Hydrothermal geothermal exploitation full-period dynamic evaluation system based on cloud platform

Abstract

The invention provides a hydrothermal geothermal exploitation full-period dynamic evaluation system based on a cloud platform, and relates to the technical field of geothermal exploitation evaluation systems. According to the method, temperature, pressure, flow, well depth, underground water level, hydrological structure data and geological structure data are collected cooperatively through multiple sensors, and a cleaning data set is formed through denoising, calibration, complementation, standardization and integration; constructing, assimilating and updating a geological dynamic model with dynamic uncertainty, and extracting input parameters of an updated calculation model; simulation and benefit, environment and risk assessment are carried out in extreme and policy scenes, an index framework and a time axis are established, and compliance checking and scoring are completed; and further mapping an evaluation result into an operation constraint, constructing rolling optimization and outputting adaptive operation control information, and realizing data-model-evaluation-control closed loop and online optimization.

Description

Technical Field

[0001] This invention relates to the field of geothermal extraction assessment system technology, and in particular to a dynamic evaluation system for the entire life cycle of hydrothermal geothermal extraction based on a cloud platform. Background Technology

[0002] Currently, hydrothermal geothermal extraction technology mainly relies on single monitoring data acquisition and simplified geological models for operation. Existing technologies typically use basic data such as temperature, pressure, and flow rate for real-time monitoring, but these systems often lack integration of geological structural data and are limited to processing only a single data source. Furthermore, existing geothermal extraction systems mostly focus on short-term operational monitoring, failing to provide dynamic assessments of the entire geothermal extraction cycle, and exhibit poor adaptability to geological changes, thus failing to effectively address the impacts of extreme conditions or policy shifts.

[0003] With the development of information technology and cloud computing, geothermal extraction systems based on big data and cloud platforms are gradually becoming mainstream. Future geothermal extraction systems will be able to integrate more sensor data, not just temperature and pressure, but also collect multi-dimensional data such as geological structures and environmental scenarios in real time, and perform unified processing and analysis. In particular, with the continuous development of policies, regulations, and scenarios, the need for dynamic assessment of geothermal extraction systems is becoming increasingly strong. More and more research is beginning to focus on how to use big data analysis and dynamic models to more accurately predict the long-term impacts of extreme scenarios and policy responses on geothermal extraction systems.

[0004] The main drawback of existing geothermal extraction technologies lies in the lack of comprehensive modeling and long-term assessment capabilities for dynamic geological changes. Existing systems largely rely on basic monitoring data for real-time adjustments, lacking the ability to assess extreme scenarios and policy changes. Traditional assessment methods typically depend on simplified static models or localized data, leading to significant prediction errors in extraction benefits and environmental impacts, and failing to make timely adjustments based on actual changes. Furthermore, existing technologies fail to provide comprehensive decision support, lacking flexible, multi-dimensional optimization suggestions, and thus cannot effectively support geothermal extraction decisions in complex geological and policy environments. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, the purpose of this invention is to provide a dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform. This invention solves the problem that existing geothermal extraction systems lack the ability to integrate multi-dimensional data and dynamically evaluate extreme scenarios, and are unable to cope with the challenges brought about by complex geological changes and policy shifts.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A cloud-based dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction, characterized by comprising:

[0008] The data acquisition module is used to collect key data and geological structure data in real time during the hydrothermal geothermal extraction process through multiple sensors;

[0009] The data transmission module is used to wirelessly upload the key data and geological structure data to the cloud platform.

[0010] The data processing module is used to perform denoising, calibration, completion and standardization on the key data and geological structure data on the cloud platform to obtain a processed clean dataset.

[0011] The geological dynamic modeling module is used to establish a geothermal geological model with dynamic uncertainty based on the processed cleaned dataset to simulate the impact of geological structure changes on the geothermal extraction system and update the input parameters of the relevant calculation model, thus obtaining the geological dynamic model and the updated calculation model input parameters.

[0012] The extreme scenario and policy response assessment module is used to assess the impact of simulated extreme scenarios and policy change scenarios on geothermal extraction based on the input parameters of the geological dynamic model and the updated calculation model, and obtains the extraction benefits, environmental impact and risk assessment results under extreme scenarios and policy responses;

[0013] The adaptive geological operation collaborative assimilation and rolling optimization module is used to perform collaborative assimilation and rolling optimization on the geological dynamic model based on the geological dynamic model and the mining benefit assessment results, environmental impact assessment results and risk assessment results under the extreme scenarios and policy responses, so as to obtain the assimilated and updated geological dynamic model and adaptive operation control information.

[0014] The evaluation and analysis module is used to conduct a full-cycle dynamic evaluation of the geothermal extraction system based on the mining benefit assessment results, environmental impact assessment results, and risk assessment results under the extreme scenarios and policy responses, and in combination with the assimilated and updated geological dynamic model and adaptive operation control information, and obtains the full-cycle dynamic evaluation results.

[0015] The present invention discloses the following technical effects:

