the target layer unit, and generate a local mesh model of the target layer unit based on the rock type and porosity properties of the target layer unit; S203, correct the material properties of the local mesh model based on the deviation values ​​between the measured temperature data and measured pressure data of the monitoring points and the corresponding nodes in the local mesh model, and stitch the corrected local mesh models together to obtain the corrected digital twin geological body model.

[0021] In this embodiment, the geothermal well was drilled to a depth of 3600 meters. Based on the logging response characteristics and core description, the entire well was divided into four layer units: Quaternary loose layer, upper clastic rock section, central fractured granite section, and lower tight granite section. Based on natural gamma and neutron density logging curves, combined with cuttings thin section identification, the average porosity of the central fractured granite section was determined to be 4.5%, while the porosity of the lower tight granite section was only 1.2%. The central fractured granite section was selected as the target layer unit. A local hexahedral grid with a radial range of 500 meters and a vertical thickness of 200 meters was established with its center as the origin. The grid step size was increased to 2 meters around the well and gradually decreased to 10 meters at the boundary. The initial material properties were assigned according to the experimentally measured thermal conductivity of 2.9 Kelvin per meter and specific heat capacity of 850 Joules per kilogram. Three monitoring points were arranged within this layer unit. The measured temperature values ​​of 46.2°C, 45.8°C, and 44.7°C, and the measured pressure values ​​of 18.5 MPa, 18.2 MPa, and 17.9 MPa were compared with the initial simulated values ​​of the corresponding nodes in the local model. The maximum temperature deviation reached 1.3°C, and the pressure deviation reached 0.6 MPa. By adjusting the permeability and thermal conductivity of the fracture zone within the local grid, the simulated temperature deviation at each monitoring point was reduced to less than 0.3°C, and the pressure deviation to less than 0.1 MPa, thus completing the correction of the material properties of this section. Subsequently, the same process was followed to generate local grids and correct the measured data for the upper clastic rock section and the lower dense granite section. Finally, the four corrected local grids were spliced ​​along the well depth direction, and continuous interpolation and smoothing of heat flow and pressure were performed on the interlayer contact surface to obtain a complete corrected digital twin geological model.

[0022] S3. Using the corrected digital twin geological model as the initial thermal reservoir model, the measured temperature data of the monitoring points are used to determine the initial state parameters of heat conduction of multiple spatial nodes in the initial thermal reservoir model. Based on the initial thermal reservoir model and the initial state parameters of heat conduction, a thermo-fluid coupling simulation is performed to obtain the temperature evolution data and pressure evolution data of each spatial node within a preset time period.

[0023] The initial reservoir model refers to a three-dimensional digital body with a realistic geological framework and property distribution after calibration with measured data. Its grid node coordinates correspond one-to-one with the spatial location of the reservoir, serving as the geometric and property basis for subsequent numerical simulations. The initial state parameters of heat conduction refer to the initial values ​​of the temperature field and heat flux density distribution at each spatial node at the start of the simulation. These are usually assigned to all nodes of the model by the measured temperatures at each monitoring point through geostatistical interpolation to ensure that the initial temperature and pressure fields are consistent with field observations. The thermofluid coupling simulation deduction refers to simultaneously solving the heat transfer equation and the fluid seepage equation in the reservoir, considering the mutual influence between the temperature field and the pressure field, including the changes in fluid properties with temperature, heat convection and conduction, and the thermal expansion and contraction effects of the rock mass, to simulate the dynamic evolution of the reservoir's thermodynamic state during mining or injection. The preset time period refers to the prediction duration set according to engineering requirements, which can cover the short-term trial production stage or the long-term stable production cycle. The temperature evolution data and pressure evolution data are the temperature and pressure value sequences of each spatial node at each time step within the time period, used to quantitatively describe the thermal front expansion path, the pressure drop funnel morphology, and the evolution trend of inter-well disturbances.

