Optimization method of heat exchange efficiency of energy shaft based on intelligent analysis of formation thermophysical properties

Abstract

The present invention discloses a method for optimizing the heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties, including: constructing a structured thermophysical parameter database by integrating laboratory tests, field exploration and literature data, covering key parameters such as thermal conductivity, specific heat capacity, and thermal diffusivity. Combining scaled physical experiments with multi-parameter coupled numerical simulations, the heat transfer model is verified and expanded; using machine learning algorithms such as random forests and neural networks, a nonlinear prediction model of thermophysical parameters and energy shaft heat exchange efficiency is established, parameter contributions are quantified, and adaptability thresholds are defined. By matching the similarity between drilling exploration data and the database, the optimal formation depth is recommended, and finally a cloud-based intelligent platform is integrated to achieve real-time data updates, online calculations, and construction recommendations. According to the present invention, the accuracy of formation adaptability assessment in the development of energy shaft ground-source heat pump systems is significantly improved, and the efficiency of geothermal energy development is significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optimized design of ground source heat pump systems and efficient utilization of underground energy, and in particular to a method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of stratum thermophysical properties. Background Art

[0002] In geothermal energy development, traditional ground-source heat pump systems (such as horizontal buried pipes or vertical U-tubes) typically rely on shallow geothermal resources. Their heat transfer performance is limited by the assumption of uniform formations and empirical parameter selection, and the adaptability requirements for formation thermophysical parameters are relatively broad. However, as a new type of high-efficiency heat exchange structure, energy shafts are deeper, have a significantly increased contact area with the formation, and require energy extraction and storage through efficient heat exchange in specific formations. This particularity requires precise screening of formations with suitable thermal conductivity, thermal diffusivity, and heat capacity, and optimization of the depth and location of shaft deployment to avoid thermal imbalance, efficiency degradation, or a surge in construction costs.

[0003] Currently, the engineering implementation of energy shafts still faces the following bottlenecks: First, traditional methods rely on local exploration data or a single thermophysical parameter (such as thermal conductivity) for formation assessment, ignoring the multi-parameter coupling and nonlinear heat transfer effects, resulting in deviations in the prediction of shaft heat exchange efficiency; second, existing numerical simulation models (such as finite element analysis) find it difficult to dynamically quantify the impact of formation heterogeneity and depth gradient changes on the long-term performance of the shaft; in addition, there is a lack of an intelligent evaluation system for energy shafts, and it is impossible to quickly match the optimal formation parameter thresholds based on multi-source data and machine learning. Construction decisions still rely on manual experience, which is inefficient and high-risk. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the purpose of the present invention is to provide a method for optimizing the heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties. To meet the special needs of energy shafts, an intelligent formation adaptability assessment system is constructed by integrating multi-source data, multi-physics field simulation, and machine learning algorithms to solve the key problems of traditional methods in parameter coupling analysis, dynamic threshold optimization, and engineering adaptability decision-making. In order to achieve the above-mentioned purpose and other advantages of the present invention, a method for optimizing the heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties is provided, including:

[0005] S1. Build a structured thermophysical property parameter database;

[0006] S2. Validate and expand the heat transfer model through scaled physical experiments and multi-parameter coupled numerical simulations;

[0007] S3. Establish a nonlinear prediction model of thermophysical parameters and heat transfer efficiency of energy shafts;

[0008] S4. By matching the similarity between drilling exploration data and the database, the optimal formation depth is recommended, and finally integrated into the cloud-based intelligent platform to achieve real-time data updates, online calculations and construction recommendations.

[0009] Preferably, the structured thermophysical parameter database is constructed by collecting thermophysical parameters such as thermal conductivity, specific heat capacity and thermal diffusivity of various soils and rocks through laboratory testing, field exploration and literature integration.

[0010] Preferably, the structured thermophysical parameter database is classified according to formation type, rock type, depth range and geographical region.

[0011] Preferably, the scaled physical experiment in step S2 specifically involves designing a scaled physical model according to target formation conditions, using transparent acrylic material to make a vertical shaft model, and filling the interior with simulated formation material.

[0012] Preferably, the multi-parameter coupled numerical simulation in step S2 is specifically performed by using COMSOL Multiphysics software, configuring multi-physics field coupling analysis, inputting experimental data, establishing a three-dimensional heat transfer model, and simulating the heat exchange process; setting boundary conditions, such as constant heat flux input and adiabatic boundary, and ensuring the accuracy and practicality of the model through meshing and parameter adjustment.