[0016] This invention provides a cloud-based dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction, comprising: a data acquisition module for real-time acquisition of key data and geological structure data during the hydrothermal geothermal extraction process using multiple sensors; a data transmission module for wirelessly uploading the key data and geological structure data to a cloud platform; a data processing module for denoising, calibrating, completing, and standardizing the key data and geological structure data on the cloud platform to obtain a processed clean dataset; a geological dynamic modeling module for establishing a geothermal geological model with dynamic uncertainty based on the processed clean dataset to simulate the impact of geological structure changes on the geothermal extraction system and update the input parameters of the relevant calculation model, thus obtaining the geological dynamic model and updated calculation model input parameters; and an extreme scenario and policy response assessment module for evaluating the geological structure and geological structure data based on the data acquisition process. The system evaluates the impact of extreme scenarios and policy changes on geothermal extraction using input parameters from a dynamic geological model and an updated computational model. This yields extraction benefits, environmental impacts, and risk assessments under extreme scenarios and policy responses. An adaptive geological operation collaborative assimilation and rolling optimization module performs collaborative assimilation and rolling optimization on the geological dynamic model based on the dynamic geological model and the extraction benefit, environmental impact, and risk assessments under extreme scenarios and policy responses. This results in an assimilated and updated geological dynamic model and adaptive operation control information. An evaluation and analysis module performs a full-cycle dynamic evaluation of the geothermal extraction system based on the extraction benefit, environmental impact, and risk assessments under extreme scenarios and policy responses, combined with the assimilated and updated geological dynamic model and adaptive operation control information. This yields a full-cycle dynamic evaluation result. The cloud-based hydrothermal geothermal extraction full-cycle dynamic evaluation system provided by this invention solves the problems of single geothermal extraction data and lack of dynamism and flexibility in existing technologies. By collecting key data and geological structure data in real time through multiple sensors and combining the data with a cloud platform for unified processing, modeling, and analysis, the system can dynamically adapt to geological changes and accurately simulate geological structural changes during the extraction process. The extreme scenario and policy response assessment module further enhances the system's ability to cope with extreme environments and policy changes, enabling real-time assessment of extraction benefits, environmental impacts, and risks. This system not only improves geothermal extraction efficiency but also provides precise data support for environmental protection and policy adjustments, demonstrating significant application prospects and social benefits. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a cloud-based dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction, provided in an embodiment of the present invention.

[0019] Figure 2 A flowchart of a cloud-based dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction, provided in this embodiment of the invention;

[0020] Figure 3 A detailed flowchart of the data processing module provided in this embodiment of the invention. Detailed Implementation

[0021] 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.

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] like Figure 1 As shown, this invention provides a dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform, comprising:

[0024] The data acquisition module is used to collect key data and geological structure data in real time during the hydrothermal geothermal extraction process through multiple sensors;

[0025] The data transmission module is used to wirelessly upload the key data and geological structure data to the cloud platform.

[0026] The data processing module is used to perform denoising, calibration, completion and standardization on the key data and geological structure data on the cloud platform to obtain a processed clean dataset.

[0027] The geological dynamic modeling module is used to establish a geothermal geological model with dynamic uncertainty based on the processed cleaned dataset to simulate the impact of geological structure changes on the geothermal extraction system and update the input parameters of the relevant calculation model, thus obtaining the geological dynamic model and the updated calculation model input parameters.

[0028] The extreme scenario and policy response assessment module is used to assess the impact of simulated extreme scenarios and policy change scenarios on geothermal extraction based on the input parameters of the geological dynamic model and the updated calculation model, and obtains the extraction benefits, environmental impact and risk assessment results under extreme scenarios and policy responses;

[0029] The adaptive geological operation collaborative assimilation and rolling optimization module is used to perform collaborative assimilation and rolling optimization on the geological dynamic model based on the geological dynamic model and the mining benefit assessment results, environmental impact assessment results and risk assessment results under the extreme scenarios and policy responses, so as to obtain the assimilated and updated geological dynamic model and adaptive operation control information.

[0030] The evaluation and analysis module is used to conduct a full-cycle dynamic evaluation of the geothermal extraction system based on the mining benefit assessment results, environmental impact assessment results, and risk assessment results under the extreme scenarios and policy responses, and in combination with the assimilated and updated geological dynamic model and adaptive operation control information, and obtains the full-cycle dynamic evaluation results.

[0031] Specifically, such as Figure 2 As shown, this embodiment also provides the corresponding system workflow as follows:

[0032] The data acquisition module first collects key data and geological structure data in real time during the hydrothermal geothermal extraction process using multiple sensors. The data transmission module then wirelessly uploads this data to the cloud platform. The data processing module performs noise reduction, calibration, completion, and standardization on the key data and geological structure data in the cloud, resulting in a cleaned dataset. The geological dynamic modeling module establishes a geothermal geological model with dynamic uncertainties based on the cleaned dataset to simulate the impact of geological structure changes on the extraction system and updates the input parameters of relevant calculation models accordingly, resulting in a geological dynamic model and updated calculation model input parameters. The extreme scenario and policy response assessment module uses the geological dynamic model and updated calculation model input parameters to assess the extraction benefits and environmental impact under extreme operating conditions and policy change scenarios. Risk assessments are conducted to obtain evaluation results under extreme scenarios and policy responses. Under the constraints and information guidance of the aforementioned evaluation results, the adaptive geological operation collaborative assimilation and rolling optimization module collaboratively assimilates the geological dynamic model and implements rolling optimization, outputting adaptive operation control information for online adjustment and forming an assimilated and updated geological dynamic model. The evaluation and analysis module combines the assimilated and updated geological dynamic model with the adaptive operation control information, and integrates the mining benefits, environmental impacts, and risk assessment results under extreme scenarios and policy responses to conduct a full-cycle dynamic evaluation of the geothermal extraction system, generating full-cycle dynamic evaluation results. The full-cycle dynamic evaluation results and adaptive operation control information are further fed back to the system, achieving a closed-loop drive for subsequent data acquisition, model iteration, and operation optimization.

[0033] Furthermore, the specific tasks of the data acquisition module are as follows:

[0034] In terms of refined acquisition of key data, this embodiment addresses the multi-source heterogeneous characteristics and time sensitivity of geothermal wells and their surrounding environment by establishing a unified timing and sampling strategy and clarifying the acquisition targets, frequencies, and quality control requirements for each sensor: Temperature sensors are deployed at designated depths and wellhead locations, acquiring water and wellhead temperatures at preset sampling frequencies, implementing range self-checks and abrupt threshold filtering to obtain temperature data; Pressure sensors are deployed in the stable section of the well, employing temperature-pressure compensation algorithms to eliminate temperature drift and triggering high-frequency sampling during pressure abrupt changes to obtain pressure data; Flow sensors are installed at the production manifold, using pulsation recognition and time window smoothing to suppress short-term disturbances to obtain flow data; Geothermal well depth sensors... The instrument uses a combination of wireline depth sounding and encoder displacement verification, periodically comparing with wellhead calibration points to eliminate cumulative errors, thus obtaining geothermal well depth data. Groundwater level sensors are deployed in adjacent observation wells, employing two-state sampling with static water level and pumping disturbance, and verifying stability values ​​using recovery curves, thus obtaining groundwater level data. Hydrological sensors are deployed at typical cross-sections of the surface and groundwater bodies, sampling in combination with cross-sectional velocity profiles and fixed-point water quality channels, yielding hydrological data including water quality, flow velocity, and water temperature. Geological structure sensors primarily use geophysical exploration and wellbore imaging to acquire stratigraphic thickness, fracture information, and relative positions between geological layers. Repeated survey lines and phase consistency checks ensure the spatial coherence of structural elements, thus obtaining geological structure data.

