Prediction method for optimal utilization of geothermal energy resources based on geothermal resource exploration data

Abstract

The present invention relates to the field of resource optimization and utilization, and discloses a geothermal energy resource optimization and utilization prediction method based on geothermal resource exploration data, which is used to solve the problem of inaccurate wellhead measurement data leading to geothermal reserve estimation deviation when predicting geothermal energy resource optimization and utilization. The method comprises the following steps: obtaining exploration data, calculating initial geothermal reserves based on the exploration data, correcting the initial geothermal reserves to obtain actual geothermal reserves, classifying geothermal resources and performing utilization allocation based on the actual geothermal reserves, monitoring wellhead flow data of collection wells, calculating a flash evaporation index, judging whether flash evaporation occurs based on the flash evaporation index, and if it is judged that flash evaporation currently occurs, correcting the wellhead flow data based on the flash evaporation index to obtain actual wellhead flow data, and dynamically managing geothermal resources based on the actual wellhead flow data, thereby effectively improving the accuracy of wellhead measurement data and improving the accuracy of resource optimization and utilization prediction.

Description

Technical Field

[0001] The present invention relates to the field of resource optimization and utilization, and more specifically to a method for predicting geothermal energy resource optimization and utilization based on geothermal resource exploration data. Background Art

[0002] In the modern field of geothermal resource development, geothermal energy, as a clean and renewable energy source, has been widely used in power generation, heating, and industrial heating. Through scientific geothermal resource exploration and reasonable resource optimization and forecasting, researchers and decision makers can improve geothermal energy utilization efficiency, extend the service life of thermal reservoirs, and reduce geothermal resource waste. Geothermal energy resource optimization and forecasting typically involve multiple steps, including the assessment of geothermal reservoir parameters, geothermal resource classification, energy allocation, and dynamic monitoring, to achieve efficient and sustainable geothermal energy development.

[0003] Existing methods for predicting the optimal utilization of geothermal energy resources typically rely on big data collection and analysis, including geological exploration and well data collection, combined with mathematical models or machine learning techniques for prediction and optimization. The general process includes big data preprocessing, geothermal reserve calculation, resource classification, energy allocation, and dynamic monitoring.

[0004] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0005] In practical applications, when optimizing geothermal resource forecasts based on wellhead data, it's often assumed that these measurements accurately reflect the true state of the underground geothermal reservoir. However, in practice, flash evaporation of geothermal fluids at the wellhead can occur, rapidly vaporizing some of the liquid. This affects the accuracy of wellhead measurements, potentially leading to errors in geothermal reserve estimates and compromising subsequent resource optimization strategies. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data to solve the problems existing in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data includes the following steps: Step 1: Conducting real-time geothermal resource exploration in a target area to obtain real-time exploration data, and calculating initial geothermal reserves using a volumetric method based on the real-time exploration data; Step 2: Correcting the initial geothermal reserves using a Monte Carlo simulation method to obtain an expected geothermal reserve value, and using the expected geothermal reserve value as the actual geothermal reserve; Step 3: Classifying geothermal resources based on actual geothermal reserves, allocating geothermal energy utilization based on the classification results, and monitoring wellhead flow data of collection wells in real time; Step 4: Obtaining flash evaporation impact data of the collection wells in real time, calculating a flash evaporation index based on the flash evaporation impact data, and determining whether flash evaporation occurs based on the flash evaporation index; Step 5: If it is determined that flash evaporation is currently occurring, correcting the wellhead flow data based on the flash evaporation index to obtain actual wellhead flow data; Step 6: Dynamically managing geothermal resources based on the actual wellhead flow data.

[0009] Preferably, the steps of calculating the initial geothermal reserves using the volumetric method based on real-time exploration data are: conducting geothermal resource exploration in the target area to obtain real-time geothermal resource exploration data, the geothermal resource exploration data including reservoir volume, formation temperature, reference temperature, thermal parameters of rocks and fluids, and reservoir porosity; preprocessing the real-time geothermal resource exploration data, the preprocessing including missing value processing, data cleaning and data standardization, using principal component analysis to perform data dimensionality reduction processing on the preprocessed geothermal resource exploration data to extract the main influencing factors; and using the volumetric method to calculate the initial geothermal reserves.

[0010] Preferably, the step of obtaining the expected value of geothermal reserves is: at the time point of real-time geothermal resource exploration, obtaining the key parameters of the geothermal reservoir in the target area, the key parameters of the geothermal reservoir including reservoir volume, reservoir temperature, porosity, permeability, groundwater recharge rate and heat loss rate, and setting a probability distribution for the key parameters of the geothermal reservoir; using the set probability distribution, randomly sampling the key parameters of the geothermal reservoir N times, performing Monte Carlo simulation on the results of each random sampling, and obtaining the results of the Monte Carlo simulation; and calculating the expected value of geothermal reserves based on the results of each Monte Carlo simulation.