[0024] For example, a production well in a geothermal field was drilled to a depth of 3800 meters. The corrected digital twin geological model contained approximately 3 million hexahedral grid cells, extending radially to 1200 meters and vertically covering the entire reservoir thickness. Using 72 hours of continuous measured temperature and pressure data from eight monitoring points around the well, initial temperature and pressure fields were assigned to all nodes of the model using Kriging interpolation. The initial temperature near the bottom of the well was measured at 182.5 degrees Celsius, and the initial pressure was 42.3 MPa. The temperatures at the distant monitoring points decreased sequentially to 156.2 degrees Celsius and 138.7 degrees Celsius, with corresponding pressures decreasing to 38.1 MPa and 35.6 MPa. After interpolation, the overall field distribution matched the geological structure. Subsequently, the production well was set to produce at a constant flow rate of 1200 cubic meters per day, and the reinjection well was set to produce at a constant flow rate of 1200 cubic meters per day. A 1000 cubic meter flow rate reinjection was simulated over a total duration of 180 days with a time step of 0.5 days, employing a fully coupled thermal-fluid transient calculation. After the simulation, temperature and pressure data were extracted from each spatial node at three key moments: 30 days, 90 days, and 180 days. The results showed that the pressure near the production well decreased by approximately 3.2 MPa and the temperature decreased by approximately 4.8 degrees Celsius within 180 days, while the pressure decrease at a radial distance of 500 meters was only 1.1 MPa and the temperature decrease was less than 0.6 degrees Celsius, confirming that the reservoir has strong recharge capacity and a low risk of thermal breakthrough. Simultaneously, three-dimensional cloud maps of isothermal and isobaric surfaces at different times were plotted using the output data, clearly indicating the preferential advance direction of the low-temperature reinjection water front along the high-permeability fracture zone, providing a quantitative basis for subsequent adjustments to the production-injection well spacing and stratified reinjection depth.

[0025] For example, S301, acquire the injection flow rate data and injection temperature data of the target geothermal well, and use the injection flow rate data and injection temperature data as heat source boundary conditions; S302, use the rock type attributes and porosity attributes of each spatial node in the corrected digital twin geological model as permeability constraints, and perform heat conduction initialization processing on the initial geothermal reservoir model based on the heat source boundary conditions and permeability constraints to obtain the initial state parameters of heat conduction; S303, input the initial state parameters of heat conduction into the thermofluid coupling simulation engine, and perform joint simulation of the heat diffusion process and fluid migration process of each spatial node within a preset time period to obtain temperature evolution data and pressure evolution data.

[0026] In this embodiment, the geothermal field adopts a dual-well model of one production well and one injection well. The production well is 3400 meters deep, and the injection well is located 600 meters northeast of the production well. The daily injection volume of the injection well was measured to be 1800 cubic meters, and the injection wellhead temperature was stabilized at 38.5 degrees Celsius after being regulated by a heat exchanger. This set of data was set as the core parameter of the heat source boundary conditions. At the same time, on the calibrated digital twin geological model with a total of 2.8 million nodes, according to the rock type of each node—including surface loose sandstone, middle argillaceous siltstone, and deep granodiorite—and its corresponding porosity value, such as deep granodiorite... The average porosity is 3.8%, and 12.2% for the central sandstone. Based on the empirical calibration relationship between permeability and porosity, a permeability distribution field for the entire space was generated. The permeability in the deep fracture zone is as high as 150 millidarcy, while that in the dense zone is as low as 0.5 millidarcy. The above boundary conditions and permeability constraints were input into the preprocessing module for heat conduction initialization solution to obtain the initial temperature and pressure fields of all nodes at the start of the simulation. The initial temperature at the bottom of the well is 176.3 degrees Celsius, and the initial pressure is 39.7 MPa. The temperature at the bottom of the reinjection well drops to 48.2 degrees Celsius after initialization due to the influence of injected cold water. After initialization, the initial temperature and pressure values ​​of each node are used as the initial field and formally fed into the thermofluid coupling simulation engine. The thermofluid coupling simulation engine is a numerical solution platform that integrates heat conduction, convection heat transfer, and porous media seepage equations. It can synchronously calculate the coupled evolution of the temperature and pressure fields in a time-step manner. The total simulation duration is set to 240 days, with a time step of 0.2 days. During the simulation, the engine outputs full node temperature and pressure data every 5 days. After the calculation is completed, the temperature evolution curve of the production well bottom node is extracted, showing that the temperature decreases slowly in the first 60 days, decreasing by only 0.8 degrees Celsius, but accelerates after 180 days, with a cumulative decrease of 6.2 degrees Celsius by 240 days. At the same time, the pressure data shows that the pressure at the bottom of the production well drops sharply by 2.5 MPa in the first 30 days, and then gradually recovers to 95% of the initial value as the injected fluid arrives. The final output temperature and pressure evolution data are stored in the form of a three-dimensional time-series field.

