An online control method for thermal management of lithium-ion power batteries

Abstract

This invention discloses an online thermal management control method for lithium-ion power batteries, comprising: acquiring battery pack temperature data; statistically analyzing the battery pack temperature data to obtain temperature fluctuation distribution characteristics; acquiring cooling power output information through a feedback control method based on the temperature fluctuation distribution characteristics; obtaining power allocation weights based on the cooling power output information; performing temperature field prediction simulation based on the power allocation weights to obtain a predicted temperature field distribution; adjusting the thermal conductivity of the variable thermal interface material in the cooling system based on the predicted temperature field distribution to obtain a thermal diffusion path optimization scheme; constructing a dynamic thermal channel network based on the thermal diffusion path optimization scheme; matching the cooling strategy based on the dynamic thermal channel network and the battery operating state; extracting hierarchical control parameters from the cooling strategy to obtain an energy allocation optimization scheme; and controlling the cooling system of the lithium-ion power battery according to the energy allocation optimization scheme to achieve thermal management control.

Description

Technical Field

[0001] This invention belongs to the field of battery thermal management technology, and particularly relates to an online control method for thermal management of lithium-ion power batteries. Background Technology

[0002] Thermal management of lithium-ion power batteries is a core area of ​​development for electric vehicles and energy storage systems, directly impacting battery performance, safety, and lifespan; its importance is self-evident. With breakthroughs in battery technology towards higher energy density, the need for thermal management is becoming increasingly urgent, as any temperature runaway can lead to performance degradation or even safety hazards.

[0003] Existing thermal management methods largely rely on static cooling strategies or simple temperature threshold control, making it difficult to adapt to the dynamic thermal behavior of batteries under complex operating conditions. This simplistic control logic often leads to insufficient cooling efficiency or excessive energy consumption, especially under high load or extreme environmental conditions, where uneven temperature distribution and frequent hotspots are particularly prominent. Furthermore, achieving a balance between system response speed and energy consumption is challenging. Despite continuous exploration in the field of thermal management, several core challenges remain. First, precise control of temperature stability is a critical problem. Due to the complex temperature gradient within the battery pack, traditional methods struggle to control temperature fluctuations within an ideal range under dynamic operating conditions. Second, the optimization of heat diffusion paths is insufficient. Current solutions are relatively crude in their design for directional heat conduction and uniform heat dissipation, making it difficult to effectively eliminate hotspot areas. In addition, optimizing the entire lifecycle operation of the thermal management system is also challenging. Existing technologies lack intelligent adaptability to multiple operating conditions, resulting in a low degree of matching between cooling strategies and actual needs. These unresolved technical factors collectively contribute to the limitations of thermal management effectiveness, hindering further improvements in battery performance. Therefore, how to achieve precise and stable temperature control of the battery pack under dynamic operating conditions, optimize the heat dissipation path to eliminate hot spots, and construct an intelligent operation optimization scheme for the entire life cycle have become key issues in the research of online control methods for thermal management of lithium-ion power batteries. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention proposes an online thermal management control method for lithium-ion power batteries, thereby resolving the issues present in the prior art.

[0005] To achieve the above objectives, the present invention provides an online control method for thermal management of lithium-ion power batteries, comprising:

[0006] The battery pack temperature data of the lithium-ion power battery is acquired, and the temperature fluctuation distribution characteristics are obtained by statistical analysis of the battery pack temperature data. Based on the temperature fluctuation distribution characteristics, cooling power output information is obtained through a feedback control method. Based on the cooling power output information, power allocation weights are obtained, and the temperature field is predicted and simulated based on the power allocation weights to obtain the predicted temperature field distribution.

[0007] The thermal conductivity of the variable thermal interface material in the cooling process is adjusted based on the predicted temperature field distribution to obtain an optimized thermal diffusion path scheme. A dynamic thermal channel network is constructed based on the optimized thermal diffusion path scheme. A cooling strategy is obtained by matching the dynamic thermal channel network with the battery operating status. Layered control parameters are extracted from the cooling strategy, and an energy distribution optimization scheme is obtained through the layered control parameters. The cooling system of the lithium-ion power battery is controlled according to the energy distribution optimization scheme to achieve thermal management regulation.

[0008] Optionally, the process of obtaining the temperature fluctuation distribution characteristics includes:

[0009] The battery pack temperature data is divided into units, and the average temperature of each unit is calculated. The deviation value is calculated based on the temperature and average value of each unit. The deviation value is judged, and the abnormal deviation distribution is obtained based on the judgment result. The fluctuation characteristics of each unit are calculated based on the abnormal deviation distribution. Based on the fluctuation characteristics, the temperature spatial distribution model of each unit is constructed to obtain the temperature distribution characteristics.

[0010] Optionally, the process of acquiring the cooling power output information includes:

[0011] The deviation is calculated based on the temperature fluctuation distribution characteristics and the control target value to obtain a deviation value sequence. The cooling power output value is obtained by controlling the calculation through an adaptive PID algorithm based on the deviation value sequence. The gain parameter of the adaptive PID algorithm is updated according to the deviation value sequence.

[0012] Optionally, the process of obtaining the predicted temperature field distribution includes:

[0013] Based on the temperature fluctuation distribution characteristics, the cooling power output information is weighted to obtain the power allocation weight; a temperature gradient model is constructed based on the temperature distribution characteristics, and the power allocated according to the power allocation weight is combined with the temperature gradient model simulation to obtain the optimized temperature distribution; the temperature change trend at subsequent times is obtained based on the optimized temperature analysis and prediction; the temperature field distribution at the next time moment is obtained based on the temperature change trend; and the temperature field distribution at the next time moment is smoothed and filtered to obtain the predicted temperature field distribution.

[0014] Optionally, the process of obtaining the optimized heat diffusion path scheme includes:

[0015] Based on the predicted temperature field distribution, the predicted temperature values ​​of each unit in the space are obtained. The predicted temperature values ​​are judged and divided to obtain a set of abnormal regions. Based on the temperature control of the abnormal region set, the corresponding variable thermal conductivity materials are obtained. The thermal conductivity adjustment value of each material is calculated by using the finite element analysis algorithm to obtain the optimized thermal conductivity set. The heat diffusion path is obtained through the optimized thermal conductivity set. The heat diffusion path is optimized and updated by the path generation algorithm to obtain the final optimized heat diffusion path scheme.

[0016] Optionally, the process of acquiring the dynamic hot aisle network includes:

[0017] According to the heat diffusion path optimization scheme, material activation points are allocated to the abnormal region set to obtain the heat absorption distribution. Based on the heat absorption distribution and the thermal conductivity of the variable thermally conductive material, a dynamic thermal channel network is constructed. The heat flow direction is extracted from the heat absorption distribution, and the heat conduction path and efficiency of the dynamic thermal channel network are obtained based on the heat flow direction.