[0035] In this embodiment, for integrated data uplink services from edge to cloud, to prevent insufficient disclosure, the key implementation details of spatiotemporal alignment, channel calibration, and quality labeling are clarified: each sensor side injects high-precision timestamps with a unified time source and generates quality labels by channel. The quality labels include at least sampling status, saturation alarm, drift indication, and missing measurement identifier; the edge side first performs lightweight anomaly removal and dimensional consistency checks, and marks samples exceeding the physical reach range as pending verification; data uplink adopts two trigger modes: batch and event. Normal batch uploads retain complete time sequence, while event triggers send the front and back buffers together to retain context when sudden changes or exceeding limits occur; after receiving the data in the cloud, multi-channel data is synchronized with unified time synchronization. Temperature data, pressure data, flow data, geothermal well depth data, groundwater level data, hydrological data, and geological structure data are initially registered according to time windows and spatial correlation to form multi-source raw data packets with time consistency, resulting in a spatiotemporally consistent dataset that can be used for fusion processing.

[0036] Furthermore, such as Figure 3 As shown, the specific workflow of the data processing module is as follows:

[0037] In terms of denoising and anomaly handling, this embodiment addresses the multi-scale noise characteristics and sudden anomalies of key data and geological structural data, clarifying a reusable implementation path: First, channel feature thresholds and spectral priors are configured according to data type. For time series such as temperature, pressure, flow rate, and groundwater level, a two-stage filtering strategy of bandpass or lowpass plus robust smoothing is adopted. For geological structural data, frequency domain denoising and spatial neighborhood smoothing are used in synergistic processing. Then, outlier detection is performed, using a sliding window-based seasonal decomposition residual test and robust statistical distance method to identify peaks, drifts, and step changes. Samples that are physically unreachable or cross the rate limit are marked as anomalies and removed or downweighted. For the filtering boundary effect caused by continuous missing measurements, boundary distortion is reduced by splicing the front and back buffers and mirror extension. After completing the above processing, a structured denoising result and quality label are output, resulting in a denoised dataset.

[0038] In this embodiment, regarding calibration and completion, two calibration links are clearly defined: sensor-level and channel-level. The calibration submodule prioritizes the application of calibration coefficients from recent sources and bias terms generated from field comparison sources to perform joint zero-point and span corrections on temperature, pressure, and flow channels, and introduces temperature compensation curves to repair the effects of thermal drift. For geothermal well depth and groundwater level channels, regression correction is performed using a cumulative error model obtained from benchmark measuring points and multiple round trip measurements. For geological structural data, reference survey lines and standard reflectors are used to fine-tune the time-depth conversion parameters, unifying the spatial benchmark of structural elements, resulting in a calibrated dataset. The completion submodule handles different missing types separately: for short gaps, conformal splines or local weighted regression based on neighborhood trends are used for completion, maintaining the continuity of the first and second derivatives; for long gaps or event segment gaps, collaborative interpolation is performed under physical constraints combined with the covariance relationship of neighboring channels, such as inferring temperature trends using the constraint relationship between pressure and flow; for spatial voids in geological structural data, triangular meshes or voxel interpolation are used with structural boundaries as hard constraints to avoid misfilling of fracture crossings, resulting in a completed dataset.

[0039] In terms of standardization and data integration, this embodiment provides clear steps for ensuring consistency and usability of cross-source and cross-scale data: The standardization submodule adopts a robust normalization strategy for numerical channels, scaling them according to the historical quantile intervals of the channels while maintaining the monotonicity of their physical meaning. For construction parameters with dimensional differences, a combination of range mapping and z-score normalization is performed to suppress the influence of extreme values. Consistent encoding is used for classification or enumeration labels, and priority synthesis rules are established for quality labels, resulting in a standardized clean dataset. The data integration submodule unifies the time base and spatial index, aligning and converging multi-channel data such as temperature, pressure, flow rate, geothermal well depth, groundwater level, scene, hydrology, and geological structure according to the well-time-depth three-dimensional key, generating a unified data structure containing a field dictionary, unit system, coordinate reference, and quality labels. At the same time, change logs and traceable metadata are output to ensure that experimental conditions and data genera can be reproduced in the subsequent modeling and evaluation stages, ultimately resulting in a processed clean dataset.

[0040] Furthermore, the internal working principle of the geological dynamic modeling module is as follows:

[0041] The geological dynamic modeling module in this embodiment takes the processed cleaned dataset as input and sequentially completes data input, preliminary model construction, introduction of dynamic uncertainty, model update, calculation model input update and model determination, ensuring full disclosure and reproducibility of each step.

[0042] First, in this embodiment, the processed cleaning dataset is received through the geological data input submodule. The temperature, pressure, flow rate, geothermal well depth, groundwater level, scene and hydrological information, and geological structure data are organized according to the three-dimensional keys of well location, time and depth to establish a geological data input set. Each record contains a time label, depth coordinates, spatial coordinates, measurement value and quality label.

[0043] Subsequently, the geological model construction submodule generates a preliminary geothermal geological model based on the geological data input set. The preliminary model adopts a one-dimensional to three-dimensional heat conduction and convection coupling framework to characterize the baseline distribution of the temperature field under the boundary and initial conditions of known surface temperature, reference depth, and geothermal flux. Among them, the surface temperature is determined by the long-term average value obtained from well site scene observations, the geothermal flux is obtained by regional geothermal flow studies or well temperature gradient inversion, the thermal conductivity and thermal diffusivity are given by lithological classification and core experimental data, and the reference depth is taken as the zero depth corresponding to the wellhead elevation or the local stratigraphic interface.