[0027] S4. Determine the thermal energy extraction potential value of each spatial node based on temperature evolution data and pressure evolution data. Divide the thermal energy extraction potential value into regions in the digital twin geological model to obtain thermal energy extraction zone identification data.

[0028] Among them, the thermal energy extraction potential value refers to a relative index obtained by quantifying multiple factors such as the temperature drop rate, pressure decay rate, and thermal reservoir recovery capacity of each spatial node within a preset time period. This index reflects the feasibility and economy of maintaining the heat production temperature and flow rate at that location under existing production and irrigation conditions. The higher the value, the more suitable the node is as a priority exploitation target area. The thermal energy extraction segment refers to a continuous vertical interval in the digital twin geological model that has sufficient thermal reservoir thickness, permeability, and fluid storage space. It usually spans multiple grid layers and is the basic unit for implementing layered well completion and segmented extraction in actual engineering. The regional division refers to dividing the entire model space into thermal energy extraction sub-regions with different priority levels according to the distribution characteristics of the thermal energy extraction potential value, such as the first-level priority area, the second-level suitable area, and the third-level potential area. Each sub-region is spatially continuous and has a relatively uniform potential level. The thermal energy extraction zoning identification data is the hierarchical coding information assigned to each grid node or segment unit, which records its zoning category in the form of numbers or symbols. It can serve as a direct basis for subsequent well layout schemes and selection of perforation locations in thermal energy extraction segments.

[0029] For example, a total of 2.8 million spatial nodes obtained complete temperature and pressure evolution data over a 240-day simulation period. Analysis showed that nodes within 100 meters of the production well experienced a cumulative temperature drop of 6.2 degrees Celsius and a pressure drop of approximately 3.1 MPa, with slow subsequent pressure recovery, resulting in a calculated thermal energy extraction potential of only 0.32 for this area, classifying it as a low-potential zone. In contrast, nodes located 200 to 400 meters to the side of the production well between the reinjection well and the production well experienced a temperature drop of only 0.8 to 1.5 degrees Celsius and a pressure drop maintained below 1.0 MPa, with the thermal front pushing... With a moderate advance rate and a calculated potential value as high as 0.85 to 0.92, it is designated as a primary priority heating zone. Meanwhile, the temperature in areas beyond 800 meters remains almost unchanged, and the pressure drop is less than 0.2 MPa, but the permeability is low, limiting flow supply; with a potential value between 0.45 and 0.55, it is designated as a secondary suitable zone. Finally, the entire heating zone of the digital twin geological model—mainly including the fractured granite section at depths of 2200 to 2800 meters and the secondary dolomite section at depths of 2800 to 3200 meters—is divided according to potential thresholds, with the total volume of the primary priority zone being approximately [missing information]. The volume of the heating zone is 18% of the total heating volume of the model, with the secondary suitable zone accounting for about 45% and the tertiary potential zone accounting for about 37%; output heating zone identification data.

[0030] For example, for each spatial node, the temperature drop value of the temperature evolution data and the pressure change rate value of the pressure evolution data of the current spatial node are obtained within a preset time period; the thermal response intensity value of the spatial node is calculated based on the weighted combination of the temperature drop value and the pressure change rate value; the thermal response intensity value of each spatial node is compared with a preset potential threshold, and the layer segment where the spatial node is located is marked as an efficient heating layer segment, and the layer segment where the spatial node is located is marked as an inefficient heating layer segment, thus obtaining heating zone identification data.

