Hydrothermal geothermal energy large well factory well arrangement method and system

Abstract

The present application relates to a kind of water hot type geothermal energy large well factory well distribution method and system, belong to geothermal resource development technical field.The method includes: using geological radar, laser scanner and at least two kinds of seismic wave detection technology to obtain three-dimensional geological data;After data fusion, construct multi-source three-dimensional geological data body and establish parameterized equipment model;Well group layout scheme is generated using genetic algorithm or particle swarm optimization algorithm, and after collision detection verification, fluid flow and heat transfer simulation analysis are executed;For well distribution parameters (well spacing, well quantity ratio, etc.) Input adjustment value, calculate predicted value by geothermal development prediction model and verify that it meets heat storage operation benchmark, output instruction value;Integrate model to generate visual construction scheme, combined with AR technology to assist field construction;Based on machine learning, predict heat storage attenuation trend and dynamically optimize well group management.The system corresponds to include data acquisition, processing modeling, optimization simulation, visual decision module.The present application improves geological modeling precision, heat storage utilization rate and construction efficiency, reduces well interference.

Description

Technical Field

[0001] This invention relates to the field of underground space exploration and geothermal resource development technology, specifically to a well layout method and system for a large-scale hydrothermal geothermal energy well plant, and particularly to a method and system for underground space three-dimensional modeling and geothermal development optimization based on multi-technology integration. Background Technology

[0002] In the development of underground space and the utilization of geothermal resources, accurate acquisition of underground geological structure information, rational layout of geothermal development equipment, and optimization of development plans are crucial. Traditional underground space exploration technologies often suffer from problems such as limited data and insufficient accuracy, making it difficult to fully reflect the complex underground geological structure. Furthermore, the layout of geothermal development equipment and the design of development plans lack scientific optimization methods, resulting in low reservoir utilization rates, significant inter-well interference, and poor resource development benefits. Therefore, there is an urgent need for a technical solution that can integrate multiple exploration technologies, achieve accurate underground space modeling, and combine optimization algorithms to realize efficient geothermal development planning. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a well layout method and system for a large-scale hydrothermal geothermal well plant, which solves the above-mentioned technical problems.

[0004] The main objective of this application is to provide a well layout method for a large-scale hydrothermal geothermal well plant, comprising the following steps:

[0005] Utilize at least two underground space exploration technologies to acquire three-dimensional geological data of the target area;

[0006] Construct a multi-source fused three-dimensional geological data volume and establish a three-dimensional parametric model of geothermal well factory equipment;

[0007] A well cluster layout scheme is generated based on an optimization algorithm, and equipment operation simulation analysis is performed after collision detection.

[0008] For the well layout parameters in the well group layout scheme, input parameter adjustment values, calculate the first predicted value through the geothermal development prediction model, and determine whether the first predicted value meets the thermal storage operation benchmark.

[0009] Input the margin verification value of the well placement parameter adjustment amount being greater than the parameter adjustment value into the prediction model, calculate the second prediction value, and determine whether the second prediction value meets the thermal storage operation benchmark.

[0010] When both the first and second predicted values ​​meet the thermal storage operation benchmark, the output parameter adjustment value is used as the well placement parameter command value.

[0011] Integrate models and command values ​​to generate visual construction plans.

[0012] Furthermore, the optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm;

[0013] The well placement parameters include well spacing, injection well / production well ratio, drilling depth, or pipeline orientation angle.

[0014] The parameter adjustment value is set as an integer multiple of the benchmark adjustment amount ΔP, which is dynamically determined based on the stratigraphic lithology parameters and fracture distribution density obtained from seismic wave inversion.

[0015] Furthermore, when there are multiple parameter adjustment values ​​that meet the operating benchmark of the thermal storage, the parameter adjustment value with the largest operating benchmark margin relative to the thermal energy extraction efficiency or equipment operating stability is selected.

[0016] The margin is dynamically calculated based on the thermal reservoir permeability heterogeneity coefficient of the three-dimensional geological data volume.

[0017] Furthermore, the geothermal development prediction model outputs a probability distribution defined by the mean and variance of the predicted values ​​of the geothermal reservoir decay trend;

[0018] When the first predicted value and the second predicted value corresponding to the first variance value do not meet the thermal storage operation benchmark, the smaller second variance value is used to recalculate and determine the result.

[0019] The variance value is calibrated based on the confidence level of the three-dimensional geological data volume, and the calibration basis is the consistency between the core data and the exploration data.