[0011] Preferably, the flash generation index acquisition step is: using high-frequency data acquisition to obtain the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value of the acquisition well, and calculating the easy flash coefficient based on the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value; using real-time Fourier transform to analyze the mass dryness change and calculate the mass dryness variation coefficient; using high-frequency data acquisition to obtain flow rate data, normalizing the easy flash coefficient, mass dryness variation coefficient and flow rate data, and performing weighted summation based on the normalized easy flash coefficient, mass dryness variation coefficient and flow rate data to obtain the flash generation index. The specific acquisition steps are: Where, Expressed as the flash generation index, It is expressed as the normalized flash coefficient, Expressed as the coefficient of variation of mass dryness after normalization, Represents the normalized flow rate data, 、 、 It is expressed as the weight coefficient of the normalized flash coefficient, the weight coefficient of the normalized mass dryness variation coefficient, and the weight coefficient of the normalized flow rate data.

[0012] Preferably, the steps for obtaining the flash easy coefficient are: using a sliding window method, setting the window length and the window step size, obtaining the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value in the window closest to the current one, and calculating the pressure factor according to the wellhead pressure value; calculating the temperature factor according to the wellhead temperature value; obtaining the saturated liquid specific enthalpy and the saturated steam specific enthalpy according to the wellhead temperature value and the wellhead pressure value through the standard water-steam thermodynamic property table, and calculating the specific enthalpy factor according to the wellhead fluid specific enthalpy value, the saturated liquid specific enthalpy and the saturated steam specific enthalpy; calculating the degree of flash easy according to the pressure factor, the temperature factor and the specific enthalpy factor; obtaining the degree of flash easy at each time point in the window, clustering the degree of flash easy using the K-means clustering method, and obtaining the flash easy coefficient according to the clustering results.

[0013] Preferably, the flash evaporation ease is clustered using the K-means clustering method, and the flash evaporation ease coefficient is obtained according to the clustering results. Step 4.1: take the flash evaporation ease as the clustering feature, take all the flash evaporation eases in the time window as the data set, each flash evaporation ease in the data set as a data point, and use the elbow method to determine the optimal cluster number K of the data set; Step 4.2: randomly select K data points in the data set as initial cluster centers, for each data point, calculate its Euclidean distance to each initial cluster center, for each data point, traverse the K initial cluster centers, and assign it to the distance The cluster corresponding to the nearest initial cluster center; Step 4.3: After traversing all data points, the initial clusters are obtained. For each initial cluster, the data points in it are averaged to obtain a new cluster center; Step 4.4: Repeat Step 4.2 and Step 4.3 until the cluster center no longer changes, and the final cluster and the final cluster center are obtained; Step 4.5: Calculate the ratio of the number of data points in each final cluster to the total number of data points to obtain the weight of each cluster, and perform weighted summation of the weight of each cluster and the final cluster center to obtain the flash evaporation coefficient.

[0014] Preferably, the steps for obtaining the mass dryness variation coefficient are: performing N random samplings within a time window, collecting N mass dryness data, and obtaining a mass dryness time series within the time window; converting the mass dryness time series into the frequency domain to obtain spectrum data of different frequencies, and calculating the amplitudes of different frequencies based on the spectrum data of different frequencies; summing the amplitudes of different frequencies to obtain the total energy; setting an amplitude threshold, screening frequencies with amplitudes greater than the amplitude threshold, recording them as high-frequency frequencies, and summing the amplitudes of high-frequency frequencies to obtain high-frequency energy; calculating the ratio of high-frequency energy to total energy to obtain the mass dryness variation coefficient.

[0015] Preferably, the step of judging whether flash evaporation occurs according to the flash evaporation index is as follows: comparing the flash evaporation index with the flash evaporation threshold; if the flash evaporation index is greater than or equal to the flash evaporation threshold, judging that flash evaporation currently occurs; if the flash evaporation index is less than the flash evaporation threshold, judging that flash evaporation currently does not occur.

[0016] Preferably, the step of acquiring the actual wellhead flow data is: calculating the ratio of the flash threshold value to the flash generation index to obtain the flow adjustment factor; and multiplying the flow adjustment factor by the flow data to obtain the actual wellhead flow data.

[0017] Preferably, the steps for dynamically managing geothermal resources based on the actual wellhead flow data are: obtaining a sustainable safety flow, calculating the ratio of the actual wellhead flow data to the sustainable safety flow to obtain flow sustainability, comparing the flow sustainability with the sustainable threshold, if the flow sustainability is greater than the sustainable threshold, judging that the current flow exceeds the sustainable range, if the flow sustainability is less than the sustainable threshold, judging that the current flow is lower than the sustainable range; if it is judged that the current flow exceeds the sustainable range, adjusting the wellhead flow to obtain a reduced wellhead flow; if it is judged that the current flow is lower than the sustainable range, adjusting the wellhead flow to obtain an increased wellhead flow; after adjusting the wellhead flow, calculating the flash evaporation index again, if the flash evaporation index after the wellhead flow adjustment is greater than or equal to the flash evaporation threshold, re-correcting the wellhead flow data according to the flash evaporation index to obtain the actual wellhead flow data; multiplying the actual wellhead flow data by the flow adjustment factor to obtain the optimal reinjection volume; continuously detecting the flow sustainability and the flash evaporation index, and dynamically adjusting the flow and reinjection volume according to the flow sustainability and the flash evaporation index.