[0013] Preferably, step S3 specifically includes cleaning and processing the thermophysical property parameters in the structured thermophysical property parameter database to ensure data quality, converting them into a format suitable for use by a machine learning algorithm, training the model using a training data set through the machine learning algorithm, and tuning hyperparameters; evaluating the performance of the model through cross-validation and test sets to ensure that the model can effectively predict heat transfer efficiency.

[0014] Preferably, a thermophysical parameter importance analysis is performed, specifically by applying SHAP values ​​or other feature importance algorithms to analyze the model, quantifying the specific contribution of each thermophysical parameter to the heat transfer efficiency, and determining key parameters based on the thermophysical parameter importance results so that they can be focused on in subsequent evaluation and design.

[0015] Preferably, a heat transfer efficiency scoring model is constructed through importance analysis of thermophysical property parameters, and the heat transfer efficiency scoring model is used to output a heat transfer efficiency score based on input parameters including thermal conductivity, specific heat capacity, and thermal diffusivity.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] 1. This invention establishes a systematic and comprehensive database of thermophysical parameters through laboratory testing, field exploration and literature integration, which significantly improves the reliability and availability of data.

[0018] 2. The present invention uses machine learning algorithms to deeply explore the nonlinear relationship between thermophysical parameters and heat transfer efficiency, construct a high-precision "parameter-performance" prediction model, and improve the prediction effect and adaptability.

[0019] 3. Based on data matching algorithms and measured parameters, the present invention provides accurate formation depth recommendations and heat exchange efficiency scoring models, significantly improving the success rate and economic benefits of geothermal mining.

[0020] 4. The present invention reduces construction risks and improves the benefits of geothermal energy development through closed-loop verification of drilling data and theoretical models. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The present invention is a flowchart of a method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermal properties. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] Reference Figure 1 , an energy shaft heat exchange efficiency optimization method based on intelligent analysis of formation thermophysical properties, including:

[0024] S1. Build a structured thermophysical parameter database. Through laboratory testing, field exploration, and literature review, collect thermophysical parameters such as thermal conductivity, specific heat capacity, and thermal diffusivity for various soils and rocks to construct a thermophysical parameter database. Use a structured database, such as a relational database or NoSQL database, to store the data. Categorize the data by stratigraphic type, depth, and geographic region, and annotate the data source and test conditions. Collect various soil and rock samples and test their thermal conductivity, specific heat capacity, and thermal diffusivity using standardized laboratory equipment, such as thermal conductivity meters, specific heat capacity meters, and thermal diffusivity meters. Establish experimental standards (such as temperature, humidity, and pressure) to ensure data reproducibility and comparability. Select target areas and utilize seismic exploration, geological drilling, and other techniques to obtain thermophysical parameters for soils and rocks. These parameters include stratigraphic type, lower and upper depth limits, geographic region, thermal conductivity, specific heat capacity, thermal diffusivity, density, water content, porosity, and test temperature. Collect thermophysical samples at various depths to ensure coverage of diverse stratigraphic types. Systematically organize literature related to existing research, extract relevant thermophysical property data, and enter them into the database in a certain format. Use a relational database to store data, such as PostgreSQL, and classify by formation type: including sandstone, shale, granite, rock type: including fine grained, medium grained, coarse grained, depth range: including 0-100m, 100-200m, and geographical region. Set fields including: sample name, formation type, rock type, depth, thermal conductivity, specific heat capacity, thermal diffusivity, data source, and test conditions. Ensure that data can be stored and retrieved efficiently. Label the data source and test conditions for each data record to ensure the verifiability of the data.

[0025] S2. Verify and expand the heat transfer model through scaled physical experiments and multi-parameter coupled numerical simulations. Design scaled physical model experiments to simulate the heat transfer process in the energy shaft under different formation conditions and measure thermal response parameters. Combined with numerical simulation tools such as COMSOL and ANSYS, establish a multi-parameter coupled heat transfer model to verify experimental data and expand the parameter range. Design a scaled physical model based on the target formation conditions to ensure that the model can realistically represent the heat transfer process in the energy shaft. Design a scaled physical model of appropriate scale. Use transparent acrylic material to construct the shaft model and fill it with simulated formation materials, such as a mixture of sand and gravel of different particle sizes. Establish a fluid circulation system to simulate the heat exchange process under actual working conditions. Install temperature sensors and heat flow meters to monitor the temperature distribution and heat flow changes within the model. Consider boundary conditions, such as thermal insulation at the top and bottom of the model, to simulate infinite formation conditions.

[0026] Furthermore, using COMSOL Multiphysics software, we configured a multiphysics coupled analysis, specifically heat conduction and fluid flow. We input experimental data, built a 3D heat transfer model, and simulated the heat transfer process. Boundary conditions, such as constant heat flux input and adiabatic boundaries, were set. Meshing and parameter adjustments ensured the accuracy and practicality of the model. The simulation results were compared with the experimental data to confirm the model's accuracy, and necessary corrections and optimizations were made.

[0027] S3. Develop a nonlinear prediction model for thermophysical parameters and heat transfer efficiency in energy shafts. Leveraging machine learning algorithms (such as random forests and neural networks), the nonlinear relationship between thermophysical parameters and heat transfer efficiency is learned from the database, creating a parameter-performance prediction model. Feature importance analysis is used to quantify the contribution of each parameter to heat transfer efficiency. Based on parameter contribution weights, a heat transfer efficiency scoring model is developed to define thermophysical parameter thresholds for suitable heat transfer formations, thereby constructing an intelligent formation suitability assessment system.

[0028] Furthermore, the thermophysical property parameters in the database are cleaned and processed to ensure data quality and converted into a format suitable for machine learning algorithms. Appropriate machine learning algorithms, such as random forests or neural networks, are selected. Model training is performed using the training dataset, and hyperparameters are tuned. Model performance is evaluated through cross-validation and test sets to ensure the model's ability to effectively predict heat transfer efficiency.

[0029] Furthermore, thermophysical parameter importance analysis is performed. SHAP values ​​or other feature importance algorithms are used to analyze the model and quantify the specific contribution of each thermophysical parameter to heat transfer efficiency. Based on the thermophysical parameter importance results, key parameters are identified for focus in subsequent evaluation and design.

[0030] Furthermore, a heat transfer efficiency scoring model was constructed. Based on an analysis of the importance of thermophysical parameters, a heat transfer efficiency scoring model was constructed. Input parameters include thermal conductivity, specific heat capacity, and thermal diffusivity, and the output is a heat transfer efficiency score (ranging from 0 to 100). Based on historical heat transfer formation data and field exploration results, thresholds for thermophysical parameters suitable for heat transfer formations were set. Weights for each parameter were determined based on their characteristic importance (e.g., a weight of 0.5 for thermal conductivity, 0.3 for specific heat capacity, and 0.2 for thermal diffusivity). The raw values ​​of each formation parameter were then normalized and mapped to a uniform range of 0-100 using a linear transformation. A comprehensive score was then calculated by multiplying the normalized scores of each parameter by their corresponding weights and summing the results to obtain a comprehensive formation score. Based on the scoring results, formations were categorized into three categories: high suitability (score > 80), moderate suitability (60 < ≤ 80), and low suitability (score ≤ 60). This process, through quantitative weight calculation and normalization, achieves standardized assessment and tiered decision-making for formation parameters.

[0031] S4. By matching the similarity between borehole exploration data and the database, the optimal formation depth is recommended. This is ultimately integrated into a cloud-based intelligent platform, enabling real-time data updates, online calculations, and construction recommendations. Drilling exploration is conducted in the target area to obtain thermophysical parameters at different depths. The measured data is compared with the optimal parameter thresholds in the database, and a similarity matching algorithm is used to recommend an optimal formation depth. Precision drilling is performed in the target area to obtain thermal conductivity, specific heat capacity, and thermal diffusivity data at different formation depths, such as 50m, 100m, and 150m. First, the data preprocessing module normalizes the measured borehole data (including thermal conductivity, specific heat capacity, and thermal diffusivity) against the database threshold parameters, and removes outliers to ensure data quality. Subsequently, a similarity calculation engine is used, employing both Euclidean distance and cosine similarity algorithms, to quantify the similarity between the measured data and the database parameters. During the matching determination phase, a multi-level screening process was designed. The primary screening process quickly filtered out unsuitable options based on distance and similarity thresholds. The depth matching phase used cubic spline interpolation to construct a continuous function of formation depth and similarity, accurately locating the optimal matching interval. Finally, when the interpolation curve met the similarity threshold at multiple consecutive depth nodes, a priority drilling recommendation was triggered. This combination of quantitative similarity calculation and intelligent matching significantly improved the scientific nature of formation selection and the success rate of exploration.