[0031] In this embodiment, the corrected digital twin geological model of the geothermal field contains approximately 3 million spatial nodes. After completing a 240-day production and irrigation simulation, the temperature and pressure evolution sequences of each node were obtained. For the main geothermal granite segment located at a depth of 2500 to 3100 meters, the temperature drop and pressure change rate were calculated for each node. Among these, within a radial range of 80 meters around the production well, some nodes experienced temperature drops as high as 6.8 degrees Celsius, and the pressure change rate decreased by 0.013 MPa per day. The two values ​​were weighted at 0.55 for temperature drop and 0.45 for pressure change rate. After combination, the calculated thermal response intensity value is 6.8×0.55+0.013×0.45×1000, which is then normalized. The actual result is 3.74, while the preset potential threshold for this area is 4.20. Therefore, it is judged as an inefficient heat harvesting section. Conversely, in the area with a radial distance of 250 meters to 400 meters, the node temperature drop is only 1.2 degrees Celsius to 1.8 degrees Celsius, and the pressure change rate is 0.004 MPa to 0.006 MPa per day. The combined thermal response intensity value is between 4.35 and 4.82, all of which are higher than the threshold of 4.20. This area is marked as an efficient heat harvesting section. In areas more than 800 meters away, the temperature drop was less than 0.3 degrees Celsius, the pressure change rate was close to zero, and the combined value was only 2.10, which was also identified as an inefficient zone. Finally, all nodes in the entire model were compared with the threshold of 4.20 based on their thermal response intensity values. Nodes with values ​​higher than this were connected to form a spatially continuous region, and three high-efficiency heat recovery zones were identified. These zones were located 300 to 450 meters northeast of the production well, 200 to 350 meters southwest of the well, and 400 to 550 meters northwest of the well. The total volume of these three zones was approximately 850,000 cubic meters, accounting for 22% of the total volume of the heat recovery zone. The remaining areas were marked as inefficient heat recovery zones. The output heat recovery zone identification data was recorded with the classification code of each grid node, with high-efficiency zones assigned a value of 1 and inefficient zones assigned a value of 0. This identification data was directly imported into the well completion design software to guide engineers to avoid inefficient areas.

[0032] S5. Based on the heat extraction zone identification data and the temperature evolution data corresponding to each spatial node, the heat extraction scheme of the target geothermal well is simulated and deduced in multiple scenarios to obtain the cumulative heat production data under different combinations of heat extraction parameters.

[0033] Among them, the heat recovery scheme refers to the production and reinjection operation strategy formulated for the target geothermal well, including but not limited to adjustable parameters such as the water production flow rate of the production well, the injection flow rate of the reinjection well, the reinjection temperature setting, the selection of the perforation section, and the opening sequence of the heat recovery section; multi-scenario simulation and deduction refers to systematically changing the above heat recovery scheme parameters under the condition of keeping the geological model and the initial thermal state unchanged, forming multiple sets of alternative operating conditions, and performing transient calculations of thermal fluid coupling in each set of operating conditions to obtain the reservoir response under each set of operating conditions; cumulative heat production data refers to the total heat carried by the fluid extracted from the production well within a specified production period in each simulation scenario, usually measured in joules or megawatt-hours, and can also be converted into equivalent standard coal or power generation. This data can intuitively reflect the thermal energy recovery benefits of each scheme.

[0034] For example, based on the preliminary zoning results, the geothermal field determined that the high-efficiency heat-producing zone is concentrated in the transition zone between granodiorite and dolomite at a depth of 2600 to 3200 meters, while the low-efficiency zone is located within an 80-meter radius of the wellbore and beyond 800 meters. Three sets of main variable parameters were designed: the water production flow rate of the production well was set to 1200 cubic meters per day, 1500 cubic meters per day, and 1800 cubic meters per day, respectively; the injection temperature of the reinjection well was set to 35 degrees Celsius, 40 degrees Celsius, and 45 degrees Celsius, respectively; and the reinjection flow rate was always kept completely equal to the water production flow rate to maintain reservoir pressure. This resulted in 9 simulation scenarios in a 3×3 pattern. The perforation sections in each scenario were strictly arranged within the high-efficiency marked area, avoiding the low-efficiency marked nodes. All scenarios were sequentially input into the thermo-fluid coupling simulation engine, with the simulation time span uniformly set to 20 years and the time step set to 1 month. The temperature field of all nodes was output every six months, and the bottom-hole temperature of the production well and the cumulative produced water volume were recorded. After the simulation was completed, the cumulative heat production over 20 years for each scenario was calculated. The results showed that the cumulative heat production was lowest at a water intake flow rate of 1200 cubic meters per day and a reinjection temperature of 35 degrees Celsius, at 1.85 × 10¹⁵ Joules. When the water intake flow rate increased to 1500 cubic meters per day and the reinjection temperature rose to 45 degrees Celsius, the cumulative heat production significantly increased to 2.34 × 10¹⁵ Joules, an increase of 26%. Further increasing the water intake flow rate to 1800 cubic meters per day resulted in higher initial heat production, but due to the accelerated advance of the thermal front, the subsequent... The wellhead temperature decreased rapidly during the initial phase, and the cumulative heat production over 20 years was only 2.21 × 10¹⁵ joules, which was lower than that of the medium flow rate scheme. In addition, comparing scenarios with different reinjection temperatures at the same flow rate, it was found that for every 5 degrees Celsius increase in reinjection temperature, the cumulative heat production increased by an average of about 8%, but due to the limitations of heat exchanger capacity, 45 degrees Celsius was the upper limit for engineering. After comprehensive comparison, the combination of a daily water intake flow of 1,500 cubic meters and a reinjection temperature of 45 degrees Celsius was determined to be the optimal heat extraction scheme. The results of this multi-scenario simulation provided quantitative decision support for the final design of the heat extraction system.

