Bimodal self-adaptive immersion phase change charging station thermal management system

Abstract

The invention discloses a bimodal adaptive immersion phase change charging station thermal management system, and relates to the technical field of charging station thermal management, and the system comprises a circulation management module which carries out the circulation mapping and optimization operation of a phase change temperature result, and generates a circulation scheme; the immersion cooling module is used for intelligently regulating and controlling the nanometer phase change slurry to flow in an immersion cooling tank in a self-adaptive manner by utilizing a circulation scheme, and dynamically switching between a single-phase liquid cooling mode and a phase change boiling mode to generate heat absorption data; the heat exchange module is used for inputting the heat absorption data into a plate heat exchanger for heat exchange to generate cooling liquid temperature data, and carrying out heat dissipation and waste heat recovery operation of a dry cooler to generate backflow heat data; feature extraction and multi-dimensional nonlinear coupling analysis are carried out on the initial working condition data of the charging station, and iterative optimization is carried out in combination with a pre-training model, so that high-precision prediction of dynamic and multi-modal temperature changes is realized, and a reliable basis is provided for circulation management and cooling mode selection.

Description

Technical Field

[0001] This invention relates to the field of thermal management technology for charging stations, and in particular to a dual-modal adaptive immersion phase change charging station thermal management system. Background Technology

[0002] In recent years, with the rapid development of new energy vehicles and high-speed charging infrastructure, charging stations face significant challenges in heat dissipation and thermal safety during continuous high-power, high-current operation. Existing thermal management technologies mainly employ single-mode cooling methods such as air cooling and liquid cooling, achieving heat conduction and dissipation by arranging cooling loops between key components such as power electronic equipment, cables, and charging guns. Meanwhile, some advanced solutions introduce phase change materials as passive heat storage media to improve heat capacity and buffering capabilities. Immersion cooling technology is also increasingly being applied to high-power electronic devices, utilizing insulating liquid in direct contact with heat-generating elements to form an efficient heat dissipation interface, and transferring waste heat through heat exchangers or dry coolers.

[0003] Under current technological conditions, thermal management systems typically operate based on preset temperature thresholds or fixed parameter adjustments, failing to fully integrate the coupling changes of the external environment and real-time load for intelligent prediction and optimized control. Although some technical solutions attempt to improve heat dissipation performance by adding phase change materials or optimizing cooling loops, certain limitations remain in dynamic mode switching, real-time adjustment of circulation parameters, and multi-modal coordination. In particular, the lack of a precise decision-making mechanism when switching between single-phase liquid cooling and phase change boiling conditions makes it difficult to balance the response speed and energy efficiency of the thermal management system. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a dual-modal adaptive immersion phase change charging station thermal management system, which solves the problems of slow response and insufficient energy utilization in the existing thermal management system.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] This invention provides a dual-modal adaptive immersion phase change charging station thermal management system, which includes a data acquisition module that collects temperature, humidity and charging power information inside and outside the charging station, performs noise reduction, normalization and integration processing to generate a preliminary operating condition dataset.

[0008] The intelligent prediction module uses intelligent algorithms to perform real-time prediction and optimization calculations on the preliminary working condition dataset to generate phase change temperature results.

[0009] The loop management module performs loop mapping and optimization operations on the phase transition temperature results to generate loop schemes.

[0010] The immersion cooling module uses a circulation scheme to intelligently regulate the flow of nano-phase change slurry in the immersion cooling tank and dynamically switches between single-phase liquid cooling mode and phase change boiling mode to generate heat absorption data.

[0011] The heat exchange module inputs heat absorption data into the plate heat exchanger for heat exchange, generates coolant temperature data, and performs heat dissipation and waste heat recovery operations for the dry cooler, generating return heat data.

[0012] The active cooling module performs active cooling operations on the cable and charging gun based on the return heat data, obtains the connector temperature data, and performs real-time monitoring and intelligent adjustment. Combined with the circulation scheme and phase change temperature results, it generates a thermal management status.

[0013] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the following steps are taken: collecting temperature, humidity, and charging power information inside and outside the charging station, performing noise reduction, normalization, and integration processing to generate a preliminary operating condition dataset.

[0014] Real-time collection of temperature, humidity and charging power information inside and outside the charging station; removal of transient spikes and noise by wavelet filtering method to obtain operating condition purification data.

[0015] The working condition purification data is processed by range scaling and normalization to obtain normalized working condition data, which is then weighted and integrated to form a preliminary working condition dataset.

[0016] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the specific steps for using intelligent algorithms to perform real-time prediction and optimization calculations on the preliminary operating condition dataset to generate phase change temperature results are as follows.

[0017] Feature extraction and time series processing are performed on the preliminary working condition dataset to obtain the working condition feature sequence. Multidimensional feature recombination and matrix mapping operations are then performed to construct the working condition feature matrix.

[0018] Nonlinear coupling analysis is performed on the operating condition characteristic matrix to generate preliminary prediction results;

[0019] The preliminary prediction results are input into the pre-trained nonlinear coupled model for iterative optimization and error correction, and the phase transition temperature results are output.

[0020] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the specific steps for performing cyclic mapping and optimization operations on the phase change temperature results to generate a cyclic scheme are as follows.

[0021] The phase transition temperature results are mapped and transformed according to the time series to generate a control vector set, and combined with nonlinear optimization calculations to obtain an optimized control vector set;

[0022] The optimized control vector set is integrated and interpolated over time to generate an optimized cyclic sequence. The cyclic scheme is then formed through time series integration and control mapping operations.

[0023] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the following steps are taken: The flow of nano-phase change slurry in the immersion cooling tank is intelligently controlled using a circulation scheme, and dynamically switched between single-phase liquid cooling mode and phase change boiling mode to generate heat absorption data.

[0024] Based on the cyclic scheme, control decomposition and time step calculation are performed to obtain the control vector for each time step. The time series is then integrated and correlated with historical cooling operation data to generate a control matrix.

[0025] The flow state and cooling mode of nano-phase change slurry are intelligently adjusted by using a control matrix, the critical point of heat exchange efficiency is continuously monitored, and dynamic switching is performed between single-phase liquid cooling and phase change boiling to obtain optimized heat absorption efficiency.

[0026] The optimization of heat absorption efficiency is recorded and summarized on a time-step basis to generate heat absorption data.

[0027] In a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the steps for inputting heat absorption data into a plate heat exchanger for heat exchange to generate coolant temperature data are as follows.

[0028] The heat absorption data is input into the plate heat exchanger according to the time series to perform flow matching and heat distribution regulation, forming a cold liquid base temperature set.

[0029] Nonlinear heat exchange calculations were performed on the base temperature set of the coolant to obtain coolant temperature data.

[0030] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the specific steps for performing dry cooler heat dissipation and waste heat recovery operations to generate return heat data are as follows.

[0031] The coolant temperature data is input into the dry cooler according to the time series for temperature comparison and control judgment, generating a set of trigger heat dissipation commands, and performing coupled regulation of coolant flow and heat exchange to obtain the coolant residual temperature set.

[0032] Waste heat recovery calculations were performed on the residual heat collection of the cold liquid to obtain the recovered heat sequence. Parameter correction and dynamic optimization were then performed to generate reflux heat data.

[0033] In a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the steps for performing active cooling operations on the cable and charging gun based on the return heat data to obtain joint temperature data are as follows:

[0034] The return heat data is input into the charging station cooling path according to the time series, and active cooling operation is carried out by a combination of air cooling and liquid cooling. The cooling intensity is adjusted according to the heat density and connector structure to obtain connector temperature change information.

[0035] Nonlinear coupling calculations and multidimensional adjustment operations are performed on the joint temperature change information to obtain joint temperature data.

[0036] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the steps for real-time monitoring and intelligent adjustment, combining the circulation scheme and phase change temperature results to generate a thermal management state, are as follows:

[0037] Real-time monitoring and intelligent adjustment of joint temperature data are performed to obtain a joint temperature sequence;

[0038] By combining the joint temperature sequence with the cyclic scheme and phase change temperature results, correlation analysis and state mapping operations are performed to generate the thermal management state.

[0039] As a preferred embodiment of the dual-modal adaptive immersion phase change charging station thermal management system of the present invention, the nonlinear coupling model is constructed as follows:

[0040] Historical operating condition data and corresponding temperature changes, flow regulation and heat recovery information are normalized and time series processed to form an operable operating condition characteristic sequence.

[0041] Based on the physical and technological relationship between the operating condition characteristic sequence and temperature change, a multidimensional nonlinear mapping relationship is established, the operating condition characteristic sequence of each dimension is coupled with the temperature output, the dependency and interaction logic between each variable is clarified, and a nonlinear coupling model is constructed.