[0018] Optionally, the process of obtaining the cooling strategy includes:

[0019] The thermal conductivity data of the dynamic thermal channel network and the battery operating status are fused to obtain fused operating data. The fused operating data is then identified using an operating condition identification algorithm to obtain operating condition characteristics. These operating condition characteristics are matched with typical operating conditions to obtain the corresponding initial cooling strategy. The operating condition identification algorithm is a clustering method, and the typical operating conditions are typical operating conditions under pre-stored historical data, each with a corresponding cooling strategy. The initial cooling strategy is then optimized based on the thermal conductivity data of the dynamic thermal channel network to obtain the final cooling strategy.

[0020] Optionally, the process of obtaining the energy allocation optimization scheme includes:

[0021] The system obtains the hierarchical control parameters in the cooling strategy, performs feature extraction on the hierarchical control parameters, identifies the strategy layer instructions, decomposes the strategy layer instructions to obtain the execution layer actions, judges the execution layer actions to obtain the action sequence, sorts the action sequence to obtain the priority of the action sequence, obtains the initial energy allocation scheme based on the action sequence and priority, and optimizes the initial energy allocation scheme to obtain the energy allocation optimization scheme.

[0022] Optionally, the process of controlling the cooling system of the lithium-ion power battery includes:

[0023] Based on the energy distribution optimization scheme, the parameters of the cooling system are adjusted to obtain the adjustment parameters. Based on the adjustment parameters, the adjustment command is obtained, and the cooling system controlled by the thermal management system is controlled by the adjustment command.

[0024] On the other hand, this application provides an online thermal management control system for lithium-ion power batteries, used to perform the above-described method.

[0025] Compared with the prior art, the present invention has the following advantages and technical effects:

[0026] This invention achieves precise online temperature control of lithium-ion power battery packs. Based on temperature fluctuation distribution characteristics and an adaptive PID algorithm, the cooling power is dynamically adjusted, effectively solving the problems of slow response and high energy consumption associated with traditional static strategies. Through optimization of the thermal conductivity of variable thermal interface materials and the construction of a dynamic thermal channel network, heat is directed and local hotspots are eliminated, significantly improving the uniformity of temperature distribution. Combined with operating condition identification algorithms and hierarchical control parameters, the optimal cooling strategy can be intelligently matched for multiple scenarios, balancing system response speed and energy efficiency. Furthermore, a closed-loop optimization mechanism continuously corrects temperature deviations, ensuring high efficiency and robustness of thermal management throughout the entire lifecycle, achieving a synergistic improvement in battery performance, safety, and lifespan under complex operating conditions. Attached Figure Description

[0027] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a flowchart of an online thermal management control method for lithium-ion power batteries according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the online thermal management control system for lithium-ion power batteries according to an embodiment of the present invention. Detailed Implementation

[0030] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0031] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0032] like Figure 1 As shown in the figure, the online thermal management control method and system for lithium-ion power batteries in this embodiment may specifically include:

[0033] S101. Real-time temperature data of the battery pack is collected by sensors. Combined with the preset temperature collection frequency, the deviation between the temperature value of each unit and the average temperature is calculated to obtain the temperature fluctuation distribution characteristics.

[0034] Temperature data for each cell in the battery pack is acquired at a preset frequency and stored as a time-series dataset to obtain the raw temperature dataset. Using this time-series dataset, the average temperature of each cell is calculated to obtain the average temperature of the battery pack. The deviation between each cell's temperature and the average temperature is calculated to obtain a set of temperature deviations for each cell. If any cell's deviation exceeds a preset threshold, it is marked as an outlier, resulting in an abnormal deviation distribution. Based on this abnormal deviation distribution, the frequency and amplitude of temperature fluctuations in each cell are calculated to obtain temperature fluctuation characteristics. Using these fluctuation characteristics, a spatial distribution model of the temperature for each cell is constructed to obtain the temperature distribution characteristics.

[0035] In battery pack temperature monitoring, sensors collect temperature data from each cell at a fixed frequency, forming a time-series dataset. The core of this process is ensuring data continuity and accuracy. Assuming a battery pack contains 10 cells, and the sensors collect temperature data once per second, running continuously for one hour, it generates 3600 data sets, each containing temperature values ​​from 10 cells. This dataset provides the foundation for subsequent analysis.

[0036] Specifically, the average temperature of each cell is calculated to obtain the average temperature of the battery pack. After collecting data for one hour, the temperatures of the 10 cells at a certain moment were 20℃, 21℃, 19℃, 22℃, 20℃, 21℃, 20℃, 23℃, 19℃, and 20℃, with an average temperature of 20.5℃. This average reflects the overall thermal state of the battery pack, laying the foundation for deviation analysis. The deviation between each cell's temperature and the average temperature is calculated. The deviation reflects the degree to which each cell's temperature deviates from the overall average. Taking the above data as an example, the deviation of cell 1's temperature of 20℃ from the average of 20.5℃ is -0.5℃, and the deviation of cell 8's temperature of 23℃ is +2.5℃. By traversing all data, the set of deviations for each cell is obtained.

[0037] Preferably, the deviation set can be used to identify potential anomalies. For example, if the preset deviation threshold is ±2℃, then unit 8 with a deviation of +2.5℃ is marked as an anomaly. Identifying anomalies helps to discover localized overheating or undercooling areas. If unit 8 experiences deviations exceeding 2℃ multiple times within one hour, an abnormal deviation distribution is generated, recording the number of anomalies and their timing. This distribution visually demonstrates the thermal behavior of the problematic unit.

[0038] In one embodiment, the frequency and amplitude of temperature fluctuations are calculated through the distribution of abnormal deviations. For example, if unit 8 experiences 10 deviations exceeding 2°C within one hour, the fluctuation frequency is 10 times / hour, and the amplitude is the range of the absolute value of the deviation, such as 2°C to 3°C. This fluctuation characteristic quantifies the dynamic nature of temperature changes, providing a basis for thermal management.

[0039] A spatial distribution model is constructed based on fluctuation characteristics to describe the temperature distribution within the battery pack. Assuming the battery pack is arranged in two dimensions, with cell 8 located in the central region, the model shows that its temperature is higher than surrounding cells, forming a localized hotspot. Preferably, the spatial distribution model is presented through a visualized thermal map, clearly showing the location and diffusion trend of high-temperature areas. Anomaly detection can provide timely warnings of potential faults, fluctuation characteristic analysis optimizes heat dissipation strategies, and the spatial distribution model provides a reference for battery pack design. These technologies collectively improve the safety and lifespan of the battery pack. Identified hotspots can guide the optimization of the cooling system, reducing the risk of overheating.

[0040] It should be noted that the data-driven analysis method is adaptable to different battery pack sizes, demonstrating strong versatility. Fluctuation characteristics can also be combined with historical data to predict future temperature trends. For example, if the fluctuation frequency of cell 8 gradually increases, it may indicate insufficient heat dissipation, requiring early intervention. This predictive capability further enhances the system's reliability. Preferably, the spatial distribution model can also be dynamically updated to adapt to changes in the battery pack's operating state, ensuring the accuracy of long-term monitoring.