[0018] The technical effects and advantages of the present invention are as follows:

[0019] Acquire survey data, calculate initial geothermal reserves based on the survey data, correct the initial geothermal reserves to obtain actual geothermal reserves, classify geothermal resources and allocate their utilization based on the actual geothermal reserves, monitor the wellhead flow data of the collection wells, calculate the flash evaporation index, and determine whether flash evaporation has occurred based on the flash evaporation index. If flash evaporation is determined to have occurred, correct the wellhead flow data based on the flash evaporation index to obtain actual wellhead flow data. Dynamic management of geothermal resources is carried out based on the actual wellhead flow data, effectively improving the accuracy of wellhead measurement data and the accuracy of resource optimization and utilization prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Flowchart of a method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data involved in the present invention is not limited to the various structures described in the following embodiments. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] The present invention provides a method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data, such as Figure 1 As shown, the following steps are included:

[0023] Step 1: Conduct real-time geothermal resource surveys in the target area to obtain real-time survey data, and calculate the initial geothermal reserves using the volumetric method based on the real-time survey data;

[0024] The volumetric method is a calculation method commonly used to estimate geothermal resource reserves. This method estimates the total amount of underground thermal energy based on data such as the volume of the geothermal reservoir, formation lithology, thermophysical properties (such as density and specific heat capacity), and reservoir temperature. It assumes uniform distribution of thermal energy within the reservoir and estimates recoverable geothermal resources by calculating the amount of heat contained per unit volume of rock and fluid within the reservoir. While the volumetric method is suitable for preliminary assessments of geothermal resources, it often requires further refinement of the results to improve prediction accuracy.

[0025] In this embodiment, it should be specifically explained that the steps for calculating the initial geothermal reserves using the volumetric method based on real-time survey data are as follows:

[0026] Conduct geothermal resource exploration in the target area and obtain real-time geothermal resource exploration data, including reservoir volume, formation temperature, reference temperature, thermal parameters of rocks and fluids, and reservoir porosity. Thermal parameters of rocks and fluids include rock density, rock specific heat capacity, fluid density, and fluid specific heat capacity;

[0027] Formation temperature: The average temperature of the reservoir is measured using temperature logging wells or geophysical exploration techniques;

[0028] Reference temperature: usually the groundwater or ambient temperature is used as the base temperature for geothermal energy calculation;

[0029] Rock density: the ratio of a rock's mass to its volume;

[0030] Specific heat capacity of rock: the heat capacity per unit mass of rock;

[0031] Fluid density: density of geothermal water;

[0032] Fluid specific heat capacity: the specific heat capacity per unit mass of geothermal water;

[0033] Reservoir porosity: indicates the proportion of fluid in the reservoir;

[0034] Preprocessing of real-time geothermal resource exploration data, including missing value processing, data cleaning and data standardization, is performed on the preprocessed geothermal resource exploration data using principal component analysis to reduce the dimensionality of the data and extract the main influencing factors. Principal component analysis is a data processing technology used for dimensionality reduction, which is mainly used to reduce the dimension of the data while retaining the key information of the original data as much as possible. In geothermal resource exploration data processing, different measurement parameters (such as temperature, pressure, flow, lithology, permeability, etc.) may have a high correlation, and principal component analysis projects these high-dimensional data onto a new set of uncorrelated variables through linear transformation. These principal components are sorted according to the importance of the data variance, so that the first few principal components can retain the main information of the data while removing redundant or noise features. Dimensionality reduction through principal component analysis can improve computational efficiency, reduce model complexity, and enhance the robustness of geothermal resource prediction and optimization.

[0035] The initial geothermal reserves are calculated using the volumetric method. The specific steps are as follows:

[0036] ;

[0037] Where, is expressed as the initial geothermal reserve, Expressed as the reservoir volume, Expressed as reservoir porosity, and Expressed as rock density and rock specific heat capacity, and Expressed as fluid density and fluid specific heat capacity, and Expressed as formation temperature and reference temperature.

[0038] Step 2: Use the Monte Carlo simulation method to correct the initial geothermal reserves to obtain the expected value of geothermal reserves, and use the expected value of geothermal reserves as the actual geothermal reserves;

[0039] Monte Carlo simulation is a numerical calculation method based on random sampling and probability statistics, used to solve problems with uncertainty. When correcting initial geothermal reserves, Monte Carlo simulation repeatedly randomly samples key parameters such as reservoir volume, temperature, porosity, heat loss rate, and groundwater recharge rate. Using these samples, the method calculates a large number of possible geothermal reserve values, ultimately deriving an expected value and confidence interval for the reserves. This method effectively accounts for the natural variability of geothermal resources, reduces measurement errors and modeling uncertainties, and makes the calculated actual geothermal reserves closer to reality, providing more reliable geothermal energy forecasting and optimization solutions.

