Geothermal energy resource optimization utilization prediction method based on geothermal resource investigation data

Abstract

The invention relates to the field of resource optimization and utilization, and discloses a geothermal energy resource optimization and utilization prediction method based on geothermal energy resource exploration data, which is used for solving the problem of geothermal energy reserve estimation deviation caused by inaccurate wellhead measurement data during geothermal energy resource optimization and utilization prediction. The method comprises the following steps: calculating initial geothermal reserves according to survey data, correcting the initial geothermal reserves to obtain actual geothermal reserves, classifying geothermal resources according to the actual geothermal reserves, utilizing and distributing, monitoring wellhead flow data of an acquisition well, calculating to obtain a flash evaporation generation index, and judging whether flash evaporation occurs according to the flash evaporation generation index. If it is judged that flash evaporation occurs currently, the wellhead flow data are corrected according to the flash evaporation occurrence index to obtain wellhead actual flow data, geothermal resource dynamic management is conducted according to the wellhead actual flow data, the accuracy of wellhead measurement data is effectively improved, and the accuracy of resource optimization utilization prediction is improved.

Description

Technical Field

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

[0002] In the field of modern geothermal resource development, geothermal energy, as a clean and renewable energy source, has been widely used in power generation, heating, industrial heat supply and other fields. Through scientific geothermal resource exploration and reasonable prediction of optimized resource utilization, researchers and decision-makers can improve the utilization efficiency of geothermal energy, extend the service life of the heat reservoir, and reduce the waste of geothermal resources. The prediction of optimized utilization of geothermal energy resources usually involves multiple links such as the evaluation of geothermal reservoir parameters, geothermal resource classification, energy distribution, and dynamic monitoring to achieve efficient and sustainable geothermal energy development.

[0003] Existing methods for predicting the optimized utilization of geothermal energy resources usually rely on big data collection and analysis technologies, including geological exploration and production well data collection, etc., and combine mathematical models or machine learning technologies for prediction and optimization. The general process includes big data preprocessing, geothermal reserve calculation, resource classification, energy distribution, dynamic monitoring, etc.

[0004] However, in the process of implementing the technical solutions of the embodiments of the present invention, it is found that the above technologies have at least the following technical problems: In practical applications, when predicting the optimized utilization of geothermal resources through the wellhead data of production wells, it is usually defaulted that the measured data at the wellhead can accurately reflect the true situation of the underground geothermal reservoir. However, in practical applications, due to the flashing of geothermal fluid at the wellhead, part of the liquid may rapidly vaporize, affecting the accuracy of the wellhead measurement data, which may lead to deviations in the estimation of geothermal reserves and affect subsequent resource optimization utilization strategies. Summary of the Invention

[0005] In order to overcome the above defects of the prior art, the present invention provides a method for predicting the optimized utilization of geothermal energy resources based on geothermal resource exploration data to solve the problems existing in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A prediction method for optimizing the utilization of geothermal energy resources based on geothermal resource exploration data includes the following steps: Step 1: Conduct real-time geothermal resource exploration on the target area to obtain real-time exploration data, and calculate the initial geothermal reserves using the volumetric method based on the real-time exploration data; Step 2: Use the Monte Carlo simulation method to correct the initial geothermal reserves to obtain the expected value of geothermal reserves, and take the expected value of geothermal reserves as the actual geothermal reserves; Step 3: Classify the geothermal energy resources according to the actual geothermal reserves, allocate the utilization of geothermal energy according to the classification results, and monitor the wellhead flow rate data of the production wells in real time; Step 4: Obtain the flashing influence data of the production wells in real time, calculate the flashing occurrence index based on the flashing influence data, and determine whether flashing occurs according to the flashing occurrence index; Step 5: If it is determined that flashing occurs currently, correct the wellhead flow rate data according to the flashing occurrence index to obtain the actual wellhead flow rate data; Step 6: Conduct dynamic management of geothermal energy resources according to the actual wellhead flow rate data.

[0007] Preferably, the step of calculating the initial geothermal reserves using the volumetric method according to the real-time exploration data is as follows: Conduct geothermal resource exploration in the target area to obtain real-time geothermal resource exploration data, where the geothermal resource exploration data includes reservoir volume, formation temperature, reference temperature, thermal properties of rock and fluid, and reservoir porosity; Preprocess the real-time geothermal resource exploration data, and the preprocessing includes missing value processing, data cleaning, and data standardization. Use the principal component analysis method to perform data dimensionality reduction processing on the preprocessed geothermal resource exploration data to extract the main influencing factors; Calculate the initial geothermal reserves using the volumetric method.

[0008] Preferably, the step of obtaining the expected value of geothermal reserves is as follows: At the time point of conducting real-time geothermal resource exploration, obtain the key parameters of the geothermal reservoir in the target area. The key parameters of the geothermal reservoir include reservoir volume, reservoir temperature, porosity, permeability, groundwater recharge rate, and heat loss rate, and set probability distributions for the key parameters of the geothermal reservoir; Use the set probability distributions to conduct N random samplings of the key parameters of the geothermal reservoir, perform Monte Carlo simulations on the results of each random sampling, and obtain the results of the Monte Carlo simulations; Calculate the expected value of geothermal reserves according to the results of each Monte Carlo simulation.