[0041] S102. Based on the temperature fluctuation distribution characteristics, an adaptive PID algorithm is used to adjust the cooling system parameters. The proportional, integral, and derivative gains are dynamically updated based on the deviation value to determine the cooling power output information.

[0042] Based on the temperature fluctuation distribution characteristics, the deviation value from the target temperature is calculated, and a deviation value sequence is determined. An adaptive PID algorithm is used to dynamically update the proportional gain, integral gain, and derivative gain based on the deviation value sequence, resulting in a gain parameter set. The cooling system operating parameters are adjusted using the gain parameter set, and the cooling power output value is calculated. If the cooling power output value exceeds a preset threshold range, the gain parameter set is further optimized, and the cooling power output value is recalculated.

[0043] Obtaining temperature fluctuation distribution characteristics is a fundamental step in battery pack thermal management. Temperature fluctuation distribution reflects the dynamic characteristics of temperature changes in each cell within the battery pack over time. For example, assuming a battery pack contains 10 cells, and sensors collect temperature data once per second, a temperature sequence containing multiple time points is formed after a period of time. Based on this sequence, fluctuation characteristics, such as periodic changes or instantaneous abrupt temperature changes in each cell, can be extracted using statistical methods. These characteristics provide the data foundation for subsequent deviation calculations.

[0044] Specifically, when calculating the deviation sequence from the target temperature, the target temperature is typically the preset optimal operating temperature in the battery pack design, such as 30 degrees Celsius. In one embodiment, it is assumed that the temperature of a cell at a certain moment is 32 degrees Celsius, which deviates from the target temperature by 2 degrees Celsius. By performing similar calculations on the temperatures of all cells and time points, a deviation sequence can be generated. The deviation sequence not only reflects the temperature difference at a single point in time but also reveals the temperature change trend over time, such as whether a cell is consistently higher or periodically deviates from the target.

[0045] Preferably, the core of the adaptive PID algorithm lies in dynamically adjusting control parameters based on the deviation value sequence. The proportional gain affects the response speed, the integral gain eliminates steady-state error, and the derivative gain suppresses rapid changes. Assuming the deviation value sequence shows that the temperature of a certain unit is consistently high, the algorithm may increase the proportional gain to accelerate the cooling response, while appropriately adjusting the integral gain to avoid long-term deviation accumulation. For example, when the deviation value suddenly increases from 2 degrees Celsius to 5 degrees Celsius, the derivative gain will rapidly increase to suppress the rapid temperature rise. This dynamic adjustment ensures the accuracy and real-time performance of the control. For example, when adjusting the operating parameters of the cooling system, the gain parameter set directly affects the cooling power output. The cooling system achieves temperature control by adjusting the fan speed or the liquid cooling pump flow rate. Assuming the gain parameter set increases the fan speed from 1000 rpm to 1500 rpm, the cooling power output value increases accordingly. The calculation of the power output value needs to comprehensively consider the system hardware characteristics, such as the fan power curve or the heat exchange efficiency of the liquid cooling system. This approach enables the cooling system to respond quickly to temperature changes.

[0046] In one embodiment, if the cooling power output exceeds a preset threshold range, for example, exceeding the maximum power of 500 watts or falling below the minimum power of 100 watts, a secondary optimization of the gain parameter set is required. This optimization process may be achieved by reducing the proportional gain or re-evaluating the weights of the deviation sequence.

[0047] For example, if the power output reaches 600 watts in a calculation, the system will automatically revert the gain parameter and recalculate to bring the output value back down to 450 watts. This secondary optimization design improves the system's stability and adaptability, avoiding overload or inefficient operation. Specifically, each step of the above method is closely integrated, from temperature fluctuation feature extraction to deviation calculation, and then to adaptive control and power optimization, forming a complete thermal management closed loop. For example, the generation of the deviation sequence depends on the accuracy of the fluctuation features, while the dynamic adjustment of the PID algorithm is based on the deviation sequence, and the optimization of the cooling system's operating parameters further ensures overall efficiency. This multi-stage collaborative approach not only improves the response speed of battery pack thermal management but also enhances the system's robustness, providing a reliable guarantee for the safe operation of the battery.

[0048] S103. Extract the power allocation weight from the cooling power output information, combine it with the temperature gradient prediction model, calculate the temperature change trend of each battery cell in the next period, and obtain the predicted temperature field distribution.

[0049] Power allocation weights are obtained from the cooling power output data, and statistical analysis methods are used to determine the cooling power allocation ratio for each battery cell. The power allocation weights are combined with a temperature gradient model to obtain the heat of each battery cell, generating an initial temperature distribution. If the initial temperature distribution exceeds a preset threshold, a linear regression algorithm is used to adjust the temperature gradient model, resulting in an optimized temperature distribution. Based on the optimized temperature distribution, the temperature change trend of each battery cell in the next time period is obtained, generating time series data. Using the time series data, interpolation methods are used to determine the temperature value of each battery cell in the next time period. Spatial correlations are extracted from the temperature values ​​to generate a temperature field distribution. If outliers exist in the temperature field distribution, smoothing filtering is applied to obtain the final temperature field distribution data.

[0050] For example, when obtaining power allocation weights from cooling power output data, statistical analysis methods can be used to clarify the power requirements of each battery cell. For instance, assuming a battery pack contains 10 cells, power output data is collected over one hour, and it is observed that some cells have higher power requirements due to their proximity to heat sources. Statistical analysis can employ a weighted average method, combined with historical data, to calculate the heat dissipation power allocation ratio for each cell. The core principle is to dynamically adjust the weights based on actual power fluctuations to ensure a reasonable allocation of heat dissipation power.

[0051] The power allocation weights are combined with a temperature gradient model, which uses heat input to generate an initial temperature distribution. This temperature gradient model can be constructed based on the spatial location and thermal conductivity characteristics of the battery cells. For example, cells closer to the center have poorer heat dissipation and therefore higher heat input. Assuming a cell has a heat dissipation power weight of 0.3, and the model estimates its heat input to be 200W, the initial temperature distribution shows that the cell's temperature is 45°C. If a region in the distribution is found to have a temperature exceeding the 50°C threshold, further optimization is required.

[0052] Specifically, when adjusting the temperature gradient model, a linear regression algorithm can be used to analyze the relationship between temperature and heat dissipation power. For example, by collecting multiple sets of power and temperature data, regression analysis reveals that for every 100W increase in heat dissipation power, the temperature decreases by approximately 5℃. Based on this, the model parameters can be adjusted to make the temperature distribution more realistic. For instance, after optimization, the temperature of a certain unit decreased from 48℃ to 43℃, and the overall distribution became more uniform.