[0040] In this embodiment, it should be specifically explained that the steps for obtaining the expected value of geothermal reserves are:

[0041] At the time of real-time geothermal resource exploration, key parameters of the geothermal reservoir in the target area are obtained. The key parameters of the geothermal reservoir include reservoir volume, reservoir temperature, porosity, permeability, groundwater recharge rate, and heat loss rate. The key parameters of the geothermal reservoir are not fixed values, but variables with error ranges. Appropriate probability distributions are set for the key parameters of the geothermal reservoir. For example, the reservoir volume can be assumed to follow a normal distribution. ,in is an estimated value, is the error range;

[0042] Using the set probability distribution, N random samples are taken for the key parameters of the geothermal reservoir. Monte Carlo simulation is performed on each random sampling result to obtain the Monte Carlo simulation results. The specific simulation steps are as follows:

[0043] ;

[0044] Where, Expressed as the result of Monte Carlo simulation, is expressed as the initial geothermal reserve, Expressed as the groundwater recharge rate, Expressed as heat loss rate;

[0045] Based on the results of each Monte Carlo simulation, the expected value of geothermal reserves is calculated. The specific steps for obtaining the value are as follows:

[0046] ;

[0047] Where, It is expressed as the expected value of geothermal reserves, N is the number of random sampling, that is, the number of simulations, Represents the result of the i-th Monte Carlo simulation.

[0048] Step 3: Classify geothermal resources according to actual geothermal reserves, allocate geothermal energy utilization based on the classification results, and monitor the wellhead flow data of the collection wells in real time;

[0049] Step 4: Obtain flash vaporization impact data of the acquisition well in real time, calculate the flash vaporization occurrence index based on the flash vaporization impact data, and determine whether flash vaporization occurs based on the flash vaporization occurrence index;

[0050] In this embodiment, it should be specifically explained that the steps for obtaining the flash generation index are:

[0051] Using high-frequency data acquisition, the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value of the acquisition well are obtained, and the flash coefficient is calculated based on the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value;

[0052] High-frequency data acquisition can accurately capture transient changes in geothermal well fluids and improve the ability to detect flash evaporation in real time. High-frequency data acquisition can more quickly reflect small fluctuations in parameters such as wellhead temperature, pressure, flow rate, and specific enthalpy, allowing for more accurate calculations of the mass dryness variation coefficient and the flash evaporation coefficient, avoiding misjudgments of flash evaporation due to data lag or long sampling intervals. Furthermore, high-frequency data can be used with frequency domain analysis methods such as Fourier transforms to identify unstable fluctuation trends in geothermal fluids, providing more accurate decision support for flow adjustment and reinjection strategies, and improving the utilization efficiency of geothermal resources and the long-term stability of reservoirs.

[0053] Real-time Fourier transform is used to analyze the change in mass dryness, and the mass dryness variation coefficient is calculated to describe the degree of change in mass dryness during the detection time period. Real-time Fourier transform is a dynamic signal processing method used to analyze the frequency components of time series data in real time and extract periodic changes and instantaneous fluctuations. Unlike traditional Fourier transform, real-time Fourier transform uses a sliding window and continuous update calculation method, so that the spectrum analysis can be continuously updated over time, thereby instantly reflecting the frequency changes of the signal. In geothermal resource monitoring, real-time Fourier transform can be used to analyze the dynamic change trend of mass dryness, detect high-frequency fluctuations, and identify possible flash evaporation phenomena, thereby providing accurate real-time data support and improving the prediction and control capabilities of the system;

[0054] Use high-frequency data acquisition to obtain flow rate data, normalize the flash vaporization coefficient, mass dryness variation coefficient, and flow rate data, and perform weighted summation based on the normalized flash vaporization coefficient, mass dryness variation coefficient, and flow rate data to obtain the flash vaporization generation index. The specific acquisition steps are as follows:

[0055] ;

[0056] Where, Expressed as the flash generation index, It is expressed as the normalized flash index, which is calculated based on key parameters such as pressure, temperature and specific enthalpy, and reflects the tendency of geothermal fluid to flash under specific conditions. When the state of geothermal fluid is closer to flash conditions, the system will detect a higher flash index. It is expressed as the normalized mass dryness variation coefficient. The mass dryness variation coefficient measures the dynamic change of the ratio of steam to liquid in geothermal fluid. If the coefficient is high, it means that the phase of geothermal fluid fluctuates violently in a short period of time, which means that the flash process is more frequent or violent. Therefore, the larger the mass dryness variation coefficient, the higher the flash generation index. Expressed as normalized flow rate data, when the flow rate is high, the pressure of the geothermal fluid at the wellhead or in the pipeline drops faster, causing partial vaporization of the liquid phase, forming a flash phenomenon. In addition, high flow rates may intensify the turbulence effect, making the gas-liquid two-phase flow more unstable. Therefore, the greater the flow rate, the higher the possibility and intensity of flash. 、 、 It is expressed as the weight coefficient of the normalized flash coefficient, the weight coefficient of the normalized mass dryness variation coefficient, and the weight coefficient of the normalized flow rate data, and , 、 、 Obtained through AHP, e.g. 、 、 It can be 0.4, 0.2, or 0.4.