[0035] For example, multiple sets of candidate heat recovery parameter combinations are obtained, wherein each set of candidate heat recovery parameter combinations includes heat recovery rate parameters and reinjection temperature parameters; for each candidate heat recovery parameter combination, the corresponding high-efficiency heat recovery layer range is determined according to heat recovery zone identification data, and the remaining heat energy reserve value within each high-efficiency heat recovery layer range is determined according to temperature evolution data; based on the remaining heat energy reserve value and the heat recovery rate parameters and reinjection temperature parameters in the candidate heat recovery parameter combinations, the heat balance state of the target geothermal well in multiple continuous production cycles is iteratively deduced to obtain the cumulative heat production data corresponding to each candidate heat recovery parameter combination.

[0036] In this embodiment, the geothermal field is planned to operate for 15 years. Based on the preliminary results of high-efficiency heat extraction zoning, the area is concentrated in the fractured granite section at a depth of 2600 to 3050 meters, with an effective heat extraction volume of approximately 920,000 cubic meters. The initial average temperature, confirmed by temperature evolution data, is 178.6 degrees Celsius, and the baseline waste temperature is set at 90 degrees Celsius. Therefore, the initial remaining thermal energy reserve is calculated to be 3.2 × 10¹⁵ joules. The design department proposed three candidate schemes: Scheme A, with a heat extraction rate of 1000 cubic meters per day and a reinjection temperature of 42 degrees Celsius; Scheme B, with a heat extraction rate of 1200 cubic meters per day and a reinjection temperature of 46 degrees Celsius; and Scheme C, with a heat extraction rate of 800 cubic meters per day and a reinjection temperature of 38 degrees Celsius. The three schemes are input into an iterative simulation process, with each year constituting a production cycle, for a total of 15 cycles. For Scheme A, the 1000 cubic meters per day multiplied by 365 days is taken out in the first cycle. 365,000 cubic meters of fluid, carrying heat calculated based on the current average temperature, are simultaneously injected with an equal amount of fluid at 42 degrees Celsius. At the end of the cycle, a reservoir heat balance calculation is performed, resulting in an average temperature decrease of 0.8 degrees Celsius at the end of the year, reducing the remaining thermal energy reserve to 3.15 × 10¹⁵ joules. This process continues until the end of the 15th year, with Scheme A yielding a cumulative heat production of 2.05 × 10¹⁵ joules. Scheme B, due to its higher heat extraction rate, exhibits a significantly higher heat production rate in the first five cycles. In option A, the thermal front advances faster, and the temperature drops more rapidly in the later stages, resulting in a cumulative heat production of 2.28 × 10¹⁵ joules by the end of the 15th year, the highest among the three groups. Although option C has a lower reinjection temperature and a larger heat extraction temperature difference, its heat extraction rate is relatively low, limiting its overall output, with a cumulative heat production of only 1.86 × 10¹⁵ joules. After comprehensive comparison, option B was determined to be the optimal candidate combination, with a 15-year heat production that is about 11% higher than option A and about 23% higher than option C.

[0037] S6. Optimize and evaluate the long-term heat extraction strategy of the target geothermal well based on the accumulated heat production data to obtain an optimized heat extraction scheme for the target geothermal well.

[0038] The long-term thermal recovery strategy encompasses the entire lifecycle operation system, including thermal recovery rate, reinjection temperature, perforation section selection, thermal recovery cycle division, and parameter adjustment schemes for each stage. Optimization evaluation refers to ranking all candidate schemes based on multiple dimensions, including extending reservoir life, controlling thermal breakthrough risk, reinjection water treatment energy consumption, equipment wear and tear, and operation and maintenance costs, while maximizing thermal benefits. The optimal thermal energy extraction scheme refers to the optimal parameter combination selected after the above evaluation and its corresponding phased control recommendations. This scheme should ensure the sustainable development of reservoir thermal energy resources while meeting engineering economic requirements, and should also have on-site operability and safety redundancy.