[0053] Preferably, time-series data is generated based on the optimized temperature distribution to predict the temperature change trend for the next period. For example, analyzing the temperature data from the previous 6 hours, if the temperature change in a certain unit is approximately 2°C per hour, the predicted temperature after 1 hour is 45°C. The time-series data can be fitted with trends to clearly demonstrate the dynamic characteristics of each unit.

[0054] In one embodiment, an interpolation method is used to determine the temperature value for the next time period. For example, if the temperature of a cell is 38°C at 0.5 hours and 40°C at 1 hour, the temperature at 0.75 hours is estimated to be approximately 39.5°C using linear interpolation. This method is suitable for scenarios with few data points and can effectively fill time gaps. It is understood that when extracting spatial correlations from temperature values ​​to generate a temperature field distribution, spatial autocorrelation analysis can be used. For example, the analysis may find that temperature changes in cells near the edge are highly correlated with neighboring cells, generating a temperature field that shows areas of concentrated heat. If the temperature in a certain area is abnormally higher than the surrounding area, such as a point reaching 55°C, it can be considered an anomaly.

[0055] For example, when dealing with outliers, smoothing filtering can effectively eliminate noise. For instance, using a moving average filter, the temperature of an outlier is replaced with the average of four surrounding points. Assuming the surrounding temperatures are all around 40°C, the filtered temperature of the outlier is adjusted to 42°C. The final temperature field distribution data is smoother, reflecting the true characteristics of heat distribution.

[0056] It should be noted that each step of the above method revolves around the thermal management of the battery cooling system. For example, dynamic adjustment of power allocation weights optimizes energy utilization, while interpolation and filtering improve the accuracy of temperature prediction. These operations are closely linked, ensuring that the generation process of the temperature field distribution is logically rigorous and efficient.

[0057] S104. For the predicted temperature field distribution, if there is a region where the temperature gradient exceeds the preset threshold, adjust the thermal conductivity of the variable thermal interface material to generate an optimized thermal diffusion path scheme.

[0058] Based on the obtained temperature field distribution data, the temperature values ​​of each region in the space are determined. If the temperature gradient of a region exceeds a preset threshold, a high-gradient region is defined according to the temperature field distribution, resulting in a set of abnormal regions. For the set of abnormal regions, a list of corresponding variable thermally conductive materials is obtained from the interface material database, and the thermal conductivity range of each material is determined. Based on the temperature field distribution of the high-gradient regions, the thermal conductivity adjustment value of each material is calculated using a finite element analysis algorithm, resulting in an optimized set of thermal conductivity. Using the optimized set of thermal conductivity, a heat diffusion path is generated to determine the heat flow direction from the high-gradient region to the low-gradient region. If the heat flow direction of the heat diffusion path covers all abnormal regions, a path generation algorithm is used to update the heat diffusion path, resulting in the final optimized solution.

[0059] For example, extracting temperature values ​​for each region from temperature field distribution data can be achieved through a grid partitioning method. Assume the battery module is divided into multiple grid cells, each recording the temperature value at a specific location. For instance, the temperature values ​​at grid points within a certain region might be 45°C, 47°C, and 50°C. By comparing these values ​​with a preset threshold, such as 48°C, abnormal temperature regions can be quickly located. This method relies on spatial sampling and can accurately capture the details of temperature distribution. If a temperature gradient in a region exceeds a threshold, such as a temperature difference between adjacent grid points exceeding 5°C / cm, then a high-gradient region needs to be identified. High-gradient regions typically indicate concentrated heat, which may affect battery performance. By analyzing the temperature field distribution, high-gradient regions can be categorized into an abnormal region set. For example, an area near a heat dissipation channel of a module might form an abnormal region set with a large temperature difference due to uneven heat flow, including grid points A and B. Specifically, when obtaining a list of variable thermally conductive materials from an interface material database, suitable thermally conductive materials can be selected based on their properties.

[0060] For example, the database includes silicon-based thermal pads, phase change materials, and graphene composites, with thermal conductivity ranging from 2 W / m·K to 10 W / m·K. For the high-temperature characteristics of abnormal regions, graphene composites with higher thermal conductivity are preferred. This screening method ensures that the material is matched to the specific scenario.

[0061] For example, when using finite element analysis to calculate the thermal conductivity adjustment value, the heat transfer process in abnormal regions can be simulated. Assuming the initial thermal conductivity of a high-gradient region is 5 W / m·K, analysis of the heat flux distribution reveals that it needs to be increased to 7 W / m·K to balance the temperature. This adjustment, based on the regional temperature field characteristics, can effectively optimize the heat distribution.

[0062] In one embodiment, when generating a heat diffusion path, the transfer of heat from a high-temperature region to a low-temperature region can be simulated based on an optimized set of thermal conductivity coefficients. For example, a heat flow path can be formed from an abnormal region A to a heat dissipation channel, covering an area where the temperature drops from 50°C to 40°C. This path generation relies on the laws of heat conduction to ensure efficient heat dissipation. Preferably, if the heat flow direction covers all abnormal regions, it can be further optimized through a path generation algorithm. For example, if the initial path only covers region A and not region B, the path direction can be adjusted to add an auxiliary path from region B to the radiator. This optimization method ensures comprehensive heat dissipation from abnormal regions through multi-path collaboration.

[0063] It should be noted that the above method, through hierarchical analysis and dynamic adjustment, can accurately address anomalies in the temperature field. Each step revolves around the thermal management needs of the battery module, logically progressing layer by layer. For example, from temperature value extraction to path optimization, a complete thermal management solution is formed. This solution ensures the evenness of heat distribution through multi-faceted collaboration.

[0064] S105. Through the thermal diffusion path optimization scheme, the phase change material layer and the graphene thermal diffusion layer are driven to work together to build a dynamic thermal channel network and balance the temperature distribution characteristics of the battery pack.

[0065] Based on the thermal diffusion path optimization scheme, the heat capacity characteristics of the phase change material (PCM) layer are utilized to allocate PCM activation points in high-heat regions, resulting in a heat absorption distribution. Leveraging the high thermal conductivity of the graphene thermal layer, a dynamic thermal channel network is constructed. The heat flow direction is extracted from the heat absorption distribution, yielding the heat conduction path and efficiency. Based on the heat conduction path, the topology of the thermal channel network is adjusted to optimize the interaction frequency between the PCM layer and the graphene layer, resulting in a balanced temperature and heat flow distribution characteristic for the battery pack.

[0066] For example, when using the thermal capacity characteristics of a phase change material (PCM) layer to optimize the heat diffusion path, the ability of PCM to absorb or release a large amount of heat at a specific temperature can be utilized to regulate the temperature of high-heat areas. PCMs are typically composed of organic or inorganic materials, such as paraffin or salt compounds, which can absorb heat near their phase change temperature without significantly increasing the temperature. In a battery pack thermal management scenario, suppose a module in the battery pack reaches a temperature of 55°C during operation, exceeding the safety threshold of 50°C. One possible implementation is to place a paraffin-based PCM layer near this module, with its phase change temperature set at 48°C. When the temperature approaches 48°C, the material begins to melt, absorbing excess heat and maintaining a stable module temperature.

