Method and system for determining heat loss of deep geothermal development drilling shaft

Abstract

The invention provides a method and a system for determining heat loss of a deep geothermal development drilling shaft, and relates to the technical field of geothermal energy, and the method specifically comprises the following steps: collecting key parameters in the shaft in real time: pressure, injected fluid flow, internal and external temperature, nanofluid thermal conductivity, specific heat capacity and injection duration data; the fluid mass is calculated through the fluid flow and the injection duration after the dimensionless treatment, and heat loss is determined by combining the internal and external temperatures of the shaft and the specific heat capacity of the fluid; analyzing the relationship between each key parameter and the heat loss by utilizing a Pearson correlation coefficient method, and identifying parameters which have obvious influence on the heat loss; and establishing a regression model to represent the relationship between the heat loss and the key parameters so as to guide an optimization strategy. The heat loss condition of the shaft can be comprehensively evaluated, and the limitation of a traditional method is overcome. By establishing a regression model, the relationship between each key parameter and the heat loss is determined, and the main factors influencing the heat loss can be effectively identified.

Description

Technical Field

[0001] The present invention relates to the field of geothermal energy technology, and in particular to a method and system for determining heat loss in a deep geothermal development drilling wellbore. Background Art

[0002] In the process of deep geothermal exploitation, heat loss in the wellbore is a key factor affecting energy efficiency and economy. Existing technologies usually rely on traditional monitoring methods to evaluate the heat loss of the wellbore through a single temperature measurement or flow monitoring. However, this method has obvious shortcomings. First, the monitoring of a single parameter cannot fully reflect the complex thermal flow phenomena in the wellbore and the coupling effects of multiple factors, resulting in inaccurate estimates of heat loss. Secondly, traditional measurement methods are mostly collected on a regular basis, lacking real-time monitoring capabilities, and unable to capture the dynamic changes of temperature, pressure and fluid state in the wellbore in a timely manner, which in turn affects the immediate response and adjustment capabilities to heat loss. This limitation makes it difficult for operators to take effective measures when faced with emergencies, resulting in increased risks of resource waste and economic losses.

[0003] In addition, existing technologies lack effective statistical analysis tools and models when analyzing the relationship between heat loss and multiple influencing factors. Although some studies have attempted to use regression analysis or other statistical methods to explore the factors affecting heat loss, they often rely only on limited data sets and fail to fully consider the interaction of multiple parameters such as fluid flow characteristics, temperature differences inside and outside the wellbore, pressure changes, and changes in fluid properties. Therefore, these analysis results often lack sufficient reliability and reference value in guiding actual operations. At the same time, due to the failure to systematically identify key parameters that significantly affect heat loss, measures to optimize fluid injection conditions are difficult to implement accurately, thereby limiting the further development of deep geothermal mining technology. Therefore, there is an urgent need for a comprehensive, multi-dimensional analysis method to more comprehensively and accurately evaluate wellbore heat loss and provide a scientific basis for actual operations.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The object of the present invention is to provide a method and system for determining heat loss in a deep geothermal development drilling wellbore to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for determining heat loss in a deep geothermal development wellbore, comprising the following steps:

[0008] Step 1: Real-time collection of key parameters of the wellbore, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data;

[0009] Step 2: Calculate the fluid mass based on the dimensionless fluid flow rate and fluid injection time, and determine the wellbore heat loss based on the fluid mass, wellbore internal and external temperature data, and the specific heat capacity of the fluid;

[0010] Step 3: Use the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss, and identify the key parameters that have a significant impact on heat loss;

[0011] Step 4: Establish a regression model to characterize the relationship between heat loss and key parameters. Use the analysis results to guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss.

[0012] Furthermore, the specific logic for collecting the key parameters of the wellbore is as follows:

[0013] A pressure sensor is installed at the wellbore entrance to monitor the wellbore pressure in real time, denoted as P;

[0014] Temperature sensors are set every 5 meters to monitor the temperature inside and outside the wellbore in real time, denoted as T in and T out , for each depth point, calculate the temperature difference between its inside and outside: Where, ΔT i is the temperature difference between inside and outside of the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, where i is the index of the depth point;

[0015] Use an electromagnetic flowmeter to monitor the flow rate of the injected fluid in real time, recorded as R, and simultaneously record the duration of the fluid injection, recorded as S;

[0016] Use an online thermal conductivity measuring instrument to monitor the thermal conductivity of the nanofluid, denoted as g;

[0017] The specific heat capacity data of nanofluids is obtained by consulting relevant materials and is denoted as C.

[0018] Furthermore, the fluid mass is calculated based on the dimensionless processed fluid flow rate and fluid injection duration, and the formula used is as follows:

[0019] M=ρ*R*S

[0020] Among them, M is the mass of the fluid, ρ is the density of the fluid, which is obtained by consulting relevant materials, S is the duration of fluid injection, and R is the flow rate of the injected fluid;

[0021] The specific logic for determining the heat loss of the wellbore based on the fluid mass, the temperature data inside and outside the wellbore, and the specific heat capacity of the fluid is as follows: for each depth point i, the corresponding heat loss is calculated:

[0022]

[0023] Among them, Q (i) is the heat loss of the wellbore at the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, C is the specific heat capacity of the fluid, and M is the mass of the fluid;

[0024] The total heat loss from the wellbore is obtained by adding:

[0025]

[0026] Among them, Q loss is the total heat loss of the wellbore, Q (i) is the heat loss of the wellbore at the i-th depth point, and n is the number of depth points.

[0027] Furthermore, the specific logic of using the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss is as follows:

[0028] The Pearson correlation coefficient is a statistic that measures the strength and direction of the linear relationship between two variables. Its value range is: (-1, +1). The specific steps are as follows:

[0029] Collect a batch of historical key parameters of the wellbore and the total heat loss data of the corresponding wellbore. The key parameters are the pressure data in the wellbore, the flow rate of the injected fluid, the temperature inside and outside the wellbore, and the fluid injection time data;

[0030] The Pearson correlation coefficient is calculated according to the following formula:

[0031]

[0032] Among them, r is the Pearson correlation coefficient, X j represents the key parameter of the jth sample, Y j represents the heat loss of the jth sample, is the mean of the key parameter X, is the mean value of heat loss;

[0033] The calculated Pearson correlation coefficient value r is used to analyze the relationship between each key parameter and the heat loss of the wellbore:

[0034] When r>0, it indicates that there is a positive correlation between the parameter and heat loss, which means that when the parameter increases, the heat loss also increases;

[0035] When r < 0, it indicates that there is a negative correlation between the parameter and the heat loss, which means that the heat loss decreases when the parameter increases:

[0036] When r = 0, there is no correlation, which means that there is no linear relationship between this parameter and heat loss;

[0037] Among them, the closer |r| is to 1, the stronger the correlation is. The absolute value |r| of the Pearson correlation coefficient of each key parameter calculated is sorted, and the key parameter whose absolute value of the Pearson correlation coefficient exceeds the preset correlation threshold RY is defined as significantly correlated with heat loss.

[0038] Furthermore, the specific logic of establishing a regression model to characterize the relationship between total heat loss and each key parameter is as follows: relying on the correlation result obtained in step 3, a linear regression model is constructed, and the key parameters significantly correlated with heat loss are defined as strongly correlated key parameters, and the strongly correlated key parameters are used as independent variables in the model, and the corresponding total heat loss is used as the dependent variable, and different types of strongly correlated key parameters are defined as T1, T2, ..., T k , k is the number of types of strongly correlated key parameters, and the model expression of the linear regression model is as follows:

[0039] Q loss =α1*T1+α2*T2+…+α k *T k +∈

[0040] Among them, Q loss is the total heat loss of the wellbore, α1, α2, ..., α k is the regression coefficient to be optimized, ∈ is the error term;

[0041] A sample set is obtained from historical data, where the sample set consists of multiple groups of strongly correlated key parameters and the corresponding total heat loss. The sample set is input into a linear regression model for training to obtain a linear regression model after training.