[0039] For example, after completing a 20-year simulation of nine candidate heat extraction parameter combinations, the geothermal field obtained the corresponding cumulative heat production data for each group. The highest heat production scheme, with a water extraction rate of 1500 cubic meters per day and a reinjection temperature of 45 degrees Celsius, yielded a 20-year cumulative heat production of 2.34 × 10¹⁵ joules. Analysis of the heat storage decay curve for this scheme revealed that by the end of the 18th year, the wellhead temperature had dropped to 115 degrees Celsius, below the original minimum inlet temperature requirement of 120 degrees Celsius for the heat pump, indicating that this scheme would face insufficient heat quality in the later stages. In contrast, another scheme, with a water extraction rate of 1300 cubic meters per day and a reinjection temperature of 42 degrees Celsius, yielded a 20-year cumulative heat production of 2.15 × 10¹⁵ joules. Although the total was about 8 percentage points lower than the highest scheme, Its wellhead temperature remained above 122 degrees Celsius throughout the entire cycle, and the pressure drop was relatively gradual, resulting in stronger thermal reservoir recovery capabilities. Meanwhile, economic calculations showed that the scheme with a water production rate of 1500 cubic meters per day required a larger power pump set and a more efficient heat exchanger, resulting in a unit heat extraction cost that was about 12 percentage points higher than the scheme with a daily production rate of 1300 cubic meters. In addition, the need to add auxiliary heating equipment in the later stage to compensate for insufficient temperature resulted in lower economic benefits over the entire life cycle compared to the medium-rate scheme. Considering the three aspects of thermal performance, economy, and stability, the optimized evaluation determined that a water production rate of 1300 cubic meters per day, a reinjection temperature of 42 degrees Celsius, and a step-by-step control strategy of gradually reducing the water production rate to 1100 cubic meters per day after the 12th year was the final recommended optimized thermal energy extraction scheme.

[0040] For example, the equipment life data and economic evaluation data of the target geothermal well are obtained, and the maximum allowable production years parameter is determined based on the equipment life data; the unit heat production cost value and wellbore heat loss rate value of each candidate heat production parameter combination are calculated based on the cumulative heat production data and economic evaluation data; a comprehensive score is performed based on the unit heat production cost value, wellbore heat loss rate value and maximum allowable production years parameter, and the candidate heat production parameter combination with the highest comprehensive score is selected as the recommended scheme, and a heat energy extraction optimization scheme is generated based on the recommended scheme.

[0041] In this embodiment, simulations of nine candidate heat extraction parameter combinations were completed in the early stages of the geothermal field. Field equipment data showed that the rated lifespan of the downhole submersible pump was 12 years, and the design lifespan of the surface heat exchanger was 15 years. After comprehensive evaluation, the maximum allowable production lifespan was determined to be 12 years. The project's economic evaluation data included an initial investment of 42 million yuan, an average annual electricity cost of 1.8 million yuan, and an annual maintenance cost of 450,000 yuan. The discount rate was 6%. Based on the cumulative heat production data of each scheme over 12 years and the aforementioned economic inputs, the unit... The unit heat production cost is as follows: Scheme A has a water extraction rate of 1000 cubic meters per day and a reinjection temperature of 42 degrees Celsius, with a unit heat production cost of 186 yuan per megawatt-hour; Scheme B has a water extraction rate of 1200 cubic meters per day and a reinjection temperature of 46 degrees Celsius, with a unit heat production cost of 162 yuan per megawatt-hour; Scheme C has a water extraction rate of 1300 cubic meters per day and a reinjection temperature of 42 degrees Celsius, with a unit heat production cost of 158 yuan per megawatt-hour; and Scheme D has a water extraction rate of 1500 cubic meters per day and a reinjection temperature of 45 degrees Celsius, with a unit heat production cost of 171 yuan per megawatt-hour. The wellbore heat loss rates for each scheme, calculated using transient heat transfer in the wellbore, are as follows: Scheme A 5.2%, Scheme B 4.7%, Scheme C 4.3%, and Scheme D 3.9%. This indicates that a higher water extraction rate results in a shorter fluid residence time in the wellbore and lower heat loss. A comprehensive score is calculated for the three indicators, with a weight of 0.50 for unit heat production cost, 0.30 for wellbore heat loss rate, and 0.20 for cumulative heat production within the maximum allowable production years. After normalization, the total score for each scheme is calculated. The results show that Scheme C ranks first with a total score of 88.6, followed by Scheme B at 84.2, Scheme D at 82.1, and Scheme A at 76.4. Ultimately, Scheme C—with a water extraction rate of 1300 cubic meters per day and a reinjection temperature of 42 degrees Celsius—is recommended as the optimal heat extraction scheme.