[0067] Preferably, the allocation of phase change material activation points is based on temperature field distribution data, prioritizing coverage of the areas with the highest temperature. For example, real-time monitoring identifies the top and middle parts of the battery pack as high-heat areas, and phase change material layers with thicknesses of 5 mm and 3 mm are configured respectively to form a heat absorption distribution.

[0068] Specifically, the high thermal conductivity of graphene thermal layers can be used to construct dynamic thermal channel networks. Graphene has extremely high thermal conductivity, approximately 2000 W / m·K, enabling it to rapidly conduct heat from high-temperature regions to low-temperature regions.

[0069] For example, a 0.2mm thick graphene film is placed in the high-heat area at the top of the battery pack and connected to the heat sink. The heat absorption distribution shows that the top module has concentrated heat, and the graphene layer conducts the heat to the heat sink along a predetermined direction, forming a heat conduction path.

[0070] It should be noted that the efficiency of the heat conduction path depends on the continuity and contact quality of the graphene layer. In one embodiment, laser cutting technology ensures a smooth contact surface between the graphene layer and the battery module, reducing thermal resistance by approximately 20%, making the heat flow direction more controllable, and significantly improving the rate at which heat is conducted from the top module to the bottom heat sink.

[0071] In one possible implementation, when adjusting the thermal channel network topology, the distribution of the graphene layer can be dynamically optimized based on the heat conduction path. For example, if the initial topology is a mesh structure, and heat flow is detected to be concentrated in the center of the battery pack, it can be adjusted to a radial topology, increasing the graphene channel density in the central region and increasing the channel width from 0.5 mm to 0.8 mm to improve heat conduction. It is understood that topology adjustments must consider material cost and processing difficulty; a preferred approach is to add local branch channels in high-heat areas rather than a complete reconfiguration. For example, optimizing the interaction frequency between the phase change material layer and the graphene layer aims to balance heat absorption and conduction efficiency. After the battery pack has been running for 30 minutes, assuming the temperature in the central region is still high, the interaction frequency can be controlled by adjusting the activation cycle of the phase change material layer. In one embodiment, the phase change material is set to enter an endothermic state every 5 minutes, while the graphene layer continues to conduct heat, resulting in a more uniform heat flow distribution. Preferably, monitoring data shows that the overall temperature fluctuation range of the battery pack decreases from ±5℃ to ±2℃, and the heat flow distribution characteristics are more balanced. Understandably, the above method, through the synergistic effect of phase change materials and graphene, precisely regulates heat in high-heat regions, and the dynamic adjustment of heat conduction paths and topology further improves thermal management efficiency. This approach has good applicability in battery pack thermal management and can effectively address heat distribution problems under complex operating conditions.

[0072] S106. Obtain the heat transfer efficiency data of the dynamic thermal channel network, combine it with the battery operating status collected by the real-time operating condition sensor, input it into the operating condition identification algorithm, and match the optimal cooling strategy in the typical operating condition library.

[0073] The system acquires thermal conductivity data from the dynamic thermal aisle network and real-time battery operating status data from sensors, performs data fusion processing to obtain fused operating data. This fused operating data is then input into an operating condition identification algorithm for feature extraction, yielding operating condition features. If the operating condition features match preset features in a typical operating condition library, the corresponding cooling strategy is retrieved from the library to determine a preliminary cooling strategy. Based on this preliminary cooling strategy and the dynamic efficiency data of the thermal aisle network, an optimization algorithm is used to adjust the strategy parameters, resulting in an optimized cooling strategy.

[0074] For example, when acquiring heat transfer efficiency data for a dynamic thermal aisle network, heat transfer can be monitored in real time using heat flux sensors deployed at key nodes of the thermal aisle. The sensors collect data once per second, recording the heat conduction rate in different regions of the thermal aisle; for example, the heat flux density at a certain node is 500 W / m². 2 The other node is 300W / m 2 These data reflect the dynamic efficiency differences in hot aisle networks, providing a basis for subsequent optimization.

[0075] When real-time sensors collect battery operating status data, temperature and voltage sensors can be used to monitor the battery pack's operation. Multi-point data acquisition provides a comprehensive picture of the operating status, laying the foundation for data fusion. The acquisition frequency can be set to once per minute to balance real-time performance and system load.

[0076] In one possible implementation, data fusion processing integrates thermal conductivity efficiency data and battery operating status data. Preferably, a weighted averaging method can be used to correlate heat flux density data with battery temperature data to generate fused operating data. For example, if a region has high heat flux density and high temperature, the fused data may indicate that this region requires priority cooling. The fusion process must consider the time synchronization of the data to ensure the accurate correspondence between thermal conductivity efficiency and battery status.

[0077] Understandably, the feature extraction process of the operating condition identification algorithm requires mining key information from the fused data. For example, by analyzing the fused data, the distribution characteristics of high-temperature areas in the battery can be extracted, such as a region experiencing sustained high temperatures for more than 10 minutes, or a temperature gradient exceeding 5°C / cm in a certain region. These features reflect anomalies in the operating conditions. The algorithm can use clustering methods to compare the extracted features with a typical operating condition database to quickly locate the current operating condition. In one embodiment, if the operating condition features match the typical operating condition database, such as identifying a "high-temperature heavy-load operating condition," the corresponding cooling strategy is retrieved from the database, such as increasing the coolant flow rate to 2L / min and prioritizing its flow to the high-temperature area. The initial cooling strategy needs to be combined with the real-time nature of the operating condition to ensure timely response. The strategies in the database are based on historical data accumulation and can quickly adapt to common operating conditions.

[0078] For example, when adjusting cooling strategy parameters, efficiency data from the dynamic thermal aisle network can be used to further refine the settings using optimization algorithms. Suppose a certain thermal aisle has low efficiency, with a heat flux density of only 200 W / m². 2 By adjusting the coolant flow rate or the thermal channel topology, heat dissipation in this area can be prioritized. The optimization algorithm can be based on the gradient descent principle, iteratively adjusting parameters until the heat flow distribution is more uniform. The adjusted strategy can more accurately adapt to the current operating conditions.

[0079] It's important to note that the optimized cooling strategy needs to be validated for its suitability in real time. For example, by re-collecting battery temperature data, it's observed whether the high-temperature area has decreased to a safe range, such as from 50℃ to 40℃. The validation process can be combined with thermal channel efficiency data to ensure improved heat transfer efficiency after strategy adjustment. The entire process forms a closed loop, from data acquisition to strategy optimization, with each step interconnected to ensure the stability of the battery pack operation.

[0080] S107. Extract hierarchical control parameters from the matched cooling strategy, decompose them into strategy layer instructions and execution layer actions using a hierarchical control architecture, and generate an energy allocation optimization scheme.