[0009] Preferably, the step of obtaining the flashing occurrence index is as follows: Use high-frequency data acquisition to obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value of the production well, and calculate the easy flashing coefficient based on the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value; Use real-time Fourier transform analysis to analyze the change in mass dryness and calculate the mass dryness change coefficient; Use high-frequency data acquisition to obtain the flow velocity data, normalize the easy flashing coefficient, mass dryness change coefficient, and flow velocity data, and perform weighted summation on the normalized easy flashing coefficient, mass dryness change coefficient, and flow velocity data to obtain the flashing occurrence index. The specific acquisition steps are as follows: ; In the formula, is expressed as the flashing occurrence index, is expressed as the flash-prone coefficient after normalization, is expressed as the coefficient of change in mass dryness after normalization, is expressed as the flow rate data after normalization, , , are expressed as the weight coefficient of the flash-prone coefficient after normalization, the weight coefficient of the coefficient of change in mass dryness after normalization, and the weight coefficient of the flow rate data after normalization.

[0010] Preferably, the steps for obtaining the flash-prone coefficient are as follows: Using the sliding window method, setting the window length and window step size, obtaining the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value within the window closest to the current time, calculating the pressure factor based on the wellhead pressure value; calculating the temperature factor based on the wellhead temperature value; obtaining the specific enthalpy of the saturated liquid and the specific enthalpy of the saturated steam according to the wellhead temperature value and wellhead pressure value through the standard water-steam thermodynamic property table, calculating the specific enthalpy factor based on the wellhead fluid specific enthalpy value, the specific enthalpy of the saturated liquid, and the specific enthalpy of the saturated steam; calculating the degree of flash-proneness based on the pressure factor, temperature factor, and specific enthalpy factor; obtaining the degree of flash-proneness at each time point within the window, using the K-means clustering method to cluster the degree of flash-proneness, and obtaining the flash-prone coefficient according to the clustering result.

[0011] Preferably, the steps of using the K-means clustering method to cluster the degree of flash-proneness and obtaining the flash-prone coefficient according to the clustering result are as follows: Step 4.1: Taking the degree of flash-proneness as the clustering feature, taking all the degrees of flash-proneness within the time window as the data set, and each degree of flash-proneness in the data set as a data point, using the elbow method to determine the optimal number of clusters K of the data set; Step 4.2: Randomly selecting K data points in the data set as the initial clustering centers, for each data point, calculating its Euclidean distance to each initial clustering center, for each data point, traversing the K initial clustering centers, and assigning it to the clustering cluster corresponding to the nearest initial clustering center; Step 4.3: After traversing all the data points, obtaining the initial clustering clusters, for each initial clustering cluster, calculating the mean value of the data points within it to obtain a new clustering center; Step 4.4: Repeating Step 4.2 and Step 4.3 until the clustering centers no longer change, obtaining the final clustering clusters and the final clustering centers; Step 4.5: Calculating the ratio of the number of data points in each final clustering cluster to the total number of data points to obtain the weight of each clustering cluster, and performing weighted summation of the weight of each clustering cluster and the final clustering center to obtain the flash-prone coefficient.

[0012] Preferably, the step of obtaining the quality dryness change coefficient is as follows: within a time window, perform N random samplings, collect N quality dryness data, and obtain a quality dryness time series within the time window; convert the quality dryness time series to the frequency domain to obtain spectral data of different frequencies, and calculate the amplitude magnitudes of different frequencies according to the spectral data of different frequencies; perform a summation calculation on the amplitude magnitudes of different frequencies to obtain the total energy; set an amplitude threshold, screen the frequencies with amplitudes greater than the amplitude threshold, denoted as high-frequency frequencies, and perform a summation calculation on the amplitudes of the high-frequency frequencies to obtain the high-frequency energy; perform a ratio calculation on the high-frequency energy and the total energy to obtain the quality dryness change coefficient.

[0013] Preferably, the step of judging whether flashing occurs according to the flashing occurrence index is as follows: compare the flashing occurrence index with the flashing threshold. If the flashing occurrence index is greater than or equal to the flashing threshold, it is judged that flashing occurs currently; if the flashing occurrence index is less than the flashing threshold, it is judged that flashing does not occur currently.

[0014] Preferably, the step of obtaining the actual wellhead flow rate data is as follows: perform a ratio calculation on the flashing threshold and the flashing occurrence index to obtain a flow rate adjustment factor; perform a multiplication calculation on the flow rate adjustment factor and the flow rate data to obtain the actual wellhead flow rate data.