[0042] Furthermore, the analysis results guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss. The specific logic is as follows:

[0043] Taking the maximum and minimum values ​​of various strongly correlated key parameters in the sample set as constraints, an initial population is randomly generated, and the initial population consists of multiple individuals. The individuals are input into the linear regression model to obtain the corresponding total heat loss, and the individuals are sorted from small to large according to the total heat loss. The individuals at the top of the sorting are selected as the parents and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parents are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the smallest total heat loss is selected as the optimal parameter combination, and the current parameter value is adjusted according to the parameter value in the optimal parameter combination.

[0044] The present invention further provides a system for determining heat loss of a deep geothermal development drilling wellbore, wherein the system for determining heat loss of a deep geothermal development drilling wellbore is used to execute the above-mentioned method for determining heat loss of a deep geothermal development drilling wellbore, comprising:

[0045] A parameter acquisition module is used to acquire key parameters of the wellbore in real time, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data;

[0046] The heat loss calculation module calculates the fluid mass based on the dimensionless fluid flow rate and fluid injection duration, and determines the wellbore heat loss based on the fluid mass, the wellbore internal and external temperature data, and the specific heat capacity of the fluid;

[0047] Correlation analysis module, used to analyze the relationship between key parameters and heat loss using the Pearson correlation coefficient method, and identify key parameters that have a significant impact on heat loss;

[0048] The model building and optimization module is used to establish a regression model to characterize the relationship between heat loss and key parameters, guide the optimization strategy through analysis results, and adjust the fluid injection conditions to reduce heat loss.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The present invention can comprehensively evaluate the heat loss of the wellbore by collecting multiple key parameters in real time, combining dimensionless processing and Pearson correlation coefficient analysis, thus overcoming the limitations of traditional methods. By establishing a regression model to clarify the relationship between each key parameter and heat loss, the main factors affecting heat loss can be effectively identified, thereby providing a scientific basis for optimizing fluid injection conditions. This method not only improves the ability to accurately assess heat loss, but also provides good technical support for reducing heat loss, further improving the efficiency and economy of deep geothermal exploitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0052] Figure 2 It is a schematic diagram of the overall system module of the present invention;

[0053] Figure 3 Calculate the results for the Pearson correlation coefficient;

[0054] Figure 4 Calculation results for the regression coefficients and error terms ∈ of key parameters significantly related to heat loss;

[0055] Figure 5 This is a table of comparative experimental data between the present invention and the prior art. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0057] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0058] Example:

[0059] See also Figure 1 , the present invention provides a technical solution:

[0060] A method for determining heat loss in a deep geothermal development wellbore, comprising the following steps:

[0061] Step 1: Real-time collection of key parameters of the wellbore, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data;

[0062] In this embodiment, the specific logic for collecting the key parameters of the wellbore is as follows:

[0063] A pressure sensor is installed at the wellbore entrance to monitor the wellbore pressure in real time, denoted as P;

[0064] Temperature sensors are set every 5 meters to monitor the temperature inside and outside the wellbore in real time, denoted as T in and T out , for each depth point, calculate the temperature difference between its inside and outside: Where, ΔT i is the temperature difference between inside and outside of the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, where i is the index of the depth point;

[0065] Use an electromagnetic flowmeter to monitor the flow rate of the injected fluid in real time, recorded as R, and simultaneously record the duration of the fluid injection, recorded as S;

[0066] Use an online thermal conductivity measuring instrument to monitor the thermal conductivity of the nanofluid, denoted as g;

[0067] The specific heat capacity data of nanofluids is obtained by consulting relevant materials and is denoted as C.

[0068] The advantage of step 1 is that the key parameters of the wellbore are collected in real time, making data acquisition more timely and comprehensive. This real-time nature can help engineers better monitor the operating status of the wellbore and discover potential problems in a timely manner, thereby reducing losses caused by delays; compared with existing technologies, this step provides more accurate and rich data support by integrating real-time monitoring of multiple key parameters. This comprehensive data collection capability helps to improve the analysis accuracy of heat loss, thereby optimizing the efficiency and economy of deep geothermal extraction; in this patent solution, the use of this step can lay a solid data foundation for subsequent heat loss calculations and correlation analysis, thereby improving the scientificity and reliability of the entire solution, and ultimately promoting the effective formulation and implementation of optimization strategies.