[0081] Layered control parameters are obtained from the cooling strategy, and a preset extraction algorithm is used to determine the parameter set. If the parameter set contains strategy-level instructions, the instructions are decomposed to generate a first instruction sequence. Based on the first instruction sequence, execution-level actions are obtained, and it is determined whether the actions meet preset execution conditions. If the actions meet the execution conditions, a first action sequence is generated, and the priority of the action sequence is determined. An initial energy allocation scheme is generated using the first action sequence and priorities. The input parameters of the optimization algorithm are obtained through the initial energy allocation scheme, and it is determined whether the optimization conditions are met. If the optimization conditions are met, an optimized energy allocation scheme is generated, and the output parameters of the final scheme are determined.

[0082] In one possible implementation, obtaining hierarchical control parameters from the cooling strategy involves a structured decomposition of the strategy. Cooling strategies typically contain multiple layers of control logic; for example, the strategy layer determines the overall cooling target, while the execution layer handles specific actions. The extraction algorithm can be based on rules or machine learning models, generating a parameter set by analyzing key fields such as time, temperature, and power in the strategy.

[0083] For example, a battery cooling strategy specifies that high-power cooling should be activated when the temperature exceeds 45 degrees Celsius. The algorithm can extract "temperature threshold of 45 degrees Celsius" and "high-power mode" as a parameter set. This method ensures the comprehensiveness of the parameters, providing a foundation for subsequent instruction decomposition.

[0084] For example, if the parameter set contains policy-level instructions, such as "prioritize reducing core area temperature," then the instructions need to be decomposed to generate a first instruction sequence. The decomposition process can be based on a predefined instruction template, breaking down the instructions into specific subtasks.

[0085] For example, reducing core temperature can be broken down into "starting the core fan" and "increasing coolant flow rate".

[0086] In one embodiment, assuming a core temperature of 50 degrees Celsius, the system can generate a sequence of instructions: first, start the fan at 80% power, then increase the coolant flow rate to 2 liters per minute. This decomposition method ensures that the instruction sequence has clear executable capabilities.

[0087] Specifically, after obtaining the execution layer action based on the first instruction sequence, it is necessary to further determine whether the action meets the execution conditions. Execution conditions may include hardware status, power consumption limitations, etc.

[0088] For example, to check if the fan is operating, you need to confirm whether its current speed is lower than the target value; to adjust the coolant flow rate, you need to check the pump's available power.

[0089] In one embodiment, if the fan's current speed is 50% and the command requires 80%, the action is satisfied; if the pump power is insufficient, the flow rate command needs to be adjusted. This judgment process ensures the feasibility of the action.

[0090] Preferably, after generating the first action sequence, the priority of the action sequence needs to be determined.

[0091] For example, excessively high core temperatures may take precedence over those at the edges, thus fan operation takes precedence over coolant adjustment.

[0092] In one possible implementation, the system can assign weights based on temperature distribution, increasing priority by 10% for every 1-degree Celsius increase in core temperature. For example, assuming a core temperature of 50 degrees Celsius and an edge temperature of 40 degrees Celsius, the fan operation priority could be set to 80, and the coolant priority adjusted to 60. This priority allocation improves the response efficiency of critical areas.

[0093] Understandably, generating an initial energy allocation scheme through the first action sequence and priority requires comprehensive consideration of energy consumption balance.

[0094] For example, the initial energy allocation scheme serves as the input parameter for the optimization algorithm, and it is necessary to determine whether the optimization conditions are met, such as the total energy consumption not exceeding the threshold or the temperature drop rate meeting the standard.

[0095] In one embodiment, the condition is met if the solution achieves a core temperature drop rate of 2 degrees Celsius per minute and the total power is below 900 watts. Otherwise, the fan power or flow rate needs to be adjusted. This judgment process improves the adaptability of the solution. In one possible implementation, parameters can be adjusted iteratively when generating an optimized energy distribution solution. For example, if the initial solution has excessively high fan power leading to excessive energy consumption, the optimization algorithm can reduce the fan power to 500 watts while increasing the coolant flow rate to 2.5 liters per minute, ultimately maintaining the temperature drop rate at 1.5 degrees Celsius per minute. This optimization method balances energy efficiency and cooling requirements. It should be noted that the output parameters of the final solution need to have clearly defined execution values, such as a fan speed of 7000 rpm and a coolant flow rate of 2.2 liters per minute. These parameters provide clear guidance to the execution layer, ensuring efficient operation of the cooling system.

[0096] S108. Based on the energy distribution optimization scheme, adjust the operating parameters of the actuators in the cooling system, update the real-time operating status of the thermal management system, and obtain new temperature fluctuation distribution characteristics.

[0097] The system collects actuator parameters from the cooling system and adjusts these parameters using a preset energy distribution model to obtain an optimized parameter set. Adjustment commands are then obtained from this optimized parameter set to update the operating status of the thermal management system, resulting in real-time status data. If the real-time status data exceeds a preset threshold, temperature fluctuations are calculated using a distribution analysis algorithm to obtain a fluctuation feature set. Distribution patterns are extracted from this fluctuation feature set, and a clustering algorithm is used to divide the fluctuation intervals, resulting in categorized fluctuation interval data. Abnormal intervals are identified from the categorized fluctuation interval data, and actuator parameters are adjusted to obtain an updated parameter configuration. Energy distribution is optimized using the updated parameter configuration, and a feedback control algorithm is used to adjust system operation, resulting in a stable temperature distribution characteristic. Key indicators are extracted from the stable temperature distribution characteristic, and the status monitoring of the thermal management system is updated to obtain the final operating status data.

[0098] For example, when acquiring actuator parameters through a cooling system, data can be obtained from devices such as heat exchangers, fan speeds, and pump flow rates. Suppose the heat exchanger's temperature sensor shows a current value of 45 degrees Celsius, and the fan speed is 1200 revolutions per minute. These parameters reflect the real-time operating status of the system. The acquisition process typically relies on a sensor network to ensure data accuracy. Preferably, the data undergoes preliminary filtering to remove outliers, improving the reliability of subsequent analysis. When adjusting parameters using a preset energy distribution model, energy can be redistributed based on the acquired data using a linear mapping method. For example, the fan speed might be adjusted from 1200 revolutions per minute to 1500 revolutions per minute to cope with increased temperature. The adjusted parameter set would include a more optimized operating configuration, such as a 10% increase in pump flow rate. The core of this approach is to ensure more efficient energy distribution through model prediction. Specifically, when obtaining adjustment instructions from the optimized parameter set, specific commands can be generated for the thermal management system. For example, the instruction might require increasing the coolant flow rate to 2 liters per minute while reducing the power of the secondary fan. This instruction acts directly on the controller, ensuring the system operates according to the optimized configuration. It should be noted that instruction generation needs to take into account the device's response time to avoid frequent adjustments that could lead to system instability.