[0057] The Analytic Hierarchy Process (AHP) is a multi-criteria decision-making method used to determine the weights of various factors in decision-making problems. It quantifies the importance of different factors by constructing a hierarchical structure, performing pairwise comparison judgment matrices, calculating weight vectors, and performing consistency tests. When calculating the flash generation index (FGEI), the AHP can be used to determine the relative weights of key parameters influencing the FGEI, ensuring that the weight distribution is reasonable and consistent with actual physical meaning, thereby improving the accuracy and scientific nature of the FGEI calculation.

[0058] In this embodiment, it should be specifically explained that the steps for obtaining the flash vaporization coefficient are:

[0059] Using the sliding window method, set the window length, for example, the window length is 5 seconds, which means that the data of the last 5 seconds is included. Set the window step size, for example, 1 second, which means that the calculation is updated every 1 second. Obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value in the window closest to the current one. Calculate the pressure factor based on the wellhead pressure value. The specific acquisition steps are as follows:

[0060] ;

[0061] Where, Expressed as the pressure factor, It is expressed as the saturated steam pressure at the wellhead temperature value. It is expressed as the wellhead pressure value, and the ratio of actual pressure to saturation pressure is quantified through a logarithmic relationship, thus providing a basis for the correction of thermodynamic properties and the judgment of fluid phase state;

[0062] The temperature factor is calculated based on the wellhead temperature value. The specific steps for obtaining it are:

[0063] ;

[0064] Where, Expressed as the temperature factor, It is expressed as the saturation temperature at the wellhead pressure value. Expressed as wellhead temperature value, the difference is normalized and added with 1 to make the calculation result continuous and smooth, which is beneficial to numerical stability control;

[0065] The saturated steam pressure and saturated temperature are obtained from the water-steam saturation table;

[0066] The saturated liquid specific enthalpy and saturated steam specific enthalpy are obtained from the standard water-steam thermodynamic property table according to the wellhead temperature and wellhead pressure values. The specific enthalpy factor is calculated based on the wellhead fluid specific enthalpy value, the saturated liquid specific enthalpy, and the saturated steam specific enthalpy. The specific acquisition steps are as follows:

[0067] ;

[0068] Where, Expressed as the specific enthalpy factor, Expressed as the specific enthalpy of the wellhead fluid, Expressed as the saturated liquid phase enthalpy, Expressed as the specific enthalpy of saturated steam, the difference is normalized and the square root is taken to enhance the sensitivity to the phase transition interval;

[0069] The flash evaporation degree is calculated based on the pressure factor, temperature factor and specific enthalpy factor. The specific steps are as follows:

[0070] ;

[0071] Where, Expressed as the degree of easy flash evaporation, Expressed as the pressure factor, Expressed as the temperature factor, Expressed as a specific enthalpy factor, the output is a sigmoid function using logistic regression. A larger value indicates that the fluid is closer to the gas-liquid phase transition and more likely to flash; conversely, a smaller value indicates that the fluid is outside the phase transition range and has a lower tendency to flash. The formula utilizes multi-dimensional thermal indicators to reflect the comprehensive phase characteristics of the fluid, enhancing the ability to quantitatively express flash risk.

[0072] The flash evaporation susceptibility at each time point within a window is obtained, the flash evaporation susceptibility is clustered using the K-means clustering method, and the flash evaporation coefficient is obtained based on the clustering results.

[0073] K-means clustering is an unsupervised machine learning algorithm that aims to partition a dataset into K distinct categories, ensuring that data points within the same category are as similar as possible and data points across different categories are as dissimilar as possible. The core idea is to iteratively optimize, updating the cluster center each time until the classification of the data points stabilizes or converges. In this application, K-means clustering is used to classify flash susceptibility data within a time window, thereby identifying different levels of flash susceptibility. Based on the clustering results, a flash susceptibility coefficient is calculated to more accurately assess the likelihood of flash susceptibility.