[0069] Step 2: Calculate the fluid mass based on the dimensionless fluid flow rate and fluid injection time, and determine the wellbore heat loss based on the fluid mass, wellbore internal and external temperature data, and the specific heat capacity of the fluid;

[0070] In this embodiment, the fluid mass is calculated based on the dimensionless fluid flow rate and fluid injection duration, and the formula used is as follows:

[0071] M=ρ*R*S

[0072] Among them, M is the mass of the fluid, ρ is the density of the fluid, which is obtained by consulting relevant materials, S is the duration of fluid injection, and R is the flow rate of the injected fluid;

[0073] The specific logic for determining the heat loss of the wellbore based on the fluid mass, the temperature data inside and outside the wellbore, and the specific heat capacity of the fluid is as follows: for each depth point i, the corresponding heat loss is calculated:

[0074]

[0075] Among them, Q (i) is the heat loss of the wellbore at the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, C is the specific heat capacity of the fluid, and M is the mass of the fluid;

[0076] The total heat loss from the wellbore is obtained by adding:

[0077]

[0078] Among them, Q loss is the total heat loss of the wellbore, Q (i) is the heat loss of the wellbore at the i-th depth point, and n is the number of depth points.

[0079] The advantage of step 2 is that by dimensionlessly processing the fluid flow rate and injection duration, the fluid mass can be accurately calculated, and the heat loss can be accurately determined by combining the temperature data inside and outside the wellbore and the specific heat capacity of the fluid. This systematic calculation method improves the accuracy of heat loss assessment and makes subsequent analysis more reliable; compared with the prior art, this step uses accurate fluid mass calculation and multi-parameter comprehensive analysis methods, which can more comprehensively reflect the actual heat loss of the wellbore compared to relying only on a single parameter or empirical formula, thereby improving the scientificity and practicality of the analysis results; in this patent solution, step 2 can provide key basic data for subsequent correlation analysis and regression model establishment, ensuring the accuracy of heat loss calculation, thereby promoting the effective implementation of the entire solution in optimizing fluid injection conditions and improving heat recovery efficiency.

[0080] Step 3: Use the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss, and identify the key parameters that have a significant impact on heat loss;

[0081] In this embodiment, the Pearson correlation coefficient method is used to analyze the relationship between each key parameter and heat loss, and the specific logic is as follows:

[0082] The Pearson correlation coefficient is a statistic that measures the strength and direction of the linear relationship between two variables. Its value range is: (-1, +1). The specific steps are as follows:

[0083] Collect a batch of historical key parameters of the wellbore and the total heat loss data of the corresponding wellbore. The key parameters are the pressure data in the wellbore, the flow rate of the injected fluid, the temperature inside and outside the wellbore, and the fluid injection time data;

[0084] The Pearson correlation coefficient is calculated according to the following formula:

[0085]

[0086] Among them, r is the Pearson correlation coefficient, X j represents the key parameter of the jth sample, Y j represents the heat loss of the jth sample, is the mean of the key parameter X, is the mean value of heat loss;

[0087] The calculated Pearson correlation coefficient value r is used to analyze the relationship between each key parameter and the heat loss of the wellbore:

[0088] When r>0, it indicates that there is a positive correlation between the parameter and the heat loss, which means that the heat loss increases when the parameter increases:

[0089] When r < 0, it indicates that there is a negative correlation between the parameter and heat loss, which means that heat loss decreases when the parameter increases;

[0090] When r = 0, there is no correlation, which means that there is no linear relationship between this parameter and heat loss;

[0091] Among them, the closer |r| is to 1, the stronger the correlation is. The absolute value |r| of the Pearson correlation coefficient of each key parameter calculated is sorted, and the key parameters whose absolute value of the Pearson correlation coefficient exceeds the preset correlation threshold RY are defined as significantly correlated with heat loss, and the key parameters significantly correlated with heat loss are identified.