[0015] Preferably, the step of performing dynamic management of geothermal resources according to the actual wellhead flow rate data is as follows: obtain a sustainable safe flow rate, perform a ratio calculation on the actual wellhead flow rate data and the sustainable safe flow rate to obtain the flow rate sustainability, compare the flow rate sustainability with the sustainable threshold. If the flow rate sustainability is greater than the sustainable threshold, it is judged that the current flow rate exceeds the sustainable range. If the flow rate sustainability is less than the sustainable threshold, it is judged that the current flow rate is lower than the sustainable range; if it is judged that the current flow rate exceeds the sustainable range, perform a wellhead flow rate adjustment to obtain a reduced wellhead flow rate; if it is judged that the current flow rate is lower than the sustainable range, perform a wellhead flow rate adjustment to obtain an increased wellhead flow rate; after performing the wellhead flow rate adjustment, calculate the flashing occurrence index again. If the flashing occurrence index after the wellhead flow rate adjustment is greater than or equal to the flashing threshold, re-correct the wellhead flow rate data according to the flashing occurrence index to obtain the actual wellhead flow rate data; perform a multiplication calculation on the actual wellhead flow rate data and the flow rate adjustment factor to obtain the optimal reinjection volume; continuously detect the flow rate sustainability and the flashing occurrence index, and dynamically adjust the flow rate and the reinjection volume according to the flow rate sustainability and the flashing occurrence index.

[0016] The technical effects and advantages of the present invention: Obtain exploration data, calculate the initial geothermal reserve based on the exploration data, correct the initial geothermal reserve to obtain the actual geothermal reserve, classify the geothermal resources according to the actual geothermal reserve and carry out utilization allocation, monitor the wellhead flow rate data of the production well, calculate the flashing occurrence index, judge whether flashing occurs according to the flashing occurrence index, if it is judged that flashing occurs currently, correct the wellhead flow rate data according to the flashing occurrence index to obtain the actual wellhead flow rate data, and carry out dynamic management of geothermal resources according to the actual wellhead flow rate data, effectively improving the accuracy of wellhead measurement data and the accuracy of resource optimization utilization prediction. Brief Description of the Drawings

[0017] Figure 1 It is a flowchart of a method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data provided by an embodiment of the present application. Detailed Embodiment

[0018] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the drawings in the present invention. In addition, the forms of the respective structures described in the following embodiments are merely examples, and the method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data involved in the present invention is not limited to the respective structures described in the following embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0019] The present invention provides a method for predicting the optimal utilization of geothermal energy resources based on geothermal resource exploration data, as Figure 1 shown, including the following steps: Step 1: Conduct real-time geothermal resource exploration on the target area to obtain real-time exploration data, and calculate the initial geothermal reserve using the volumetric method according to the real-time exploration data; The volumetric method is a calculation method commonly used to estimate geothermal resource reserves. This method is based on data such as the volume of the geothermal reservoir, formation lithology, thermal physical properties parameters (such as density, specific heat capacity), and reservoir temperature to evaluate the total amount of underground thermal energy. It assumes that the thermal energy in the reservoir is evenly distributed, and estimates the exploitable geothermal resources by calculating the heat contained in the rock and fluid per unit volume in the reservoir. The volumetric method is suitable for the preliminary assessment of geothermal resources, but usually needs to be combined with further correction of the calculation results to improve the prediction accuracy.

[0020] In this embodiment, it should be specifically noted that the steps of calculating the initial geothermal reserve using the volumetric method according to the real-time exploration data are as follows: Conduct geothermal resource exploration in the target area to obtain real-time geothermal resource exploration data, which includes reservoir volume, formation temperature, reference temperature, thermal properties of rock and fluid, and reservoir porosity. The thermal properties of rock and fluid include rock density, specific heat capacity of rock, fluid density, and specific heat capacity of fluid; Formation temperature: Measure the average temperature of the reservoir using a temperature measuring well or geophysical exploration technology; Reference temperature: Usually take the groundwater or ambient temperature as the reference temperature for geothermal energy calculation; Rock density: The ratio of the mass of rock to its volume; Specific heat capacity of rock: The heat capacity per unit mass of rock; Fluid density: The density of geothermal water; Specific heat capacity of fluid: The specific heat capacity per unit mass of geothermal water; Reservoir porosity: Represents the proportion of fluid in the reservoir; Preprocess the real-time geothermal resource exploration data. The preprocessing includes missing value handling, data cleaning, and data standardization. Use the principal component analysis method to perform data dimensionality reduction on the preprocessed geothermal resource exploration data and extract the main influencing factors. The principal component analysis method is a data processing technology for dimensionality reduction, mainly used to reduce the dimensionality of data while retaining as much key information of the original data as possible. In the processing of geothermal resource exploration data, different measurement parameters (such as temperature, pressure, flow rate, lithology, permeability, etc.) may have high correlations. The principal component analysis method projects these high-dimensional data onto a set of new, uncorrelated variables through linear transformation. These principal components are sorted according to the importance of data variance, so that the first few principal components can retain the main information of the data while removing redundant or noisy features. By reducing the dimensionality through the principal component analysis method, the calculation efficiency can be improved, the model complexity can be reduced, and the robustness of geothermal resource prediction and optimization can be enhanced; Calculate the initial geothermal reserve using the volumetric method. The specific acquisition steps are as follows: ; In the formula, represents the initial geothermal reserve, represents the reservoir volume, represents the reservoir porosity, and represent the rock density and specific heat capacity of rock, and represent the fluid density and specific heat capacity of fluid, and represent the formation temperature and reference temperature.

