Artificial cooling device parameter automatic optimization method and system based on soil data analysis

Abstract

The application discloses an artificial cooling equipment parameter automatic optimization method and system based on soil data analysis, and relates to the technical field of artificial cooling. The method comprises the following steps: building a regional soil cooling simulation space according to three-dimensional soil structure information, water injection well distribution information and extraction well distribution information; obtaining three-dimensional soil temperature distribution through distributed optical fiber temperature measurement equipment monitoring, and calculating three-dimensional soil temperature difference distribution in combination with a preset cooling target; constructing a regional soil cooling prediction model based on a soil flow mechanism and the regional soil cooling simulation space; using the regional soil cooling prediction model to perform iterative optimization of cooling equipment parameters, and outputting adaptive equipment parameters; and controlling the cooling device and the heat energy recovery device to perform soil cooling work in a target region according to the adaptive equipment parameters. The technical problems of low cooling efficiency, excessive resource consumption and local hot area residue caused by the fact that the artificial cooling equipment parameters cannot be dynamically changed and optimized in real time according to soil data in the prior art are solved.

Description

Technical Field

[0001] This application relates to the field of artificial cooling technology, specifically to an automatic optimization method and system for artificial cooling equipment parameters based on soil data analysis. Background Technology

[0002] With rapid industrialization and urbanization, soil pollution has become increasingly prominent. Artificial cooling equipment is becoming more and more common in soil remediation. However, traditional artificial cooling equipment parameter settings often rely on experience and simple estimations, lacking precise consideration of actual soil conditions. The parameters of artificial cooling equipment cannot be optimized in real time according to dynamic changes in soil data, potentially leading to problems such as excessive energy consumption, poor cooling effect, and uneven temperature distribution. Summary of the Invention

[0003] This application provides an automatic optimization method and system for artificial cooling equipment parameters based on soil data analysis, which solves the technical problem in the prior art that the parameters of artificial cooling equipment cannot be optimized in real time according to the dynamic changes of soil data, resulting in low cooling efficiency, excessive resource consumption, and residual local heat zones.

[0004] The technical solution to the above-mentioned technical problems in this application is as follows:

[0005] In a first aspect, this application provides an automatic optimization method for the parameters of artificial cooling equipment based on soil data analysis, the method comprising:

[0006] A regional soil cooling simulation space is constructed based on the three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information of the target area;

[0007] The current three-dimensional soil temperature distribution is obtained by monitoring the distributed fiber optic temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target in the preset time zone.

[0008] A regional soil cooling prediction model is constructed based on the soil flow mechanism and the simulation space of the regional soil cooling.

[0009] Using the regional soil cooling prediction model, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized, and the adapted equipment parameters are output. The cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device.

[0010] Within the preset time zone, the cooling device and heat recovery device are controlled according to the parameters of the adapted equipment to perform soil cooling operations in the target area.

[0011] Secondly, this application provides an automatic optimization system for the parameters of artificial cooling equipment based on soil data analysis, including:

[0012] The simulation space construction module is used to build a regional soil cooling simulation space based on the three-dimensional soil structure information, water injection well distribution information and extraction well distribution information of the target area; the current three-dimensional soil temperature distribution is monitored and obtained through distributed fiber optic temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target within the preset time zone.

[0013] The temperature difference distribution calculation module is used to monitor and obtain the current three-dimensional soil temperature distribution through distributed fiber optic temperature measurement equipment, and calculate the three-dimensional soil temperature difference distribution by combining it with the preset cooling target in the preset time zone.

[0014] The prediction model building module is used to build a regional soil cooling prediction model based on the soil flow mechanism and the regional soil cooling simulation space.

[0015] The adaptation parameter output module is used to utilize the regional soil cooling prediction model, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption, water consumption, and maximizing task completion and temperature distribution uniformity, to iteratively optimize the cooling equipment parameters and output the adaptation equipment parameters. The cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device.

[0016] The cooling operation execution module is used to control the cooling device and the heat recovery device to perform soil cooling operations in the target area according to the adapted equipment parameters within the preset time zone.

[0017] This application provides one or more technical solutions, which have at least the following technical effects or advantages:

[0018] This application provides a method and system for automatically optimizing the parameters of artificial cooling equipment based on soil data analysis. It utilizes three-dimensional soil structure information and the distribution information of injection and extraction wells to construct a simulation space, and builds a predictive model based on soil flow mechanisms to iteratively optimize the cooling equipment parameters. By optimizing equipment parameters in real time according to the dynamic changes in soil data, it effectively reduces equipment energy consumption, minimizes water consumption, improves task completion, and makes the soil temperature distribution more uniform. This enhances the effectiveness and efficiency of soil cooling operations, providing a more scientific and precise solution for the artificial cooling stage in soil remediation, helping to solve soil pollution problems and promoting the efficient implementation of soil remediation work.

[0019] Through the above technical solution, this application achieves automatic optimization of artificial cooling equipment parameters by conducting in-depth analysis and three-dimensional modeling of soil data. Based on the soil characteristics and cooling requirements of different target areas, the cooling equipment parameters are dynamically adjusted in real time to ensure that the equipment is always in the best operating condition. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the automatic optimization method for artificial cooling equipment parameters based on soil data analysis provided in this application embodiment;

[0022] Figure 2 This is a schematic diagram of the structure of the automatic optimization system for artificial cooling equipment parameters based on soil data analysis provided in the embodiments of this application.

[0023] The components represented by each number in the attached diagram are explained below:

[0024] The simulation space construction module 11, the temperature distribution calculation module 12, the prediction model construction module 13, the adaptation parameter output module 14, and the cooling operation execution module 15 are all included. Detailed Implementation

[0025] This application provides a method and system for automatically optimizing the parameters of artificial cooling equipment based on soil data analysis. This addresses the technical problem in the prior art where the parameters of artificial cooling equipment cannot be optimized in real time according to dynamic changes in soil data, resulting in low cooling efficiency, excessive resource consumption, and residual local heat zones.

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0028] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessarily obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0029] Example 1, as Figure 1 As shown in the embodiments of this application, an automatic optimization method for parameters of artificial cooling equipment based on soil data analysis is provided, including:

[0030] S10: Construct a regional soil cooling simulation space based on the three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information of the target area;

[0031] In this embodiment, three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information of the target area are first collected. The three-dimensional soil structure information can reflect the soil's layers, texture, porosity, and other characteristics, and affects the transfer and diffusion of heat in the soil. The water injection well distribution information and extraction well distribution information determine the location and method of cold water injection and hot water extraction during the cooling process, which is related to the cooling effect.

[0032] Secondly, the collected information is integrated to construct a regional soil cooling simulation space, which can simulate soil temperature changes under different cooling equipment parameters. By constructing the regional soil cooling simulation space, the temperature distribution and change trend during the soil cooling process can be observed, providing a basis for adjusting the cooling equipment parameters.

[0033] Specifically, step S10 in the method includes:

[0034] Obtain three-dimensional soil structure information of the target area, wherein the three-dimensional soil structure information includes soil type, soil particle composition, soil permeability coefficient, soil porosity, soil heat capacity, soil thermal conductivity and soil spatial distribution;

[0035] The topology and attribute information of the heating wells during in-situ thermal desorption of soil in the target area are used as the distribution information of the water injection wells, and the topology and attribute information of the extraction wells are used as the distribution information of the extraction wells.

[0036] Within the 3D simulation platform, regional simulation modeling is performed based on the 3D soil structure information, water injection well distribution information, and extraction well distribution information to generate a regional soil cooling simulation space.

[0037] In this embodiment, firstly, various parameters from the three-dimensional soil structure information are acquired, including soil type, soil particle composition, soil permeability coefficient, soil porosity, soil heat capacity, soil thermal conductivity, and soil spatial distribution. Soil type determines the basic properties of the soil; soil particle composition affects soil porosity and permeability coefficient, thus influencing the transfer of water and heat; soil permeability coefficient determines the flow rate of water in the soil, affecting the injection of cold water and extraction of hot water during cooling; soil porosity relates to soil aeration and water retention, and also affects heat transfer; soil heat capacity and soil thermal conductivity directly affect the thermal properties of the soil, determining the ease with which the soil can be heated or cooled; soil spatial distribution describes the type and thickness of soil layers in three-dimensional space, determining the path and rate of heat transfer in soil layers at different depths.

[0038] Secondly, the distribution information of injection wells and extraction wells within the target area is determined, including the topological distribution and attribute information of heating wells during in-situ thermal desorption operations. In-situ thermal desorption technology is an efficient and thorough method for remediating organically contaminated soils, such as volatile organic compounds (VOCs), semi-volatile organic compounds (SVOCs), polychlorinated biphenyls (PCBs), and pesticides. The topological distribution and attribute information of heating wells during in-situ thermal desorption operations in the target area are used as the distribution information for injection wells. Since the role of injection wells is similar to that of heating wells in in-situ thermal desorption operations during soil cooling, their location and attributes will affect the effectiveness of cold water injection. Similarly, the topological distribution and attribute information of extraction wells are used as the distribution information for extraction wells. Extraction wells are used to extract hot water, and their distribution and attributes affect the efficiency of hot water extraction. The attribute information of heating wells includes features such as diameter and depth.

[0039] Finally, regional simulation modeling was performed within a 3D simulation platform. Using the acquired 3D soil structure information, injection well distribution information, and extraction well distribution information, a regional soil cooling simulation space was generated. Within this simulation space, different combinations of cooling equipment parameters could be simulated, and soil temperature changes could be observed, thus providing accurate data support for subsequent parameter optimization.

[0040] S20: The current three-dimensional soil temperature distribution is obtained by monitoring the distributed optical fiber temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target in the preset time zone;

[0041] In this embodiment, the distributed fiber optic temperature measurement device can measure the temperature at different locations and depths of the soil. A preset cooling target within a preset time zone is set based on the actual needs and expected effects of soil remediation, specifying the temperature standard the soil needs to reach within a specified time. By comparing the current three-dimensional soil temperature distribution with the preset cooling target, the resulting three-dimensional soil temperature difference distribution reflects the differences in cooling requirements at different locations within the target area. The initial temperature range for the start of cooling is wide, ranging from approximately 100°C to over 400°C. For example, this application calculates the three-dimensional soil temperature difference distribution using the formula "cooling target - current three-dimensional soil temperature distribution".

[0042] For example, assuming the cooling target is 300℃ and the current three-dimensional soil temperature distribution is 400℃, the calculated three-dimensional soil temperature difference distribution is -100℃, indicating that the soil in this area needs to be reduced by 100℃ to achieve the preset cooling target. By analyzing the three-dimensional soil temperature difference distribution at different locations, the parameters of the cooling equipment can be adjusted to meet the cooling needs of different areas.

[0043] In areas with large temperature differences, the power of the cooling device can be increased or the amount of cold water injected can be increased to accelerate the cooling rate; while in areas with small temperature differences, the operating intensity of the equipment can be reduced to avoid unnecessary energy waste.

[0044] S30: Construct a regional soil cooling prediction model based on soil flow mechanism and the regional soil cooling simulation space;

[0045] In this embodiment, a regional soil cooling prediction model is constructed based on soil flow mechanisms and a regional soil cooling simulation space. Soil flow mechanisms refer to the movement patterns of water, heat, and solutes in the soil, while the regional soil cooling simulation space simulates soil temperature changes under different cooling equipment parameters. Based on the soil flow mechanisms and the aforementioned regional soil cooling simulation space, a regional soil cooling prediction model is constructed using a generative adversarial network to predict the time-varying trend of soil temperature in the target area under different cooling equipment parameters.

[0046] Specifically, step S30 in the method includes:

[0047] The three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information are expanded according to a preset tolerance interval to obtain a three-dimensional soil structure information interval, a water injection well distribution information interval, and an extraction well distribution information interval, which serve as retrieval constraints.

[0048] With the aforementioned retrieval constraints as a limit, big data technology is used to collect sample information, obtain a sample three-dimensional soil temperature distribution set and a sample cooling device parameter set, and obtain the historical three-dimensional soil temperature distribution at the end of the historical time zone as the sample predicted three-dimensional soil temperature distribution, thus obtaining the sample predicted three-dimensional soil temperature distribution set, wherein the time interval between the historical time zone and the preset time zone is the same;

[0049] Based on the soil flow mechanism and the simulation space of soil cooling in the region, an initial regional soil cooling prediction model is constructed by combining generative adversarial networks.

[0050] Using the sample three-dimensional soil temperature distribution set and the sample cooling device parameter set as inputs, and using the sample predicted three-dimensional soil temperature distribution set as supervision, the initial regional soil cooling prediction model is trained to convergence, thus obtaining the regional soil cooling prediction model.

[0051] In this embodiment, firstly, the three-dimensional soil structure information, injection well distribution information, and extraction well distribution information are expanded according to a preset tolerance range, considering the uncertainty and possible changes in the data within this range. The preset tolerance range is set based on the understanding of the actual soil environment and the possible fluctuation range of these information under different working conditions. By expanding the information, the three-dimensional soil structure information range, injection well distribution information range, and extraction well distribution information range are obtained, and these are used as retrieval constraints. For example, taking soil porosity as an example, assuming the soil porosity of the target area is 40 and the porosity tolerance range is ±10%, then the porosity range is 36-44, which serves as a constraint for comparison.

[0052] Secondly, using big data technology to collect sample information, the search constraints are applied. Big data technology has powerful data collection and processing capabilities, enabling the selection of samples that meet the search constraints from a large amount of historical and real-time monitoring data. The three-dimensional soil temperature distribution set and the parameter set of the cooling equipment are obtained, reflecting the relationship between soil temperature and cooling equipment parameters under different conditions. Simultaneously, the historical three-dimensional soil temperature distribution at the end of the historical time zone is obtained as the sample's predicted three-dimensional soil temperature distribution, resulting in the sample's predicted three-dimensional soil temperature distribution set. The time interval between the historical time zone and the preset time zone is the same, ensuring the consistency and comparability of the sample data in the time dimension, providing a reliable data foundation for model training.

[0053] Then, based on the soil flow mechanism and the regional soil cooling simulation space, an initial regional soil cooling prediction model was constructed using a generative adversarial network (GAN). A GAN is a powerful machine learning model consisting of a generator and a discriminator. In constructing the initial regional soil cooling prediction model, the generator attempts to generate soil temperature change predictions that conform to the soil flow mechanism and the simulated conditions of the simulation space, while the discriminator is responsible for judging whether the generated predictions are realistic and reasonable. Through adversarial training between the two, the model continuously learns and optimizes, improving its predictive ability for soil cooling processes.

[0054] Finally, using the sample 3D soil temperature distribution set and the sample cooling device parameter set as inputs, and the sample predicted 3D soil temperature distribution set as supervision, the initial regional soil cooling prediction model was trained until convergence, resulting in the regional soil cooling prediction model. During training, the model continuously adjusts its parameters based on the input sample data to make the prediction results as close as possible to the sample predicted 3D soil temperature distribution set. When the model's prediction error reaches a small stable value, i.e., when training converges, the obtained regional soil cooling prediction model can accurately predict the trend of soil temperature change over time in the target area under different cooling device parameters, providing a reliable basis for subsequent iterative optimization of cooling device parameters.

[0055] For example, the initial regional soil cooling prediction model based on generative adversarial networks is constructed through the following path:

[0056] First, data preparation involves obtaining the sample's three-dimensional soil temperature distribution set and the sample cooling device parameter set. Historical three-dimensional soil temperature distributions at the end of the historical time zone are then used as the sample's predicted three-dimensional soil temperature distribution set. The historical sample three-dimensional soil temperature distribution set and the sample cooling device parameter set are then used as input.

[0057] Secondly, the model is built, defining the network structures of the generator and discriminator. The generator is a neural network that receives random noise and some known soil-related information as input, processes it through a series of neuron layers and activation functions, and generates predicted soil temperature distribution data. The discriminator receives real soil temperature distribution data and the predicted data generated by the generator as input, and determines whether the input data is real.

[0058] Then, the model is trained using the Adam optimizer and the mean squared error (MSE) loss function to build the training framework. The batch size is set to 32 and the total number of training rounds is 50. An early stopping mechanism (patience=5) is introduced. When the validation set loss does not decrease for 5 consecutive rounds, the training process is automatically terminated, and the initial regional soil cooling prediction model is obtained after training. This effectively avoids model overfitting while ensuring that the model reaches the convergence state.

[0059] During training, the parameters of the generator and discriminator are updated alternately. First, the generator parameters are fixed while the discriminator parameters are updated to more accurately distinguish between real and generated data. Then, the discriminator parameters are fixed while the generator parameters are updated, making the generator's data closer to real data, thus deceiving the discriminator. Through multiple iterations of training, the generator and discriminator continuously evolve, eventually reaching a relatively stable state. At this point, the generator's predicted data can effectively simulate the real soil temperature distribution.

[0060] Among them, using the aforementioned search constraints as limitations, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling equipment, including:

[0061] Obtain the equipment attribute information of the cooling device and the heat recovery device, and add it to the search constraints. The heat recovery device is a heat pump heat recovery system applied to a ground sedimentation tank.

[0062] Using the aforementioned search constraints as a limit, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling equipment. This parameter set includes first sample equipment parameters and second sample equipment parameters. The first sample equipment parameters are the operating parameters of the cooling device, and the second sample equipment parameters are the operating parameters of the heat recovery device.

[0063] The parameters of the first sample equipment include the water injection flow rate and water injection temperature of the injection well, and the extraction vacuum degree of the extraction well.

[0064] The parameters of the second sample equipment include compressor frequency, expansion valve opening degree, and water pump speed.

[0065] In this embodiment, the equipment attribute information of the cooling device and the heat recovery device is first obtained, and then added to the obtained search constraints. The heat recovery device is a heat pump heat recovery system applied to a ground sedimentation tank, which can effectively recover the heat energy generated during the cooling process and improve energy utilization efficiency.

[0066] The heat pump heat recovery system involves injecting clean water into a heated well during the in-situ thermal desorption process after soil remediation. The mud-water mixture is then extracted from the well and allowed to settle in a sedimentation tank. Simultaneously, a heat pump heat recovery system is designed within the sedimentation tank to recover heat energy into electrical or mechanical energy, which can be used to power refrigeration equipment and cool circulating water, achieving efficient energy utilization. Alternatively, the electrical energy can be used for other electrical facilities on the construction site.

[0067] Secondly, using big data technology to collect sample information based on search constraints that include equipment attribute information, samples meeting the criteria are selected. Ultimately, a parameter set of sample cooling equipment is obtained, covering a variety of key parameters.

[0068] The parameters of the sample cooling equipment are divided into the parameters of the first sample equipment and the parameters of the second sample equipment.

[0069] The first set of equipment parameters pertains to the operating parameters of the cooling device, including the water injection flow rate and temperature of the injection well, and the extraction vacuum level of the extraction well. The water injection flow rate directly affects the amount of cold water injected into the soil; different soil structures and cooling requirements necessitate adjustments to the flow rate. The injection temperature affects the cooling speed and effectiveness; a suitable temperature lowers the soil temperature more efficiently. The extraction vacuum level of the extraction well influences the efficiency of hot water extraction, ensuring timely extraction and maintaining the smooth progress of the cooling process. For example, in highly permeable sand layers, only a small vacuum level is needed to achieve a high extraction rate. Conversely, in low-permeability clay layers, even a high vacuum level may result in a low extraction rate because the fluid struggles to flow through the dense soil pores.

[0070] The second set of equipment parameters pertains to the operating parameters of the heat recovery device, including compressor frequency, expansion valve opening, and water pump speed. Changes in compressor frequency affect the cooling and heating capacity of the heat pump; a suitable compressor frequency ensures effective heat recovery. The expansion valve opening determines the refrigerant flow rate and pressure, affecting the performance of the heat pump system. The water pump speed affects the flow rate of the circulating water, thus influencing the efficiency of heat recovery.

[0071] By collecting and analyzing the parameters of the first and second sample equipment, more accurate and detailed data support is provided for the subsequent regional soil cooling prediction model, thereby achieving precise optimization of the cooling equipment parameters.

[0072] S40: Using the regional soil cooling prediction model, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption, water consumption, and maximizing task completion and temperature distribution uniformity, iterative optimization of cooling equipment parameters is performed, and adapted equipment parameters are output. The cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device.

[0073] In this embodiment, a trained regional soil cooling prediction model is used, combined with a three-dimensional soil temperature difference distribution, to iteratively optimize the parameters of the cooling equipment. Using the three-dimensional soil temperature difference distribution as the expected workload means adjusting the equipment parameters, including the operating parameters of the cooling device and the heat recovery device, according to the cooling needs of different regions. During the optimization process, multiple objectives are set, including minimizing equipment energy consumption and water consumption, and maximizing task completion and temperature distribution uniformity. To minimize equipment energy consumption, the operating parameters of the cooling device and the heat recovery device need to be reasonably adjusted while meeting the cooling requirements to avoid excessive equipment operation and energy waste. For example, reducing the water injection flow rate of the injection well and adjusting the compressor frequency can reduce the energy consumption of the equipment.

[0074] To minimize water consumption, the injection of cold water from injection wells and the extraction of hot water from extraction wells during soil cooling processes consume significant amounts of water. Therefore, it is necessary to optimize the injection flow rate of injection wells and the extraction vacuum level of extraction wells to reduce water consumption.

[0075] To maximize task completion, the soil temperature in the target area must reach the preset cooling target as much as possible within the specified preset time zone. Based on the three-dimensional soil temperature difference distribution, parameters such as the power of the cooling device and the water injection temperature of the injection well are precisely adjusted to ensure that the soil in each area can be effectively cooled.

[0076] Regarding temperature distribution uniformity, uneven soil temperature distribution may lead to excessive cooling in some areas and insufficient cooling in others. By adjusting the distribution and operating parameters of injection and extraction wells, cold water can flow evenly in the soil, thereby achieving a more uniform cooling effect.

[0077] Through continuous iteration and optimization, the operating parameters of the cooling device and the heat recovery device are gradually adjusted until suitable equipment parameters that can simultaneously meet multiple objectives are found.

[0078] Specifically, step S40 in the method includes:

[0079] Obtain the first equipment parameter adjustment space of the cooling device and the second equipment parameter adjustment space of the heat recovery device. Randomly select multiple parameters within the first and second equipment parameter adjustment spaces and combine them to obtain multiple initial cooling device parameters.

[0080] Using the regional soil cooling prediction model, soil cooling is predicted based on the current three-dimensional soil temperature distribution and the parameters of the multiple initial cooling devices, and multiple predicted three-dimensional soil temperature distributions are output.

[0081] Based on digital twins, a joint simulation model of the cooling device and the heat recovery device is constructed to build a twin model of the cooling equipment.

[0082] Using the twin model of the cooling equipment, simulations are performed based on the parameters of the multiple initial cooling equipment, and the energy consumption and water consumption of the multiple simulated equipment are output.

[0083] Based on the multiple predicted three-dimensional soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, taking the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized, and the adapted equipment parameters are output.

[0084] In this embodiment, firstly, the first equipment parameter adjustment space of the cooling device and the second equipment parameter adjustment space of the heat recovery device are obtained. The first equipment parameter adjustment space includes the adjustable range of parameters such as water injection flow rate of the injection well, water injection temperature, and vacuum degree of the extraction well. The range is set based on the performance limitations of the equipment and the specific requirements of the soil environment. The second equipment parameter adjustment space includes the reasonable variation range of parameters such as compressor frequency, expansion valve opening degree, and water pump speed.

[0085] Secondly, after obtaining the adjustment space for the two parameters, multiple parameters are randomly selected and combined. Through a large number of random combinations, multiple initial cooling equipment parameters are obtained, and the combinations of initial cooling equipment parameters represent different equipment operation schemes.

[0086] Next, using a pre-trained regional soil cooling prediction model, soil cooling predictions were made based on the current three-dimensional soil temperature distribution and the initial cooling equipment parameters. The regional soil cooling prediction model can simulate the change of soil temperature over time under different parameter combinations, outputting multiple predicted three-dimensional soil temperature distributions. The prediction results demonstrate the changing trends and final distribution of soil temperature under different equipment operating parameters.

[0087] Then, based on digital twin technology, a joint simulation model of the cooling device and the heat recovery device is constructed to create a digital twin model of the cooling equipment. The digital twin model can reproduce the actual operation process of the equipment and simulate its operating state under different parameters. Using the cooling equipment twin model, simulations are performed based on multiple initial cooling equipment parameters, outputting the energy consumption and water consumption of multiple simulated devices.

[0088] Finally, based on multiple predicted 3D soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, and taking the 3D soil temperature difference distribution as the expected workload, the parameters of the cooling equipment are iteratively optimized to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity. During the iteration process, the equipment parameters are continuously adjusted, considering the weight of each objective, and gradually finding the optimal parameter combination that simultaneously satisfies multiple objectives, ultimately outputting the adapted equipment parameters.

[0089] Specifically, based on the multiple predicted three-dimensional soil temperature distributions, the energy consumption of multiple simulation devices, and the water consumption of multiple simulations, and taking the three-dimensional soil temperature difference distribution as the expected workload, the cooling equipment parameters are iteratively optimized with the goals of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity. The resulting optimized equipment parameters include:

[0090] Using the three-dimensional soil temperature difference distribution as the expected workload, multiple task completion rates are calculated based on the multiple predicted three-dimensional soil temperature distributions.

[0091] Temperature distribution uniformity analysis is performed on the multiple predicted three-dimensional soil temperature distributions, and multiple temperature distribution uniformity coefficients are output.

[0092] Based on preset weight ratios, and with the goals of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, a quality evaluation function for equipment parameters is constructed.

[0093] Using the equipment parameter quality evaluation function, multiple parameter quality coefficients are calculated based on multiple task completion rates, multiple temperature distribution uniformity coefficients, multiple simulated equipment energy consumption, and multiple simulated water consumption.

[0094] Based on the multiple parameter quality coefficients, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters.

[0095] In this embodiment, firstly, multiple task completion rates are calculated based on the three-dimensional soil temperature difference distribution and multiple predicted three-dimensional soil temperature distributions. The task completion rate reflects the degree to which the soil temperature in the target area reaches the preset cooling target under different initial cooling equipment parameters. By comparing the predicted soil temperature distribution with the expected three-dimensional soil temperature difference distribution, the task completion status corresponding to each parameter combination is quantified. For example, the proportion of the area where the cooling value is greater than the temperature difference represents the proportion of task completion.

[0096] Secondly, temperature distribution uniformity analysis was performed on multiple predicted three-dimensional soil temperature distributions to obtain multiple temperature distribution uniformity coefficients. The temperature distribution uniformity coefficient measures the uniformity of soil temperature distribution within a target area under different equipment parameters. Statistical methods, such as calculating the standard deviation and coefficient of variation of temperature, can be used to assess the dispersion of temperature distribution, thereby obtaining the corresponding temperature distribution uniformity coefficient.

[0097] Next, based on preset weighting ratios, a device parameter quality evaluation function is constructed with the objectives of minimizing equipment energy consumption and water consumption, and maximizing task completion and temperature distribution uniformity. The preset weighting ratios reflect the importance of each objective in the overall optimization process; different weights can be set for different application scenarios and needs. Dynamic weights can be configured for the indicators, tailored to specific circumstances; for example, if the target area has a water shortage, the weight for water consumption can be appropriately increased.

[0098] Then, using the equipment parameter quality evaluation function, combined with multiple task completion rates, multiple temperature distribution uniformity coefficients, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, multiple parameter quality coefficients are calculated. A higher parameter quality coefficient indicates that the corresponding combination of equipment parameters performs better in meeting multiple objectives.

[0099] Finally, the cooling equipment parameters are iteratively optimized based on multiple parameter quality coefficients. During the iteration process, the equipment parameters are continuously adjusted, and the parameter quality coefficients are recalculated, gradually approaching the optimal solution. When certain convergence conditions are met, such as when the parameter quality coefficients no longer show significant improvement or when the preset number of iterations is reached, the adapted equipment parameters are output. These adapted equipment parameters can minimize equipment energy consumption and water consumption while ensuring task completion and temperature distribution uniformity, achieving efficient operation of the cooling equipment.

[0100] For example, suppose a soil cooling regulation scenario has the following preset weightings: equipment energy consumption 0.25, water consumption 0.25, task completion rate 0.25, and temperature distribution uniformity 0.25. The optimal equipment energy consumption is 5 kWh, and the optimal water consumption is 4 m³ / h. 3 .

[0101] Each indicator is set to a maximum score of 100 points. Equipment energy consumption and water consumption are scored in reverse order of "actual value / optimal value × 100", with the smaller the value, the higher the score. Task completion and temperature distribution uniformity are scored directly based on the actual value.

[0102] Three sets of equipment parameters to be evaluated were selected, and the calculations were performed as follows:

[0103] Parameter group 1: Equipment energy consumption 8kWh, score 5 / 8×100=62.5; water consumption 6m³ 3The score is 4 / 6×100≈66.7; the task completion rate is 80%, the score is 80, and the temperature distribution uniformity coefficient is 0.7, the score is 70. The parameter quality coefficient is 62.5×25%+66.7×25%+80×25%+70×25%≈69.8.

[0104] Parameter group 2: Equipment energy consumption 5kWh, score 100; water consumption 4m³ 3 , score 100; task completion rate 70%, score 70; temperature distribution uniformity coefficient 0.6, score 60. Parameter quality coefficient = 100×25% + 100×25% + 70×25% + 60×25% = 82.5.

[0105] Parameter group 3: Equipment energy consumption 10kWh, score 50; water consumption 8m³ 3 50 points; 90% task completion, 90 points; 0.8 temperature distribution uniformity coefficient, 80 points. Parameter quality coefficient = 50×25% + 50×25% + 90×25% + 80×25% = 67.5.

[0106] Since a higher parameter quality coefficient indicates that the corresponding combination of equipment parameters performs better in meeting multiple objectives, parameter group 2 has the highest parameter quality coefficient and is the optimal parameter selection.

[0107] Furthermore, based on the aforementioned multiple parameter quality coefficients, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters, including:

[0108] The initial cooling equipment parameters are set as the initial solution, and multiple initial solutions are arranged in descending order of parameter quality coefficient to obtain the initial solution sequence;

[0109] The first solution in the initial solution sequence is set as the head solution, the remaining solutions are set as inferior solutions, and multiple inferior solutions are adjusted according to a preset optimization step size, with the head solution as the direction, to obtain multiple updated inferior solutions.

[0110] The head solution and multiple updated inferior solutions are rearranged according to the parameter quality coefficient from large to small to obtain an updated solution sequence. In the updated solution sequence, inferior solutions with a predetermined proportion are eliminated. Equal supplementation is performed based on the first device parameter adjustment space and the second device parameter adjustment space. The predetermined proportion decreases as the number of optimization attempts increases.

[0111] The optimization process continues iteratively, following the optimization mechanism of selecting the first solution, adjusting the inferior solution, eliminating the inferior solution, and supplementing the initial solution, until the preset number of convergences is reached. The first solution of the current updated solution sequence is then set to the parameters of the adapted device.

[0112] In this embodiment, firstly, the initial cooling equipment parameters are used as initial solutions, and multiple initial solutions are sorted from largest to smallest according to the parameter quality coefficients to form an initial solution sequence. The first solution in the initial solution sequence is determined as the head solution, and the remaining solutions are considered inferior solutions. Using the head solution as the direction, multiple inferior solutions are adjusted according to a preset optimization step size, thereby obtaining multiple updated inferior solutions. The preset optimization step size determines the magnitude of the adjustment of inferior solutions. If the step size is too large, the optimal solution may be skipped; if the step size is too small, the optimization process will become slow.

[0113] Next, the initial solution and multiple updated inferior solutions are rearranged again according to the parameter quality coefficients from largest to smallest, resulting in an updated solution sequence. Then, a predetermined proportion of inferior solutions in the updated solution sequence are eliminated. This predetermined proportion decreases as the number of optimization attempts increases. For example, initially 30% are eliminated, and then the proportion is gradually reduced. This expands the search range in the early stages of optimization and improves convergence accuracy in the later stages.

[0114] After eliminating inferior solutions, equivalent replacements are made based on the first and second equipment parameter adjustment spaces to ensure a stable number of solution sequences.

[0115] Then, iterative optimization is continuously performed according to the optimization mechanism of selecting the first solution, adjusting inferior solutions, eliminating inferior solutions, and supplementing the initial solution. During the iteration process, the changes in the parameter quality coefficients are constantly observed. When the preset number of convergences is reached, it indicates that the optimization process has basically stabilized. At this point, the first solution of the current updated solution sequence is set as the parameters suitable for the equipment. Since the parameters suitable for the equipment are obtained through multiple rounds of iterative optimization, the energy consumption and water consumption of the equipment are reduced to the greatest extent while ensuring the completion of the task and the uniformity of temperature distribution, thus achieving efficient operation of the cooling equipment.

[0116] S50: Within the preset time zone, control the cooling device and heat recovery device to perform soil cooling operations in the target area according to the parameters of the adapter device.

[0117] In this embodiment, after obtaining the appropriate equipment parameters, the cooling device and the heat recovery device will strictly execute the soil cooling operation in the target area within a preset time zone according to the parameters. For the cooling device, the injection well will inject cold water into the soil at an appropriate injection flow rate and temperature, while the extraction well will extract hot water at a suitable vacuum level to ensure that the soil temperature can be effectively reduced. At the same time, the heat recovery device will efficiently recover heat energy according to appropriate parameters such as compressor frequency, expansion valve opening, and pump speed, thereby improving energy utilization efficiency.

[0118] During operation, soil temperature changes are monitored in real time. For example, temperature sensors distributed throughout the target area continuously collect soil temperature data and feed it back to the control system. The control system compares and analyzes the real-time temperature data with the preset cooling target. If the soil temperature trend deviates from expectations, or if the temperature in some areas fails to meet the cooling requirements, the control system will promptly adjust the operating parameters of the cooling and heat recovery devices.

[0119] In summary, the embodiments of this application have at least the following technical effects:

[0120] This application provides a method and system for automatically optimizing the parameters of artificial cooling equipment based on soil data analysis. It utilizes three-dimensional soil structure information and the distribution information of injection and extraction wells to construct a simulation space, and builds a predictive model based on soil flow mechanisms to iteratively optimize the cooling equipment parameters. By optimizing the equipment parameters in real time according to the dynamic changes in soil data, it effectively reduces equipment energy consumption, minimizes water consumption, improves task completion, and makes the soil temperature distribution more uniform, thereby enhancing the effectiveness and efficiency of soil cooling operations. This provides a more scientific and precise solution for the artificial cooling stage in soil remediation, helping to solve soil pollution problems and promoting the efficient implementation of soil remediation work. Through the above technical solution, this application achieves automatic optimization of artificial cooling equipment parameters through in-depth analysis and three-dimensional modeling of soil data. Based on the soil characteristics and cooling requirements of different target areas, it dynamically adjusts the cooling equipment parameters in real time, ensuring the equipment is always in optimal operating condition.

[0121] Example 2, as Figure 2 As shown, based on the same inventive concept as the automatic optimization method for artificial cooling equipment parameters based on soil data analysis provided in Embodiment 1, this application also provides an automatic optimization system for artificial cooling equipment parameters based on soil data analysis, including:

[0122] The simulation space construction module 11 is used to construct a regional soil cooling simulation space based on the three-dimensional soil structure information, water injection well distribution information and extraction well distribution information of the target area; the current three-dimensional soil temperature distribution is monitored and obtained through distributed fiber optic temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target in the preset time zone.

[0123] The temperature difference distribution calculation module 12 is used to monitor and obtain the current three-dimensional soil temperature distribution through distributed optical fiber temperature measurement equipment, and calculate the three-dimensional soil temperature difference distribution by combining the preset cooling target in the preset time zone.

[0124] Prediction model building module 13 is used to build a regional soil cooling prediction model based on the soil flow mechanism and the regional soil cooling simulation space.

[0125] The adaptation parameter output module 14 is used to utilize the regional soil cooling prediction model, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption, water consumption, and maximizing task completion and temperature distribution uniformity, to iteratively optimize the cooling equipment parameters and output the adaptation equipment parameters, wherein the cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device.

[0126] The cooling operation execution module 15 is used to control the cooling device and the heat recovery device to perform soil cooling operations in the target area according to the adapter parameters within the preset time zone.

[0127] In one embodiment, the simulation space construction module 11 is specifically used for:

[0128] Obtain three-dimensional soil structure information of the target area, wherein the three-dimensional soil structure information includes soil type, soil particle composition, soil permeability coefficient, soil porosity, soil heat capacity, soil thermal conductivity and soil spatial distribution;

[0129] The topology and attribute information of the heating wells during in-situ thermal desorption of soil in the target area are used as the distribution information of the water injection wells, and the topology and attribute information of the extraction wells are used as the distribution information of the extraction wells.

[0130] Within the 3D simulation platform, regional simulation modeling is performed based on the 3D soil structure information, water injection well distribution information, and extraction well distribution information to generate a regional soil cooling simulation space.

[0131] In one embodiment, the prediction model building module 13 is specifically used for:

[0132] The three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information are expanded according to a preset tolerance interval to obtain a three-dimensional soil structure information interval, a water injection well distribution information interval, and an extraction well distribution information interval, which serve as retrieval constraints.

[0133] With the aforementioned retrieval constraints as a limit, big data technology is used to collect sample information, obtain a sample three-dimensional soil temperature distribution set and a sample cooling device parameter set, and obtain the historical three-dimensional soil temperature distribution at the end of the historical time zone as the sample predicted three-dimensional soil temperature distribution, thus obtaining the sample predicted three-dimensional soil temperature distribution set, wherein the time interval between the historical time zone and the preset time zone is the same;

[0134] Based on the soil flow mechanism and the simulation space of soil cooling in the region, an initial regional soil cooling prediction model is constructed by combining generative adversarial networks.

[0135] Using the sample three-dimensional soil temperature distribution set and the sample cooling device parameter set as inputs, and using the sample predicted three-dimensional soil temperature distribution set as supervision, the initial regional soil cooling prediction model is trained to convergence, thus obtaining the regional soil cooling prediction model.

[0136] Furthermore, in one embodiment of the application, using the aforementioned search constraints as a limit, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling device, including:

[0137] Obtain the equipment attribute information of the cooling device and the heat recovery device, and add it to the search constraints. The heat recovery device is a heat pump heat recovery system applied to a ground sedimentation tank.

[0138] Using the aforementioned search constraints as a limit, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling equipment. This parameter set includes first sample equipment parameters and second sample equipment parameters. The first sample equipment parameters are the operating parameters of the cooling device, and the second sample equipment parameters are the operating parameters of the heat recovery device.

[0139] The parameters of the first sample equipment include the water injection flow rate and water injection temperature of the injection well, and the extraction vacuum degree of the extraction well.

[0140] The parameters of the second sample equipment include compressor frequency, expansion valve opening degree, and water pump speed.

[0141] In one embodiment, the adaptation parameter output model 14 is specifically used for:

[0142] Obtain the first equipment parameter adjustment space of the cooling device and the second equipment parameter adjustment space of the heat recovery device. Randomly select multiple parameters within the first and second equipment parameter adjustment spaces and combine them to obtain multiple initial cooling device parameters.

[0143] Using the regional soil cooling prediction model, soil cooling is predicted based on the current three-dimensional soil temperature distribution and the parameters of the multiple initial cooling devices, and multiple predicted three-dimensional soil temperature distributions are output.

[0144] Based on digital twins, a joint simulation model of the cooling device and the heat recovery device is constructed to build a twin model of the cooling equipment.

[0145] Using the twin model of the cooling equipment, simulations are performed based on the parameters of the multiple initial cooling equipment, and the energy consumption and water consumption of the multiple simulated equipment are output.

[0146] Based on the multiple predicted three-dimensional soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, taking the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized, and the adapted equipment parameters are output.

[0147] Furthermore, in one embodiment, based on the multiple predicted three-dimensional soil temperature distributions, the energy consumption of multiple simulation devices, and the multiple simulated water consumptions, with the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize device energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, iterative optimization of cooling device parameters is performed, outputting adapted device parameters, including:

[0148] Using the three-dimensional soil temperature difference distribution as the expected workload, multiple task completion rates are calculated based on the multiple predicted three-dimensional soil temperature distributions.

[0149] Temperature distribution uniformity analysis is performed on the multiple predicted three-dimensional soil temperature distributions, and multiple temperature distribution uniformity coefficients are output.

[0150] Based on preset weight ratios, and with the goals of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, a quality evaluation function for equipment parameters is constructed.

[0151] Using the equipment parameter quality evaluation function, multiple parameter quality coefficients are calculated based on multiple task completion rates, multiple temperature distribution uniformity coefficients, multiple simulated equipment energy consumption, and multiple simulated water consumption.

[0152] Based on the multiple parameter quality coefficients, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters.

[0153] Furthermore, based on the aforementioned multiple parameter quality coefficients, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters, including:

[0154] The initial cooling equipment parameters are set as the initial solution, and multiple initial solutions are arranged in descending order of parameter quality coefficient to obtain the initial solution sequence;

[0155] The first solution in the initial solution sequence is set as the head solution, the remaining solutions are set as inferior solutions, and multiple inferior solutions are adjusted according to a preset optimization step size, with the head solution as the direction, to obtain multiple updated inferior solutions.

[0156] The head solution and multiple updated inferior solutions are rearranged according to the parameter quality coefficient from large to small to obtain an updated solution sequence. In the updated solution sequence, inferior solutions with a predetermined proportion are eliminated. Equal supplementation is performed based on the first device parameter adjustment space and the second device parameter adjustment space. The predetermined proportion decreases as the number of optimization attempts increases.

[0157] The optimization process continues iteratively, following the optimization mechanism of selecting the first solution, adjusting the inferior solution, eliminating the inferior solution, and supplementing the initial solution, until the preset number of convergences is reached. The first solution of the current updated solution sequence is then set to the parameters of the adapted device.

[0158] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0159] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0160] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. An automatic optimization method for parameters of artificial cooling equipment based on soil data analysis, characterized in that the method... include: A regional soil cooling simulation space is constructed based on the three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information of the target area; The current three-dimensional soil temperature distribution is obtained by monitoring the distributed fiber optic temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target in the preset time zone. A regional soil cooling prediction model is constructed based on the soil flow mechanism and the simulation space of the regional soil cooling. Using the aforementioned regional soil cooling prediction model, with the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters. These cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device, including: Obtain the first equipment parameter adjustment space of the cooling device and the second equipment parameter adjustment space of the heat recovery device. Randomly select multiple parameters within the first and second equipment parameter adjustment spaces and combine them to obtain multiple initial cooling device parameters. Using the regional soil cooling prediction model, soil cooling is predicted based on the current three-dimensional soil temperature distribution and the parameters of the multiple initial cooling devices, and multiple predicted three-dimensional soil temperature distributions are output. Based on digital twins, a joint simulation model of the cooling device and the heat recovery device is constructed to build a twin model of the cooling equipment. Using the twin model of the cooling equipment, simulations are performed based on the parameters of the multiple initial cooling equipment, and the energy consumption and water consumption of the multiple simulated equipment are output. Based on the multiple predicted three-dimensional soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized, and the appropriate equipment parameters are output. Within the preset time zone, the cooling device and heat recovery device are controlled according to the parameters of the adapted equipment to perform soil cooling operations in the target area.

2. The method for automatic optimization of artificial cooling equipment parameters based on soil data analysis according to claim 1, characterized in that, Based on the three-dimensional soil structure information, injection well distribution information, and extraction well distribution information of the target area, a regional soil cooling simulation space is constructed, including: Obtain three-dimensional soil structure information of the target area, wherein the three-dimensional soil structure information includes soil type, soil particle composition, soil permeability coefficient, soil porosity, soil heat capacity, soil thermal conductivity and soil spatial distribution; The topology and attribute information of the heating wells during in-situ thermal desorption of soil in the target area are used as the distribution information of the water injection wells, and the topology and attribute information of the extraction wells are used as the distribution information of the extraction wells. Within the 3D simulation platform, regional simulation modeling is performed based on the 3D soil structure information, water injection well distribution information, and extraction well distribution information to generate a regional soil cooling simulation space.

3. The method for automatic optimization of artificial cooling equipment parameters based on soil data analysis according to claim 1, characterized in that, Based on soil flow mechanisms and the simulated soil cooling space of the region, a regional soil cooling prediction model is constructed, including: The three-dimensional soil structure information, water injection well distribution information, and extraction well distribution information are expanded according to a preset tolerance interval to obtain a three-dimensional soil structure information interval, a water injection well distribution information interval, and an extraction well distribution information interval, which serve as retrieval constraints. With the aforementioned retrieval constraints as a limit, big data technology is used to collect sample information, obtain a sample three-dimensional soil temperature distribution set and a sample cooling device parameter set, and obtain the historical three-dimensional soil temperature distribution at the end of the historical time zone as the sample predicted three-dimensional soil temperature distribution, thus obtaining the sample predicted three-dimensional soil temperature distribution set, wherein the time interval between the historical time zone and the preset time zone is the same; Based on the soil flow mechanism and the simulation space of soil cooling in the region, an initial regional soil cooling prediction model is constructed by combining generative adversarial networks. Using the sample three-dimensional soil temperature distribution set and the sample cooling device parameter set as inputs, and using the sample predicted three-dimensional soil temperature distribution set as supervision, the initial regional soil cooling prediction model is trained to convergence, thus obtaining the regional soil cooling prediction model.

4. The method for automatic optimization of artificial cooling equipment parameters based on soil data analysis according to claim 3, characterized in that, Using the aforementioned search constraints as a limit, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling equipment, including: Obtain the equipment attribute information of the cooling device and the heat recovery device, and add it to the search constraints. The heat recovery device is a heat pump heat recovery system applied to a ground sedimentation tank. Using the aforementioned search constraints as a limit, big data technology is employed to collect sample information and obtain a parameter set for the sample cooling equipment. This parameter set includes first sample equipment parameters and second sample equipment parameters. The first sample equipment parameters are the operating parameters of the cooling device, and the second sample equipment parameters are the operating parameters of the heat recovery device. The parameters of the first sample equipment include the water injection flow rate and water injection temperature of the injection well, and the extraction vacuum degree of the extraction well. The parameters of the second sample equipment include compressor frequency, expansion valve opening degree, and water pump speed.

5. The method for automatic optimization of artificial cooling equipment parameters based on soil data analysis according to claim 1, characterized in that, Based on the multiple predicted three-dimensional soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, taking the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, iterative optimization of cooling equipment parameters is performed, outputting adapted equipment parameters, including: Using the three-dimensional soil temperature difference distribution as the expected workload, multiple task completion rates are calculated based on the multiple predicted three-dimensional soil temperature distributions. Temperature distribution uniformity analysis is performed on the multiple predicted three-dimensional soil temperature distributions, and multiple temperature distribution uniformity coefficients are output. Based on preset weight ratios, and with the goals of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, a quality evaluation function for equipment parameters is constructed. Using the equipment parameter quality evaluation function, multiple parameter quality coefficients are calculated based on multiple task completion rates, multiple temperature distribution uniformity coefficients, multiple simulated equipment energy consumption, and multiple simulated water consumption. Based on the multiple parameter quality coefficients, the parameters of the cooling equipment are iteratively optimized to output suitable equipment parameters.

6. The method for automatic optimization of artificial cooling equipment parameters based on soil data analysis according to claim 5, characterized in that, Based on the aforementioned multiple parameter quality coefficients, iterative optimization of the cooling equipment parameters is performed to output suitable equipment parameters, including: The initial cooling equipment parameters are set as the initial solution, and multiple initial solutions are arranged in descending order of parameter quality coefficient to obtain the initial solution sequence; The first solution in the initial solution sequence is set as the head solution, the remaining solutions are set as inferior solutions, and multiple inferior solutions are adjusted according to a preset optimization step size, with the head solution as the direction, to obtain multiple updated inferior solutions. The head solution and multiple updated inferior solutions are rearranged according to the parameter quality coefficient from large to small to obtain an updated solution sequence. In the updated solution sequence, inferior solutions with a predetermined proportion are eliminated. Equal supplementation is performed based on the first device parameter adjustment space and the second device parameter adjustment space. The predetermined proportion decreases as the number of optimization attempts increases. The optimization process continues iteratively, following the optimization mechanism of selecting the first solution, adjusting the inferior solution, eliminating the inferior solution, and supplementing the initial solution, until the preset number of convergences is reached. The first solution of the current updated solution sequence is then set to the parameters of the adapted device.

7. An automatic parameter optimization system for artificial cooling equipment based on soil data analysis, characterized in that, For performing the method according to any one of claims 1-6, comprising: The simulation space construction module is used to build a regional soil cooling simulation space based on the three-dimensional soil structure information, water injection well distribution information and extraction well distribution information of the target area; the current three-dimensional soil temperature distribution is monitored and obtained through distributed fiber optic temperature measurement equipment, and the three-dimensional soil temperature difference distribution is calculated by combining the preset cooling target within the preset time zone. The temperature difference distribution calculation module is used to monitor and obtain the current three-dimensional soil temperature distribution through distributed fiber optic temperature measurement equipment, and calculate the three-dimensional soil temperature difference distribution by combining it with the preset cooling target in the preset time zone. The prediction model building module is used to build a regional soil cooling prediction model based on the soil flow mechanism and the regional soil cooling simulation space. The adaptation parameter output module is used to utilize the regional soil cooling prediction model, taking the three-dimensional soil temperature difference distribution as the expected workload, and aiming to minimize equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, to iteratively optimize the cooling equipment parameters and output the adaptation equipment parameters. These cooling equipment parameters include the operating parameters of the cooling device and the heat recovery device, including: Obtain the first equipment parameter adjustment space of the cooling device and the second equipment parameter adjustment space of the heat recovery device. Randomly select multiple parameters within the first and second equipment parameter adjustment spaces and combine them to obtain multiple initial cooling device parameters. Using the regional soil cooling prediction model, soil cooling is predicted based on the current three-dimensional soil temperature distribution and the parameters of the multiple initial cooling devices, and multiple predicted three-dimensional soil temperature distributions are output. Based on digital twins, a joint simulation model of the cooling device and the heat recovery device is constructed to build a twin model of the cooling equipment. Using the twin model of the cooling equipment, simulations are performed based on the parameters of the multiple initial cooling equipment, and the energy consumption and water consumption of the multiple simulated equipment are output. Based on the multiple predicted three-dimensional soil temperature distributions, multiple simulated equipment energy consumptions, and multiple simulated water consumptions, with the three-dimensional soil temperature difference distribution as the expected workload, and with the goal of minimizing equipment energy consumption and water consumption while maximizing task completion and temperature distribution uniformity, the parameters of the cooling equipment are iteratively optimized, and the appropriate equipment parameters are output. The cooling operation execution module is used to control the cooling device and the heat recovery device to perform soil cooling operations in the target area according to the adapted equipment parameters within the preset time zone.

Images