[0020] Furthermore, half of the adjustment amount corresponding to the margin verification value is set as the parameter adjustment value;

[0021] When ΔP / 2 has a decimal value, round it to the nearest whole number to increase the thermal storage utilization margin.

[0022] Furthermore, for the selected well placement parameters, a stepwise verification is performed:

[0023] Determine whether the first predicted value corresponding to the parameter adjustment values ​​with adjustment amounts of ΔP×1, ΔP×2, ..., ΔP×M / 2 all meet the thermal storage operation benchmark;

[0024] Determine whether the second predicted value corresponding to the margin verification value of the adjustment amount ΔP×(M / 2+1), ΔP×(M / 2+2), ..., ΔP×M all meet the thermal storage operation benchmark.

[0025] If satisfied, the output adjustment amount is ΔP×M / 2, which is the parameter adjustment value used as the command value; where M is an even number, and the value of M is determined based on the ratio of the thermal reservoir volume to the single well control area.

[0026] Furthermore, when a combination that meets the operating benchmark of the thermal reservoir cannot be found for the current well placement parameters, the search is switched to other well placement parameters with the second highest contribution.

[0027] The contribution ranking is as follows: well spacing > injection well / production well ratio > drilling depth > pipeline inclination angle;

[0028] The contribution was determined through sensitivity analysis using Monte Carlo simulations, with the inputs being the fracture connectivity parameters and reservoir porosity of the three-dimensional geological data volume.

[0029] Furthermore, the instruction value is triggered to be output under any of the following conditions:

[0030] (A) Abnormal reservoir pressure or excessive inter-well interference was detected;

[0031] (B) The thermal energy extraction efficiency of the current well cluster layout deviates from the benchmark value by more than 15%;

[0032] (C) The predicted thermal reservoir decay trend based on real-time drilling data does not meet the long-term operating benchmark.

[0033] This invention also provides a hydrothermal geothermal energy large-scale well factory well layout system, comprising:

[0034] Data acquisition module: used to acquire three-dimensional geological data of the target area using at least two underground space exploration technologies;

[0035] Data processing and modeling module: includes data preprocessing unit, data fusion unit, and model building unit;

[0036] The data preprocessing unit performs noise reduction, filtering, and interpolation on the three-dimensional geological data.

[0037] The data fusion unit constructs a multi-source fused three-dimensional geological data volume and dynamically updates the model parameters;

[0038] The model building unit establishes a three-dimensional parametric model of the geothermal well factory equipment;

[0039] Optimization and Simulation Module: Includes optimization algorithm unit, collision detection unit, and simulation analysis unit;

[0040] The optimization algorithm unit generates a well group layout scheme based on genetic algorithm or particle swarm optimization algorithm, combined with geological conditions and construction cost constraints.

[0041] The collision detection unit verifies spatial conflicts between equipment and automatically adjusts the well spacing and pipeline routing.

[0042] The simulation analysis unit performs equipment operation simulations involving fluid flow and heat transfer.

[0043] Visualization and Decision Module: Includes predictive analytics unit;

[0044] Integrate 3D geological models, equipment models, and layout schemes to generate visualized construction drawings;

[0045] Predict the thermal reservoir decay trend using machine learning models and dynamically optimize well cluster management strategies.

[0046] This technology utilizes AR to enable real-time overlay of virtual models onto actual construction scenes.

[0047] Furthermore, the optimization algorithm unit is configured as follows:

[0048] When the well placement parameters cannot meet the benchmark for thermal reservoir operation, the system is sorted by contribution (well spacing > injection well / production well ratio > drilling depth > pipeline inclination) and then switched to the second highest parameter for re-search.

[0049] The contribution was determined through sensitivity analysis of Monte Carlo simulation, with the inputs being the fracture connectivity parameters and reservoir porosity of the three-dimensional geological data volume;

[0050] The predictive analysis unit is configured as follows:

[0051] The probability distribution of the thermal reservoir decay trend is output based on the geothermal development prediction model;

[0052] When the predicted value does not meet the operating baseline, the model is recalibrated using a lower variance value. The calibration is based on the degree of agreement between the core data and the detection data. Attached Figure Description

[0053] Figure 1 This is a flowchart of the method of the present invention;

[0054] Figure 2 This is a schematic diagram of the system framework principle in this invention. Detailed Implementation

[0055] 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.