[0021] Step 2: Use the Monte Carlo simulation method to correct the initial geothermal reserve to obtain the expected value of the geothermal reserve, and take the expected value of the geothermal reserve as the actual geothermal reserve; The Monte Carlo simulation method is a numerical calculation method based on random sampling and probability statistics, used to solve problems with uncertainty. When correcting the initial geothermal reserve, the Monte Carlo simulation method randomly extracts key parameters such as reservoir volume, temperature, porosity, heat loss rate, and groundwater recharge rate multiple times, and uses these samples to calculate a large number of possible geothermal reserve values. Finally, the expected value and confidence interval of the reserve are obtained. This method can effectively consider the natural variability of geothermal resources, reduce measurement errors and modeling uncertainties, make the calculated actual geothermal reserve closer to the real situation, and provide a more reliable geothermal energy prediction and optimization plan.

[0022] In this embodiment, it should be specifically noted that the steps for obtaining the expected value of the geothermal reserve are as follows: At the time point of real-time geothermal resource exploration, obtain the key parameters of the geothermal reservoir in the target area. 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 an error range. Set appropriate probability distributions for the key parameters of the geothermal reservoir. For example, the reservoir volume can be assumed to follow a normal distribution , where is the estimated value, is the error range; Using the set probability distributions, conduct N random samplings of the key parameters of the geothermal reservoir, and perform Monte Carlo simulations on the results of each random sampling to obtain the results of the Monte Carlo simulations. The specific simulation steps are as follows: ; In the formula, represents the result of the Monte Carlo simulation, represents the initial geothermal reserve, represents the groundwater recharge rate, represents the heat loss rate; According to the results of each Monte Carlo simulation, calculate the expected value of the geothermal reserve. The specific acquisition steps are as follows: ; In the formula, represents the expected value of the geothermal reserve, N is the number of random samplings, that is, the number of simulations, represents the result of the i-th Monte Carlo simulation.

[0023] Step 3: Classify the geothermal resources according to the actual geothermal reserve, allocate the utilization of geothermal energy according to the classification results, and monitor the wellhead flow data of the production wells in real time; Step 4: Obtain the flashing influence data of the production well in real time, calculate the flashing occurrence index based on the flashing influence data, and determine whether flashing occurs according to the flashing occurrence index; In this embodiment, it should be specifically noted that the steps for obtaining the flashing occurrence index are as follows: Use high-frequency data acquisition to obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value of the production well, and calculate the flashability coefficient based on the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value; Using high-frequency data acquisition can accurately capture the instantaneous changes of geothermal well fluid and improve the real-time detection ability of the flashing phenomenon. High-frequency data acquisition can more quickly reflect the minute fluctuations of parameters such as wellhead temperature, pressure, flow rate, and specific enthalpy, so as to more accurately calculate the quality dryness change coefficient and flashability coefficient, and avoid misjudgment of flashing caused by data lag or too long sampling interval. In addition, high-frequency data can also be used in frequency domain analysis methods such as Fourier transform to identify the unstable fluctuation trend of geothermal fluid, provide more accurate decision-making support for flow rate adjustment and reinjection strategies, and improve the utilization efficiency of geothermal resources and the long-term stability of the reservoir.

[0024] Use real-time Fourier transform to analyze the quality dryness change, calculate the quality dryness change coefficient, which is used to describe the degree of change of quality 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 the periodic changes and instantaneous fluctuations therein. Different from the traditional Fourier transform, real-time Fourier transform adopts the method of sliding window and continuous update calculation, so that the spectrum analysis can be continuously updated over time, thus immediately 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 quality dryness, detect high-frequency fluctuations, identify possible flashing phenomena, so as to provide accurate real-time data support and improve the prediction and regulation ability of the system; Use high-frequency data acquisition to obtain the flow rate data, normalize the flashability coefficient, quality dryness change coefficient, and flow rate data, and perform weighted summation on the normalized flashability coefficient, quality dryness change coefficient, and flow rate data to obtain the flashing occurrence index. The specific acquisition steps are as follows: ; In the formula, represents the flashing occurrence index, represents the normalized flashability coefficient. The flashability coefficient 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 the flashing conditions, the system will detect a higher flashing occurrence index. is expressed as the coefficient of change in mass dryness after normalization. The coefficient of change in mass dryness measures the degree of dynamic change in the ratio of steam to liquid phase in geothermal fluid. If this coefficient is high, it indicates that the phase state of the geothermal fluid fluctuates violently in a short period of time, meaning that the flashing process is more frequent or intense. Therefore, the larger the coefficient of change in mass dryness, the higher the flashing occurrence index. is expressed as the normalized flow rate data. When the flow rate is high, the pressure of the geothermal fluid drops faster at the wellhead or in the pipeline, resulting in the partial vaporization of the liquid phase and the formation of a flashing phenomenon. In addition, a high flow rate may exacerbate the turbulent effect, making the gas-liquid two-phase flow more unstable. Therefore, the greater the flow rate, the higher the possibility and intensity of flashing. 、 、 are expressed as the weight coefficient of the easy-flashing coefficient after normalization, the weight coefficient of the coefficient of change in mass dryness after normalization, and the weight coefficient of the normalized flow rate data, and , 、 、 are obtained through the analytic hierarchy process. For example, 、 、 can be 0.4, 0.2, 0.4.