[0044] To reflect the dynamic impact of geological structure changes and fluid flow changes on the temperature field, this embodiment introduces dynamic uncertainty into the preliminary model. Specifically, this is implemented by a dynamic uncertainty introduction submodule: the geological change influence function characterizes the systematic deviations in temperature caused by fault activity, formation thickness fluctuations, and permeability changes; the external disturbance term characterizes unmeasurable or short-term sudden disturbances; Monte Carlo simulation is used to generate multiple sets of uncertainty samples, covering parameters such as geological layer weighting factors, geological layer attenuation coefficients, coupling coefficients between temperature and geological influences, depth-related thermal diffusion correction terms, and external disturbance intensity. By solving the temperature field for each set of samples and statistically analyzing the distribution interval, an uncertain geological dynamic model is obtained.

[0045] The geological change influence function represents the mapping relationship between geological factors and temperature deviation, and is used to equate the enhanced conductivity of fractures, formation densification, or changes in hydraulic connectivity to additive or multiplicative effects on the temperature baseline; the geological layer weighting factor represents the relative importance of different geological layers in contributing to overall heat transfer and flow, and is used to synthesize the overall influence by layer weighting; the geological layer attenuation coefficient is used to describe the attenuation law of influence with depth or time, avoiding the infinite spread of local anomalies; the coupling coefficient between temperature and geological influence is used to quantitatively characterize the linkage strength between the temperature baseline and geological disturbances; the external disturbance term is used to describe the short-term non-equilibrium effects caused by construction, extreme scenarios, or injection-production fluctuations.

[0046] During the model update phase, the model update submodule, based on key data from real-time monitoring and the prediction residuals of the uncertain geological dynamic model, employs a recursive state and parameter assimilation strategy to dynamically adjust the coupling coefficients, layer weights, attenuation parameters, and diffusion correction terms. This ensures the model remains consistent with field observations after new observations arrive. The update strategy includes two channels: a slow variable channel, using weekly or monthly observations to perform small-step convergence corrections to layer weights and attenuation parameters; and a fast variable channel, using hourly to daily observations to rapidly correct coupling coefficients and external disturbance intensity, ensuring responsiveness during event periods. After the update is complete, the computational model input update submodule extracts a set of parameters from the updated geological dynamic model that can be used for thermal fluid numerical calculations and operational optimization. These parameters include effective values ​​of thermal properties, equivalent tensors of thermal conductivity and permeability for each layer, time series of boundary and source terms, and prior distribution intervals for different scenarios. All parameters are accompanied by metadata about their sources and effective intervals for easy auditing and reproducibility.

[0047] Finally, the model determination submodule performs consistency checks on the uncertainty set, eliminates parameter combinations that are inconsistent with long-term observation statistics, and generates the final geological dynamic model using expected values ​​or quantile representative values, while retaining confidence intervals for subsequent risk assessment.

[0048] For ease of implementation, the temperature field baseline is jointly determined by surface temperature, geothermal flux, thermal conductivity, and thermal diffusivity, with values ​​derived from long-term mean values ​​of the scenario, regional heat flow data or well temperature gradient inversion, core experiments, and literature databases, respectively. Temperature deviations caused by geological changes are given by a geological change influence function, whose inputs are fracture information, formation thickness and relative interlayer positions, and time-varying records of permeability and porosity; the output is a correction to the baseline temperature. Initial geological influences are used to define the background influence levels of each layer at the initial moment of the model, with values ​​derived from historical logging and well test data. The geological layer weighting factor is obtained by assimilating and fine-tuning the thickness, thermal conductivity, and fluid flux ratio of each layer. The geological layer attenuation coefficient is set according to the degree of heterogeneity within the layer and the degree of interface scattering, with typical values ​​estimated by seismic quality factor and drilling lithology statistics. The coupling coefficient between temperature and geological influence represents the conversion ratio of geological disturbance to temperature response, which can be obtained through joint fitting of historical periods and relaxed in the upper and lower limits during extreme events. The external disturbance term comes from changes in injection and production strategies, equipment start-up and shutdown, and short-term anomalies caused by extreme scenarios, and its intensity is adaptively estimated during the assimilation process. Through the above continuous process of data organization, model construction, uncertainty injection, assimilation update, and parameter extraction, this embodiment can generate a geological dynamic model that meets both the accuracy of field fitting and extrapolation capabilities.

[0049] Furthermore, the work content of the extreme scenario and policy response assessment module is as follows:

[0050] This embodiment clarifies the key implementation details of scenario parameterization and data integration in the scenario input submodule to ensure full disclosure and reproducibility. This embodiment first receives input parameters from the geological dynamic model and the updated computational model, and establishes a scenario input parameter library. The scenario input parameter library contains at least two categories: extreme scenario parameters and policy change scenario parameters. Extreme scenario parameters include upper and lower limits of injection and production conditions, well network start-up and shutdown combinations, the amplitude and duration of formation pressure boundary disturbances, temporary enhancement or attenuation of fracture conductivity, and abnormal geothermal flow pulses. Policy change scenario parameters include emission intensity limits, water extraction limits, energy efficiency thresholds, peak-valley electricity price constraints, carbon cost ranges, extraction intensity quotas, and safety regulatory thresholds, etc. This embodiment uses scenario templates to drive parameter instantiation. The templates define the names, units, allowed intervals, priorities, and conflict resolution rules of the input items, and map them one-to-one with the parameter interfaces of the geological dynamic model to achieve automated assignment of injection-production rates, boundary conditions, physical property tensors, source-sink terms, and control variables. For parameter pairs with mutually exclusive strategies, the conflict resolution rules prioritize the execution of safety and policy constraints, resulting in a scenario input dataset that can be directly used for simulation.