[0074] In this embodiment, it should be specifically explained that the flash evaporation ease is clustered using the K-means clustering method, and the flash evaporation ease coefficient is obtained according to the clustering results in the following steps:

[0075] Step 4.1: Take the degree of flash evaporation as the clustering feature, all the degrees of flash evaporation in the time window as the data set, and each degree of flash evaporation in the data set as a data point. Use the elbow method to determine the optimal number of clusters K of the data set. The elbow method is a method for determining the optimal number of clusters K. By calculating the clustering error under different K values, the trend of the error changing with K is observed. When K increases, the clustering error will gradually decrease, but the magnitude of the decrease will gradually slow down. The elbow method draws a curve of the clustering error changing with K to find the position where the error decreases significantly, that is, the "elbow" inflection point. At this time, K represents the optimal number of clusters. In this embodiment, the elbow method can be used to determine the optimal number of clusters of the data set of the degree of flash evaporation in the time window, ensure reasonable classification, and improve the accuracy of flash risk assessment;

[0076] Step 4.2: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate the Euclidean distance from each initial cluster center. The specific method is:

[0077] ;

[0078] Where, Expressed as the Euclidean distance from the data point to the cluster center, Represented as data points, Represented as the initial cluster center, for each data point, traverse the K initial cluster centers and assign it to the cluster corresponding to the nearest initial cluster center;

[0079] Step 4.3: After traversing all data points, we get the initial clusters. For each initial cluster, we calculate the mean of the data points in it and get the new cluster center.

[0080] Step 4.4: Repeat steps 4.2 and 4.3 until the cluster center no longer changes, and obtain the final cluster and the final cluster center;

[0081] Step 4.5: Calculate the ratio of the number of data points in each final cluster to the total number of data points to obtain the weight of each cluster, and perform a weighted summation of the weight of each cluster and the final cluster center to obtain the flash evaporation coefficient.

[0082] In this embodiment, it should be specifically explained that the steps for obtaining the mass dryness variation coefficient are:

[0083] In a time window, N random samplings are performed to collect N mass dryness data, and the mass dryness time series in the time window is obtained. The mass dryness is calculated from the wellhead fluid specific enthalpy, saturated liquid specific enthalpy, and saturated steam specific enthalpy at the sampling time point. The specific acquisition steps are as follows:

[0084] ;

[0085] Where, Expressed as mass dryness, Expressed as the specific enthalpy of the wellhead fluid, Expressed as the saturated liquid phase enthalpy, Expressed as the specific enthalpy of saturated steam, the formula is directly calculated based on thermodynamic state parameters and is an important indicator for identifying wellbore flow state;

[0086] The mass dryness time series is converted to the frequency domain to obtain spectrum data of different frequencies, and the amplitude of different frequencies is calculated based on the spectrum data of different frequencies to represent the fluctuation size of the frequency;

[0087] The total energy is calculated by summing up the amplitudes of different frequencies;

[0088] Set the amplitude threshold, filter the frequencies whose amplitude is greater than the amplitude threshold, record them as high-frequency frequencies, sum the amplitudes of the high-frequency frequencies to obtain the high-frequency energy, and the amplitude threshold is obtained by the adaptive threshold method;

[0089] The ratio of high-frequency energy to total energy is calculated to obtain the mass dryness variation coefficient.

[0090] In this embodiment, it should be specifically explained that the step of determining whether flash evaporation occurs according to the flash evaporation index is:

[0091] The flash generation index is compared with the flash threshold, which is determined using an adaptive threshold method. If the flash generation index is greater than or equal to the flash threshold, flash is determined to be occurring; if the flash generation index is less than the flash threshold, flash is determined not to be occurring. The adaptive threshold method is a technology that dynamically adjusts the threshold, automatically setting the optimal threshold based on data characteristics rather than using a fixed value. In geothermal resource optimization and prediction, the flash threshold needs to be adjusted based on dynamic data such as wellhead temperature, pressure, flow rate, and environmental conditions to improve the accuracy of the judgment. The adaptive threshold method automatically determines the most appropriate flash threshold by analyzing the statistical characteristics of historical data, real-time monitoring data, or based on machine learning algorithms. This ensures a more accurate comparison of the flash generation index and the threshold, reduces misjudgments, and optimizes geothermal resource utilization and management.

[0092] Step 5: If it is determined that flash vaporization is currently occurring, the wellhead flow rate data is corrected according to the flash vaporization occurrence index to obtain the actual wellhead flow rate data;

[0093] When flashing occurs, the measured flow rate is often higher than the actual flow rate. This is because during the flashing process, some of the geothermal fluid vaporizes due to the sudden drop in pressure, causing the fluid volume to expand and form a gas-liquid two-phase flow. When measuring this flow, traditional flow meters may mistakenly include the vapor phase in the total flow, causing the measured flow rate to be higher than the actual liquid phase flow.

[0094] In this embodiment, it should be specifically explained that the steps for obtaining the actual wellhead flow data are:

[0095] The flow rate regulation factor is calculated by calculating the ratio of the flash threshold value to the flash generation index;

[0096] The actual flow data at the wellhead is obtained by multiplying the flow adjustment factor and the flow data.

[0097] Step 6: Dynamically manage geothermal resources based on actual wellhead flow data to prevent the geothermal reservoir from cooling too quickly.