[0025] The analytic hierarchy process is a multi-criteria decision-making method used to determine the weights of various factors in a decision-making problem. It quantifies the importance of different factors by constructing a hierarchical structure, pairwise comparison judgment matrices, calculating weight vectors, and consistency tests. When calculating the flashing occurrence index, the analytic hierarchy process can be used to determine the relative weights between the key parameters affecting the flashing occurrence index, ensuring that the weight distribution is reasonable and conforms to the actual physical meaning, thereby improving the accuracy and scientific nature of the calculation of the flashing occurrence index.

[0026] In this embodiment, it should be specifically noted that the steps for obtaining the easy-flashing coefficient are as follows: The sliding window method is adopted. Set the window length, for example, the window length is 5 seconds, that is, it includes the data of the most recent 5 seconds. Set the window step size, for example, 1 second, indicating that the calculation is updated every 1 second. Obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value within the window closest to the current time. Calculate the pressure factor based on the wellhead pressure value. The specific obtaining steps are as follows: ; In the formula, is expressed as the pressure factor, is expressed as the saturated vapor pressure at this wellhead temperature value, is expressed as the wellhead pressure value. Quantify the ratio of the actual pressure to the saturated pressure through a logarithmic relationship, thereby providing a basis for thermodynamic property correction and fluid phase state judgment; The temperature factor is calculated based on the wellhead temperature value. The specific acquisition steps are as follows: ; In the formula, is expressed as the temperature factor, is expressed as the saturation temperature at this wellhead pressure value, is expressed as the wellhead temperature value. By normalizing the difference and adding 1, the calculation result has continuity and smoothness, which is beneficial to numerical stability control; The saturated steam pressure and saturated temperature are obtained through the water-steam saturation table; The specific enthalpy of the saturated liquid phase and the specific enthalpy of the saturated steam phase are obtained according to the wellhead temperature value and the wellhead pressure value through the standard water-steam thermodynamic property table. The specific enthalpy factor is calculated based on the wellhead fluid specific enthalpy value, the specific enthalpy of the saturated liquid phase, and the specific enthalpy of the saturated steam phase. The specific acquisition steps are as follows: ; In the formula, is expressed as the specific enthalpy factor, is expressed as the wellhead fluid specific enthalpy value, is expressed as the specific enthalpy of the saturated liquid phase, is expressed as the specific enthalpy of the saturated steam phase. By normalizing the difference and taking the square root, the sensitivity to the phase transition interval is enhanced; The flash tendency is calculated based on the pressure factor, the temperature factor, and the specific enthalpy factor. The specific acquisition steps are as follows: ; In the formula, is expressed as the flash tendency, is expressed as the pressure factor, is expressed as the temperature factor, is expressed as the specific enthalpy factor. The result is output through the Sigmoid function in the form of logistic regression. The larger the value, the closer the fluid is to the gas-liquid phase transition condition and the easier it is to flash; on the contrary, it means that the fluid deviates from the phase transition interval and the flash tendency is lower. The principle of the formula is to use multi-dimensional thermodynamic indicators to jointly reflect the comprehensive phase state characteristics of the fluid and improve the quantitative expression ability of the flash risk; Obtain the flash tendency at each time point within a window, use the K-means clustering method to cluster the flash tendency, and obtain the flash coefficient according to the clustering result.

[0027] K-means clustering is an unsupervised machine learning algorithm aimed at dividing a dataset into K different categories, such that data points within the same category are as similar as possible, while data points in different categories are as different as possible. Its core idea is to optimize iteratively by updating the center points of the clusters each time until the classification of the data points no longer changes or converges. In this application, K-means clustering is used to classify the flash evaporation degree data within a time window, thereby identifying different flash evaporation risk levels, and calculating the flash evaporation coefficient based on the clustering results to more accurately evaluate the likelihood of flash evaporation occurring.

[0028] In this embodiment, it should be specifically noted that the steps to obtain the flash evaporation coefficient according to the clustering results by using the K-means clustering method to cluster the flash evaporation degree are as follows: Step 4.1: Take the flash evaporation degree as the clustering feature, and use all the flash evaporation degrees within the time window as the dataset. Each flash evaporation degree in the dataset is a data point. Use the elbow method to determine the optimal number of clusters K for the dataset. The elbow method is a method for determining the optimal number of clusters K. By calculating the clustering error under different K values and observing the trend of the error changing with K. When K increases, the clustering error will gradually decrease, but the decreasing amplitude will gradually slow down. The elbow method finds the position where the error decrease significantly slows down, that is, the "elbow" inflection point, by plotting the curve of the clustering error changing with K. 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 for the flash evaporation degree dataset within the time window, ensure reasonable classification, and improve the accuracy of flash evaporation risk assessment; Step 4.2: Randomly select K data points in the dataset as the initial clustering centers. For each data point, calculate its Euclidean distance to each initial clustering center. The specific acquisition method is as follows: ; In the formula, represents the Euclidean distance from the data point to the clustering center, represents the data point, represents the initial clustering center. For each data point, traverse the K initial clustering centers and assign it to the clustering cluster corresponding to the nearest initial clustering center; Step 4.3: After traversing all the data points, obtain the initial clustering clusters. For each initial clustering cluster, calculate the mean value of the data points within it to obtain a new clustering center; Step 4.4: Repeat Step 4.2 and Step 4.3 until the clustering centers no longer change, to obtain the final clustering clusters and the final clustering centers; Step 4.5: Calculate the ratio of the number of data points in each final clustering cluster to the total number of data points to obtain the weight of each clustering cluster, and perform weighted summation of the weight of each clustering cluster and the final clustering center to obtain the flash evaporation coefficient.

[0029] In this embodiment, it should be specifically noted that the steps for obtaining the quality dryness change coefficient are as follows: Within a time window, N random samplings are performed, and N quality dryness data are collected to obtain the quality dryness time series within the time window. The quality dryness is calculated from the wellhead fluid specific enthalpy value, saturated liquid specific enthalpy, and saturated vapor specific enthalpy at the sampling time point. The specific obtaining steps are as follows: ; In the formula, represents the quality dryness, represents the wellhead fluid specific enthalpy value, represents the saturated liquid specific enthalpy, represents the saturated vapor specific enthalpy. The formula is directly deduced based on thermodynamic state parameters and is an important index for identifying the wellbore flow state; Convert the quality dryness time series to the frequency domain to obtain spectral data of different frequencies, and calculate the amplitude magnitudes of different frequencies based on the spectral data of different frequencies, which represents the fluctuation magnitude of that frequency; Sum up the amplitude magnitudes of different frequencies to obtain the total energy; Set an amplitude threshold, screen the frequencies with amplitudes greater than the amplitude threshold, denoted as high-frequency frequencies, and sum up the amplitudes of the high-frequency frequencies to obtain the high-frequency energy. The amplitude threshold is obtained through the adaptive threshold method; Calculate the ratio of the high-frequency energy to the total energy to obtain the quality dryness change coefficient.

[0030] In this embodiment, it should be specifically noted that the steps for judging whether flashing occurs based on the flashing occurrence index are as follows: Compare the flashing occurrence index with the flashing threshold. The flashing threshold is obtained through the adaptive threshold method. If the flashing occurrence index is greater than or equal to the flashing threshold, it is judged that flashing occurs currently; if the flashing occurrence index is less than the flashing threshold, it is judged that flashing does not occur currently. The adaptive threshold method is a technique for dynamically adjusting the threshold, which is used to automatically set the optimal threshold according to the data characteristics instead of using a fixed value. In the optimization prediction of geothermal resources, the flashing threshold needs to be adjusted according to dynamic data such as wellhead temperature, pressure, flow rate, and environmental conditions to improve the accuracy of judgment. The adaptive threshold method determines the most appropriate flashing threshold automatically by analyzing the statistical characteristics of historical data and real-time monitoring data, or based on machine learning algorithms. This can ensure a more accurate comparison between the flashing occurrence index and the threshold, reduce misjudgment, and optimize the utilization management of geothermal resources.

[0031] Step 5: If it is judged that flashing occurs currently, correct the wellhead flow rate data according to the flashing occurrence index to obtain the actual wellhead flow rate data; When flashing occurs, the measured flow data is usually larger than the actual flow. This is because during the flashing process, part of the geothermal fluid vaporizes due to a sudden drop in pressure, causing the fluid volume to expand and forming a gas-liquid two-phase flow. During measurement, traditional flow meters may miscount the steam-phase part into the total flow, resulting in a measured flow value higher than the actual liquid-phase flow.

[0032] In this embodiment, it should be specifically noted that the steps for obtaining the actual wellhead flow data are as follows: Calculate the ratio of the flashing threshold to the flashing occurrence index to obtain the flow adjustment factor; Calculate the product of the flow adjustment factor and the flow data to obtain the actual wellhead flow data.

[0033] Step 6: Conduct dynamic management of geothermal resources based on the actual wellhead flow data to prevent the geothermal reservoir from cooling down too quickly.