[0042] The beneficial effects of this invention are as follows: By extracting features from the initial operating data of the charging station, performing multidimensional nonlinear coupling analysis, and iteratively optimizing the pre-trained model, high-precision prediction of dynamic and multimodal temperature changes is achieved, providing a reliable basis for cyclic management and cooling mode selection; subsequently, by converting the cyclic scheme into a time-series control vector, adaptive flow regulation of the nano-phase change slurry is achieved, and dynamic switching between single-phase liquid cooling and phase change boiling modes is performed, maximizing the heat absorption efficiency of the cooling medium, ensuring the thermal stability and energy efficiency of the system under different operating conditions, forming a prediction-driven closed-loop thermal management, thereby significantly improving the intelligence, reliability, and overall efficiency of the charging station thermal management system. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of a dual-modal adaptive immersion phase change charging station thermal management system.

[0045] Figure 2 This is a flowchart of the data collection and intelligent prediction process.

[0046] Figure 3 This is a flowchart of the immersion cooling dual-mode switching and heat exchange process.

[0047] Figure 4 A flowchart for generating active cooling and thermal management status is provided. Detailed Implementation

[0048] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0051] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a dual-modal adaptive immersion phase change charging station thermal management system, such as... Figure 1 As shown, a dual-modal adaptive immersion phase change charging station thermal management system includes: a data acquisition module, an intelligent prediction module, a circulation management module, an immersion cooling module, a heat exchange module, and an active cooling module, comprising the following steps:

[0052] The data acquisition module collects temperature, humidity, and charging power information inside and outside the charging station, performs noise reduction, normalization, and integration processing to generate a preliminary operating condition dataset.

[0053] Real-time data on temperature, humidity, and charging power inside and outside the charging station are collected. Transient spikes and noise are removed using wavelet filtering to obtain clean operating data.

[0054] Furthermore, real-time temperature, humidity, and charging power information inside and outside the charging station are collected. Wavelet filtering is used to process the temperature, humidity, and charging power information inside and outside the charging station to smooth out abnormal fluctuation signals and maintain effective measurement change characteristics without loss, thus obtaining operating condition purification data.

[0055] During processing, the acquired signal is segmented according to the time series, and each segment is input into the wavelet filtering method for smoothing calculation. The degree of suppression of transient spikes is automatically adjusted by the weight of the energy distribution of wavelet coefficients, while maintaining the dynamic response of temperature, humidity and charging power information.

[0056] After continuous iterative processing using wavelet decomposition and reconstruction methods, the temperature, humidity, and charging power information at each time step are updated and corrected using residual correction methods to generate a complete set of working condition purification data.

[0057] The working condition purification data is processed by range scaling and normalization to obtain normalized working condition data, and then weighted and integrated to form a preliminary working condition dataset.

[0058] Furthermore, the operating condition purification data is processed by interval scaling and normalization according to their respective dimensional ranges. The temperature, humidity and charging power information are mapped to preset standard intervals through linear normalization. During the normalization process, the importance weights of temperature, humidity and charging power information in the thermal management objectives are combined with the relative importance parameters of each time step and temperature, humidity and charging power information, and the temperature, humidity and charging power information are weighted and integrated to directly generate a preliminary operating condition dataset.

[0059] It should also be noted that the preset standard range setting process is based on the historical temperature, humidity and charging power data collected during the operation of the charging station, statistically analyzing the value range under different operating conditions, and combining the equipment's allowable safe operating range and engineering experience range to determine the upper and lower limits of temperature, humidity and charging power information parameters respectively.

[0060] Reasonable corrections are made to the determined boundary values ​​to ensure that temperature, humidity and charging power information can still be covered under extreme operating conditions, while avoiding distortion of the normalization effect due to excessively wide ranges, and mapping the value range of each type of parameter to a unified standardized range.

[0061] The preset strategy combination setting process analyzes the control objectives and operating characteristics of each time step based on the cyclic parameter matrix, phase change temperature results, joint temperature sequence and thermal management status, and extracts key parameter combinations that can be used for adjustment, such as temperature gradient, flow fluctuation and heat recovery efficiency.

[0062] Based on the optimization of heat absorption efficiency, reflux heat distribution, and residual temperature changes of the coolant, the control parameter combinations for different time steps are categorized and matched to form a preliminary strategy set. A multidimensional linear mapping method is used to map the preliminary strategy set to a preset standard range to ensure that each strategy is feasible within the operating range of the corresponding time step, while also taking into account the dynamic switching requirements of single-phase liquid cooling, phase change boiling, and composite cooling modes. The mapped strategy set is then combined and optimized, arranged in chronological order, and the strategy priorities are adjusted to form a complete preset strategy combination.

[0063] The intelligent prediction module uses intelligent algorithms to perform real-time prediction and optimization calculations on the preliminary working condition dataset, generating phase transition temperature results, such as... Figure 2 As shown.

[0064] Feature extraction and time series processing are performed on the preliminary working condition dataset to obtain the working condition feature sequence. Then, the working condition feature matrix is ​​constructed through multi-dimensional feature recombination and matrix mapping operations.