[0051] This embodiment details the numerical simulation solution, result productization, and quality control within the scenario simulation submodule. To ensure the distinguishability of events at different time scales, this embodiment employs a rolling time window simulation strategy: fine time steps and adaptive step size control are used for short-term extreme disturbances, while a phased steady-state-transient hybrid solution is used for long-term policy constraints. Within each time window, the coupled thermal, fluid, and force fields are discretely solved according to the scenario input dataset, simultaneously outputting wellbore temperature and pressure, production capacity curves, reservoir pressure recovery, reinjection absorption capacity, thermal breakthrough time, boundary flux, and energy balance, among other mining status indicators. To avoid numerical artifacts, this embodiment performs residual threshold checks and quality label generation after each solution. For time periods that exceed limits or have insufficient convergence, local mesh refinement and step size rollback are triggered, and the iteration count, constraint trigger count, and sensitive channel identifiers are recorded.

[0052] The simulation results, after time alignment and spatial resampling, form a unified simulation result data package, which serves as the sole input data source for the evaluation phase, yielding simulation results of mining status under extreme scenarios and policy responses. Based on this, this embodiment implements three sub-modules: mining benefit assessment, environmental impact assessment, and risk assessment. Mining benefit assessment uses energy output, thermal recovery efficiency, unit energy cost, equipment load, and availability as core indicators, and performs scenario-based discounting of policy-related benefits and costs, resulting in the mining benefit assessment results. Environmental impact assessment uses surface and groundwater impacts, land subsidence, heat plume expansion, noise, and emission intensity as core indicators, and generates compliance labels based on regional benchmarks and red-line limits, resulting in the environmental impact assessment results. Risk assessment employs event trees and parameter uncertainty propagation to generate quantitative results on the probability, severity, and detectability of scenarios such as excessive capacity reduction, reinjection instability, damage to wellbore integrity, and policy violations, resulting in the risk assessment results.

[0053] This embodiment provides a reusable implementation path for weighted analysis, multi-dimensional analysis, and comprehensive scoring in the comprehensive evaluation submodule, ensuring the traceability and auditability of the conclusions. The weighted analysis unit aggregates the mining benefit assessment results, environmental impact assessment results, and risk assessment results according to preset weights. The weights are derived from the priority settings of project objectives and regulatory requirements, and include weight uncertainty intervals and sensitivity records, resulting in the weighted analysis results. The multi-dimensional analysis unit analyzes the weighted analysis results in time, space, and operating condition dimensions: the time dimension outputs stage performance and volatility; the spatial dimension identifies inter-well differences and hotspot areas; and the operating condition dimension assesses the performance boundaries under different control strategies and marks the intervals that trigger policy constraints, resulting in the multi-dimensional analysis results.

[0054] The comprehensive scoring unit generates a comprehensive score and sub-item scores based on the multi-dimensional analysis results. The scoring structure includes the overall score, the achievement status of key indicators, a list of warnings for exceeding or approaching limits, optimization suggestions and implementation priorities for adaptive operation control, and metadata such as data source, model version, scenario template and weight configuration. It outputs a complete comprehensive evaluation report, which includes the mining benefit assessment results, environmental impact assessment results and risk assessment results under extreme scenarios and policy responses, realizing the structured presentation of the assessment conclusions and the usability of decision-making.

[0055] Furthermore, the adaptive geological operation collaborative assimilation and rolling optimization module's working content includes:

[0056] In the assimilation and constraint preparation phase, this embodiment clearly defines the data structure, mapping relationships, and verification process to ensure full disclosure and reproducibility. In the assimilation input preparation submodule, the state variables, key parameters, and observations of the geological dynamic model are organized into an assimilation input set. State variables include at least the reservoir temperature field, pore pressure field, saturation field, and wellbore temperature and pressure state. Key parameters include at least the equivalent tensors of thermal conductivity and permeability for each layer, fracture conductivity, heat capacity and diffusion correction terms, geological layer weights and attenuation parameters, and the coupling coefficient between temperature and geological influences. Observations are derived from real-time and near-real-time monitoring data of temperature, pressure, flow rate, groundwater level, and structural changes, accompanied by timestamps, spatial indexes, and quality tags. After the assimilation input set is established, this embodiment performs joint parameter and state updates in the data assimilation submodule, employing a sequential ensemble filtering or variational assimilation architecture to reduce computational overhead: first, prior states and prior parameter distributions are obtained by model forward propagation; then, gain calculation is driven by observation-prior residuals to update the states and sensitive parameters, outputting an assimilation model with uncertainty characterization. Subsequently, in the operational constraint mapping submodule, this embodiment transforms the limits, thresholds, and red lines in the mining benefit assessment results, environmental impact assessment results, and risk assessment results under extreme scenarios and policy responses into a mathematically calculable set of constraints and risk boundaries. This set covers the lower limit of production capacity, the upper limit of reinjection pressure, the safety window for wellbore integrity, the limit of groundwater level fluctuation, the upper limit of thermal plume expansion radius, emission and water intake quotas, carbon cost budgets, and the lower limit of energy efficiency. For each constraint, the applicable time period, spatial domain, soft and hard properties, and boundary violation penalty rules are given, thus obtaining the set of operational constraints and risk boundaries.

