Battery pre-cooling and pre-heating management control method and equipment and readable storage medium

Abstract

According to the battery pre-cooling and pre-heating management control method and device and the readable storage medium, the whole vehicle operation mode in the battery temperature prediction period is recognized, a temperature prediction model pre-trained for the operation mode is matched and called, the model is used for dynamically predicting the battery temperature in the prediction period, pre-cooling and pre-heating regulation is triggered according to the prediction result, and the battery pre-cooling and pre-heating management is achieved. The temperature of the battery entering the charging stage in the future is in the optimal working interval, so that the problem of insufficient cooling or excessive cooling of the battery temperature at the beginning of charging caused by dependence on static data judgment is solved, the requirement of high-rate fast charging on the battery temperature is met, and the charging efficiency, the service life and the safety of the battery are guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of battery thermal management, in particular to a battery pre-cooling thermal management control method, device and readable storage medium. BACKGROUND

[0002] With the rapid development of the new energy vehicle industry, high-rate fast charging technology has become one of the core directions to improve the user's energy supplement experience. However, a large amount of heat will be generated in the high-rate charging process of the power battery, and if the temperature control is not proper, not only the charging efficiency will be reduced and the battery life will be shortened, but also safety risks such as thermal runaway may be caused. Therefore, adjusting and controlling the temperature of the battery in the pre-cooling process to be in the optimal working interval before charging the battery has become a key technical link to meet the fast charging demand and ensure the safety and performance of the battery.

[0003] In the related art, in a case where the vehicle is in a navigation mode and located in a target charging area, or in a case where the vehicle is not in the navigation mode and located in the target charging area and the electric quantity of the battery is less than a preset electric quantity threshold, a current temperature of the battery is acquired; and the battery is temperature-regulated based on the current temperature and a preset temperature range, so as to regulate the temperature of the battery to be in the preset temperature range before performing a battery charging operation.

[0004] However, only relying on static data for judgment may cause insufficient cooling or excessive cooling. SUMMARY

[0005] The present application provides a battery pre-cooling thermal management control method, device and readable storage medium, which can solve the technical problem that in the related art, only relying on static data for judgment may cause insufficient cooling or excessive cooling when adjusting the battery temperature to a preset range according to the current battery temperature.

[0006] In a first aspect, an embodiment of the present application provides a battery pre-cooling thermal management control method, which comprises: Based on the whole vehicle operation mode in the battery temperature prediction period, a temperature prediction model corresponding to the pre-trained temperature prediction model is selected to predict the battery temperature in the battery temperature prediction period.

[0007] In combination with the first aspect, in an implementation mode, the battery pre-cooling thermal management control method comprises: If the whole vehicle operation mode in the battery temperature prediction period is the charging-first driving-later mode, the current battery temperature, the current battery electric quantity, the environment temperature, the battery heat generation amount, the battery refrigeration amount and the remaining charging time obtained based on the physical model are introduced into the pre-trained temperature prediction model one to predict the battery temperature in the battery temperature prediction period. In conjunction with the first aspect, in one embodiment, before selecting a pre-trained temperature prediction model corresponding to the vehicle operating mode within the battery temperature prediction period to predict the battery temperature within the battery temperature prediction period, the method further includes: The battery temperature prediction value is calculated based on the battery temperature rise during charging, the battery temperature rise during driving, and the initial battery temperature obtained from the physical model. This predicted battery temperature value is used as the output value of the training set of temperature prediction model one.

[0008] In conjunction with the first aspect, in one implementation, the determination of the charging-before-driving mode includes: If the vehicle speed is zero and the battery output current is negative, it is determined to be in charge-then-drive mode.

[0009] In conjunction with the first aspect, in one implementation, the step of selecting a pre-trained temperature prediction model based on the vehicle's operating mode within the battery temperature prediction period to predict the battery temperature within the prediction period includes: If the vehicle's operating mode during the battery temperature prediction period is driving mode only, the current battery temperature and the battery heat generation and cooling capacity obtained based on the physical model are imported into the pre-trained temperature prediction model 2 to predict the battery temperature during the battery temperature prediction period.

[0010] In conjunction with the first aspect, in one implementation, the determination of the driving mode only includes: If the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction period, it is determined to be in driving mode only.

[0011] In conjunction with the first aspect, in one implementation, the step of selecting a pre-trained temperature prediction model based on the vehicle's operating mode within the battery temperature prediction period to predict the battery temperature within the prediction period includes: If the vehicle's operating mode during the battery temperature prediction period is a charging-then-driving mode, then the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining driving time between the vehicle and the target charging station, calculated based on the physical model, are imported into the pre-trained temperature prediction model 3 to predict the battery temperature during the battery temperature prediction period.

[0012] In conjunction with the first aspect, in one implementation, the determination of the vehicle-first-charge mode includes: If the vehicle speed is zero and the battery output current is negative, or if the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction cycle, it is determined to be a non-drive-before-charge mode. If the vehicle is determined to be in a non-driving-before-charging mode and the remaining driving time between the vehicle and the target charging station is less than or equal to the battery temperature prediction period, then the vehicle operation mode within the battery temperature prediction period is determined to be a driving-before-charging mode.

[0013] Secondly, embodiments of this application provide a battery pre-cooling thermal management control device, which includes a processor, a memory, and a battery pre-cooling thermal management control program stored in the memory and executable by the processor. When the battery pre-cooling thermal management control program is executed by the processor, it implements the steps of the battery pre-cooling thermal management control method as described in some of the above embodiments.

[0014] Thirdly, embodiments of this application provide a computer-readable storage medium storing a battery pre-cooling thermal management control program, wherein when the battery pre-cooling thermal management control program is executed by a processor, it implements the steps of the battery pre-cooling thermal management control method as described in some of the above embodiments.

[0015] The beneficial effects of the technical solutions provided in this application include: By identifying the vehicle's operating mode within the battery temperature prediction cycle, matching and calling the temperature prediction model pre-trained for that operating mode, and using this model to dynamically predict the battery temperature within the prediction cycle, pre-cooling thermal regulation is triggered based on the prediction results, so that the battery temperature is in the optimal operating range when it enters the charging stage in the future. This solves the problem that the battery temperature is prone to insufficient or excessive cooling at the start of charging due to the reliance on static data judgment, thereby meeting the battery temperature requirements of high-rate fast charging and ensuring battery charging efficiency, lifespan and safety. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of an embodiment of the battery pre-cooling thermal management control method of this application; Figure 2 This is a schematic diagram illustrating the training and prediction process of the temperature prediction model in this application. Figure 3 This is a schematic diagram of the hardware structure of the battery pre-cooling thermal management control device involved in the embodiments of this application. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0019] In a first aspect, embodiments of this application provide a battery pre-cooling thermal management control method.

[0020] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the battery pre-cooling thermal management control method of this application. Figure 1 As shown, the battery pre-cooling thermal management control method includes: S100: Based on the vehicle's operating mode within the battery temperature prediction period, select the corresponding pre-trained temperature prediction model to predict the battery temperature within the battery temperature prediction period.

[0021] In this embodiment, by identifying the vehicle's operating mode within the battery temperature prediction cycle, matching and calling the temperature prediction model pre-trained for that operating mode, the battery temperature within the prediction cycle is dynamically predicted using this model. Based on the prediction results, pre-cooling thermal regulation is triggered so that the battery temperature is in the optimal operating range when it enters the charging stage in the future. This solves the problem that the battery temperature is prone to insufficient or excessive cooling at the start of charging due to reliance on static data judgment, thereby meeting the battery temperature requirements of high-rate fast charging and ensuring battery charging efficiency, lifespan, and safety.

[0022] Furthermore, in one embodiment, S100 includes S101, which includes the following steps: S101-2: If the vehicle operation mode during the battery temperature prediction period is the charging-then-driving mode, then the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining charging time obtained based on the physical model are imported into the pre-trained temperature prediction model 1 to predict the battery temperature during the battery temperature prediction period.

[0023] In this embodiment, if the vehicle operation mode during the battery temperature prediction period is a charging-then-driving mode, the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining charging time obtained based on the physical model are imported into a temperature prediction model 1 pre-trained for this mode. This model then predicts the battery temperature during the prediction period. By integrating the charge status, environmental influences, and thermal interaction parameters during the charging phase in this mode, combined with the temperature accumulation duration during the charging phase reflected by the remaining charging time, and leveraging the physical consistency of the parameters derived from the physical model, the temperature prediction model 1 can accurately capture the temperature change pattern between the heat generation during charging and the subsequent driving thermal state. This improves the accuracy of battery temperature prediction in this mode, thereby providing a temperature basis adapted to the charging and driving transition scenario for subsequent pre-cooling thermal control. This ensures that the battery temperature remains within a reasonable range during charging and subsequent driving, avoiding prediction deviations caused by missing parameters or insufficient model adaptation, and guaranteeing battery performance and safety.

[0024] Furthermore, in one embodiment, before S101-2, the following steps are also included: S101-1: The battery temperature prediction value is calculated based on the battery temperature rise during charging, the battery temperature rise during driving, and the initial battery temperature obtained from the physical model. This battery temperature prediction value is used as the output value of the training set of temperature prediction model one.

[0025] In this embodiment, the battery temperature rise during charging and during driving, obtained from the physical model, as well as the initial battery temperature, are used to calculate the predicted battery temperature. This predicted battery temperature is used as the output value of the training set of the temperature prediction model one, providing a physically consistent output benchmark for the training of the temperature prediction model one, so as to ensure that the model one can learn the inherent logic of battery temperature change in the charging-then-driving mode.

[0026] Furthermore, in one embodiment, the determination of the charging-before-driving mode includes the following steps: If the vehicle speed is zero and the battery output current is negative, it is determined to be in charge-then-drive mode.

[0027] In this embodiment, if the vehicle speed is zero and the battery output current is negative, the vehicle operation mode is determined to be the charging-then-driving mode. This clarifies the operating condition characteristics of charging operation first and then driving in this mode, providing a basis for matching the corresponding temperature prediction model and ensuring that the temperature prediction and pre-cooling thermal control for this specific operating condition can accurately adapt to its operating characteristics.

[0028] Furthermore, in one embodiment, S100 includes the following steps: S102: If the vehicle's operating mode during the battery temperature prediction period is driving mode only, then the current battery temperature and the battery heat generation and cooling capacity obtained based on the physical model are imported into the pre-trained temperature prediction model 2 to predict the battery temperature during the battery temperature prediction period.

[0029] In this embodiment, if the vehicle operation mode during the battery temperature prediction period is driving-only mode, the current battery temperature, along with the battery heat generation and cooling capacity calculated based on the physical model, are input into a pre-trained temperature prediction model two for this mode. This model then predicts the battery temperature during the prediction period. By focusing on the core thermal balance characteristics of dynamic heat generation and real-time cooling of the battery during continuous driving in driving-only mode, and leveraging the physical consistency of the parameters derived from the physical model, the temperature prediction model two can accurately capture the changes in battery temperature during driving in this mode, improving the relevance and accuracy of the prediction. This provides a temperature basis adapted to continuous driving scenarios for subsequent pre-cooling and thermal regulation, ensuring that the battery temperature remains within a reasonable range during driving, avoiding prediction deviations caused by parameter redundancy or insufficient mode adaptation, and guaranteeing battery performance and safety.

[0030] Furthermore, in one embodiment, the determination of the driving mode only includes: If the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction period, it is determined to be in driving mode only.

[0031] In this embodiment, if the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction cycle, the vehicle operation mode is determined to be driving mode only. This defines the operating condition characteristics of the vehicle under this mode, where there is no charging operation and only driving process during the prediction cycle. This provides a judgment benchmark for matching the corresponding temperature prediction model, ensuring that the temperature prediction and pre-cooling and heating control for this specific operating condition can accurately adapt to its operating characteristics and avoid prediction deviations caused by mode misjudgment.

[0032] Furthermore, in one embodiment, S100 includes the following steps: S103: If the vehicle's operating mode during the battery temperature prediction period is a charging-then-driving mode, then the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining driving time between the vehicle and the target charging station obtained based on the physical model are imported into the pre-trained temperature prediction model three to predict the battery temperature during the battery temperature prediction period.

[0033] In this embodiment, if the vehicle operation mode during the battery temperature prediction period is a charging-then-driving mode, the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining driving time between the vehicle and the target charging station, calculated based on the physical model, are imported into the temperature prediction model three, which has been pre-trained for this mode. This model then predicts the battery temperature during the prediction period. By integrating the key influencing parameters of the charging stage and the subsequent driving stage in this mode, and leveraging the physical consistency of the parameters derived from the physical model, the temperature prediction model three can accurately capture the temperature change correlation between the accumulation of heat generated during charging and the continuation of the driving thermal state. This improves the completeness and accuracy of the battery temperature prediction in this mode, thereby providing a temperature basis covering the transition from charging to driving for subsequent pre-cooling thermal control. This ensures that the battery temperature remains within a reasonable range during charging and subsequent driving, avoiding prediction deviations caused by fragmented stage parameters or insufficient model adaptation, and guaranteeing battery performance and safety.

[0034] Furthermore, in one embodiment, the determination of the vehicle-first-charge-later mode includes: If the vehicle speed is zero and the battery output current is negative, or if the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction cycle, it is determined to be a non-drive-before-charge mode. If the vehicle is determined to be in a non-driving-before-charging mode and the remaining driving time between the vehicle and the target charging station is less than or equal to the battery temperature prediction period, then the vehicle operation mode within the battery temperature prediction period is determined to be a driving-before-charging mode.

[0035] In this embodiment, if the vehicle speed is zero and the battery output current is negative, or if the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction period, the vehicle operation mode is determined to be a non-vehicle-first-charge mode. If it has been determined to be a non-vehicle-first-charge mode, and the remaining driving time between the vehicle and the target charging station is less than or equal to the battery temperature prediction period, the vehicle operation mode within the battery temperature prediction period is further determined to be a vehicle-first-charge mode. This eliminates the possibility of the vehicle entering the charging stage first, thus clarifying the operating characteristics of this mode through elimination. This provides an accurate judgment benchmark for matching the corresponding temperature prediction model, ensuring that the temperature prediction and pre-cooling thermal control for this transitional operating condition can adapt to the characteristics of the transition from driving to charging.

[0036] The differences in input value selection across the three modes are determined based on the core influencing factors of battery temperature change and the differences in operating conditions under each mode. The specific reasons are as follows: In the charge-then-drive mode, battery temperature changes are simultaneously affected by the combined effects of heat generation during charging, cooling regulation, and subsequent driving. The battery status and ambient temperature during charging directly affect the rate of heat generation during charging, the remaining charging time determines the duration of temperature accumulation during charging, and the temperature baseline before driving affects the thermal state at the beginning of driving. Therefore, it is necessary to include the current battery temperature, current battery level, ambient temperature, heat generation, cooling capacity, and remaining charging time to fully cover the temperature-related factors between charging and driving.

[0037] In driving mode only, there is no charging operation during the prediction period. The battery temperature is mainly determined by the dynamic heat generation and real-time cooling balance during continuous driving. Parameters that are not directly related to driving, such as the state of charge and ambient temperature, have a weak impact on the temperature change during this period. Therefore, only the current battery temperature, heat generation and cooling capacity are retained, focusing on the core relationship between real-time heat generation and heat dissipation during driving, and simplifying redundant parameters to improve prediction efficiency.

[0038] The "drive first, charge later" mode involves the connection between temperature accumulation during driving and the risk of temperature rise during charging. Temperature changes during driving lay the initial thermal state for subsequent charging, and the remaining driving time determines the degree of temperature accumulation during driving. Ambient temperature and battery status will simultaneously affect the heat generation characteristics of driving and charging. Therefore, it is necessary to integrate the current battery temperature, current battery level, ambient temperature, heat generation, cooling capacity, and remaining driving time to cover the continuity of temperature influencing factors in each stage of the transition from driving to charging, and ensure that the prediction can reflect the temperature change pattern between stages.

[0039] Furthermore, in one embodiment, after S100, the following steps are included: S200: If the battery temperature prediction value output by the temperature prediction model in any vehicle operation mode reaches the preset threshold temperature within the battery temperature prediction cycle, the minimum cooling power to prevent the battery from overheating within the battery temperature prediction cycle is calculated, and the water pump speed, fan speed and compressor power of the liquid cooling system are adjusted according to the minimum cooling power.

[0040] In this embodiment, if the battery temperature prediction value output by the temperature prediction model in any vehicle operation mode reaches the preset threshold temperature within the battery temperature prediction cycle, the minimum cooling power that can ensure the battery does not exceed the threshold temperature within the prediction cycle is calculated, and the water pump speed, fan speed and compressor power of the liquid cooling system are adjusted according to the minimum cooling power. By precisely matching the power adjustment of cooling demand, the battery temperature is kept within a safe range while avoiding energy redundancy caused by excessive cooling, thus achieving a balance between temperature control effect and energy consumption cost.

[0041] In summary, the battery pre-cooling thermal management control method provided in the embodiments of this application is described in full as follows: I. Data Collection Phase The vehicle's current speed (V), ambient temperature (Tamb), and total battery output / charging current (I) can be obtained from the vehicle's CAN bus. all The system contains numerous pieces of information, including the battery's SOC, temperature information Tbat at each battery sampling point, battery inlet water temperature Tin and outlet water temperature Tout, battery water pump speed N, and location information S (distance S from the target location or charging station), all of which are related to the current time point t. Because these related information themselves affect battery cooling and temperature rise, indirectly influencing the battery's average temperature, some of this information can be directly used as feature values ​​for the LSTM prediction model.

[0042] II. Data Processing Stage Based on data processing, a portion of the collected data can be directly used as feature values ​​for subsequent models. Furthermore, the above information can be used to calculate virtual factors affecting battery temperature rise using a physical model. These virtual values ​​can then be used as feature values ​​for the LSTM prediction model. By adding these virtual values ​​strongly correlated with battery temperature rise, it's equivalent to adding physical constraints to the LSTM model, thus improving prediction accuracy and robustness. These virtual feature values ​​can be determined through the physical model.

[0043] For battery heat generation, a simplified Bernardi battery heat generation model can be used for estimation. For the entire battery system, heat generation mainly depends on Joule heating, with reaction heat accounting for a smaller proportion. This latter model, simplified to improve calculation speed, is discarded.

[0044] Where Ii is the current of a single cell, which can be calculated by combining the data Iall with the number of cells. Ri is the internal resistance of a single cell, which is mainly related to the cell temperature when the SOC is greater than a certain value. The curve of R changing with TI can be obtained through experimental testing to determine it.

[0045] Meanwhile, the actual cooling power of the current coolant can be calculated in the following ways.

[0046] Where c is the specific heat capacity of the coolant; ρ is the density of the coolant; Q is the coolant flow rate, which can be calculated by combining the current battery water pump speed and the battery outlet water temperature Tout; Tout is the battery inlet water temperature. The current battery temperature rise rate can be deduced from the above information;

[0047] Where Cbat is the specific heat capacity of the battery, and m is the mass of the battery; For the entire vehicle, the highest battery temperature typically occurs under high-temperature conditions, such as after prolonged driving to a low SOC and the initiation of fast charging. To predict the temperature throughout the entire battery charging process, it is necessary to predict the battery temperature and SOC at the start of charging.

[0048] Battery starting charging temperature The calculation can be simplified to the following formula:

[0049] Where t is the total vehicle travel time, which can be estimated based on the distance S to the target charging station and the current vehicle speed V.

[0050] The SOC (State of Charge) at the start of charging is calculated based on the current power consumption and the distance to the target charging station.

[0051] in Let t represent the total capacity of the battery system, and t be the time from the current moment to the start of charging. During the charging process, to determine whether the battery overheats during the entire charging process, the maximum cooling capacity is used. To calculate the cooling effect during the process, the maximum cooling capacity Related to ambient temperature Tamb, it can be calculated in advance and entered into a table; During the charging process, the charging rate is determined by the maximum power of the charging pile, the SOC, and the cell temperature. The above information can be calculated in advance and entered into a table. It is usually built into the BMS charging strategy. The charging current at the corresponding moment can be obtained through the above information. The temperature rise during battery charging is as follows:

[0052] The above method can roughly predict the average battery temperature of the next node. However, in reality, the battery temperature rise is affected by many factors, and some factors with minor influences are omitted in the formula. This leads to certain errors in the actual calculation, which increase with each iteration, affecting the accuracy of predictions over longer periods. To improve the overall prediction accuracy, LSTM combined with the physical model can be used for correction and calibration. The specific combination method can be achieved by concatenating a physical model with an LSTM model. Simultaneously, the collected data used in the physical model is pre-processed and used as input feature values. Taking the physical model above as an example, the seven feature values ​​in Table 1 below can be initially utilized. In practical applications, a more accurate physical model can be referenced, and more relevant elements can be selected as feature values. For this model, the virtual data obtained from the physical model can be synchronously added to the feature values, forcing the model to focus on the core parameters related to the principle and guiding the model to learn in a direction that conforms to physical laws.

[0053]

[0054] Table 1 In practical applications, due to limited temperature accuracy and the inherent delay in heat transfer, we predict the average battery temperature over 60 minutes, using a 1-minute time step. For the calculation frequency of this model, as mentioned above, due to the lag in temperature readings, we tentatively set it to once per 1-minute step; each calculation covers data for 1 hour (one cycle), totaling 60 steps.

[0055] For the example vehicle model, the charging time at normal temperature is less than 60 minutes. Therefore, the following three modes should be considered for the next 60 minutes: A. