An intelligent phase-change condensation dehumidification method and system for high-temperature and high-humidity environments in deep wells

Abstract

The present invention relates to the field of data processing and environmental control technology, and in particular to an intelligent phase-change condensation dehumidification method and system for a high-temperature and high-humidity environment of a deep well, the method comprising the following steps: obtaining historical temperature and humidity standardized data of the deep well under a high-temperature and high-humidity environment; constructing a heat and mass transfer optimization model based on the historical temperature and humidity standardized data; constructing a nested optimization model based on the heat and mass transfer optimization model in combination with an optimization algorithm; training the nested optimization model in accordance with the historical temperature and humidity standardized data to obtain a nested optimization control model; and completing the intelligent phase-change condensation dehumidification of the deep well in accordance with the nested optimization control model in combination with the real-time temperature and humidity data of the deep well. The present invention utilizes historical temperature and humidity data to construct a heat and mass transfer model, and combines an optimization algorithm to obtain a nested optimization control model, thereby realizing intelligent phase-change condensation dehumidification of the deep well, improving dehumidification efficiency and energy utilization, and providing an intelligent technical solution for deep well dehumidification.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and environmental control, and in particular to an intelligent phase-change condensation dehumidification method and system for a high-temperature and high-humidity environment in a deep well. Background Art

[0002] As the mining of mineral resources develops in depth, the mining depth continues to increase. At present, a considerable number of mines have a mining depth of more than 800 meters, and some mines have even reached more than 1,500 meters. In such a deep mine environment, due to the combined effects of multiple factors such as geothermal gradient effects, groundwater infiltration, heating of mechanical equipment, and rock stress deformation, the working face generally faces severe challenges with temperatures exceeding 40°C and relative humidity exceeding 85%. This high temperature and high humidity environment not only seriously threatens the health and work efficiency of the operators, but also accelerates the corrosion and aging of tunnel support materials and electromechanical equipment, becoming a key technical bottleneck restricting the safe and efficient production of deep mines.

[0003] At present, the commonly used methods for treating high temperature and high humidity environments in deep wells include open ice cooling, mechanical refrigeration, compression dehumidification, solid adsorption dehumidification, and chemical adsorption dehumidification. Although open ice cooling and dehumidification have the advantages of being clean, environmentally friendly, and low cost, the dehumidification effect is poor due to the limited contact area between ice and air, and the ambient humidity may even increase due to the melting of ice. Mechanical refrigeration and compression dehumidification have stable effects, but they have disadvantages such as high energy consumption, large equipment size, and high maintenance costs. Solid adsorption dehumidification has a simple structure, but its efficiency drops significantly under high temperature conditions and requires frequent regeneration; although chemical adsorption dehumidification has significant effects, it is prone to corrosion, the regeneration process is complex, and the operating cost is high. These technologies generally have problems such as low dehumidification efficiency, poor energy utilization, insufficient regulation capabilities, and poor system reliability, making it difficult to fully meet the needs of complex environments in deep wells.

[0004] In terms of control algorithms, existing deep well dehumidification systems mostly use traditional PID or fuzzy control algorithms, or use single intelligent optimization algorithms such as genetic algorithms, particle swarm algorithms, etc. These methods usually only optimize a single target (such as dehumidification efficiency or energy consumption), and it is difficult to balance multiple mutually constrained targets such as dehumidification efficiency, energy consumption, and phase change rate. In addition, these algorithms are mostly based on simplified heat and mass transfer models, and do not fully consider the coupling effects of multiple physical fields such as condensation latent heat release, liquid film thickness changes, and turbulent energy in deep well environments, resulting in insufficient model accuracy and difficulty in coping with complex working conditions. At the same time, traditional algorithms respond slowly to changes in environmental parameters and have poor adaptability. They are inefficient when dealing with multi-objective optimization problems and are prone to falling into local optimal solutions. Especially in the complex environment of deep wells, due to the complex coupling relationship between system parameters, it is difficult for traditional algorithms to achieve global optimization.

[0005] Therefore, it is urgent to develop a new intelligent dehumidification system to achieve efficient, energy-saving and stable dehumidification in the high temperature and high humidity environment of deep wells by improving heat and mass transfer efficiency, optimizing control strategies and enhancing system reliability. The system should have multi-objective optimization capabilities, be able to establish high-precision optimization models based on multi-physical field coupling, quickly respond to environmental changes, balance optimization objectives such as dehumidification efficiency, energy consumption and phase change rate, improve system operation efficiency, and provide an innovative technical path for deep well high temperature and high humidity environment management. Summary of the invention

[0006] In view of the defects in the prior art, the present invention provides an intelligent phase-change condensation dehumidification method and system for a high-temperature and high-humidity environment in a deep well.

[0007] In order to achieve the above-mentioned objectives, in the first aspect, the present invention provides an intelligent phase change condensation and dehumidification method for a high temperature and high humidity environment of a deep well, and the method comprises the following steps: obtaining historical temperature and humidity standardized data of the deep well under a high temperature and high humidity environment; constructing a heat and mass transfer optimization model based on the historical temperature and humidity standardized data; constructing a nested optimization model based on the heat and mass transfer optimization model in combination with an optimization algorithm; training the nested optimization model based on the historical temperature and humidity standardized data to obtain a nested optimization control model; and completing the intelligent phase change condensation and dehumidification of the deep well based on the nested optimization control model in combination with the real-time temperature and humidity data of the deep well. The present invention constructs an accurate heat and mass transfer optimization model by acquiring historical temperature and humidity standardized data of deep wells under high temperature and high humidity environments, and further combines the nested optimization model established by the optimization algorithm. After training, the model is converted into a nested optimization control model, which can significantly improve the adaptability of the nested optimization control model to changes in the deep well environment. Combined with the real-time temperature and humidity data of the deep well, the phase change condensation dehumidification process of the deep well is intelligently controlled, which effectively improves the dehumidification efficiency and energy utilization rate, ensures the stability and safety of the deep well environment, and provides an efficient, convenient and intelligent solution for deep well dehumidification operations under high temperature and high humidity environments.

[0008] Optionally, the acquisition of historical temperature and humidity standardized data of the deep well under a high temperature and high humidity environment includes: acquiring historical temperature and humidity data of the deep well under a high temperature and high humidity environment; performing data cleaning on the historical temperature and humidity data to obtain first historical temperature and humidity optimization data; performing interval mapping on the first historical temperature and humidity optimization data to obtain second historical temperature and humidity optimization data; optimizing the second historical temperature and humidity optimization data according to data standardization to obtain historical temperature and humidity standardized data. The present invention acquires historical temperature and humidity data of a deep well under a high temperature and high humidity environment, and performs data cleaning, interval mapping and standardization; data cleaning removes outliers, interval mapping ensures the consistency and comparability of the data, and data standardization further enhances the generalization ability of the model, significantly improves the accuracy and availability of the data, and provides a solid data foundation for building an accurate heat and mass transfer model.

[0009] Optionally, the heat and mass transfer optimization model is constructed according to the historical temperature and humidity standardized data, including: constructing a liquid film thickness model based on the ice melting rate; establishing a condensation latent heat release rate model according to the liquid film thickness model; and constructing a turbulent energy driven model according to the historical temperature and humidity standardized data. The present invention simulates the liquid film thickness by introducing the ice melting rate, and then establishes a mathematical model of the condensation latent heat release rate, and constructs a turbulent energy driven model in combination with historical data, thereby enhancing the adaptability of the heat and mass transfer optimization model to the complex changes in the deep well environment, not only improving the accuracy of the model, but also providing a scientific basis for subsequent nested optimization and regulation, which is helpful to achieve high efficiency and intelligence in the deep well dehumidification process.

[0010] Optionally, constructing a liquid film thickness model based on the ice melting rate includes:

[0011]

[0012] in, is the liquid film thickness, is the dynamic viscosity of the liquid, is the melting rate of ice, is the evaporation rate, is the characteristic length of the ice cube, is the liquid density, The present invention quantifies the thickness of the liquid film through mathematical expressions, which enhances the ability of the liquid film thickness model to describe the dynamic change process of the liquid film, making the prediction and control of the liquid film thickness more accurate and efficient, and helps to deeply understand the heat and mass transfer logic in deep well environments, and provides a reference for the subsequent optimization of the condensation and dehumidification process.

[0013] Optionally, constructing a turbulence energy driven model according to the historical temperature and humidity standardized data includes:

[0014]

[0015] in, is the interface heat transfer coefficient, is the empirical coefficient, is the turbulent kinetic energy, is the characteristic length, is the kinematic viscosity, is the experience index, is the Prandtl number, is the experience index, is the thermal conductivity of air. The present invention quantifies the interface heat transfer coefficient using an expression, achieves an accurate description of the turbulent heat transfer process in a deep well environment, improves the ability of the turbulent energy-driven model to describe complex heat transfer phenomena, makes the regulation of the heat transfer coefficient more intuitive and efficient, helps optimize the energy transfer efficiency in the deep well dehumidification process, and provides key parameters for intelligent regulation.

[0016] Optionally, the heat and mass transfer optimization model is based on a nested optimization model constructed in combination with an optimization algorithm, including: establishing an optimization target based on the heat and mass transfer optimization model; optimizing the optimization target according to a multi-objective optimization algorithm to obtain a first optimization solution set; updating the first optimization solution set according to a single-objective optimization algorithm to obtain a second optimization solution set; establishing a nested optimization strategy to construct a nested optimization model in combination with the second optimization solution set. The present invention effectively improves the comprehensive performance of the nested optimization model by establishing an optimization target and using a multi-objective optimization algorithm and a single-objective optimization algorithm for iterative solution; the nested optimization strategy ensures the systematicness and comprehensiveness of the optimization process, and obtains a more efficient optimization solution by gradually screening and optimizing the solution set, thereby promoting the intelligence of deep well dehumidification technology and providing solid technical support for achieving efficient and stable dehumidification effects.

[0017] Optionally, optimizing the optimization objective according to a multi-objective optimization algorithm to obtain a first optimization solution set includes:

[0018]

[0019] in, For solution The crowding distance, represents the traversal count of the target, is the total number of targets, For solution On Target The target value of the upper adjacent solution, For the goal The maximum value of For the goal The present invention optimizes the optimization target based on a multi-objective optimization algorithm, calculates the crowding distance to ensure the diversity of the solution set, and effectively evaluates the distribution of solutions and the competition relationship between them by calculating the crowding distance of each solution in the target space, thereby retaining solutions with better distribution characteristics in the selection process, enhancing the robustness of the optimization algorithm, and improving the quality and diversity of the first optimization solution set.

[0020] Optionally, the nested optimization model is trained according to the historical temperature and humidity standardized data to obtain a nested optimization control model, including: obtaining model training parameters of the nested optimization model; based on the model training parameters, inputting the historical temperature and humidity standardized data into the nested optimization model to obtain a model training result; and adjusting the structure and parameters of the nested optimization model according to the model training result to obtain a nested optimization control model. The present invention obtains the model training parameters of the nested optimization model and uses the historical temperature and humidity standardized data for model training to ensure the accuracy and reliability of the nested optimization model in practical applications, adjusts the structure and parameters of the nested optimization model based on the model training results, further optimizes the performance of the model, improves the accuracy and generalization ability of the nested optimization control model, and provides strong technical support and guarantee for subsequent practical applications.

[0021] Optionally, the combination of the real-time temperature and humidity data of the deep well and the completion of the intelligent phase-change condensation dehumidification of the deep well according to the nested optimization control model includes: inputting the real-time temperature and humidity data into the nested optimization control model, thereby performing real-time prediction of the condensation efficiency and the temperature and humidity field of the deep well to obtain a real-time prediction result; performing dynamic feedback adjustment on the nested optimization control model based on the real-time prediction result, thereby realizing the intelligent phase-change condensation dehumidification of the deep well. The present invention inputs the real-time temperature and humidity data into the nested optimization control model to realize the real-time prediction of the condensation efficiency and the temperature and humidity field of the deep well, ensuring the rapid response of the nested optimization control model to environmental changes, and continuously optimizing the control strategy based on the dynamic feedback adjustment of the real-time prediction results, improving the dehumidification efficiency and stability; enhancing the intelligence level of deep well dehumidification, significantly improving the dehumidification effect and energy utilization efficiency, and providing an intelligent solution for the dehumidification of deep wells in high temperature and high humidity environments.

[0022] In the second aspect, the present invention provides an intelligent phase-change condensation and dehumidification system for a deep well with high temperature and high humidity. The system executes the intelligent phase-change condensation and dehumidification method for a deep well with high temperature and high humidity provided by the present invention. The system includes an input device, an output device, a processor and a memory. The gain lies in that the hardware facilities integrated by the present invention have excellent performance, the input device, the output device, the processor and the memory are interconnected, and the information transmission between the various components is smooth. Through the interaction of multiple hardware facilities, an efficient information processing system is constructed. The intelligent phase-change condensation and dehumidification system provided by the present invention, by integrating high-performance hardware facilities, constructs an efficient information processing platform, which can quickly respond to environmental changes, accurately execute the intelligent phase-change condensation and dehumidification method, improve the dehumidification efficiency and accuracy, enhance the stability and reliability of the system, and provide effective intelligent improvement for the condensation and dehumidification of deep wells in high temperature and high humidity environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of an intelligent phase-change condensation dehumidification method for a deep well high-temperature and high-humidity environment according to an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of an intelligent phase-change condensation and dehumidification system device according to an embodiment of the present invention;

[0025] Figure 3 The water vapor mass fraction and temperature field distribution structure cloud diagram of the dehumidification system device of the embodiment of the present invention when the interior is closed for 16 seconds;

[0026] Figure 4 The water vapor mass fraction and temperature field distribution structure cloud diagram of the dehumidification system device of the embodiment of the present invention when the interior is closed for 32 seconds;

[0027] Figure 5 The water vapor mass fraction and temperature field distribution structure cloud diagram of the dehumidification system device of the embodiment of the present invention when the interior is closed for 48 seconds;

[0028] Figure 6 This is a framework diagram of an intelligent phase-change condensation and dehumidification system for a deep well high-temperature and high-humidity environment according to an embodiment of the present invention;

[0029] Figure 7 This is a system flow chart of the intelligent phase change condensation and dehumidification system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0031] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or subcombination. In addition, it should be understood by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale.

[0032] See also Figure 1An embodiment of the present invention provides an intelligent phase-change condensation dehumidification method for a deep well high temperature and high humidity environment, the method comprising the following steps:

[0033] S1. Obtain the historical temperature and humidity standardized data of deep wells under high temperature and high humidity environment.

[0034] Among them, S1 specifically includes the following steps:

[0035] S11. Acquire historical temperature and humidity data of the deep well under a high temperature and high humidity environment.

[0036] Specifically, a temperature and humidity sensor array is set in the tunnel of the deep well. The temperature and humidity sensor array is used to collect environmental parameter data of the deep well in real time. The environmental parameter data includes temperature, relative humidity and pressure. The environmental parameter data is saved in a memory as historical temperature and humidity data to provide accurate data support for system optimization.

[0037] S12. Clean the historical temperature and humidity data to obtain first historical temperature and humidity optimization data.

[0038] In this embodiment, a data cleaning algorithm is used to preprocess the collected historical temperature and humidity data to obtain first historical temperature and humidity optimization data, and the preprocessing includes removing noise, filling missing values, and eliminating outliers, thereby improving the quality of the data.

[0039] Specifically, the filling of missing values ​​includes filling of non-time series missing values ​​and filling of ordered time series missing values.

[0040] The non-time series missing value filling supplement uses the median to replace the missing value, satisfying the following relationship:

[0041]

[0042] in, is the data value after non-time series filling, represents the median operator, Indicates valid historical temperature and humidity data.

[0043] The missing values ​​of the ordered time series are filled and supplemented to satisfy the following relationship:

[0044]

[0045] in, is the data value after filling the ordered time series, For time point, is the number of time points, To traverse the count mark, is the weight coefficient, It is the historical temperature and humidity data.

[0046] Furthermore, the outliers are removed according to The data points that are out of the normal range determined by the method satisfy the following relationship:

[0047]

[0048] in, is an outlier, is any data point in the historical temperature and humidity data, is the first quartile, indicating the lower bound of 25% of the data points in the historical temperature and humidity data. It is the third quartile, indicating the upper limit of 75% of the data points in the historical temperature and humidity data.

[0049] S13. Perform interval mapping on the first historical temperature and humidity optimization data to obtain second historical temperature and humidity optimization data.

[0050] In this embodiment, the temperature data and humidity data in the first historical temperature and humidity optimization data are mapped to a specified interval to obtain the second historical temperature and humidity optimization data, and the temperature data and humidity data are mapped to the specified interval to satisfy the following relationship:

[0051]

[0052] in, is the data value after interval mapping, , are the lower and upper bounds of the target interval, is the original data value, is the minimum value of the original data, is the maximum value of the original data.

[0053] S14. Optimize the second historical temperature and humidity optimization data according to data standardization to obtain historical temperature and humidity standardized data.

[0054] Specifically, the second historical temperature and humidity optimization data is standardized by using a data standardization method to obtain historical temperature and humidity standardized data, and the data standardization method satisfies the following relationship:

[0055]

[0056] in, is the standardized data, is the original data value, is the minimum value of the original data, is the maximum value of the original data.

[0057] S15. Construct a data quality assessment system to perform data quality assessment on the historical temperature and humidity standardized data.

[0058] In an optional embodiment, a data quality assessment system is constructed to evaluate core indicators such as data completeness, accuracy, and timeliness; by establishing thresholds, monitoring mechanisms, and feedback processes, the quality of data is continuously evaluated and improved to provide a solid guarantee for decision support.

[0059] S2. Constructing a heat and mass transfer optimization model based on the historical temperature and humidity standardized data.

[0060] Among them, S2 specifically includes the following steps:

[0061] S21. Construct a liquid film thickness model based on the ice melting rate.

[0062] In this embodiment, the ice melting rate is used to construct a liquid film thickness model for analyzing the phase change behavior of the condensing medium. The liquid film thickness model satisfies the following relationship:

[0063]

[0064] in, is the liquid film thickness, is the dynamic viscosity of the liquid, is the melting rate of ice, is the evaporation rate, is the characteristic length of the ice cube, is the liquid density, is the acceleration due to gravity.

[0065] S22. Establishing a condensation latent heat release rate model based on the liquid film thickness model.

[0066] Specifically, a condensation latent heat release rate model is established based on the liquid film thickness obtained by the liquid film thickness model to calculate the condensation efficiency of water vapor in the air. The condensation latent heat release rate model satisfies the following relationship:

[0067]

[0068] in, is the condensation latent heat release rate, is the thermal conductivity of the liquid film, is the saturation temperature, is the liquid film temperature, is the liquid film thickness.

[0069] S23. Constructing a turbulent energy driven model based on the historical temperature and humidity standardized data.

[0070] In this embodiment, a turbulence energy driven model is constructed, and the turbulence energy driven model includes the calculation of turbulence kinetic energy and the calculation of interface heat transfer coefficient.

[0071] Specifically, the calculation of the turbulent kinetic energy satisfies the following relationship:

[0072]

[0073] in, is the turbulent kinetic energy, , , are the three components of turbulent pulsation velocity, is the time average.

[0074] The interface heat transfer coefficient includes the interface heat transfer coefficient of turbulent energy and phase change material, and the interface heat transfer coefficient satisfies the following relationship:

[0075]

[0076] in, is the interface heat transfer coefficient, is the empirical coefficient, is the turbulent kinetic energy, is the characteristic length, is the kinematic viscosity, is the experience index, is the Prandtl number, is the experience index, is the thermal conductivity of air.

[0077] S3. Based on the heat and mass transfer optimization model, a nested optimization model is constructed in combination with an optimization algorithm.

[0078] Among them, S3 specifically includes the following steps:

[0079] S31. Establishing an optimization target based on the heat and mass transfer optimization model.

[0080] In this embodiment, an optimization goal of the system is established. On a global scale, the optimization goal includes maximizing condensation efficiency, minimizing phase change rate deviation, and minimizing energy consumption.

[0081] Specifically, the condensation efficiency is maximized to satisfy the following relationship:

[0082]

[0083] in, To optimize the target value, is the condensation efficiency, The latent heat released by condensation is is the total energy consumed by the system.

[0084] The phase change rate deviation minimization satisfies the following relationship:

[0085]

[0086] in, To optimize the target value, is the phase change rate deviation, is the target melting rate, is the actual melting rate.

[0087] The energy consumption minimization satisfies the following relationship:

[0088]

[0089] in, To optimize the target value, is the total energy consumed by the system, is the power consumption of the fan, is the air density, is the turbulence energy, is the effective cross-sectional area of ​​the fan, is the fan efficiency.

[0090] S32. Optimizing the optimization objectives according to a multi-objective optimization algorithm to obtain a first optimization solution set.

[0091] Wherein, S32 specifically includes the following steps:

[0092] S321. Generate an initial population including condensation efficiency, energy consumption and phase change rate.

[0093] Specifically, the initial population is randomly generated with a population size of N, and each individual consists of the following decision variables:

[0094]

[0095] in, is the initial population, is the wind speed, is the fan angle, is the weighted average turbulent energy density, is the effective condensation area size, is the liquid film temperature on the surface of the phase change material, is the relative humidity, is the fan power.

[0096] S322: Perform non-dominated sorting on the initial population and calculate the crowding distance.

[0097] In this embodiment, the individuals in the initial population are sorted according to the Pareto optimization rule and divided into multiple non-dominated layers. ; It should be noted that if the initial population individual A is not inferior to the initial population individual B in all objectives, and is superior to B in at least one objective, then A is said to dominate B.

[0098] Specifically, the non-dominated sorting satisfies the following relationship:

[0099]

[0100] in, For solution The target value set, For solution The target value set, represents the traversal count of the target, For solution On Target The target value of the current solution, For solution On Target The target value of the current solution.

[0101] Furthermore, for the initial population individuals in the same non-dominated layer, the crowding distance is calculated to ensure the diversity of the solution set distribution. The crowding distance is calculated based on the normalized distance of the target value range and is used to give priority to individuals with higher diversity to ensure a uniform distribution of the Pareto solution set. The crowding distance satisfies the following relationship:

[0102]

[0103] in, For solution The crowding distance, represents the traversal count of the target, is the total number of targets, For solution On Target The target value of the upper adjacent solution, For the goal The maximum value of For the goal The minimum value of .

[0104] S323, selecting the next generation population based on the Pareto level and the crowding distance.

[0105] In this embodiment, the first N initial population individuals are selected from the non-dominated layer to form the next generation population, and initial population individuals with low Pareto rank and large crowding distance are preferentially selected, and new individuals are generated through crossover and mutation operations.

[0106] Specifically, the crossover process satisfies the following relationship:

[0107]

[0108] in, For the new individual The value of a variable, The parent individual The value of a variable, is a randomly generated mixing factor.

[0109] The mutation operation process satisfies the following relationship:

[0110]

[0111] in, is the value after mutation, is the value before mutation, is the variation range, is the upper limit of the current variable, is the lower limit of the current variable, is the random disturbance factor.

[0112] S324, iterative optimization until a Pareto frontier solution set is generated.

[0113] Specifically, a termination condition of the iterative optimization is set, wherein the termination condition includes reaching a maximum number of iterations or a change in a Pareto front solution set being less than a threshold.

[0114] Furthermore, when the termination condition of the iterative optimization is met, the Pareto frontier solution set is output, each solution in the Pareto frontier solution set is a combination of decision variables for multi-objective balance, and the optimization target value corresponding to each solution is It can be used for subsequent single-objective optimization or engineering decision-making. The decision variable combination satisfies the following relationship:

[0115]

[0116] in, is the Pareto frontier solution set, is the initial population, is the wind speed, is the fan angle, is the weighted average turbulent energy density, is the effective condensation area size, is the liquid film temperature on the surface of the phase change material, is the relative humidity, is the fan power.

[0117] S33. Update the first optimization solution set according to a single-objective optimization algorithm to obtain a second optimization solution set.

[0118] Wherein, S33 specifically includes the following steps:

[0119] S331, initializing the particle swarm, including particle velocity initialization and particle position initialization.

[0120] Specifically, the particle velocity initialization satisfies the following relationship:

[0121]

[0122] in, is the initial velocity of the particle, represents uniform distribution, Indicates location The maximum value of Indicates location The minimum value of .

[0123] The particle position initialization satisfies the following relationship:

[0124]

[0125] in, is the initial position of the particle, represents uniform distribution, is the minimum wind speed, is the minimum wind speed, is the minimum value of the fan angle, is the maximum value of the fan angle, is the minimum value of turbulent energy density, is the maximum value of the turbulent energy density.

[0126] S332, dynamically adjust particle speed and position to optimize wind speed, fan angle and turbulence energy.

[0127] In this embodiment, each solution in the Pareto solution set is used as the initial particle position for single-objective optimization, and the initialization speed of each particle is a random value, and the range is set according to the upper and lower limits of the variable; the particle swarm size is set according to actual needs; and the speed and position of the particle are dynamically adjusted and updated.

[0128] Specifically, the particle speed is dynamically adjusted and updated to satisfy the following relationship:

[0129]

[0130] in, Indicates that at time step speed, is the inertia weight, Indicates that at time step speed, , is the acceleration factor, , is a random number, is the best historical position of the particle, is the global optimal position, is the current particle position.

[0131] Furthermore, the position of the particles is dynamically adjusted and updated to satisfy the following relationship:

[0132]

[0133] in, Indicates that at time step location, Indicates that at time step location, Indicates that at time step speed.

[0134] S333. Evaluate the performance of each particle through the fitness function until the convergence condition is reached.

[0135] Specifically, the fitness function is used to evaluate the particle performance to obtain the fitness evaluation result. If the current fitness value is better than the historical record, the particle's historical optimal position is updated. If the current optimal particle is better than the global one, the optimal position is updated.

[0136] Furthermore, the convergence condition satisfies the following relationship:

[0137]

[0138] in, is the new optimal solution, is the old optimal solution, Tolerance error, is the number of iterations, is the maximum number of iterations.

[0139] S334. The optimal solution of the single-objective optimization is used as a basis for fitness evaluation of the multi-objective optimization.

[0140] Specifically, the optimal solution of the single-objective optimization satisfies the following relationship:

[0141]

[0142] in, is the optimal solution, is the optimal wind speed, is the optimal fan angle, is the optimal weighted average turbulent energy density, is the optimal effective condensation area size, is the optimal phase change material surface liquid film temperature, For the optimum relative humidity, is the optimal fan power, For optimal condensation efficiency.

[0143] Furthermore, the optimal solution after single-objective optimization update will be used to update the Pareto frontier solution set.

[0144] S34: Establish a nested optimization strategy and construct a nested optimization model in combination with the second optimization solution set.

[0145] Wherein, S34 specifically includes the following steps:

[0146] S341. Construct an interactive process of nested optimization.

[0147] In this embodiment, the interactive process of nested optimization achieves efficient collaboration by setting the iterative cycle of the outer multi-objective optimization and the inner single-objective optimization; the outer multi-objective optimization is based on the cycle Initialize the population and record the start time. The inner single-objective optimization is based on the cycle For individual local optimization, the single optimization time is limited to , when the timeout is reached or the optimization threshold is met, the nested optimization is terminated and the multi-objective optimization population is updated.

[0148] S342. Establishing timing control of nested optimization.

[0149] Specifically, efficient coordination is achieved by setting the iteration cycle and optimization switching conditions of the outer multi-objective optimization and the inner single-objective optimization; the outer multi-objective optimization is based on the cycle Run, initialize the current generation population And record the cycle start time ; The inner layer single objective optimization is based on the cycle Run, optimize the individual parts, and then update the multi-objective optimization population.

[0150] S343. Obtain the data interaction mechanism of the nested optimization algorithm.

[0151] In this embodiment, the nested optimization data interaction transmits the condensation area, temperature and flow constraints through multi-objective optimization, and the single-objective optimization returns the optimized wind speed, angle and fitness value; real-time update is performed in the single-objective optimization, and the fitness and search range are adjusted immediately after optimization. During the generational update of the multi-objective optimization, the processing results are updated in batches to ensure the coordinated and efficient operation of the inner and outer layers.

[0152] S344. Obtain an exception handling mechanism for the nested optimization process.

[0153] In this embodiment, when the local optimization of single-objective optimization times out, the current optimal solution is returned; if no feasible solution can be found, the default parameters are used; for the loss of population diversity in multi-objective optimization, population reinitialization is triggered and the number of retries is limited; if parameter constraints are violated during the optimization process, the fitness is reduced through soft constraint penalties or the parameters are corrected through hard constraints to ensure that the algorithm continues to optimize within the constraints, thereby improving the reliability and operation efficiency of the system; the exception handling mechanism of nested optimization ensures the robustness and stability of the optimization process.

[0154] S345. Establish a collaborative strategy for nested optimization.

[0155] Specifically, the overall efficiency and stability are improved through adaptive control, computing resource allocation and optimization effect evaluation; the particle size of single-objective optimization and the population size of multi-objective optimization are adaptively adjusted, and the search accuracy is dynamically optimized according to the optimization effect; computing resources are dynamically allocated according to inner and outer loops, and the single single-objective optimization time is limited to ensure the balance between global and local optimization; the degree of optimization improvement is regularly evaluated, and the strategy is adjusted based on the results to improve the optimization efficiency and the ability to adapt to complex environments.

[0156] S4. Training the nested optimization model based on the historical temperature and humidity standardized data to obtain a nested optimization control model.

[0157] Wherein, S4 specifically includes the following steps:

[0158] S41, obtaining model training parameters of the nested optimization model.

[0159] In this embodiment, an optimizer is used to set the training parameters of the optimization model; including setting the parameters of multi-objective optimization and the parameters of single-objective optimization; the parameters of the multi-objective optimization include but are not limited to the population size, the maximum number of iterations, the crossover probability and the mutation probability; the single-objective optimization parameters include but are not limited to the particle swarm size, the maximum number of iterations and the dynamic adjustment of the inertia weight.

[0160] Specifically, the inertia weight is dynamically adjusted to satisfy the following relationship:

[0161]

[0162] in, Indicates dynamic adjustment of inertia weight, Provides a strong global search capability for initial weights. Enhance local search capabilities for final weights, is the maximum number of iterations, is the current iteration number.

[0163] S42. Based on the model training parameters, the historical temperature and humidity standardized data is input into the nested optimization model to obtain a model training result.

[0164] Specifically, the standardized historical temperature and humidity standardized data is used as input and imported into the nested optimization model with configured model training parameters. The nested optimization model iteratively optimizes the nested optimization model according to the input historical temperature and humidity standardized data and the preset model training parameters to achieve the best fitting effect, thereby obtaining the model training results.

[0165] S43. Adjust the structure and parameters of the nested optimization model according to the model training result to obtain a nested optimization control model.

[0166] Specifically, the structure and parameters of the nested optimization model are gradually adjusted according to the model training results, and the error index is calculated through the validation set. The error index is used to evaluate the model performance of the nested optimization model. The optimization model parameters are iteratively adjusted based on the model performance until the error index converges to a preset threshold range, thereby obtaining the nested optimization control model.

[0167] Furthermore, in this embodiment, the symmetric mean absolute percentage error is used as an error indicator to evaluate the model performance. The symmetric mean absolute percentage error satisfies the following relationship:

[0168]

[0169] in, is the symmetric mean absolute percentage error, is the total number of samples, is the traversal count flag, For the The true value of the samples, For the The predicted value of a sample.

[0170] S5. In combination with the real-time temperature and humidity data of the deep well, the intelligent phase-change condensation and dehumidification of the deep well is completed according to the nested optimization control model.

[0171] See also Figure 2 The figure shows a schematic diagram of an intelligent phase change condensation and dehumidification system device, which shows the size and structural composition of the system device, which includes an outlet gate, a condensation baffle, a drainage channel, an inlet gate, a phase change material, a condensation channel, a convection cooling fan, a water storage box, and a temperature and humidity monitoring point; then, based on the real-time temperature and humidity data of the deep well, the nested optimization control model is converted into an intelligent phase change condensation and dehumidification system device to realize intelligent phase change condensation and dehumidification of the deep well.

[0172] It should be noted that in this embodiment, the inlet gate and the outlet gate need to be opened to discharge the low-temperature and high-humidity gas, and then a convection cooling fan is needed to dissipate internal machine heat, while at the same time combining with the deep well tunnel wall to release heat to the internal environment, thereby reducing the relative humidity of the deep well in a high temperature and high humidity environment.

[0173] Among them, S5 specifically includes the following steps:

[0174] S51, inputting the real-time temperature and humidity data into the nested optimization control model, so as to perform real-time prediction on the condensation efficiency and the temperature and humidity field of the deep well to obtain a real-time prediction result.

[0175] In an optional embodiment, the system device is initialized, and the initialization includes determining system operating parameters, checking the status of inlet and outlet gates, confirming the working status of ice cubes, and checking the operating status of convection cooling fans.

[0176] Specifically, the system operating parameters are determined, and the initial system operating parameters are calculated and set according to the real-time monitored temperature and humidity data. The inlet and outlet gate status is checked to confirm that the inlet and outlet gates are in the initial closed state to prevent air flow from affecting system operation. The ice working status is confirmed to confirm that the ice or phase change material is in a usable state and the temperature is lower than the set threshold; if the ice or phase change material is exhausted, a replacement prompt is triggered or the standby mode is entered. The convection cooling fan operation status is checked to confirm that the convection cooling fan is in standby mode and is in good operation without abnormal noise or fault alarm.

[0177] Further, after the initialization is completed, the high temperature and high humidity air is introduced into the intelligent phase change condensation and dehumidification system device to provide the original working conditions for the condensation and dehumidification process. The original working conditions are shown in Table 1:

[0178] Table 1:

[0179]

[0180] First, open the inlet gate and connect it to the tunnel through the air guide device to introduce external high-temperature and high-humidity air into the system device; then, start the negative pressure fan to draw the air in the tunnel into the condensation cavity, and monitor the air flow in the system in real time to ensure that the air flow is controlled within the design range to avoid overload; then, monitor the temperature and humidity changes in the system in real time, monitor the humidity and temperature of the air inside the cavity through temperature and humidity sensors, and record the dynamic changes in the air entry process. When the temperature of the temperature monitoring point in the system is <15°C, the operation of closing the inlet gate is triggered; finally, when the air volume in the cavity reaches the preset value, the system automatically closes the air inlet gate.

[0181] S52. Performing dynamic feedback adjustment on the nested optimization control model based on the real-time prediction result, thereby realizing intelligent phase change condensation and dehumidification of the deep well.

[0182] In an optional embodiment, air condensation and dehumidification are completed in a closed state by a circulating fan and ice cubes. First, ensure that the inlet gate and the outlet gate are both in a closed state to form a completely closed cavity environment; then, start the circulating fan to circulate the air in the condensation cavity, and optimize the wind speed and guide angle to make the air fully contact with the surface of the ice cube; then, when the air passes through the surface of the ice cube, the water vapor condenses into liquid water and precipitates from the air, the humidity gradually decreases, and the condensed water flows into the drainage channel under the action of gravity and is collected by the water storage box; at the same time, monitor the temperature and humidity changes in the cavity in real time, and dynamically adjust the fan speed or guide angle according to the condensation efficiency; finally, monitor the dehumidification effect, continuously monitor the air temperature changes in the cavity, and use the algorithm to control the stop of the circulating fan in combination with the temperature changes.

[0183] For details, see Figure 3 , Figure 4 as well as Figure 5 The figures respectively show the water vapor mass fraction and the temperature field distribution structure cloud diagram when the dehumidification system device is closed for 16 seconds, the water vapor mass fraction and the temperature field distribution structure cloud diagram when the dehumidification system device is closed for 32 seconds, and the water vapor mass fraction and the temperature field distribution structure cloud diagram when the dehumidification system device is closed for 48 seconds. By comparing the water vapor mass fraction and the temperature field distribution inside the system device at different times, the dehumidification efficiency of the system device can be effectively reflected.

[0184] Furthermore, the low-temperature gas is discharged from the system. First, the circulation fan is stopped to avoid air disturbance in the cavity affecting the exhaust efficiency; then, the outlet gate is opened to discharge the fully cooled and condensed air into the tunnel through the exhaust duct. During the exhaust process, the air flow rate is monitored in real time to ensure that the low-humidity air is discharged smoothly; at the same time, the system monitors the duration of exhaust to ensure that the humidity in the cavity is balanced with the outside air. When the temperature at the cavity monitoring point is close to the outside environment level, the outlet gate is automatically closed.

[0185] See also Figure 6In an optional embodiment, in order to be able to efficiently execute the intelligent phase-change condensation and dehumidification method for a deep well high temperature and high humidity environment provided by the present invention, the present invention provides an intelligent phase-change condensation and dehumidification system for a deep well high temperature and high humidity environment, the system comprising an input device, an output device, a processor and a memory, the hardware facilities being interconnected, wherein the memory is used to store a computer program, the computer program comprising program instructions, the processor being configured to call the program instructions and execute the specific steps of the relevant embodiments of the intelligent phase-change condensation and dehumidification method for a deep well high temperature and high humidity environment provided by the present invention. The intelligent phase-change condensation and dehumidification system for a deep well high temperature and high humidity environment provided by the present invention has a complete structure, is objective and stable, and can efficiently execute the intelligent phase-change condensation and dehumidification method for a deep well high temperature and high humidity environment provided by the present invention, thereby improving the overall applicability and practical application capabilities of the present invention.

[0186] Specifically, the nested optimization control model is transformed into an intelligent phase-change condensation dehumidification system for deep well high temperature and high humidity environments in actual operation, with ice or phase-change materials as the core medium to achieve efficient condensation and dehumidification effects. The intelligent phase-change condensation and dehumidification system is suitable for intelligent dehumidification in deep well high temperature and high humidity environments, with efficient condensation and dehumidification as the core, ensuring that the system hardware and control process meet the requirements of dynamic adaptability and high efficiency.

[0187] Furthermore, the hardware components include input devices, output devices and processors, wherein the input devices include a temperature and humidity sensor array, an air intake valve and an exhaust valve; the output devices include a circulating fan, a condensation module and a drainage system; the processor includes a central processing unit, an embedded system and a data storage device. Among them, the data acquisition module reads the real-time temperature and humidity data and transmits it to the processor, the processor runs the optimization model, calculates the control parameters according to the real-time data, and outputs control instructions to dynamically control the equipment (fan, valve, condensation module).

[0188] It should be noted that the intelligent phase change condensation and dehumidification system adopts a closed structure design, and the condensation chamber is made of corrosion-resistant materials to ensure sealing to avoid external interference. The air intake and exhaust channels are equipped with one-way valves to ensure one-way airflow.

[0189] Furthermore, the memory is used to store and deploy a computer program, wherein the computer program includes program function module division, program deployment steps and program execution logic.

[0190] Among them, the program function module includes a data acquisition module, an optimization model call module, a parameter control module (adjusting the fan speed, fan angle and valve status according to the optimization model output), and a feedback control module. The program deployment steps include initialization, dynamic update and fault tolerance mechanism; the initialization includes loading the optimization model weights and system configuration parameters, testing the connection status of sensors, fans, valves and other equipment, the dynamic update supports remote update of model weights to adapt to environmental changes, and the fault tolerance mechanism automatically switches to safe mode when the program is abnormal, stops the operation of key equipment and alarms. The program execution logic includes collecting sensor data, inputting optimization models, outputting equipment control instructions, and realizing real-time regulation.

[0191] In an optional embodiment, an intelligent phase change condensation dehumidification system is used to perform real-time dehumidification control, including real-time operation process, dehumidification control steps, real-time feedback and dynamic adjustment, as well as intelligent regulation and reliability assurance.

[0192] Specifically, in the real-time operation process, during the real-time dehumidification control process, the system collects temperature, humidity and pressure data of the deep well environment through the temperature and humidity sensor array, and transmits it to the central processing unit in real time. The optimization model receives the standardized environmental data and calculates the optimal condensation efficiency, energy consumption level and control parameters (such as fan speed, guide angle and valve status). At the beginning of each dehumidification cycle, the system first ensures that the temperature of the condensation module (such as ice or phase change material) is within the target range and initializes the fan and valve status. According to the output of the optimization model, the air intake valve is opened, and the high-temperature and high-humidity air enters the condensation chamber through the air guide device to start the air treatment stage.

[0193] Specifically, in the dehumidification control step, after the air is introduced, the system closes the air intake valve and starts the circulating fan to circulate the air in the cavity, ensuring that the airflow is in full contact with the surface of the ice cubes, condensing and dehumidifying, and the condensed water is collected through the drainage channel. When the humidity in the cavity drops to the target range, the system stops the fan and opens the exhaust valve to discharge the treated low-humidity air out of the cavity. The entire dehumidification process is monitored in real time by sensors, and the fan speed, guide angle and other parameters are dynamically adjusted through the feedback mechanism to optimize the condensation efficiency and energy consumption, ensuring efficient and stable operation of the system.

[0194] Specifically, in the real-time feedback and dynamic adjustment, at each stage of dehumidification control, the sensor monitors the temperature and humidity data in the cavity in real time, and inputs the feedback results into the optimization model. The optimization model dynamically adjusts the system operating parameters, such as fan speed, guide angle, and cycle time length, based on the deviation between the feedback data and the target parameters (such as humidity range or condensation efficiency). This real-time feedback and adjustment mechanism can ensure the continuous improvement of condensation efficiency and respond quickly when environmental conditions change, so that the system remains in an efficient operating state. In addition, for large deviations, the system will trigger multiple iterative updates to achieve the optimal control effect.

[0195] Specifically, the intelligent control and reliability guarantee, the intelligent control logic of the system enables it to provide a stable dehumidification effect in a complex deep well environment. By combining the optimization model with feedback control, the system can dynamically optimize the operation strategy to achieve a balance between dehumidification efficiency and energy consumption. At the same time, the system is equipped with an automatic fault detection and protection mechanism. When an abnormality occurs in the sensor, fan or valve, the system will enter a safe mode, stop the operation of key components and issue an alarm. This reliability design ensures the safety and long-term stability of the system in high temperature and high humidity environments.

[0196] See also Figure 7 , the figure is a system flow chart of the intelligent phase change condensation and dehumidification system, which shows in detail the operation process of the intelligent phase change condensation and dehumidification system and describes the specific intelligent phase change condensation and dehumidification processing process of the system processor.

[0197] In summary, the method of the present invention provides an intelligent phase-change condensation dehumidification method and system for a deep well high temperature and high humidity environment. By collecting and analyzing the historical temperature and humidity standardized data of the deep well under high temperature and high humidity conditions, a heat and mass transfer optimization model is constructed, and the optimization algorithm is further integrated to establish a nested optimization model. After systematic training, an efficient nested optimization control model is obtained, which significantly enhances its adaptability to changes in the deep well environment. Combined with the real-time temperature and humidity data of the deep well, the phase-change condensation dehumidification process in the deep well can be intelligently controlled, thereby greatly improving the dehumidification efficiency and energy utilization, ensuring the continuous stability and safety of the deep well environment; and providing an efficient, convenient and intelligent new way for deep well dehumidification operations in high temperature and high humidity environments. The method of the present invention is easy to understand and convenient for engineering application, and provides a theoretical basis and technical support for the further development of data processing and environmental control technology.

[0198] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An intelligent phase-change condensation dehumidification method for high-temperature and high-humidity environments in deep wells, characterized in that: The steps include: Obtain historical temperature and humidity standardized data of deep wells in high temperature and high humidity environments; Constructing a heat and mass transfer optimization model based on the historical temperature and humidity standardized data; The heat and mass transfer optimization model is constructed according to the historical temperature and humidity standardized data, including: Construct a liquid film thickness model based on the melting rate of ice cubes; Establishing a condensation latent heat release rate model based on the liquid film thickness model; Constructing a turbulent energy driven model based on the historical temperature and humidity standardized data; Based on the heat and mass transfer optimization model, a nested optimization model is constructed in combination with an optimization algorithm; The heat and mass transfer optimization model is based on the optimization algorithm to construct a nested optimization model, including: Establishing an optimization target based on the heat and mass transfer optimization model; The optimization objectives include maximizing condensation efficiency, minimizing phase change rate deviation, and minimizing energy consumption; Optimizing the optimization target according to a multi-objective optimization algorithm to obtain a first optimization solution set; Updating the first optimization solution set according to a single-objective optimization algorithm to obtain a second optimization solution set; Establishing a nested optimization strategy and constructing a nested optimization model in combination with the second optimization solution set; The nested optimization model is trained according to the historical temperature and humidity standardized data to obtain a nested optimization control model; Combined with the real-time temperature and humidity data of the deep well, intelligent phase change condensation and dehumidification of the deep well is completed according to the nested optimization control model.

2. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The acquisition of historical temperature and humidity standardized data of deep wells in a high temperature and high humidity environment includes: Acquire historical temperature and humidity data of the deep well under high temperature and high humidity environment; Performing data cleaning on the historical temperature and humidity data to obtain first historical temperature and humidity optimization data; Performing interval mapping on the first historical temperature and humidity optimization data to obtain second historical temperature and humidity optimization data; The second historical temperature and humidity optimization data is optimized according to data standardization to obtain historical temperature and humidity standardized data.

3. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The method of constructing a liquid film thickness model based on the ice melting rate includes: in, is the liquid film thickness, is the dynamic viscosity of the liquid, is the melting rate of ice, is the evaporation rate, is the characteristic length of the ice cube, is the liquid density, is the acceleration due to gravity.

4. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The method of establishing a condensation latent heat release rate model based on the liquid film thickness model comprises: in, is the condensation latent heat release rate, is the thermal conductivity of the liquid film, is the saturation temperature, is the liquid film temperature, is the liquid film thickness.

5. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The step of constructing a turbulent energy driven model according to the historical temperature and humidity standardized data includes: in, is the interface heat transfer coefficient, is the empirical coefficient, is the turbulent kinetic energy, is the characteristic length, is the kinematic viscosity, is the experience index, is the Prandtl number, is the experience index, is the thermal conductivity of air.

6. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The heat and mass transfer optimization model is based on the optimization algorithm to construct a nested optimization model, including: The step of optimizing the optimization target according to the multi-objective optimization algorithm to obtain a first optimization solution set includes: generating an initial population including the condensation efficiency, the energy consumption and the phase change rate; The initial population is non-dominatedly sorted and the crowding distance is calculated to satisfy the following relationship: in, For solution The crowding distance, represents the traversal count of the target, is the total number of targets, For solution On Target The target value of the upper adjacent solution, For the goal The maximum value of For the goal The minimum value of Selecting the next generation population based on the Pareto rank and the crowding distance; Iteratively optimizing the population until a Pareto frontier solution set is generated as the first optimized solution set; The updating of the first optimization solution set according to the single-objective optimization algorithm to obtain the second optimization solution set includes: Initialize the particle swarm, including particle velocity initialization and particle position initialization; Dynamically adjust the particle velocity and the particle position to optimize wind speed, fan angle and turbulence energy; The performance of the particles is evaluated by a fitness function until a convergence condition is reached and an optimal solution is obtained; Using the optimal solution of the single-objective optimization as a basis for multi-objective optimization fitness evaluation, updating the first optimization solution set to obtain the second optimization solution set; The step of establishing a nested optimization strategy and constructing a nested optimization model in combination with the second optimization solution set includes: Construct the interaction process, timing control, data interaction mechanism and exception handling mechanism of nested optimization to establish a collaborative strategy for nested optimization; Based on the collaborative strategy, the nested optimization model is constructed.

7. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1 is characterized in that: The nested optimization model is trained according to the historical temperature and humidity standardized data to obtain a nested optimization control model, including: Obtaining model training parameters of the nested optimization model; Based on the model training parameters, the historical temperature and humidity standardized data is input into the nested optimization model to obtain a model training result; The structure and parameters of the nested optimization model are adjusted according to the model training results to obtain a nested optimization control model.

8. The intelligent phase-change condensation dehumidification method for deep well high temperature and high humidity environment according to claim 1, characterized in that: The method combines the real-time temperature and humidity data of the deep well and completes the intelligent phase change condensation dehumidification of the deep well according to the nested optimization control model, including: Inputting the real-time temperature and humidity data into the nested optimization control model, thereby performing real-time prediction on the condensation efficiency and the temperature and humidity field of the deep well to obtain a real-time prediction result; Based on the real-time prediction results, the nested optimization control model is dynamically feedback adjusted to achieve intelligent phase change condensation and dehumidification of the deep well.

9. An intelligent phase-change condensation dehumidification system for deep well high temperature and high humidity environment, characterized in that: The system includes an input device, an output device, a processor and a memory, and the input device, the output device, the processor and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the intelligent phase change condensation dehumidification method for a deep well high temperature and high humidity environment as described in any one of claims 1-8.

Images