[0056] Reference Figure 1 and Figure 2The main objective of this application is to provide a well layout method for a large-scale geothermal well plant, comprising the following steps: acquiring three-dimensional geological data of the target area using at least two underground space exploration technologies; constructing a multi-source fused three-dimensional geological data volume and establishing a three-dimensional parametric model of the geothermal well plant equipment; generating a well group layout scheme based on an optimization algorithm, and performing equipment operation simulation analysis after collision detection; inputting parameter adjustment values ​​for the well layout parameters in the well group layout scheme, calculating a first predicted value through a geothermal development prediction model, and determining whether the first predicted value meets the thermal reservoir operation benchmark; inputting a margin verification value where the adjustment amount of the well layout parameters is greater than the parameter adjustment value into the prediction model, calculating a second predicted value, and determining whether the second predicted value meets the thermal reservoir operation benchmark; when both the first and second predicted values ​​meet the thermal reservoir operation benchmark, outputting the parameter adjustment value as the well layout parameter instruction value; and integrating the model and instruction value to generate a visualized construction scheme.

[0057] Furthermore, the optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm; the well placement parameters include well spacing, injection well / production well ratio, drilling depth or pipeline orientation angle; the parameter adjustment value is set as an integer multiple of the benchmark adjustment amount ΔP, and ΔP is dynamically determined based on the formation lithology parameters and fracture distribution density obtained from seismic wave inversion.

[0058] Furthermore, when there are multiple parameter adjustment values ​​that meet the operating benchmark of the thermal reservoir, the parameter adjustment value with the largest operating benchmark margin relative to the thermal energy extraction efficiency or equipment operating stability is selected; the margin is dynamically calculated based on the thermal reservoir permeability heterogeneity coefficient of the three-dimensional geological data volume.

[0059] Furthermore, the geothermal development prediction model outputs a probability distribution defined by the average and variance of the predicted values ​​of the geothermal reservoir decay trend; when the first predicted value and the second predicted value corresponding to the first variance value do not meet the benchmark for geothermal reservoir operation, a smaller second variance value is used to recalculate and determine the result; the variance value is calibrated based on the confidence level of the three-dimensional geological data volume, and the calibration basis is the degree of agreement between the borehole core data and the exploration data.

[0060] Furthermore, half of the adjustment amount corresponding to the margin verification value is set as the parameter adjustment value; when ΔP / 2 has a decimal, it is rounded up in the direction of increasing the thermal storage utilization margin.

[0061] Furthermore, for the selected well placement parameters, a tiered verification is performed: it is determined whether the first predicted values ​​corresponding to the parameter adjustment values ​​with adjustment amounts of ΔP×1, ΔP×2, ..., ΔP×M / 2 all meet the thermal reservoir operation benchmark; it is determined whether the second predicted values ​​corresponding to the margin verification values ​​with adjustment amounts of ΔP×(M / 2+1), ΔP×(M / 2+2), ..., ΔP×M all meet the thermal reservoir operation benchmark; if they meet the benchmark, the parameter adjustment value with an adjustment amount of ΔP×M / 2 is output as the command value; where M is an even number, and the value of M is determined based on the ratio of the thermal reservoir volume to the single well control area.

[0062] Furthermore, when a combination of well placement parameters that meets the operating benchmark of the thermal reservoir cannot be found for the current well placement parameters, the search is switched to other well placement parameters with the second highest contribution. The contribution ranking is as follows: well spacing > injection well / production well ratio > drilling depth > pipeline inclination angle. The contribution is determined by sensitivity analysis of Monte Carlo simulation, and the input is the fracture connectivity parameter and thermal reservoir porosity of the three-dimensional geological data volume.

[0063] Furthermore, the command value output will be triggered under any of the following circumstances: (A) abnormal reservoir pressure or excessive inter-well interference is detected; (B) the thermal energy extraction efficiency of the current well group layout deviates from the benchmark value by more than 15%; (C) the reservoir decay trend predicted based on real-time drilling data does not meet the long-term operating benchmark.

[0064] This invention also provides a well layout system for a large-scale geothermal well factory, comprising: a data acquisition module for acquiring three-dimensional geological data of a target area using at least two underground space exploration technologies; a data processing and modeling module including a data preprocessing unit, a data fusion unit, and a model building unit; the data preprocessing unit performs noise reduction, filtering, and interpolation processing on the three-dimensional geological data; the data fusion unit constructs a multi-source fused three-dimensional geological data volume and dynamically updates model parameters; the model building unit establishes a three-dimensional parametric model of the geothermal well factory equipment; an optimization and simulation module including an optimization algorithm unit, a collision detection unit, and a simulation analysis unit; the optimization algorithm unit generates a well group layout scheme based on a genetic algorithm or particle swarm optimization algorithm, combined with geological conditions and construction cost constraints; the collision detection unit verifies equipment spatial conflicts and automatically adjusts well spacing and pipeline routing; the simulation analysis unit performs equipment operation simulation of fluid flow and heat transfer; and a visualization and decision-making module including a predictive analysis unit; integrating the three-dimensional geological model, equipment model, and layout scheme to generate a visualized construction drawing; predicting the thermal reservoir decay trend through a machine learning model and dynamically optimizing the well group management strategy; and realizing real-time overlay of the virtual model and the actual construction scene based on AR technology.

[0065] Furthermore, the optimization algorithm unit is configured as follows: when the well placement parameters cannot meet the operating benchmark of the thermal reservoir, the second highest parameter is switched to be searched again according to the contribution ranking (well spacing > injection well / production well ratio > drilling depth > pipeline inclination angle); the contribution is determined by the sensitivity analysis of Monte Carlo simulation, and the input is the fracture connectivity parameter of the three-dimensional geological data volume and the thermal reservoir porosity.

[0066] The predictive analysis unit is configured to output the probability distribution of the thermal reservoir decay trend based on the geothermal development prediction model; when the predicted value does not meet the operating benchmark, the model is recalibrated using a lower variance value, and the calibration basis is the consistency between the borehole core data and the detection data.

[0067] The technical principle of this application is based on the deep coupling of four major technology chains: multi-source underground space exploration data fusion, parametric equipment modeling, well cluster layout generation and verification driven by intelligent optimization algorithms, and dynamic prediction decision-making closed loop. Specifically, three-dimensional geological data of the target area is acquired through at least two combinations of ground-penetrating radar, laser scanner, and seismic wave detection technologies. After the data preprocessing unit performs denoising, filtering, and interpolation algorithms to eliminate data loss and noise interference, the data fusion unit integrates the heterogeneous data into a multi-source fused three-dimensional geological data volume based on spatial coordinate matching and feature weighting algorithms, and simultaneously and dynamically updates key parameters such as the heterogeneity coefficient of geothermal reservoir permeability and fracture distribution density. At the same time, a geothermal well factory equipment library (covering well casings, heat exchangers, pipelines, etc.) is constructed using parametric modeling tools, and the three-dimensional models of the equipment are imported into the geological spatial coordinate system. During the well layout optimization phase, the optimization algorithm unit employs either a genetic algorithm or a particle swarm optimization algorithm, with the dual objective function of maximizing reservoir utilization and minimizing inter-well interference. It generates an initial well group layout scheme by combining geological conditions (such as formation dip limits), construction constraints (drilling depth thresholds), and economic costs (pipeline material cost weights). The collision detection unit verifies the feasibility of equipment installation using a spatial envelope detection algorithm. When the well spacing is identified as less than the safety threshold or the pipeline direction conflicts with the direction of rock fractures, an automatic parameter adjustment mechanism is triggered: adjustment values ​​for well spacing, injection well / production well ratio, drilling depth, or pipeline direction angle are set as integer multiples of the baseline adjustment amount ΔP. These values ​​are then input into the geothermal development prediction model to calculate the first predicted value (reservoir pressure). The force field / temperature field distribution is used to determine whether it meets the operating benchmarks of the thermal reservoir (such as pressure fluctuation threshold ±10%, temperature decay rate ≤5% / year). If it meets the benchmarks, the adjustment amount is further expanded to a margin verification value of ΔP×M (M is an even number determined based on the ratio of thermal reservoir volume to single well control area) and input into the model to calculate the second predicted value. When both predicted values ​​pass the benchmark verification, ΔP×M / 2 is output as the well placement parameter command value. If the current parameter combination cannot meet the benchmark, it is sorted by contribution (well spacing > injection well / production well ratio > drilling depth > pipeline inclination) and switched to the second highest parameter for re-search. This contribution is determined by the sensitivity analysis of Monte Carlo simulation. The input quantities are the fracture connectivity parameters and thermal reservoir porosity of the three-dimensional geological data volume.The simulation analysis unit, based on the principles of computational fluid dynamics and heat transfer, uses multiphysics coupling simulation software to simulate the fluid flow and heat transfer processes corresponding to command values. It analyzes the heat extraction efficiency and equipment stress distribution under different operating conditions (flow rate 20-50 kg / s, temperature 150-200℃, pressure 15-25 MPa). The visualization and decision-making module integrates simulation results to generate 3D construction drawings and AR overlay models (achieving millimeter-level alignment between the virtual equipment model and the actual scene through SLAM algorithm). The predictive analysis unit, through a machine learning model (inputting historical production data, real-time drilling data, and environmental monitoring data), outputs the probability distribution of the thermal reservoir decay trend (mean reflecting the predicted value). The variance characterizes the prediction uncertainty (the decay rate over time). The variance value is calibrated based on the consistency between the core data and the exploration data (the variance is compressed by 30% when the consistency is ≥90%). When abnormal geothermal reservoir pressure is detected (fluctuation exceeds ±15%), the deviation between the thermal energy extraction efficiency and the benchmark value is >15%, or the predicted geothermal reservoir decay trend breaks through the long-term operating benchmark, the system triggers a dynamic update mechanism for the command value: recalibrate the variance of the geothermal development prediction model (using a lower variance value to improve the prediction confidence), update the fracture connectivity parameters of the three-dimensional geological data body in combination with the latest drilling data, and restart the step-by-step verification process (the adjustment amount is verified step by step from ΔP×1 to ΔP×M / 2) until a new command value is output. The innovation of this technology chain lies in: establishing for the first time a dynamic calculation model for the ΔP benchmark adjustment (ΔP=α·rock compressive strength / fracture density+β·thermal reservoir porosity, where α and β are calibration coefficients), realizing quantitative control of parameter adjustment; ensuring the robustness of the scheme through a step-by-step two-level verification mechanism (the first predicted value verifies the basic feasibility, and the second predicted value checks the safety margin); and significantly improving optimization efficiency through a contribution-driven parameter switching strategy.

[0068] In the foregoing description, examples have been described with reference to specific exemplary embodiments. However, it will be apparent that various modifications and changes can be made to the specific examples without departing from the scope set forth in the appended claims, and the claims are not limited to the specific examples described above.

Claims

1. A well layout method for a large-scale hydrothermal geothermal well plant, characterized in that, Includes the following steps: Utilize at least two underground space exploration technologies to acquire three-dimensional geological data of the target area; Construct a multi-source fusion three-dimensional geological data volume, synchronously and dynamically update key parameters such as the heterogeneity coefficient of geothermal reservoir permeability and fracture distribution density, and establish a three-dimensional parametric model of geothermal well factory equipment; A well cluster layout scheme is generated based on an optimization algorithm, and after collision detection, equipment operation simulation analysis is performed. The optimization algorithm is either a genetic algorithm or a particle swarm optimization algorithm. The optimization algorithm unit uses a genetic algorithm or a particle swarm optimization algorithm, combined with geological conditions, construction constraints, and economic costs, to generate an initial well cluster layout scheme. For the well layout parameters in the well cluster layout scheme, input parameter adjustment values ​​are used, and the first predicted value is calculated through the geothermal development prediction model to determine whether the first predicted value meets the thermal reservoir operation benchmark; the geothermal development prediction model outputs a probability distribution defined by the average and variance of the predicted value of thermal reservoir decay trend. Input the margin verification value of the well placement parameter adjustment amount being greater than the parameter adjustment value into the prediction model, calculate the second prediction value, and determine whether the second prediction value meets the thermal storage operation benchmark. When both the first and second predicted values ​​meet the thermal storage operation benchmark, the output parameter adjustment value is used as the well placement parameter command value; half of the adjustment amount corresponding to the margin verification value is set as the parameter adjustment value. Integrate models and command values ​​to generate visualized construction plans; The well placement parameters include well spacing, injection well / production well ratio, drilling depth, or pipeline orientation angle. The parameter adjustment value is set as an integer multiple of the benchmark adjustment amount ΔP, which is dynamically determined based on the stratigraphic lithology parameters and fracture distribution density obtained from seismic wave inversion; when ΔP / 2 has a decimal, it is rounded up in the direction of increasing the thermal reservoir utilization margin. When multiple parameter adjustment values ​​meet the operating benchmark of thermal storage, the parameter adjustment value is selected; the parameter adjustment value has the largest operating benchmark margin relative to the thermal energy extraction efficiency or equipment operating stability. The margin is dynamically calculated based on the thermal reservoir permeability heterogeneity coefficient of the three-dimensional geological data volume.