[0099] In one embodiment, after updating the thermal management system's operating status, real-time status data might show a core component temperature of 40 degrees Celsius, slightly lower than expected. If it exceeds a preset threshold (e.g., 42 degrees Celsius), further analysis is triggered. For example, temperature fluctuations might exhibit periodic increases. Distribution analysis algorithms can identify fluctuations concentrated in the 38-42 degree Celsius range. This analysis relies on statistical methods to extract the frequency and amplitude of fluctuations. For example, after extracting the fluctuation feature set, it might be found that the fluctuations are mainly caused by changes in the external ambient temperature. Clustering algorithms will divide the fluctuation range into high-frequency and low-frequency categories. The classified interval data clearly shows the distribution pattern of abnormal fluctuations. For example, high-frequency fluctuations might be concentrated in scenarios where the temperature rises rapidly in a short period. This division facilitates subsequent precise adjustments. Understandably, after identifying the abnormal range, when adjusting actuator parameters, the fan speed might be specifically reduced to 1000 revolutions per minute to reduce unnecessary energy consumption. The updated parameter configuration will rebalance the system's operating load. For example, the coolant flow rate might be fine-tuned to 1.8 liters per minute. This adjustment, based on the characteristics of the abnormal range, ensures smoother system operation. Preferably, when optimizing energy distribution through feedback control algorithms, a proportional control mechanism can be introduced. For example, when the temperature deviates from the target value, the pump power is gradually adjusted to avoid sudden changes. The core of this method lies in dynamic response, ensuring that the temperature distribution tends to stabilize. A stable temperature distribution characteristic may be that the temperature of the core components is maintained at around 39 degrees Celsius, with a fluctuation range of less than 1 degree Celsius. In one embodiment, when extracting key indicators from stable temperature distribution characteristics, attention can be paid to temperature uniformity and energy efficiency. For example, the uniformity indicator may show that the temperature difference between all components is less than 2 degrees Celsius. These indicators are directly used to update status monitoring. For example, the monitoring system may record the daily temperature change trend for long-term optimization. The core of this approach is to improve the predictability of the system through data-driven decision-making.

[0100] S109. If there are still areas in the new temperature fluctuation distribution characteristics where the deviation exceeds the threshold, return to the adaptive PID algorithm to recalculate the cooling parameters and iterate until the temperature fluctuation meets the preset range.

[0101] If there are regions in the temperature fluctuation distribution that exceed the threshold, the fluctuation data of these regions is extracted from the distribution characteristics to obtain a set of regional deviations. Using this set, an adaptive PID algorithm is invoked to calculate the adjustment values ​​for the cooling parameters, resulting in a set of parameter increments. Based on these increments, the cooling parameters are adjusted to generate a new parameter configuration, leading to an updated cooling scheme. Using this updated cooling scheme, the temperature fluctuation distribution is recalculated to obtain new distribution characteristics. If regions in the new distribution characteristics still exceed the threshold, fluctuation data is extracted from these characteristics to obtain an updated set of deviations. Using this updated set, iterative optimization is performed to adjust the cooling parameters, resulting in an optimized parameter configuration. Based on the optimized parameter configuration, it is verified whether the temperature fluctuations meet the preset range, yielding the final fluctuation distribution.

[0102] In one possible implementation, deviation analysis of temperature fluctuation distribution can begin with data acquisition. The cooling system uses sensors to acquire real-time temperature data from heat exchangers and pipes, creating a distribution map. Identification of deviation areas relies on the visual analysis of the distribution map; the system automatically marks areas exceeding the standard for easier subsequent processing. This method quickly locates problem areas through intuitive data presentation.

[0103] Specifically, extracting the regional deviation set involves further organizing the data from the areas exceeding the standard. For example, assuming the temperature points in the exceeding areas are 45 degrees Celsius, 46 degrees Celsius, and 44 degrees Celsius, the system will categorize these points into a deviation set and record their location and timestamp. Understandably, this set-based processing facilitates subsequent algorithm calls because it integrates scattered data points into an operable whole.

[0104] Preferably, the application of an adaptive PID algorithm is key to adjusting cooling parameters. In one embodiment, for the aforementioned set of deviations, the algorithm analyzes the duration and magnitude of the deviations. For example, if the temperature exceeds the threshold for 3 minutes, the algorithm might suggest increasing the coolant flow rate by 10%. A parameter increment set is thus generated, containing the flow rate adjustment value and the pump speed change value. This adaptive adjustment, based on learning from historical operating data, can dynamically adapt to different operating conditions. In one possible implementation, the cooling system applies the new parameter configuration immediately after it is generated. For example, the coolant flow rate is adjusted from 100 liters / hour to 110 liters / hour, and the pump speed is increased from 1200 rpm to 1300 rpm. It should be noted that the generation of the new configuration considers the overall system balance, avoiding instability in other areas caused by a single parameter adjustment. For example, when recalculating the temperature fluctuation distribution, the system simulates the heat transfer process under the new configuration. For instance, the adjusted heat exchanger temperature distribution map shows that the temperature in the exceeding area drops to 41 degrees Celsius, but a small area still exceeds the threshold. In this case, the system will extract a new set of deviations again, such as the point sets at 41 degrees Celsius and 42 degrees Celsius. Understandably, this iterative process ensures that the deviation gradually converges.

[0105] Specifically, the execution of the loop optimization relies on multiple iterative adjustments. In the second iteration, the coolant flow rate is further increased to 115 liters / hour, while the fan speed is fine-tuned. Preferably, a maximum number of iterations is set, such as 5, to avoid infinite loops. After several adjustments, the number of points in the deviation set is significantly reduced, and the temperature distribution tends to be more uniform.

[0106] In one possible implementation, verifying that temperature fluctuations meet a preset range is the final step. For example, the adjusted distribution map shows that temperatures in all areas are between 38 and 40 degrees Celsius, meeting the threshold requirement. It's important to note that this verification not only focuses on numerical values ​​but also checks the stability of the distribution, such as whether the fluctuation frequency is too high. This comprehensive check ensures the long-term reliability of the system. For instance, the generation of the final fluctuation distribution will produce a detailed operational report. Exemplarily, the report records a comparison of the temperature curves before and after adjustment, as well as the changes in deviation points for each iteration. This data recording provides a reference for subsequent optimization, demonstrating the system's efficiency in dynamic adjustments.

[0107] On the other hand, such as Figure 2 As shown, this invention provides an online thermal management and control system for lithium-ion power batteries, mainly comprising:

[0108] The temperature acquisition and deviation calculation module is used to acquire battery pack temperature data in real time through sensors, and calculate the deviation between the temperature value of each unit and the average temperature by combining the preset temperature acquisition frequency, so as to obtain the temperature fluctuation distribution characteristics.

[0109] The adaptive PID control module is used to adjust the cooling system parameters according to the temperature fluctuation distribution characteristics using an adaptive PID algorithm. It dynamically updates the proportional, integral, and derivative gains based on the deviation value to determine the cooling power output information.