[0065] Furthermore, by analyzing the changing trends of temperature, humidity, and charging power at adjacent time points, calculating the fluctuation amplitude, and identifying periodic characteristics, the continuous changes of each operating condition parameter are converted into a numerical description, thereby forming an operating condition characteristic sequence.

[0066] The operating condition feature sequence is reorganized in a multi-dimensional space. The operating condition parameters are arranged and combined according to time steps and feature dimensions. The reorganized multi-dimensional features are organized into an operating condition feature matrix through matrix mapping operations. This allows the temperature, humidity and charging power information in the matrix to reflect the dynamics of the time series and the correlation between multi-dimensional parameters, while maintaining the original logical order of the operating condition parameters and the integrity of the operating condition feature sequence.

[0067] Nonlinear coupling analysis is performed on the operating condition characteristic matrix to generate preliminary prediction results.

[0068] Furthermore, nonlinear correlation analysis is performed on the temperature, humidity, and charging power information in the operating condition feature matrix in the time series and multidimensional parameter space to identify the coupling relationship and mutual influence between the parameters. Combined with historical operating condition characteristics and heat change trends, the possible temperature response and energy transfer state at each time step are calculated to form preliminary prediction results.

[0069] The preliminary prediction results are input into the pre-trained nonlinear coupled model for iterative optimization and error correction, and the phase transition temperature results are output.

[0070] Furthermore, the preliminary prediction results are input into a pre-trained nonlinear coupled model according to the time series. The temperature, humidity and charging power information are iteratively optimized and calculated through the multidimensional nonlinear mapping relationship inside the model. The prediction error is corrected in each iteration. The actual operating conditions are compared and adjusted with the prediction results to minimize the prediction deviation and enhance the response capability to dynamic operating conditions. After continuous iterative optimization, the complete phase change temperature result is output.

[0071] It should also be explained that the process of constructing the nonlinear coupling model is as follows:

[0072] Historical operating condition data and corresponding temperature changes, flow regulation and heat recovery information are normalized and time series processed to form an operable operating condition characteristic sequence.

[0073] Based on the physical and technological relationship between the operating condition characteristic sequence and temperature change, a multidimensional nonlinear mapping relationship is established, the operating condition characteristic sequence of each dimension is coupled with the temperature output, the dependency and interaction logic between each variable is clarified, and a nonlinear coupling model is constructed.

[0074] It should also be noted that the intelligent algorithm refers to the closed loop of prediction and optimization from operating condition data to phase change temperature. The intelligent algorithm first extracts and quantifies the time-series features of temperature, humidity and charging power, and forms an operating condition feature matrix through multi-dimensional recombination and matrix mapping; through nonlinear coupling analysis, it obtains a preliminary prediction of temperature response and energy transfer at each time step; then, the preliminary prediction is fed into a pre-trained nonlinear coupling model according to the time series for iterative optimization and error correction, so that the prediction continuously matches the actual operating conditions, minimizes the deviation, and outputs a stable and reliable phase change temperature result.

[0075] The loop management module performs loop mapping and optimization operations on the phase change temperature results to generate loop schemes.

[0076] The phase transition temperature results are mapped and transformed according to the time series to generate a control vector set, and then combined with nonlinear optimization operations to obtain an optimized control vector set.

[0077] Furthermore, the phase transition temperature results are processed sequentially according to the time series. The temperature value at each time step is converted into the corresponding control parameter vector through mapping rules to form a preliminary control vector set.

[0078] After forming the control vector set, nonlinear optimization calculations are performed on each control vector. By calculating the changes and correlations between the control vector at each time step and the adjacent time steps and related control parameters, the coupling relationship and mutual influence law between parameters are identified. Then, combined with the cooling flow characteristics and heat transfer efficiency, each control parameter is adjusted through an iterative algorithm so that the temperature regulation response at each time step can match the expected thermal management target.

[0079] During the optimization process, the deviation of the control parameters is continuously corrected to ensure that the control vectors are continuous in time and have a clear sequential logic, and finally an optimized control vector set is generated.

[0080] The optimized control vector set is integrated and interpolated over time to generate an optimized cyclic sequence. The cyclic scheme is then formed through time series integration and control mapping operations.

[0081] Furthermore, the optimized control vector set is integrated in chronological order. First, interpolation is used to fill in the gaps or missing values ​​between consecutive time steps, so that the control parameters of each time step are smoothly connected to form an optimized cyclic sequence.