[0032] Furthermore, we will build an intelligent database and cloud computing platform, deploying a cloud-based database to support real-time data updates and multi-terminal access. We will also build an intelligent database and cloud computing platform. We will establish a cloud-based intelligent database system to ensure real-time updates and high availability. We will also design a multi-terminal access mechanism and set data access permissions to ensure users can query and use data securely and conveniently.

[0033] Furthermore, online calculation and recommendation services are integrated, integrating a heat transfer efficiency prediction model and a suitability assessment module to provide online calculations and construction recommendations. Embedding the heat transfer efficiency prediction model and the suitability assessment module into the cloud platform ensures that users can easily access relevant calculation results. A user-friendly interface allows users to input parameters, view calculation results, and generate construction recommendation reports, enhancing the user experience. The suitability assessment module comprises a scoring model and threshold judgment.

[0034] The number of devices and processing scales described herein are intended to simplify the description of the present invention, and the application, modification, and variation of the present invention will be apparent to those skilled in the art. Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiment. They can be applied to various fields suitable for the present invention. For those skilled in the art, additional modifications can be easily implemented. Therefore, the present invention is not limited to the specific details and illustrations shown and described herein without departing from the general concept defined by the claims and their equivalents.

Claims

1. A method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermal properties, characterized in that: The following steps are involved: S1. Build a structured thermophysical property parameter database; S2. Validate and expand the heat transfer model through scaled physical experiments and multi-parameter coupled numerical simulations; S3. Establish a nonlinear prediction model for thermophysical parameters and heat transfer efficiency of energy shafts. Utilize machine learning algorithms to learn the nonlinear relationship between thermophysical parameters and heat transfer efficiency from the database and construct a "parameter-performance" prediction model. Through feature importance analysis, the contribution of each parameter to heat transfer efficiency is quantified. Based on the parameter contribution weights, a heat transfer efficiency scoring model is established, the thresholds of thermophysical parameters suitable for heat transfer formations are defined, and an intelligent assessment system for formation suitability is constructed. S4. By matching the similarity between drilling exploration data and the database, the optimal formation depth is recommended, and finally integrated into the cloud-based intelligent platform to achieve real-time data updates, online calculations and construction recommendations.

2. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 1, characterized in that: The structured thermophysical parameter database is constructed by collecting thermophysical parameters such as thermal conductivity, specific heat capacity, and thermal diffusivity of various soils and rocks through laboratory testing, field exploration, and literature integration.

3. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 2, characterized in that: The structured thermophysical parameter database is classified according to formation type, rock type, depth range and geographical region.

4. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 1, characterized in that: The scaled physical experiment in step S2 specifically involves designing a scaled physical model according to target formation conditions, making a vertical shaft model using transparent acrylic material, and filling the interior with simulated formation material.

5. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 4, characterized in that: The multi-parameter coupled numerical simulation in step S2 specifically includes using COMSOL Multiphysics software, configuring multi-physics field coupling analysis, inputting experimental data, establishing a three-dimensional heat transfer model, and simulating the heat exchange process; setting boundary conditions, such as constant heat flux input and adiabatic boundaries, and ensuring the accuracy and practicality of the model through meshing and parameter adjustment.

6. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 1, characterized in that: Step S3 specifically includes cleaning and processing the thermophysical property parameters in the structured thermophysical property parameter database to ensure data quality, converting them into a format suitable for use by the machine learning algorithm, training the model using the training data set through the machine learning algorithm, and tuning the hyperparameters; evaluating the performance of the model through cross-validation and test sets to ensure that the model can effectively predict heat transfer efficiency.

7. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 6, characterized in that: Conduct thermophysical parameter importance analysis, specifically by applying SHAP values ​​or other feature importance algorithms to analyze the model, quantify the specific contribution of each thermophysical parameter to heat transfer efficiency, and determine key parameters based on the thermophysical parameter importance results so that they can be focused on in subsequent evaluation and design.

8. The method for optimizing heat exchange efficiency of energy shafts based on intelligent analysis of formation thermophysical properties according to claim 7, characterized in that: Through the importance analysis of thermophysical parameters, a heat transfer efficiency scoring model is constructed, which is used to output a heat transfer efficiency score based on input parameters including thermal conductivity, specific heat capacity, and thermal diffusivity.

Images