[0042] Furthermore, for example, by superimposing the unit heat production cost, wellbore heat loss rate, and maximum allowable production years parameters, a comprehensive score is obtained for the candidate heat extraction parameter combinations; the comprehensive scores of all candidate heat extraction parameter combinations are sorted, and the candidate heat extraction parameter combination ranked first is selected as the recommended scheme; a heat energy extraction optimization scheme is generated based on the heat extraction rate parameter and reinjection temperature parameter in the recommended scheme; wherein, the heat energy extraction optimization scheme includes scheduling instructions for each production cycle.

[0043] In this embodiment, the geothermal field scored 9 candidate schemes. Scheme C had the highest unit heat production cost score of 92 points, Scheme D had a wellbore heat loss rate score of 88 points but a lower cost score, and Scheme B had a maximum allowable production years score of 85 points. After combining the three scores, Scheme C had a comprehensive score of 91.5 points, Scheme B had 87.2 points, Scheme D had 86.8 points, and Scheme A had 79.3 points. After ranking, Scheme C ranked first. The heat extraction rate of this scheme is 1300 cubic meters per day, and the reinjection temperature is 42 degrees Celsius. Based on this, 12 annual scheduling instructions were generated: the water extraction rate is maintained at 1300 cubic meters per day and the reinjection temperature is 42 degrees Celsius from year 1 to year 4; the water extraction rate is adjusted to 1250 cubic meters per day from year 5 to year 8, and the reinjection temperature is maintained at 42 degrees Celsius; from year 9 to year 12, the water extraction rate is reduced to 1150 cubic meters per day, and the reinjection temperature is increased to 43 degrees Celsius to mitigate the thermal breakthrough.

[0044] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins, characterized in that, include: Obtain the wellbore structural parameters and formation thermal properties parameters of the target geothermal well, as well as the measured temperature and pressure data of multiple pre-set monitoring points in the area surrounding the target geothermal well; A three-dimensional geological digital twin model of the target geothermal well is constructed based on wellbore structural parameters and formation thermal properties. The three-dimensional geological digital twin model is then corrected based on measured temperature and pressure data from monitoring points to obtain a corrected digital twin geological body model. The corrected digital twin geological model is used as the initial thermal reservoir model. The measured temperature data of the monitoring points are used to determine the initial state parameters of heat conduction of multiple spatial nodes in the initial thermal reservoir model. Based on the initial thermal reservoir model and the initial state parameters of heat conduction, a thermo-fluid coupling simulation is performed to obtain the temperature evolution data and pressure evolution data of each spatial node within a preset time period. Based on temperature and pressure evolution data, the thermal energy extraction potential value of each spatial node is determined. Based on the thermal energy extraction potential value, the thermal energy extraction sections in the digital twin geological model are divided into regions to obtain thermal energy extraction zone identification data. Based on the heat extraction zone identification data and the temperature evolution data corresponding to each spatial node, the heat extraction scheme of the target geothermal well is simulated and deduced in multiple scenarios to obtain the cumulative heat production data under different combinations of heat extraction parameters. Based on the accumulated heat production data, the long-term heat recovery strategy of the target geothermal well is optimized and evaluated to obtain an optimized scheme for heat energy extraction from the target geothermal well.

2. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 1, characterized in that, The target geothermal well comprises multiple strata units; A three-dimensional geological digital twin model of the target geothermal well is constructed based on wellbore structural parameters and formation thermal property parameters. The three-dimensional geological digital twin model is then corrected using measured temperature and pressure data from monitoring points to obtain a corrected digital twin geological body model, including: Acquire logging curve data and geological exploration data of the target geothermal well, and determine the rock type and porosity properties of each layer unit based on the logging curve data and geological exploration data; Select one of the multiple segment units as the target segment unit, and generate a local mesh model of the target segment unit based on the rock type and porosity properties of the target segment unit; Based on the deviation values ​​between the measured temperature and pressure data at the monitoring points and the corresponding nodes in the local mesh model, the material properties of the local mesh model are corrected. The corrected local mesh models are then stitched together to obtain the corrected digital twin geological model.

3. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 2, characterized in that, The initial state parameters of heat conduction at multiple spatial nodes within the initial thermal reservoir model are determined using measured temperature data from monitoring points. Based on the initial thermal reservoir model and the initial state parameters of heat conduction, a thermofluid coupling simulation is performed to obtain the temperature evolution data and pressure evolution data of each spatial node within a preset time period, including: Obtain the injection flow rate and injection temperature data of the target geothermal well, and use the injection flow rate and injection temperature data as the heat source boundary conditions; Using the rock type and porosity properties of each spatial node in the corrected digital twin geological model as permeability constraints, the initial thermal conduction initialization process of the initial thermal reservoir model is performed based on the heat source boundary conditions and permeability constraints to obtain the initial state parameters of thermal conduction. The initial state parameters of heat conduction are input into the thermo-fluid coupling simulation engine, and the heat diffusion process and fluid transport process of each spatial node within a preset time period are jointly simulated to obtain temperature evolution data and pressure evolution data.

4. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 3, characterized in that, Based on temperature and pressure evolution data, the thermal energy extraction potential value of each spatial node is determined. Based on this potential value, the thermal energy extraction zones in the digital twin geological model are divided into regions, resulting in thermal energy extraction zone identification data, including: For each spatial node, obtain the temperature drop value of the temperature evolution data of the current spatial node and the pressure change rate value of the pressure evolution data within a preset time period; The thermal response intensity value of the space node is calculated based on the weighted combination of the temperature drop value and the pressure change rate value. The thermal response intensity value of each spatial node is compared with the preset potential threshold. The spatial nodes with values ​​higher than the potential threshold are marked as high-efficiency heating zones, and the spatial nodes with values ​​lower than the potential threshold are marked as low-efficiency heating zones, thus obtaining heating zone identification data.

5. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 4, characterized in that, Based on the heat extraction zone identification data and the temperature evolution data corresponding to each spatial node, multi-scenario simulations were performed on the heat extraction scheme of the target geothermal well to obtain cumulative heat production data under different combinations of heat extraction parameters, including: Multiple sets of candidate heat harvesting parameter combinations are obtained, wherein each set of candidate heat harvesting parameter combinations includes heat harvesting rate parameters and reinjection temperature parameters; For each candidate combination of heating parameters, the range of the corresponding high-efficiency heating section is determined based on the heating zone identification data, and the remaining heat energy reserve value within each high-efficiency heating section is determined based on the temperature evolution data. Based on the remaining thermal energy reserves and the thermal recovery rate and reinjection temperature parameters in the candidate thermal recovery parameter combinations, the thermal balance state of the target geothermal well in multiple consecutive production cycles is iteratively extrapolated to obtain the cumulative heat production data corresponding to each candidate thermal recovery parameter combination.

6. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 5, characterized in that, Based on the accumulated heat production data, the long-term heat recovery strategy of the target geothermal well is optimized and evaluated to obtain an optimized scheme for heat energy extraction from the target geothermal well, including: Obtain equipment life data and economic assessment data for the target geothermal well, and determine the maximum allowable production life parameters based on the equipment life data; The unit heat production cost and wellbore heat loss rate of each candidate heat production parameter combination are calculated based on cumulative heat production data and economic evaluation data. The unit heat production cost, wellbore heat loss rate, and maximum allowable production years are comprehensively evaluated. The candidate heat extraction parameter combination with the highest comprehensive score is selected as the recommended scheme, and an optimized heat extraction scheme is generated based on the recommended scheme.

7. The method for simulating and extrapolating geothermal well thermal energy extraction data based on digital twins according to claim 6, characterized in that, Based on a comprehensive evaluation of unit heat production cost, wellbore heat loss rate, and maximum allowable production years, the candidate heat extraction parameter combination with the highest comprehensive score is selected as the recommended scheme. An optimized heat extraction scheme is then generated based on the recommended scheme, including: The comprehensive score of the candidate heat production parameter combination is obtained by superimposing the unit heat production cost value, the wellbore heat loss rate value, and the sub-item scores corresponding to the maximum allowable production years parameter. The comprehensive scores of all candidate heat harvesting parameter combinations are ranked, and the candidate heat harvesting parameter combination ranked first is selected as the recommended scheme. An optimized heat extraction scheme is generated based on the heat extraction rate parameters and reinjection temperature parameters in the recommended scheme; the optimized heat extraction scheme includes scheduling instructions for each production cycle.

Images