[0057] This embodiment provides a reusable modeling and implementation path in the rolling optimization construction and solution phase, ensuring that the control strategy can be implemented online. In the rolling optimization problem construction submodule, this embodiment uses an assimilation model as the prediction model, takes the set of operational constraints and risk boundaries as constraints, and combines them with project objectives to form a multi-objective trade-off criterion. It prioritizes a weighted combination of maximizing energy output, minimizing unit energy consumption, minimizing environmental boundary violations, and minimizing risk exposure, and clarifies the source and adjustable range of the weights of the objective terms, thus obtaining the description of the rolling optimization problem. To improve real-time performance, this embodiment implements the following sub-modules within the rolling optimization solution module: The prediction time domain setting unit sets the prediction time domain length and control step size based on the scene disturbance time scale and facility adjustment inertia, forming a time discretization scheme, resulting in the prediction time domain and the time discretization scheme; the initial value and boundary loading unit loads the current state of the assimilation model, initial parameter values, and upper and lower limits of operational constraints into the optimization problem according to the time discretization scheme, obtaining the initial set of optimization conditions; the objective function instantiation unit generates computable objective terms based on multi-objective trade-off criteria, and applies decreasing weight coefficients or peak weighting to future time periods to reflect operational preferences, obtaining the instantiated objective function; the constraint discretization unit discretizes the set of operational constraints and risk boundaries to various time periods. The first step involves forming inequality and equality constraints using a joint assimilation model, incorporating chance constraints or robust radii to cover uncertainties, resulting in a discretized constraint set. The solver selection and initialization unit prioritizes quadratic or nonlinear programming solvers with sparse structure utilization based on the differentiability and scale of the objective and constraints. If necessary, a hierarchical decomposition or a hybrid strategy of heuristic global search and local optimization is employed to configure step size, tolerance, and maximum iteration count, resulting in an initialized optimization solver. The optimization iteration solving unit calls the solver to iteratively solve the problem under the instantiated objective function, discretized constraint set, and initial optimization condition set, generating multiple candidate sets of running control sequences that satisfy different weights and starting point perturbations, thus obtaining the running control sequence candidate set. To ensure executability and disturbance resistance, this embodiment performs constraint satisfaction checks, worst-case assessments under disturbance injection, and cross-scenario replays on candidate sequences in the feasibility and robustness verification unit. Those that do not meet the requirements are eliminated or penalized, while those that pass are retained and robustness scores are calculated, resulting in a valid operating control sequence. The current control action selection unit selects the control action for the current moment from the valid operating control sequence, generates a reference trajectory for subsequent time periods, and outputs adaptive operating control information, thus obtaining adaptive operating control information.

[0058] In this embodiment, during the closed-loop feedback and model update stages, the control strategy and model boundary conditions are kept consistent, forming a continuous improvement mechanism. In the feedback update submodule, adaptive operational control information is applied to the assimilation model, updating boundary conditions, source and sink terms, the execution status of control variables, and equipment constraint occupancy. The actual execution control log and short-cycle field observation data are written back as the assimilation input source for the next period, compensating for and re-predicting any potential execution deviations. This process is repeated in each rolling cycle, reconstructing the rolling optimization problem from the assimilation model as a new starting point and solving it again, forming a stable online closed-loop optimization. Through this chain, this embodiment explicitly connects the layers of products—from constructing the assimilation input set, generating the assimilation model, mapping operational constraints and risk boundary sets, forming the rolling optimization problem description, to the output and writing back of adaptive operational control information—ultimately updating the model's operational boundaries and inputs, resulting in an assimilated and updated geological dynamic model.

[0059] Furthermore, the evaluation and analysis module specifically includes:

[0060] This embodiment, in the stage of establishing the indicator framework and timeline, clarifies the structured organization method and reusable data connection method throughout the entire cycle to ensure full disclosure and traceability of conclusions. This embodiment first constructs a comprehensive indicator framework throughout the entire cycle based on the mining benefit assessment results, environmental impact assessment results, and risk assessment results under extreme scenarios and policy responses, combined with an assimilated and updated geological dynamic model and adaptive operation control information. The framework includes at least three main categories: benefit dimension, environmental dimension, and risk dimension, with core and supporting indicators refined under each category. For example, the benefit dimension is refined into energy output, unit energy consumption, equipment availability, and economic efficiency; the environmental dimension is refined into surface and groundwater impact, land subsidence, thermal plume expansion, and emission intensity; and the risk dimension is refined into production capacity decline risk, reinjection instability risk, wellbore integrity risk, and compliance risk. To ensure cross-stage comparison and scenario consistency, this embodiment defines a full-cycle stage timeline and adopts a hybrid method of dividing stages into milestones and operational stages. The construction and commissioning period, ramp-up period, steady-state operation period, aging and degradation period, and decommissioning transition period are set as stage nodes. Each stage sets a minimum evaluation step size and a list of necessary observations. By mapping with the state variables of the assimilated and updated geological dynamic model, the triggering conditions and rollback rules for the start and end of the stage are determined, resulting in a full-cycle comprehensive index framework and a full-cycle stage timeline.

[0061] In this embodiment, key details of indicator alignment, temporal processing, and control injection are disclosed during the assessment result mapping and scenario prediction injection stages to avoid insufficient disclosure. The assessment result mapping submodule maps the mining benefit assessment results, environmental impact assessment results, and risk assessment results to the full-cycle stage time axis according to the definition of the full-cycle comprehensive indicator framework, forming a staged indicator sequence. The mapping rules include three steps: time alignment, spatial aggregation, and standardization. Time alignment uses a sliding window transition and weight smoothing at stage boundaries to avoid breakpoint effects; spatial aggregation aggregates by well group and fault block while retaining hotspot identifiers; standardization ensures that results from different sources are additive and comparable through unit system and statistical standard conversion. The scenario prediction and control injection submodule calls the assimilated and updated geological dynamic model to perform scenario prediction on the staged indicator sequence in the future time domain, outputting indicator predictions containing reference trajectories and quantile intervals. Simultaneously, adaptive operation control information is injected into the prediction process to generate control scenario trajectories, which characterize the achievable boundaries of the indicators under a given control strategy. In this embodiment, the compliance verification submodule performs consistency verification and boundary crossing marking on the control scenario trajectory based on policy constraints and security boundaries. It clarifies the limit type, applicable time period and geographical scope of each indicator, and provides early warning and buffer period marking for adjacent boundary crossing intervals, outputting the compliance-marked indicator trajectory. For conflicting constraints, a priority chain and penalty factor adjustment strategy are adopted to ensure that safety and compliance take priority.

[0062] This embodiment refines the implementation path for normalized weighting and scoring, confidence interval setting, and structured report generation in the quantitative scoring and conclusion generation stages. The normalized weighting and scoring submodule normalizes the dimensions of compliance indicator trajectories, employing robust scaling and quantile pruning to suppress the impact of extreme values. Weight setting provides benchmark weights based on project objectives and regulatory priorities, along with weight uncertainty intervals and sensitivity profiles. Based on this, stage scores and full-cycle comprehensive scores are calculated, simultaneously outputting statistical confidence intervals and scenario confidence intervals obtained from model uncertainty propagation, forming a dual-confidence expression. The conclusions and recommendations summary submodule, based on the full-cycle comprehensive score and confidence intervals, extracts key bottlenecks, identifies the weakest links contributing most to the score, and generates execution-oriented improvement recommendations based on adaptive operational control information. These recommendations include expected benefits, compliance improvement magnitude, implementation conditions, and priorities. Finally, an evaluation report is output in an itemized structure, with content including at least the performance of indicators at each stage, a list of out-of-bounds and critical intervals, improvement space under control scenarios, residual risks, and monitoring enhancement recommendations, resulting in a full-cycle dynamic evaluation result.