2. The well layout method for a large-scale hydrothermal geothermal well plant according to claim 1, characterized in that: When the first predicted value and the second predicted value corresponding to the first variance value do not meet the thermal storage operation benchmark, the smaller second variance value is used to recalculate and determine the result. The variance value is calibrated based on the confidence level of the three-dimensional geological data volume, and the calibration basis is the consistency between the core data and the exploration data.

3. The well layout method for a large-scale hydrothermal geothermal well plant according to claim 1, characterized in that: Perform stepwise verification for the selected well placement parameters: Determine whether the first predicted value corresponding to the parameter adjustment values ​​with adjustment amounts of ΔP×1, ΔP×2, ..., ΔP×M / 2 all meet the thermal storage operation benchmark; Determine whether the second predicted value corresponding to the margin verification value of the adjustment amount ΔP×(M / 2+1), ΔP×(M / 2+2), ..., ΔP×M all meet the thermal storage operation benchmark. If satisfied, the output adjustment amount is ΔP×M / 2, which is the parameter adjustment value used as the command value; where M is an even number, and the value of M is determined based on the ratio of the thermal reservoir volume to the single well control area.

4. The well layout method for a large-scale hydrothermal geothermal well plant according to claim 1, characterized in that: When a combination of well layout parameters that meets the operating benchmark of the thermal reservoir cannot be found for the current well layout parameters, switch to other well layout parameters with the second highest contribution and search again. The contribution ranking is as follows: well spacing > injection well / production well ratio > drilling depth > pipeline inclination angle; The contribution was determined through sensitivity analysis using Monte Carlo simulations, with the inputs being the fracture connectivity parameters and reservoir porosity of the three-dimensional geological data volume.

5. The well layout method for a large-scale hydrothermal geothermal well plant according to claim 1, characterized in that, The instruction value will be output under any of the following conditions: (A) Abnormal reservoir pressure or excessive inter-well interference was detected; (B) The thermal energy extraction efficiency of the current well cluster layout deviates from the benchmark value by more than 15%; (C) The predicted thermal reservoir decay trend based on real-time drilling data does not meet the long-term operating benchmark.

6. A well placement system for a large-scale hydrothermal geothermal well factory, comprising the well placement method described in claim 1, characterized in that, include: Data acquisition module: used to acquire three-dimensional geological data of the target area using at least two underground space exploration technologies; Data processing and modeling module: includes data preprocessing unit, data fusion unit, and model building unit; The data preprocessing unit performs noise reduction, filtering, and interpolation on the three-dimensional geological data. The data fusion unit constructs a multi-source fused three-dimensional geological data volume and dynamically updates the model parameters; The model building unit establishes a three-dimensional parametric model of the geothermal well factory equipment; Optimization and Simulation Module: Includes optimization algorithm unit, collision detection unit, and simulation analysis unit; The optimization algorithm unit uses a genetic algorithm or a particle swarm optimization algorithm to generate an initial well group layout scheme by combining geological conditions, construction constraints, and economic costs. The collision detection unit verifies spatial conflicts between equipment and automatically adjusts the well spacing and pipeline routing. The simulation analysis unit performs equipment operation simulations involving fluid flow and heat transfer. Visualization and Decision Module: Includes predictive analytics unit; Integrate 3D geological models, equipment models, and layout schemes to generate visualized construction drawings; Predict the thermal reservoir decay trend using machine learning models and dynamically optimize well cluster management strategies. This technology utilizes AR to enable real-time overlay of virtual models onto actual construction scenes.

7. The hydrothermal geothermal energy large-scale well factory well layout system according to claim 6, characterized in that, The optimization algorithm unit is configured as follows: When the well placement parameters cannot meet the benchmark for thermal reservoir operation, the system is sorted by contribution (well spacing > injection well / production well ratio > drilling depth > pipeline inclination) and then switched to the second highest parameter for re-search. The contribution was determined through sensitivity analysis of Monte Carlo simulation, with the inputs being the fracture connectivity parameters and reservoir porosity of the three-dimensional geological data volume; The predictive analysis unit is configured as follows: The probability distribution of the thermal reservoir decay trend is output based on the geothermal development prediction model; When the predicted value does not meet the operating baseline, the model is recalibrated using a lower variance value. The calibration is based on the degree of agreement between the core data and the detection data.

Images