[0098] In this embodiment, it should be specifically explained that the steps for dynamically managing geothermal resources based on actual wellhead flow data are as follows:

[0099] To obtain a sustainable safe flow rate, the actual wellhead flow rate data is compared with the sustainable safe flow rate to obtain the flow sustainability. The flow sustainability is then compared with the sustainable threshold. If the flow sustainability is greater than the sustainable threshold, the current flow rate is judged to be beyond the sustainable range, which may aggravate reservoir cooling and the flow rate needs to be reduced. If the flow sustainability is less than the sustainable threshold, the current flow rate is judged to be below the sustainable range and the flow rate can be increased to improve geothermal energy utilization. The sustainable threshold is obtained through the adaptive threshold method.

[0100] The optimal recharge rate is calculated by multiplying the actual wellhead flow data with the flow adjustment factor to replenish the reservoir pressure, prevent the temperature from dropping too quickly, and maintain long-term stability;

[0101] If the current flow rate is judged to be beyond the sustainable range, the wellhead flow rate is adjusted by setting a flow reduction factor, usually ranging from 0.8 to 0.95. The reduced wellhead flow rate is calculated by multiplying the actual wellhead flow rate data by the flow reduction factor. The flow reduction factor is obtained through historical data using linear regression or machine learning models.

[0102] If the current flow rate is judged to be lower than the sustainable range, the wellhead flow rate is adjusted. The difference between 1 and the flow reduction factor is calculated to obtain the flow growth factor. The flow growth factor is multiplied by the actual wellhead flow data and then added to the actual wellhead flow data to obtain the increased wellhead flow rate.

[0103] After the wellhead flow rate is adjusted, the flash generation index is calculated again. If the flash generation index after the wellhead flow rate adjustment is greater than or equal to the flash threshold, the wellhead flow rate data is re-corrected according to the flash generation index to obtain the actual wellhead flow rate data;

[0104] Continuously monitor the flow sustainability and flash generation index, and dynamically adjust the flow and reinjection volume based on the flow sustainability and flash generation index to ensure the sustainable utilization of geothermal sources.

[0105] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0106] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data, characterized in that: The following steps are involved: Step 1: Conduct real-time geothermal resource surveys in the target area to obtain real-time survey data, and calculate the initial geothermal reserves using the volumetric method based on the real-time survey data; Step 2: Use the Monte Carlo simulation method to correct the initial geothermal reserves to obtain the expected value of geothermal reserves, and use the expected value of geothermal reserves as the actual geothermal reserves; Step 3: Classify geothermal resources according to actual geothermal reserves, allocate geothermal energy utilization based on the classification results, and monitor the wellhead flow data of the collection wells in real time; Step 4: Obtain flash vaporization impact data of the acquisition well in real time, calculate the flash vaporization occurrence index based on the flash vaporization impact data, and determine whether flash vaporization occurs based on the flash vaporization occurrence index; Step 5: If it is determined that flash vaporization is currently occurring, the wellhead flow rate data is corrected according to the flash vaporization occurrence index to obtain the actual wellhead flow rate data; Step 6: Dynamically manage geothermal resources based on actual wellhead flow data; The steps for obtaining the flash generation index are as follows: Using high-frequency data acquisition, the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value of the acquisition well are obtained, and the flash coefficient is calculated based on the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value; Use real-time Fourier transform to analyze the mass dryness change and calculate the mass dryness change coefficient; Use high-frequency data acquisition to obtain flow rate data, normalize the flash vaporization coefficient, mass dryness variation coefficient, and flow rate data, and perform weighted summation based on the normalized flash vaporization coefficient, mass dryness variation coefficient, and flow rate data to obtain the flash vaporization generation index. The specific acquisition steps are as follows: ； Where, Expressed as the flash generation index, It is expressed as the normalized flash coefficient, Expressed as the coefficient of variation of mass dryness after normalization, Represents the normalized flow rate data, It is expressed as the weight coefficient of the normalized flash vaporization coefficient, the weight coefficient of the normalized mass dryness variation coefficient, and the weight coefficient of the normalized flow rate data; The steps for dynamically managing geothermal resources based on actual wellhead flow data are as follows: Obtain a sustainable safe flow rate, calculate the ratio of the actual wellhead flow data to the sustainable safe flow rate, and obtain the flow sustainability. Compare the flow sustainability with the sustainable threshold. If the flow sustainability is greater than the sustainable threshold, the current flow is judged to be beyond the sustainable range. If the flow sustainability is less than the sustainable threshold, the current flow is judged to be below the sustainable range. If it is determined that the current flow rate exceeds the sustainable range, the wellhead flow rate is adjusted to obtain a reduced wellhead flow rate; If the current flow rate is judged to be lower than the sustainable range, the wellhead flow rate is adjusted to obtain the increased wellhead flow rate; After the wellhead flow rate is adjusted, the flash generation index is calculated again. If the flash generation index after the wellhead flow rate adjustment is greater than or equal to the flash threshold, the wellhead flow rate data is re-corrected according to the flash generation index to obtain the actual wellhead flow rate data; The optimal recharge volume is calculated by multiplying the actual wellhead flow data with the flow adjustment factor; Continuously detect flow sustainability and flash generation index, and dynamically adjust flow and recharge volume based on flow sustainability and flash generation index.

2. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The steps for calculating the initial geothermal reserves using the volumetric method based on real-time survey data are as follows: Conduct geothermal resource exploration in the target area and obtain real-time geothermal resource exploration data, including reservoir volume, formation temperature, reference temperature, thermal parameters of rocks and fluids, and reservoir porosity; Preprocessing of real-time geothermal resource exploration data, including missing value processing, data cleaning and data standardization, uses principal component analysis to reduce the dimension of the preprocessed geothermal resource exploration data and extract the main influencing factors; The initial geothermal reserves were calculated using the volumetric method.

3. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The steps for obtaining the expected value of geothermal reserves are: At the time of real-time geothermal resource exploration, key parameters of the geothermal reservoir in the target area are obtained, including reservoir volume, reservoir temperature, porosity, permeability, groundwater recharge rate, and heat loss rate, and probability distributions are set for the key parameters of the geothermal reservoir; Using the set probability distribution, random sampling is performed N times on the key parameters of the geothermal reservoir, and Monte Carlo simulation is performed on each random sampling result to obtain the Monte Carlo simulation result; Based on the results of each Monte Carlo simulation, the expected value of geothermal reserves is calculated.

4. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The steps for obtaining the flash coefficient are as follows: The sliding window method is used to set the window length and window step size, obtain the wellhead pressure value, wellhead temperature value and wellhead fluid specific enthalpy value in the window closest to the current one, and calculate the pressure factor based on the wellhead pressure value; The temperature factor is calculated based on the wellhead temperature value; The saturated liquid specific enthalpy and saturated steam specific enthalpy are obtained from the standard water-steam thermodynamic property table according to the wellhead temperature and wellhead pressure values. The specific enthalpy factor is calculated based on the wellhead fluid specific enthalpy value, the saturated liquid specific enthalpy and the saturated steam specific enthalpy. The degree of flash evaporation is calculated based on the pressure factor, temperature factor and specific enthalpy factor; The flash evaporation susceptibility at each time point within the window is obtained, the flash evaporation susceptibility is clustered using the K-means clustering method, and the flash evaporation susceptibility coefficient is obtained based on the clustering results.

5. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 4, characterized in that: The K-means clustering method is used to cluster the degree of easy flashing, and the steps of obtaining the easy flashing coefficient according to the clustering results are as follows: Step 4.1: Use the flash evaporation ease as the clustering feature, all flash evaporation eases within the time window as the data set, and each flash evaporation ease in the data set as a data point. Use the elbow method to determine the optimal number of clusters K for the data set. Step 4.2: Randomly select K data points in the data set as initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center. For each data point, traverse the K initial cluster centers and assign it to the cluster corresponding to the initial cluster center closest to it. Step 4.3: After traversing all data points, we get the initial clusters. For each initial cluster, we calculate the mean of the data points in it and get the new cluster center. Step 4.4: Repeat steps 4.2 and 4.3 until the cluster center no longer changes, and obtain the final cluster and the final cluster center; Step 4.5: Calculate the ratio of the number of data points in each final cluster to the total number of data points to obtain the weight of each cluster, and perform a weighted summation of the weight of each cluster and the final cluster center to obtain the flash evaporation coefficient.

6. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The steps for obtaining the mass dryness variation coefficient are as follows: In a time window, N random samplings are performed to collect N mass dryness data and obtain the mass dryness time series in the time window; The mass dryness time series is converted into the frequency domain to obtain spectrum data of different frequencies, and the amplitudes of different frequencies are calculated based on the spectrum data of different frequencies; The total energy is calculated by summing up the amplitudes of different frequencies; Set an amplitude threshold, filter out frequencies with amplitudes greater than the threshold, record them as high-frequency frequencies, and sum the amplitudes of the high-frequency frequencies to obtain high-frequency energy. The ratio of high-frequency energy to total energy is calculated to obtain the mass dryness variation coefficient.

7. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The step of judging whether flash evaporation occurs according to the flash evaporation index is as follows: The flash evaporation index is compared with the flash evaporation threshold. If the flash evaporation index is greater than or equal to the flash evaporation threshold, it is determined that flash evaporation is currently occurring; if the flash evaporation index is less than the flash evaporation threshold, it is determined that flash evaporation is not currently occurring.

8. The method for predicting optimal utilization of geothermal energy resources based on geothermal resource exploration data according to claim 1, characterized in that: The steps for obtaining the actual wellhead flow data are as follows: The flow rate regulation factor is calculated by calculating the ratio of the flash threshold value to the flash generation index; The actual flow data at the wellhead is obtained by multiplying the flow adjustment factor and the flow data.

Images