[0063] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0064] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform, characterized in that, include: The data acquisition module is used to collect key data and geological structure data in real time during the hydrothermal geothermal extraction process through multiple sensors; The data transmission module is used to wirelessly upload the key data and geological structure data to the cloud platform. The data processing module is used to perform denoising, calibration, completion and standardization on the key data and geological structure data on the cloud platform to obtain a processed clean dataset. The geological dynamic modeling module is used to establish a geothermal geological model with dynamic uncertainty based on the processed cleaned dataset to simulate the impact of geological structure changes on the geothermal extraction system and update the input parameters of the relevant calculation model, thus obtaining the geological dynamic model and the updated calculation model input parameters. The extreme scenario and policy response assessment module is used to assess the impact of simulated extreme scenarios and policy change scenarios on geothermal extraction based on the input parameters of the geological dynamic model and the updated calculation model, and obtains the extraction benefits, environmental impact and risk assessment results under extreme scenarios and policy responses; The adaptive geological operation collaborative assimilation and rolling optimization module is used to perform collaborative assimilation and rolling optimization on the geological dynamic model based on the geological dynamic model and the mining benefit assessment results, environmental impact assessment results and risk assessment results under the extreme scenarios and policy responses, so as to obtain the assimilated and updated geological dynamic model and adaptive operation control information. The evaluation and analysis module is used to conduct a full-cycle dynamic evaluation of the geothermal extraction system based on the mining benefit assessment results, environmental impact assessment results, and risk assessment results under the extreme scenarios and policy responses, and in combination with the assimilated and updated geological dynamic model and adaptive operation control information, and obtains the full-cycle dynamic evaluation results.

2. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform as described in claim 1, characterized in that, The key data includes: Temperature, pressure, flow rate, geothermal well depth, groundwater level, and hydrological data.

3. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 2, characterized in that, The data acquisition module includes: Temperature sensors are used to collect real-time data on water temperature and wellhead temperature in geothermal wells, thus obtaining temperature data. Pressure sensors are used to collect downhole pressure data from geothermal wells in real time, thus obtaining pressure data. A flow sensor is used to collect flow data of geothermal fluids in real time, and the flow data is obtained. Geothermal well depth sensor is used to collect geothermal well depth data in real time, thus obtaining geothermal well depth data; Groundwater level sensor is used to collect groundwater level data in real time to obtain groundwater level data; Hydrological sensors are used to collect hydrological data in geothermal areas, including water quality, water flow velocity, and water temperature. Geological structure sensors are used to collect geological structure data in real time, including stratum thickness, fault information, and the relative positions between geological strata. The data fusion submodule is used to synchronize, calibrate, and merge the temperature data, pressure data, flow data, depth data, water level data, hydrological data, and geological structure data collected by the various sensors, so as to obtain complete key data and geological structure data.

4. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 1, characterized in that, The data processing module includes: The denoising submodule is used to remove noise and interference signals from the key data and geological structure data through filtering algorithms and outlier detection methods, resulting in a denoised dataset. The calibration submodule is used to calibrate the denoised data according to known standards or calibration data, adjust the data deviation caused by sensor error, and obtain the calibrated dataset. The completion submodule is used to complete the missing data in the calibrated dataset based on an interpolation algorithm, thus obtaining the completed dataset; The standardization submodule is used to normalize the completed dataset to obtain a standardized clean dataset. The data integration submodule is used to integrate and uniformly format the standardized cleaned dataset, resulting in a processed cleaned dataset.

5. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 1, characterized in that, The geological dynamic modeling module includes: The geological data input submodule is used to receive the processed and cleaned dataset, thus obtaining the geological data input set; The geological model construction submodule is used to build a preliminary geothermal geological model based on the geological data input set. The dynamic uncertainty introduction submodule is used to introduce dynamic uncertainty into the preliminary geological model and model it through Monte Carlo simulation to obtain an uncertain geological dynamic model. The dynamic uncertainty includes geological structure change factors and fluid flow change factors. The model update submodule is used to dynamically adjust the parameters of the uncertain geological dynamic model based on key data monitored in real time and feedback information in the uncertain geological dynamic model, thus obtaining an updated geological dynamic model. The calculation model input update submodule is used to extract update parameters from the updated geological dynamic model to obtain updated calculation model input parameters; The model determination submodule is used to determine the final geological dynamic model based on the updated computational model input parameters; The preliminary expression for the geothermal geological model is as follows: ； Expression for an uncertain geological dynamics model: ； The expression for updating the geological dynamic model: ； The final expression for the geological dynamics model: ； in, Geothermal well depth In time The temperature at that time; It refers to the surface temperature; For geothermal flux; Thermal conductivity; For reference depth; Temperature deviation caused by geological changes; This is a function representing the influence of geological changes. Initial geological impacts; For depth Thermal diffusivity at that location; The random error term introduced to address uncertainty; For the updated geological dynamics model; This is the initial geological model; This represents the coupling coefficient between temperature and geological influences; For the first Weighting factors for each geological layer; For the first Attenuation coefficient of each geological layer; This represents the external disturbance term.

6. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 1, characterized in that, The extreme scenario and policy response assessment module includes: The scenario input submodule is used to receive the geological dynamic model and the updated calculation model input parameters, and set the scenario input parameters according to different extreme scenarios and policy change scenarios to obtain the scenario input dataset; The scenario simulation submodule is used to simulate extreme scenarios and policy change scenarios using numerical simulation methods based on the scenario input dataset, and to obtain simulation results of mining status under extreme scenarios and policy responses. Based on the simulation results, the mining benefits are evaluated under extreme and policy change scenarios to obtain mining benefit evaluation results; The environmental impact assessment submodule is used to assess the environmental impact under extreme scenarios and policy change scenarios based on the simulation results, and obtain the environmental impact assessment results. The risk assessment submodule is used to assess the risks under extreme scenarios and policy change scenarios based on the simulation results, and obtain the risk assessment results; The comprehensive assessment submodule is used to comprehensively analyze the mining benefits, environmental impacts and risk assessment results to obtain a comprehensive assessment report under extreme scenarios and policy responses.

7. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 6, characterized in that, The comprehensive evaluation submodule includes: The weighted analysis unit is used to perform weighted analysis on the mining benefit assessment results, environmental impact assessment results, and risk assessment results according to preset weights, and obtain the weighted analysis results. A multi-dimensional analysis unit is used to perform multi-dimensional analysis on the weighted analysis results to obtain multi-dimensional analysis results. The comprehensive scoring unit is used to perform a comprehensive scoring based on the multi-dimensional analysis results and generate a comprehensive assessment report. The comprehensive assessment report includes: mining benefits, environmental impact and risk assessment results under extreme scenarios and policy responses.

8. The dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform according to claim 1, characterized in that, The adaptive geological operation collaborative assimilation and rolling optimization module includes: The assimilation input preparation submodule is used to construct an assimilation input set containing model state variables, key parameters and observations based on the geological dynamic model and the mining benefit assessment results, environmental impact assessment results and risk assessment results under the extreme scenarios and policy responses, thus obtaining the assimilation input set; The data assimilation submodule is used to jointly update the parameters and states of the geological dynamic model based on the assimilation input set to obtain the assimilation model; The operation constraint mapping submodule is used to transform policy requirements and safety boundaries into a set of operation constraints and risk boundaries based on the mining benefit assessment results, environmental impact assessment results, and risk assessment results under the extreme scenarios and policy responses, thus obtaining the set of operation constraints and risk boundaries. The rolling optimization problem construction submodule is used to construct a rolling time-domain optimization problem by using the assimilation model as the prediction model, the set of operational constraints and risk boundaries as constraints, and combining the multi-objective trade-off criterion, thus obtaining the description of the rolling optimization problem. The rolling optimization solution submodule is used to solve the rolling optimization problem description, generate the running control sequence in the prediction time domain and select the current control action to obtain adaptive running control information. The feedback update submodule is used to apply the adaptive operation control information to the assimilation model to update the model operation boundary and input, thereby obtaining the assimilated and updated geological dynamic model.

9. A dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform as described in claim 8, characterized in that, The rolling optimization solution submodule includes: The prediction time domain setting unit is used to set the prediction time domain length and control step size according to the description of the rolling optimization problem and form a time discretization scheme, thus obtaining the prediction time domain and the time discretization scheme. The initial value and boundary loading unit is used to load the current model state, initial parameter values, and upper and lower limit constraints into the prediction time domain and time discretization scheme based on the assimilation model and the set of running constraints and risk boundaries, thereby obtaining the optimized initial condition set; The objective function instantiation unit is used to perform weighted processing on the objective terms according to the multi-objective trade-off criterion in the description of the rolling optimization problem, under the constraints of the prediction time domain and time discretization scheme and the optimization initial condition set, to obtain the instantiated objective function; The constraint discretization unit is used to discretize the set of operational constraints and risk boundaries under the prediction time domain and time discretization scheme, and combine it with the assimilation model and the optimization initial condition set to form a computable constraint system, thus obtaining the discretized constraint set. The solver selection and initialization unit is used to select and configure the optimization solver based on the differentiability and scale characteristics of the instantiated objective function and the discretized constraint set, thus obtaining the initialized optimization solver; The optimization iterative solution unit is used to call the initialized optimization solver, and perform iterative solution with the instantiated objective function as the optimization objective and the discretized constraint set and the optimization initial condition set as the constraints and starting point, to obtain a candidate set of running control sequences; The feasibility and robustness verification unit is used to verify the constraint satisfaction and robustness of the candidate set of operation control sequences under the discretized constraint set and the optimization initial condition set, and to remove those that do not meet the requirements, thereby obtaining the operation control sequences that pass the verification. The current control action selection unit is used to select the control action at the current moment from the verified operation control sequence and generate a reference trajectory for subsequent time periods, thereby obtaining adaptive operation control information.

10. A dynamic evaluation system for the entire lifecycle of hydrothermal geothermal extraction based on a cloud platform as described in claim 1, characterized in that, The evaluation and analysis module includes: The indicator framework and time axis establishment sub-module are used to construct a full-cycle comprehensive indicator framework and define the stage time axis based on the mining benefit assessment results, environmental impact assessment results and risk assessment results under extreme scenarios and policy responses, combined with the assimilated and updated geological dynamic model and adaptive operation control information, so as to obtain the full-cycle comprehensive indicator framework and the full-cycle stage time axis. The assessment result mapping submodule is used to map the mining benefit assessment results, environmental impact assessment results, and risk assessment results to the full-cycle stage time axis according to the full-cycle comprehensive index framework, forming a staged index sequence. The scenario prediction and control injection submodule is used to call the assimilated and updated geological dynamic model to perform scenario prediction on the staged index sequence, and inject adaptive operation control information to generate control scenario trajectory, thus obtaining the scenario prediction index trajectory. The compliance verification submodule is used to perform consistency verification and boundary crossing annotation on the scenario prediction indicator trajectory based on policy constraints and security boundaries under extreme scenarios and policy responses, thus obtaining the compliance-annotated indicator trajectory. The normalized weighting and scoring submodule is used to normalize the dimensions and set the weights for the compliance labeling indicator trajectory, and calculate the stage score, the full-cycle comprehensive score and the confidence interval, thus obtaining the full-cycle comprehensive score and the confidence interval. The Conclusions and Recommendations Summary submodule is used to extract key bottlenecks and improvement suggestions related to adaptive operation control information based on the full-cycle comprehensive score and confidence interval, and to output the evaluation report items in a structured manner, thus obtaining the full-cycle dynamic evaluation results.

Images