[0082] After generating the optimized loop sequence, the control vector of each time step in the sequence is mapped to the loop control strategy. The response relationship of the control parameters to the flow and heat conduction of the nano phase change slurry in the immersion cooling tank (e.g., flow rate change, local temperature peak and heat transfer efficiency change) is analyzed. The control intensity and distribution of each time step are adjusted in combination with historical cooling operation data to make the optimized loop sequence continuous in time and logically consistent, forming a loop scheme that can be directly used for the operation of the immersion cooling tank.

[0083] The immersion cooling module uses a circulation scheme to intelligently regulate the flow of nano-phase change slurry in the immersion cooling tank and dynamically switches between single-phase liquid cooling mode and phase change boiling mode to generate heat absorption data.

[0084] Based on the cyclic scheme, control decomposition and time step calculation are performed to obtain the control vector for each time step. The time series is then integrated and correlated with historical cooling operation data to generate a control matrix.

[0085] Furthermore, the cyclic scheme is decomposed into control parameters and time steps are calculated. Based on the control parameters at each time step, the corresponding control vector is calculated, expressed as:

[0086]

[0087] in, Indicates time step The control vector, Indicates the time step index. Indicates at time step The temperature recorded in the immersion cooling tank, Indicates time step Temperature information, Indicates at time step Humidity recorded in the immersion cooling tank. Indicates at time step The charging power recorded in the immersion cooling tank;

[0088] Record the effects of temperature, humidity, and charging power information at each time step on the flow of the nano-phase change slurry;

[0089] The control vectors of each time step are integrated into a time series, and the control vectors of consecutive time steps are arranged in order and correlated with historical cooling operation data. Historical temperature gradient, flow characteristics and heat absorption data are analyzed, and the current control vector is matched with historical operation characteristics (including temperature gradient change rate, local flow velocity distribution, cold liquid residual temperature change and local heat absorption efficiency example indicators) to generate a control matrix.

[0090] By using a control matrix to intelligently regulate the flow state and cooling mode of nano-phase change slurry, continuously monitoring the critical point of heat exchange efficiency, triggering mode switching commands, and dynamically switching between single-phase liquid cooling and phase change boiling, the optimized heat absorption efficiency is obtained.

[0091] Furthermore, the temperature gradient and flow characteristics of the nano-phase change slurry in the immersion cooling tank are analyzed in real time using a control matrix. By continuously monitoring the critical point of heat transfer efficiency at each time step, the local overheating or flow stagnation regions that may occur in the slurry flow can be identified.

[0092] The thermal conductivity and heat capacity utilization of nano-phase change slurry under different working conditions are dynamically evaluated based on temperature gradient, flow velocity, and heat absorption efficiency. The most suitable cooling method for the slurry is dynamically determined based on the temperature gradient, flow velocity, and heat absorption efficiency of the nano-phase change slurry at each time step. For example, when the temperature gradient is low and the flow velocity is uniform, the liquid single-phase cooling mode is selected. When the temperature gradient exceeds the set threshold or local flow stagnation occurs and the heat absorption efficiency is higher than the example standard, the phase change boiling cooling mode is selected. The switching operation between the liquid single-phase cooling and phase change boiling cooling modes can be performed. The switching can be performed according to the immediate needs, or according to the predetermined time period, or the switching timing and duration can be adaptively adjusted according to the real-time working conditions to ensure that the slurry flow and heat absorption efficiency are always in the optimal state.

[0093] By comparing the control results under the same or similar temperature gradients, flow rates, and heat absorption efficiencies in historical operations with the state corresponding to the current control vector, and combining past operating experience with real-time operating conditions, the timing and duration of switching are adjusted to ensure that the nano-phase change slurry obtains continuous, stable, and efficient heat absorption performance throughout the entire cycle, thereby optimizing the heat absorption efficiency.

[0094] The optimization of heat absorption efficiency is recorded and summarized on a time-step basis to generate heat absorption data.

[0095] Furthermore, the optimization of heat absorption efficiency is recorded in time steps, and the temperature gradient, flow characteristics and corresponding heat absorption information of each time step are saved sequentially to form a continuous time series record.

[0096] The records at each time step are summarized to integrate the changes in optimized heat absorption efficiency throughout the entire cycle. The average heat absorption level, peak heat absorption point, and flow characteristic change trend of each time period are calculated to generate complete heat absorption data.

[0097] The heat exchange module inputs heat absorption data into the plate heat exchanger for heat exchange, generates coolant temperature data, and performs dry cooler heat dissipation and waste heat recovery operations, generating return heat data, such as... Figure 3 As shown.

[0098] The heat absorption data is input into the plate heat exchanger according to the time series to perform flow matching and heat distribution adjustment, forming a cold liquid base temperature set.