[0034] In this embodiment, it should be specifically noted that the steps for conducting dynamic management of geothermal resources based on the actual wellhead flow data are as follows: Obtain the sustainable safe flow rate. Calculate the ratio of the actual wellhead flow data to the sustainable safe flow rate to obtain the flow sustainability. Compare the flow sustainability with the sustainable threshold. If the flow sustainability is greater than the sustainable threshold, it is determined that the current flow exceeds the sustainable range, which may exacerbate reservoir cooling, and the flow needs to be reduced. If the flow sustainability is less than the sustainable threshold, it is determined that the current flow is lower than the sustainable range, and the flow can be increased to improve the utilization rate of geothermal energy. The sustainable threshold is obtained through the adaptive threshold method; Calculate the product of the actual wellhead flow data and the flow adjustment factor to obtain the optimal reinjection volume, replenish the reservoir pressure, prevent the temperature from dropping too quickly, and maintain long-term stability; If it is determined that the current flow exceeds the sustainable range, adjust the wellhead flow. Set the flow reduction factor, usually taking a value of 0.8 - 0.95. Calculate the product of the actual wellhead flow data and the flow reduction factor to obtain the reduced wellhead flow. The flow reduction factor is obtained through historical data using linear regression or a machine learning model; If it is determined that the current flow is lower than the sustainable range, adjust the wellhead flow. Calculate the difference between 1 and the flow reduction factor to obtain the flow increase factor. Calculate the product of the flow increase factor and the actual wellhead flow data and then add it to the actual wellhead flow data to obtain the increased wellhead flow; After adjusting the wellhead flow, calculate the flashing occurrence index again. If the flashing occurrence index after adjusting the wellhead flow is greater than or equal to the flashing threshold, re-correct the wellhead flow data according to the flashing occurrence index to obtain the actual wellhead flow data; Continuously detect the flow sustainability and flashing occurrence index, and dynamically adjust the flow rate and recharge volume according to the flow sustainability and flashing occurrence index to ensure the sustainable utilization of the ground heat source.

[0035] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0036] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or replacements, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope 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, It includes the following steps: Step 1: Conduct real-time geothermal resource exploration on the target area to obtain real-time exploration data, and calculate the initial geothermal reserves using the volume method according to the real-time exploration data; Step 2: Use the Monte Carlo simulation method to correct the initial geothermal reserves to obtain the expected value of geothermal reserves, and take the expected value of geothermal reserves as the actual geothermal reserves; Step 3: Classify geothermal resources according to the actual geothermal reserves, allocate geothermal energy utilization according to the classification results, and monitor the wellhead flow data of the production well in real time; Step 4: Obtain the flashing influence data of the production well in real time, calculate the flashing occurrence index according to the flashing influence data, and judge whether flashing occurs according to the flashing occurrence index; Step 5: If it is judged that flashing occurs currently, correct the wellhead flow data according to the flashing occurrence index to obtain the actual wellhead flow data; Step 6: Conduct dynamic management of geothermal resources according to the actual wellhead flow data.

2. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 1, wherein: The step of calculating the initial geothermal reserves using the volume method according to the real-time exploration data is as follows: Conduct geothermal resource exploration in the target area to obtain real-time geothermal resource exploration data. The geothermal resource exploration data includes reservoir volume, formation temperature, reference temperature, thermal properties of rock and fluid, and reservoir porosity; Preprocess the real-time geothermal resource exploration data. The preprocessing includes missing value processing, data cleaning, and data standardization. Use the principal component analysis method to conduct data dimensionality reduction processing on the preprocessed geothermal resource exploration data, and extract the main influencing factors; Calculate the initial geothermal reserves using the volume method.

3. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 1, wherein, The step of obtaining the expected value of geothermal reserves is as follows: At the time point of conducting real-time geothermal resource exploration, obtain the key parameters of the geothermal reservoir in the target area. The key parameters of the geothermal reservoir include reservoir volume, reservoir temperature, porosity, permeability, groundwater recharge rate, and heat loss rate, and set probability distributions for the key parameters of the geothermal reservoir; Use the set probability distributions to conduct N random samplings on the key parameters of the geothermal reservoir, and conduct Monte Carlo simulations on the results of each random sampling to obtain the results of Monte Carlo simulations; Calculate the expected value of geothermal reserves according to the results of each Monte Carlo simulation.

4. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 1, characterized in that, The step of obtaining the flashing occurrence index is as follows: Use high-frequency data acquisition to obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value of the production well, and calculate the easy flashing coefficient according to the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value; Use real-time Fourier transform to analyze the change in quality dryness and calculate the quality dryness change coefficient; Use high-frequency data acquisition to obtain the flow velocity data, normalize the easy flashing coefficient, quality dryness change coefficient, and flow velocity data, and conduct weighted summation according to the normalized easy flashing coefficient, quality dryness change coefficient, and flow velocity data to obtain the flashing occurrence index. The specific acquisition steps are as follows: ； In the formula, is expressed as the flashing occurrence index, is expressed as the flashable coefficient after normalization, is expressed as the mass dryness change coefficient after normalization, is expressed as the flow rate data after normalization, , , are expressed as the weight coefficient of the flashable coefficient after normalization, the weight coefficient of the mass dryness change coefficient after normalization, and the weight coefficient of the flow rate data after normalization.

5. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 4, characterized in that: The step of obtaining the easy flashing coefficient is as follows: Adopt the sliding window method, set the window length and window step size, obtain the wellhead pressure value, wellhead temperature value, and wellhead fluid specific enthalpy value within the window closest to the current time, and calculate the pressure factor according to the wellhead pressure value; Calculate the temperature factor according to the wellhead temperature value; Obtain the specific enthalpy of the saturated liquid phase and the specific enthalpy of the saturated vapor according to the wellhead temperature value and the wellhead pressure value through the standard water-steam thermodynamic property table, and calculate the specific enthalpy factor based on the wellhead fluid specific enthalpy value, the specific enthalpy of the saturated liquid phase, and the specific enthalpy of the saturated vapor; Calculate the flash tendency degree according to the pressure factor, the temperature factor, and the specific enthalpy factor; Obtain the flash tendency degree at each time point within the window, use the K-means clustering method to cluster the flash tendency degree, and obtain the flash coefficient according to the clustering result.

6. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 5, characterized in that: The steps of using the K-means clustering method to cluster the flash tendency degree and obtaining the flash coefficient according to the clustering result are as follows: Step 4.1: Use the flash tendency degree as the clustering feature, take all the flash tendency degrees within the time window as the data set, each flash tendency degree in the data set as a data point, and use the elbow method to determine the optimal number of clusters K of the data set; Step 4.2: Randomly select K data points in the data set as the 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 nearest initial cluster center; Step 4.3: After traversing all the data points, obtain the initial clusters. For each initial cluster, calculate the mean value of the data points within it to obtain a new cluster center; Step 4.4: Repeat Step 4.2 and Step 4.3 until the cluster centers no longer change, and obtain the final clusters and the final cluster centers; 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 coefficient.

7. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 4, characterized in that: The steps for obtaining the quality dryness change coefficient are as follows: Within a time window, perform N random samplings, collect N quality dryness data, and obtain the quality dryness time series within the time window; Convert the quality dryness time series to the frequency domain to obtain spectral data of different frequencies, and calculate the amplitude magnitudes of different frequencies according to the spectral data of different frequencies; Perform summation calculation on the amplitude magnitudes of different frequencies to obtain the total energy; Set an amplitude threshold, screen the frequencies with amplitudes greater than the amplitude threshold, denoted as high-frequency frequencies, and perform summation calculation on the amplitudes of the high-frequency frequencies to obtain the high-frequency energy; Perform ratio calculation on the high-frequency energy and the total energy to obtain the quality dryness change coefficient.

8. The geothermal energy resource optimal utilization prediction method based on geothermal resource exploration data according to claim 1, characterized in that: The steps for judging whether flashing occurs according to the flashing occurrence index are as follows: Compare the flashing occurrence index with the flashing threshold. If the flashing occurrence index is greater than or equal to the flashing threshold, it is judged that flashing occurs currently; if the flashing occurrence index is less than the flashing threshold, it is judged that flashing does not occur currently.

9. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 1, characterized in that: The steps for obtaining the actual wellhead flow rate data are as follows: Perform ratio calculation on the flashing threshold and the flashing occurrence index to obtain the flow rate adjustment factor; Perform multiplication calculation on the flow rate adjustment factor and the flow rate data to obtain the actual wellhead flow rate data.

10. The geothermal energy resource optimization utilization prediction method based on geothermal resource exploration data according to claim 1, characterized in that: The steps for dynamically managing geothermal resources according to the actual wellhead flow rate data are as follows: Obtain sustainable safe flow rate, calculate the ratio of the actual wellhead flow rate data to the sustainable safe flow rate to get the flow rate sustainability, and compare the flow rate sustainability with the sustainable threshold. If the flow rate sustainability is greater than the sustainable threshold, it is determined that the current flow rate exceeds the sustainable range. If the flow rate sustainability is less than the sustainable threshold, it is determined that the current flow rate is below the sustainable range; If it is determined that the current flow rate exceeds the sustainable range, adjust the wellhead flow rate to obtain the reduced wellhead flow rate; If it is determined that the current flow rate is below the sustainable range, adjust the wellhead flow rate to obtain the increased wellhead flow rate; After adjusting the wellhead flow rate, calculate the flashing occurrence index again. If the flashing occurrence index after adjusting the wellhead flow rate is greater than or equal to the flashing threshold, re-correct the wellhead flow rate data according to the flashing occurrence index to obtain the actual wellhead flow rate data; Multiply the actual wellhead flow rate data by the flow rate adjustment factor to obtain the optimal recharge volume; Continuously detect the flow rate sustainability and the flashing occurrence index, and dynamically adjust the flow rate and recharge volume according to the flow rate sustainability and the flashing occurrence index.

Images