[0110] The temperature prediction module is used to extract power allocation weights from cooling power output information, combine them with the temperature gradient prediction model, calculate the temperature change trend of each battery cell in the next period, and obtain the predicted temperature field distribution.

[0111] The thermal diffusion optimization module is used to adjust the thermal conductivity of the variable thermal interface material and generate an optimized thermal diffusion path scheme if there is a region where the temperature gradient exceeds a preset threshold for the predicted temperature field distribution.

[0112] The dynamic thermal channel construction module is used to drive the phase change material layer and the graphene thermal diffusion layer to work together through a thermal diffusion path optimization scheme to build a dynamic thermal channel network and balance the temperature distribution characteristics of the battery pack.

[0113] The operating condition identification and strategy matching module is used to acquire the heat transfer efficiency data of the dynamic thermal aisle network, combine it with the battery operating status collected by the real-time operating condition sensor, input it into the operating condition identification algorithm, and match the optimal cooling strategy in the typical operating condition library.

[0114] The hierarchical control and energy distribution module is used to extract hierarchical control parameters from the matched cooling strategy, decompose them into strategy layer instructions and execution layer actions using a hierarchical control architecture, and generate an energy distribution optimization scheme.

[0115] The actuator parameter adjustment module is used to adjust the operating parameters of the actuators in the cooling system according to the energy distribution optimization scheme, update the real-time operating status of the thermal management system, and obtain new temperature fluctuation distribution characteristics.

[0116] The loop optimization module is used to recalculate the cooling parameters using the adaptive PID algorithm if there are still areas in the new temperature fluctuation distribution characteristics where the deviation exceeds the threshold. The loop optimization continues until the temperature fluctuation meets the preset range.

[0117] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for online regulation of thermal management of a lithium-ion power battery, characterized in that, The method comprises the following steps: acquiring battery pack temperature data of a lithium ion power battery, statistically analyzing the battery pack temperature data to obtain temperature fluctuation distribution characteristics, acquiring cooling power output information through a feedback control method according to the temperature fluctuation distribution characteristics, and obtaining power distribution weights according to the cooling power output information, and predicting and simulating a temperature field according to the power distribution weights to obtain a predicted temperature field distribution; adjusting the thermal conductivity of a variable thermal interface material in a cooling system according to the predicted temperature field distribution to obtain a thermal diffusion path optimization scheme, constructing a dynamic thermal channel network according to the thermal diffusion path optimization scheme, and matching a cooling strategy according to the dynamic thermal channel network and the battery operating state; extracting hierarchical control parameters from the cooling strategy, and obtaining an energy distribution optimization scheme through the hierarchical control parameters; controlling the cooling system according to the energy distribution optimization scheme to realize thermal management regulation and control; the process of obtaining the thermal diffusion path optimization scheme comprises: obtaining predicted temperature values of each unit in the space according to the predicted temperature field distribution, judging and dividing the predicted temperature values to obtain an abnormal region set, obtaining corresponding variable thermal conductive materials according to the temperature regulation of the abnormal region set, calculating the thermal conductivity adjustment value of each material by using a finite element analysis algorithm to obtain an optimized thermal conductivity set, obtaining a thermal diffusion path through the optimized thermal conductivity set, and optimizing and updating the thermal diffusion path through a path generation algorithm to obtain the final thermal diffusion path optimization scheme; the process of obtaining the dynamic thermal channel network comprises: allocating material activation points to the abnormal region set according to the thermal diffusion path optimization scheme to obtain a heat absorption distribution, constructing a dynamic thermal channel network according to the heat absorption distribution and the thermal conductivity of the variable thermal conductive material, extracting a heat flow direction from the heat absorption distribution, and obtaining the heat conduction path and efficiency of the dynamic thermal channel network according to the heat flow direction.

2. The method of claim 1, wherein: the process of obtaining the temperature fluctuation distribution characteristics comprises: dividing the battery pack temperature data into units, and statistically analyzing the temperature mean values of the divided units, calculating deviation values according to the temperature mean values of the units, judging the deviation values, obtaining an abnormal deviation distribution based on the judgment result, calculating the fluctuation characteristics of the units according to the abnormal deviation distribution, constructing a temperature spatial distribution model of each unit according to the fluctuation characteristics, and obtaining the temperature distribution characteristics.

3. The method of claim 1, wherein: the process of obtaining the cooling power output information comprises: calculating a deviation according to the temperature fluctuation distribution characteristics and a control target value to obtain a deviation value sequence, and obtaining a cooling power output value through adaptive PID algorithm control calculation according to the deviation value sequence, wherein the gain parameter of the adaptive PID algorithm is updated according to the deviation value sequence.

4. The method of claim 1, wherein: the process of obtaining the predicted temperature field distribution comprises: According to the temperature fluctuation distribution characteristics, the cooling power output information is weighted and allocated to obtain a power allocation weight; a temperature gradient model is constructed according to the temperature distribution characteristics, and the optimized temperature distribution is obtained by combining the power allocation weight with the temperature gradient model simulation; the temperature change trend at the subsequent moment is obtained according to the optimized temperature analysis prediction; the temperature field distribution at the next moment is obtained according to the temperature change trend; and the predicted temperature field distribution is obtained by smoothing filtering the temperature field distribution at the next moment.

5. The method of claim 1, wherein, The cooling strategy acquisition process comprises: According to the thermal conduction efficiency data of the dynamic thermal channel network and the battery operating state, the fused operating data is obtained, the fused operating data is identified by the operating condition identification algorithm to obtain the operating condition characteristics, and the operating condition characteristics and the typical operating conditions are matched to obtain the corresponding initial cooling strategy; wherein the operating condition identification algorithm is a clustering method, the typical operating conditions are typical operating conditions under pre-stored historical data, and the cooling strategy corresponding thereto is obtained; and the preliminary cooling strategy is optimized according to the thermal conduction efficiency data of the dynamic thermal channel network to obtain the cooling strategy.

6. The method of claim 1, wherein, The energy distribution optimization scheme acquisition process comprises: The hierarchical control parameters in the cooling strategy are extracted, the strategy layer instruction is obtained, the strategy layer instruction is decomposed to obtain the execution layer action, the execution layer action is judged to obtain the action sequence, the action sequence is sorted to obtain the priority of the action sequence, the initial energy distribution scheme is obtained according to the action sequence and the priority, the initial energy distribution scheme is optimized to obtain the energy distribution optimization scheme.

7. The method of claim 1, wherein, The process of controlling the cooling system comprises: According to the energy distribution optimization scheme, the device parameters of different regions of the cooling system are adjusted to obtain adjustment parameters, the adjustment instructions are obtained according to the adjustment parameters, and the cooling system controlled by the thermal management system is controlled through the adjustment instructions.

8. A lithium-ion power battery thermal management online regulation system, characterized in that, A device for executing the method of any one of claims 1-7.

Images