[0099] Furthermore, the heat absorption data is input into the plate heat exchanger according to the time series, and the coolant flow rate is matched at each time step. The heat distribution is adjusted according to the heat absorption of the nano phase change slurry, so that the heat is evenly transferred between the channels of the plate heat exchanger.

[0100] Simultaneously, the flow rate and temperature relationship at different time steps are analyzed, and the heat exchange path is adjusted to keep the coolant temperature stable at each time step and match the heat absorption input, ultimately forming a continuous set of coolant base temperatures.

[0101] Nonlinear heat exchange calculations were performed on the base temperature set of the coolant to obtain coolant temperature data.

[0102] Furthermore, nonlinear heat exchange calculations are performed on the base temperature set of the coolant. By analyzing the temperature difference, flow distribution, and heat transfer efficiency of each channel in the plate heat exchanger, the base temperature set of the coolant is coupled with the heat absorption data. Considering the changes in fluid flow resistance and heat transfer coefficient in different time steps, the coolant temperature of each time step is accurately calculated and adjusted to generate continuous coolant temperature data.

[0103] The coolant temperature data is input into the dry cooler according to the time series for temperature comparison and control judgment, generating a set of trigger heat dissipation commands, and performing coupled regulation of coolant flow and heat exchange to obtain the coolant residual temperature set.

[0104] Furthermore, the coolant temperature data is input into the dry cooler in a time series, and the coolant temperature at each time step is monitored and compared in real time. The monitored temperature is compared with the preset temperature threshold and operating conditions (such as coolant inlet pressure, ambient temperature and wind speed) to control and determine the heat dissipation command set, and to clarify the heat dissipation requirements of each channel and time step.

[0105] The coolant flow rate is adjusted according to the set of triggering heat dissipation commands. By adjusting the flow distribution, inlet pressure and flow rate, the coupling control of heat exchange between the coolant and the dry cooler is realized, so that the heat is evenly distributed in each channel. The residual heat of the coolant at each time step is continuously recorded, and the temperature change, residual heat and flow state at each time step are integrated to form a coolant residual heat set.

[0106] It should also be explained that the process of setting the preset temperature threshold involves organizing historical operating data, analyzing temperature changes, humidity fluctuations, and charging power information at each time step, and extracting temperature peaks, valleys, and average trends. Based on safe operation requirements and heat absorption efficiency targets, the upper and lower temperature limits are initially determined, typically ranging from 20°C to 60°C (example value).

[0107] The upper and lower temperature limits are mapped to the loop parameters and control vectors of each time step, and fine-tuned in combination with preset strategies, so that the preset temperature threshold can adapt to different working conditions and realize on-demand, time-sharing and adaptive mode switching, ensuring that the nano phase change slurry obtains continuous, stable and efficient heat absorption.

[0108] Operating conditions are determined by real-time collection and recording of ambient temperature, humidity, wind speed, coolant inlet pressure, flow rate, velocity, and load conditions around the dry cooler, and then organizing these data into a time series to form the operating conditions corresponding to each time step.

[0109] Waste heat recovery calculations were performed on the residual heat collection of the cold liquid to obtain the recovered heat sequence. Parameter correction and dynamic optimization were then performed to generate reflux heat data.

[0110] Furthermore, the residual temperature of the cold liquid is input into the waste heat recovery calculation program of the dry cooler according to the time series. Energy conversion analysis is performed on the residual temperature of the cold liquid at each time step to calculate the recoverable heat and form a recoverable heat sequence.

[0111] Based on the recovered heat sequence, parameters such as temperature gradient, flow distribution, and heat exchange efficiency are corrected, and the recovery path and energy distribution are adjusted to achieve dynamic optimization of waste heat recovery. The recovered heat after optimization at each time step is summarized and integrated to form reflux heat data.

[0112] The active cooling module performs active cooling of the cable and charging gun based on the return heat data, obtains the connector temperature data, and performs real-time monitoring and intelligent adjustment. Combined with the circulation scheme and phase change temperature results, it generates a thermal management status, such as... Figure 4 As shown.

[0113] The return heat data is input into the charging station cooling path according to the time series, and active cooling operation is carried out by a combination of air cooling and liquid cooling. The cooling intensity is adjusted according to the heat density and connector structure to obtain connector temperature change information.

[0114] Furthermore, the return heat data is input into the charging station cooling path according to the time series, and the temperature distribution, flow rate distribution and heat transfer characteristics in the cooling path at each time step are analyzed in real time. The combined active cooling operation of air cooling and liquid cooling is executed. By coordinating the matching of air cooling volume and liquid cooling flow rate, the cooling intensity and heat exchange efficiency of each joint are precisely controlled.

[0115] During the combined active cooling operation of air cooling and liquid cooling, the air cooling volume and liquid cooling flow rate are dynamically adjusted based on the deviation between the joint temperature and the target temperature, the heat density distribution, and the real-time flow rate of the cooling path at each time step. At the same time, the required local cooling intensity for each joint is determined by combining the joint geometry and the thermal conductivity of the materials. This allows for real-time fine-tuning and optimization of cooling parameters (including air cooling volume, liquid cooling flow rate, and cooling distribution sequence), so that the joint temperature gradually approaches the expected target and remains continuous and stable. This ensures that the temperature changes of each joint are stable and controllable under different loads, ambient temperatures, and operating conditions, and generates continuous, complete, and time-sequential joint temperature change information.

[0116] Nonlinear coupling calculations and multidimensional adjustment operations are performed on the joint temperature change information to obtain joint temperature data.

[0117] Furthermore, a comprehensive analysis of the joint temperature change information at each time step is conducted, taking into account the heat transfer relationship between joints, local temperature differences, and the influence of coolant or phase change slurry flow on temperature. These factors are then linked together using a matrix mapping method to assess the interaction between joints and adjust the cooling intensity, flow rate, and heat exchange parameters accordingly. This ensures that the temperature change of each joint not only reflects its own conditions but also its coupling relationship with other joints, thereby forming consistent joint temperature data throughout the entire time series.

[0118] The joint temperature data is monitored in real time and intelligently adjusted to obtain the joint temperature sequence.

[0119] Furthermore, the joint temperature data is monitored in real time according to the time series. By analyzing the temperature change trend, gradient fluctuation and environmental influencing factors of each joint, intelligent adjustment operations are performed, including adjusting the coolant flow rate, cooling intensity and local heat exchange efficiency, so that the joint temperature maintains dynamic balance and optimal distribution at each time step, and finally obtains a continuous joint temperature sequence arranged in time order.

[0120] By combining the joint temperature sequence with the cyclic scheme and phase change temperature results, correlation analysis and state mapping operations are performed to generate the thermal management state.

[0121] Furthermore, the joint temperature sequence is correlated with the cycle scheme and phase change temperature results in chronological order. By analyzing the temperature changes, cycle parameter adjustments and phase change temperature responses at each time step, a state mapping operation is performed to comprehensively evaluate the thermal management characteristics at each time step and generate a continuous thermal management state arranged in chronological order.

[0122] In summary, this invention achieves high-precision prediction of dynamic, multimodal temperature changes by extracting features from preliminary operating data of charging stations, performing multidimensional nonlinear coupling analysis, and iteratively optimizing the data using a pre-trained model. This provides a reliable basis for cyclic management and cooling mode selection. Subsequently, by converting the cyclic scheme into a time-series control vector, adaptive flow regulation of the nano-phase change slurry is achieved, and dynamic switching between single-phase liquid cooling and phase change boiling modes is implemented. This maximizes the heat absorption efficiency of the cooling medium, ensuring the thermal stability and energy efficiency of the system under different operating conditions. This forms a prediction-driven closed-loop thermal management system, thereby significantly improving the intelligence, reliability, and overall efficiency of the charging station thermal management system.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A dual-modal adaptive immersion phase change charging station thermal management system, characterized in that: include, The data acquisition module collects temperature, humidity and charging power information inside and outside the charging station, performs noise reduction, normalization and integration processing to generate a preliminary operating condition dataset. The intelligent prediction module uses intelligent algorithms to perform real-time prediction and optimization calculations on the preliminary working condition dataset to generate phase change temperature results. The loop management module performs loop mapping and optimization operations on the phase transition temperature results to generate loop schemes. The immersion cooling module uses a circulation scheme to intelligently regulate the flow of nano-phase change slurry in the immersion cooling tank and dynamically switches between single-phase liquid cooling mode and phase change boiling mode to generate heat absorption data. The heat exchange module inputs heat absorption data into the plate heat exchanger for heat exchange, generates coolant temperature data, and performs heat dissipation and waste heat recovery operations for the dry cooler, generating return heat data. The active cooling module performs active cooling operations on the cable and charging gun based on the return heat data, obtains the connector temperature data, and performs real-time monitoring and intelligent adjustment. Combined with the circulation scheme and phase change temperature results, it generates a thermal management status.

2. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 1, characterized in that: The collected temperature, humidity, and charging power information inside and outside the charging station are then processed through noise reduction, normalization, and integration to generate a preliminary operating condition dataset. The specific steps are as follows. Real-time collection of temperature, humidity and charging power information inside and outside the charging station; removal of transient spikes and noise by wavelet filtering method to obtain operating condition purification data. The working condition purification data is processed by range scaling and normalization to obtain normalized working condition data, which is then weighted and integrated to form a preliminary working condition dataset.

3. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 2, characterized in that: The process of using intelligent algorithms to perform real-time prediction and optimization calculations on the preliminary working condition dataset to generate phase transition temperature results involves the following specific steps. Feature extraction and time series processing are performed on the preliminary working condition dataset to obtain the working condition feature sequence, and a working condition feature matrix is ​​constructed through multi-dimensional feature recombination and matrix mapping operations. Nonlinear coupling analysis is performed on the operating condition characteristic matrix to generate preliminary prediction results; The preliminary prediction results are input into the pre-trained nonlinear coupled model for iterative optimization and error correction, and the phase transition temperature results are output.

4. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 3, characterized in that: The process of performing cyclic mapping and optimization operations on the phase transition temperature results to generate a cyclic scheme involves the following steps: The phase transition temperature results are mapped and transformed according to the time series to generate a control vector set, and combined with nonlinear optimization calculations to obtain an optimized control vector set; The optimized control vector set is integrated and interpolated over time to generate an optimized cyclic sequence. The cyclic scheme is then formed through time series integration and control mapping operations.

5. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 4, characterized in that: The method of intelligently controlling the flow of nano-phase change slurry in an immersion cooling tank using a circulation scheme, and dynamically switching between single-phase liquid cooling mode and phase change boiling mode to generate heat absorption data, is as follows: Based on the cyclic scheme, control decomposition and time step calculation are performed to obtain the control vector for each time step. The time series is then integrated and correlated with historical cooling operation data to generate a control matrix. The flow state and cooling mode of nano-phase change slurry are intelligently adjusted by using a control matrix, the critical point of heat exchange efficiency is continuously monitored, and dynamic switching is performed between single-phase liquid cooling and phase change boiling to obtain optimized heat absorption efficiency. The optimization of heat absorption efficiency is recorded and summarized on a time-step basis to generate heat absorption data.

6. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 5, characterized in that: The process of inputting heat absorption data into a plate heat exchanger for heat exchange to generate coolant temperature data involves the following steps: The heat absorption data is input into the plate heat exchanger according to the time series to perform flow matching and heat distribution regulation, forming a cold liquid base temperature set. Nonlinear heat exchange calculations were performed on the base temperature set of the coolant to obtain coolant temperature data.

7. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 6, characterized in that: The process of performing heat dissipation and waste heat recovery operations in the dry cooler to generate reflux heat data is described in the following steps. The coolant temperature data is input into the dry cooler according to the time series for temperature comparison and control judgment, generating a set of trigger heat dissipation commands, and performing coupled regulation of coolant flow and heat exchange to obtain the coolant residual temperature set. Waste heat recovery calculations were performed on the residual heat collection of the cold liquid to obtain the recovered heat sequence. Parameter correction and dynamic optimization were then performed to generate reflux heat data.

8. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 7, characterized in that: The process of actively cooling the cable and charging gun based on the return heat data to obtain connector temperature data involves the following steps: The return heat data is input into the charging station cooling path according to the time series, and active cooling operation is carried out by a combination of air cooling and liquid cooling. The cooling intensity is adjusted according to the heat density and connector structure to obtain connector temperature change information. Nonlinear coupling calculations and multidimensional adjustment operations are performed on the joint temperature change information to obtain joint temperature data.

9. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 1, characterized in that: The process involves real-time monitoring and intelligent adjustment, combining the circulation scheme and phase change temperature results to generate a thermal management status. The specific steps are as follows: Real-time monitoring and intelligent adjustment of joint temperature data are performed to obtain a joint temperature sequence; By combining the joint temperature sequence with the cyclic scheme and phase change temperature results, correlation analysis and state mapping operations are performed to generate the thermal management state.

10. The dual-modal adaptive immersion phase change charging station thermal management system as described in claim 3, characterized in that: The nonlinear coupling model is constructed as follows. Historical operating condition data and corresponding temperature changes, flow regulation and heat recovery information are normalized and time series processed to form an operable operating condition characteristic sequence. Based on the physical and technological relationship between the operating condition characteristic sequence and temperature change, a multidimensional nonlinear mapping relationship is established, the operating condition characteristic sequence of each dimension is coupled with the temperature output, the dependency and interaction logic between each variable is clarified, and a nonlinear coupling model is constructed.

Images