[0092] The advantage of step 3 is that it uses the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss, and clearly identify the key factors that have a significant impact on heat loss. This analysis method can provide data support for decision-making, making optimization measures more targeted and effective; compared with the prior art, this step can more scientifically and systematically reveal the intrinsic relationship between each parameter and heat loss through quantitative analysis rather than subjective judgment. This method not only improves the objectivity of the analysis, but also better adapts to the complex geothermal mining environment and ensures the effectiveness of the optimization strategy; in this patent solution, the implementation of step 3 provides a key data basis for the establishment of the subsequent regression model, so that the model can accurately reflect the relationship between heat loss and key parameters. This process enhances the scientific nature of the overall solution, makes the design of the optimization solution more accurate and effective, and thus improves the efficiency of geothermal mining.

[0093] Step 4: Establish a regression model to characterize the relationship between heat loss and key parameters. The analysis results guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss.

[0094] In this embodiment, the specific logic of establishing a regression model to characterize the relationship between total heat loss and various key parameters is as follows:

[0095] Relying on the correlation results obtained in step 3, a linear regression model is constructed, and the key parameters significantly correlated with heat loss are defined as strongly correlated key parameters. The strongly correlated key parameters are used as independent variables in the model, and the corresponding total heat loss is used as the dependent variable. Different types of strongly correlated key parameters are defined as T1, T2, ..., T k , k is the number of types of strongly correlated key parameters, and the model expression of the linear regression model is as follows:

[0096] Q loss =α1*T1+α2*T2+…+α k *T k +∈

[0097] Among them, Q loss is the total heat loss of the wellbore, α1, α2, ..., α k is the regression coefficient to be optimized, ∈ is the error term;

[0098] A sample set is obtained from historical data, where the sample set consists of multiple groups of strongly correlated key parameters and corresponding total heat loss, and the sample set is input into a linear regression model for training to obtain a linear regression model after training;

[0099] The regression coefficients α1, α2, ..., α k The determination process of and error term ∈ specifically includes:

[0100] A set of sample data of known wellbore heat loss is collected, and key parameters significantly related to heat loss in the sample data are different from each other to form a data set;

[0101] Combine the sample data of known wellbore heat loss with the corresponding key parameters significantly related to heat loss to form a data matrix; the rows represent the samples and the columns represent the key parameters significantly related to heat loss;

[0102] The target variable is set as the wellbore heat loss of the sample, and the key parameters significantly related to heat loss are used as independent variables;

[0103] Select the linear regression model for modeling. The regression model is expressed as:

[0104] Qloss =α1*T1+α2*T2+…+α k *T k +∈

[0105] Among them, Q loss is the target variable, T1, T2, ..., T k is the key parameter significantly related to heat loss, k is the number of key parameters, ∈ is the error term; α1, α2, ..., α k is the regression coefficient to be obtained,

[0106] The model is fitted by the least squares method to minimize the square error between the predicted value and the actual value. The minimized objective function is as follows:

[0107]

[0108] Among them, P u is the wellbore heat loss of the uth sample, is the wellbore heat loss predicted by the model, and m is the total number of samples;

[0109] Through linear regression analysis, the regression coefficient and error term ∈ of each key parameter significantly associated with heat loss were calculated.

[0110] The analysis results guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss. The specific logic is as follows:

[0111] Taking the maximum and minimum values ​​of various strongly correlated key parameters in the sample set as constraints, the initial population is randomly generated, and the initial population consists of multiple individuals. The individuals are input into the linear regression model to obtain the corresponding total heat loss, and the individuals are sorted from small to large according to the total heat loss. The individuals at the top of the sorting are selected as the parents and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parents are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the smallest total heat loss is selected as the optimal parameter combination, and the current parameter value is adjusted according to the parameter value in the optimal parameter combination. For example: when the strongly correlated key parameters are the flow rate of the injected fluid, the injection time of the fluid, and the thermal conductivity of the nanofluid, the individual is composed of the above three genes, and each gene corresponds to a strongly correlated key parameter, and the value of the gene is between the maximum and minimum values ​​of the strongly correlated key parameters of the sample set.

[0112] The advantage of step 4 is that by establishing a regression model, the relationship between heat loss and key parameters can be clearly characterized, allowing researchers to optimize the system based on the model results. This modeling method provides a powerful tool for quantitative analysis, which can better predict heat loss and formulate more effective optimization strategies; compared with the existing technology, this step not only improves the prediction accuracy of heat loss, but also reveals the complex interactive relationship between parameters through regression analysis, surpassing the traditional empirical formula or simple linear analysis. This method is more scientific and adaptable, and can more effectively respond to challenges under different operating conditions; in this patent scheme, step 4 provides strong decision-making support for the implementation of the entire scheme. By analyzing the parameters through genetic algorithms, the adjustment of fluid injection conditions can be more effectively guided, thereby reducing heat loss, improving the overall efficiency of deep geothermal mining, and enhancing the practical application value of the scheme.

[0113] See also Figure 2 , a system for determining heat loss from a wellbore in a deep geothermal development well, comprising:

[0114] A parameter acquisition module is used to acquire key parameters of the wellbore in real time, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data;

[0115] The heat loss calculation module calculates the fluid mass based on the dimensionless fluid flow rate and fluid injection duration, and determines the wellbore heat loss based on the fluid mass, the wellbore internal and external temperature data, and the specific heat capacity of the fluid;

[0116] Correlation analysis module, used to analyze the relationship between key parameters and heat loss using the Pearson correlation coefficient method, and identify key parameters that have a significant impact on heat loss;

[0117] The model building and optimization module is used to establish a regression model to characterize the relationship between heat loss and key parameters, guide the optimization strategy through analysis results, and adjust the fluid injection conditions to reduce heat loss.

[0118] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0119] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for determining heat loss in a deep geothermal development wellbore, characterized in that: The specific steps include: Step 1: Real-time collection of key parameters of the wellbore, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data; Step 2: Calculate the fluid mass based on the dimensionless fluid flow rate and fluid injection time, and determine the wellbore heat loss based on the fluid mass, wellbore internal and external temperature data, and the specific heat capacity of the fluid; Step 3: Use the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss, and identify the key parameters that have a significant impact on heat loss; Step 4: Establish a regression model to characterize the relationship between heat loss and key parameters. Use the analysis results to guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss.

2. A method for determining heat loss in a deep geothermal development wellbore according to claim 1, characterized in that: The specific logic for collecting the key parameters of the wellbore is as follows: A pressure sensor is installed at the wellbore entrance to monitor the wellbore pressure in real time, denoted as P; Temperature sensors are set every 5 meters to monitor the temperature inside and outside the wellbore in real time, denoted as T in and T out , for each depth point, calculate the temperature difference between its inside and outside: Where, ΔT i is the temperature difference between inside and outside of the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, i is the index of the depth point; Use an electromagnetic flowmeter to monitor the flow rate of the injected fluid in real time, recorded as R, and simultaneously record the duration of the fluid injection, recorded as S; Use an online thermal conductivity measuring instrument to monitor the thermal conductivity of the nanofluid, denoted as g; The specific heat capacity data of nanofluids is obtained by referring to relevant materials and is denoted as C.

3. A method for determining heat loss in a deep geothermal development wellbore according to claim 2, characterized in that: The fluid mass is calculated based on the dimensionless fluid flow rate and fluid injection duration, and the formula is as follows: M=ρ*R*S Among them, M is the mass of the fluid, ρ is the density of the fluid, which is obtained by consulting relevant materials, S is the duration of fluid injection, and R is the flow rate of the injected fluid; The specific logic for determining the heat loss of the wellbore based on the fluid mass, the temperature data inside and outside the wellbore, and the specific heat capacity of the fluid is as follows: for each depth point i, the corresponding heat loss is calculated: Among them, Q (i) is the heat loss of the wellbore at the i-th depth point, is the internal temperature of the i-th depth point, is the external temperature at the i-th depth point, C is the specific heat capacity of the fluid, and M is the mass of the fluid; The total heat loss from the wellbore is obtained by adding: Among them, Q loss is the total heat loss of the wellbore, Q (i) is the heat loss of the wellbore at the i-th depth point, and n is the number of depth points.

4. A method for determining heat loss in a deep geothermal development wellbore according to claim 1, characterized in that: The specific logic of using the Pearson correlation coefficient method to analyze the relationship between each key parameter and heat loss is as follows: The Pearson correlation coefficient is a statistic that measures the strength and direction of the linear relationship between two variables. Its value range is: (-1, +1). The specific steps are as follows: Collect a batch of historical key parameters of the wellbore and the total heat loss data of the corresponding wellbore. The key parameters are the pressure data in the wellbore, the flow rate of the injected fluid, the temperature inside and outside the wellbore, and the fluid injection time data; The Pearson correlation coefficient is calculated according to the following formula: Among them, r is the Pearson correlation coefficient, X j represents the key parameter of the jth sample, Y j represents the heat loss of the jth sample, is the mean of the key parameter X, is the mean value of heat loss; The calculated Pearson correlation coefficient value r is used to analyze the relationship between each key parameter and the heat loss of the wellbore: When r>0, it indicates that there is a positive correlation between the parameter and heat loss, which means that when the parameter increases, the heat loss also increases; When r < 0, it indicates that there is a negative correlation between the parameter and heat loss, which means that heat loss decreases when the parameter increases; When r = 0, there is no correlation, which means that there is no linear relationship between this parameter and heat loss; Among them, the closer |r| is to 1, the stronger the correlation is. The absolute value |r| of the Pearson correlation coefficient of each key parameter calculated is sorted, and the key parameter whose absolute value of the Pearson correlation coefficient exceeds the preset correlation threshold RY is defined as significantly correlated with heat loss.

5. A method for determining heat loss in a deep geothermal development wellbore according to claim 4, characterized in that: The specific logic of establishing a regression model to characterize the relationship between total heat loss and each key parameter is as follows: relying on the correlation result obtained in step 3, a linear regression model is constructed, and the key parameters significantly correlated with heat loss are defined as strongly correlated key parameters, and the strongly correlated key parameters are used as independent variables in the model, and the corresponding total heat loss is used as the dependent variable, and different types of strongly correlated key parameters are defined as T1, T2, ..., T k , k is the number of types of strongly correlated key parameters, and the model expression of the linear regression model is as follows: Q loss =α1*T1+α2*T2+…+α k *T k +∈ Among them, Q loss is the total heat loss of the wellbore, α1,α2,…,α k is the regression coefficient to be optimized, ∈ is the error term; A sample set is obtained from historical data, where the sample set consists of multiple groups of strongly correlated key parameters and the corresponding total heat loss. The sample set is input into a linear regression model for training to obtain a linear regression model after training.

6. A method for determining heat loss in a deep geothermal development wellbore according to claim 5, characterized in that: The analysis results guide the optimization strategy and adjust the fluid injection conditions to reduce heat loss. The specific logic is as follows: Taking the maximum and minimum values ​​of various strongly correlated key parameters in the sample set as constraints, an initial population is randomly generated, and the initial population consists of multiple individuals. The individuals are input into the linear regression model to obtain the corresponding total heat loss, and the individuals are sorted from small to large according to the total heat loss. The individuals at the top of the sorting are selected as the parents and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parents are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the smallest total heat loss is selected as the optimal parameter combination, and the current parameter value is adjusted according to the parameter value in the optimal parameter combination.

7. A system for determining heat loss in a deep geothermal wellbore, characterized in that: The system for determining heat loss of a deep geothermal development drilling wellbore is used to execute the method for determining heat loss of a deep geothermal development drilling wellbore according to any one of claims 1 to 6, comprising: A parameter acquisition module is used to acquire key parameters of the wellbore in real time, including pressure data in the wellbore, flow rate of injected fluid, temperature inside and outside the wellbore, thermal conductivity of nanofluid, specific heat capacity of fluid, and fluid injection duration data; The heat loss calculation module calculates the fluid mass based on the dimensionless fluid flow rate and fluid injection duration, and determines the wellbore heat loss based on the fluid mass, the wellbore internal and external temperature data, and the specific heat capacity of the fluid; Correlation analysis module, used to analyze the relationship between key parameters and heat loss using the Pearson correlation coefficient method, and identify key parameters that have a significant impact on heat loss; The model building and optimization module is used to establish a regression model to characterize the relationship between heat loss and key parameters, guide the optimization strategy through analysis results, and adjust the fluid injection conditions to reduce heat loss.

Images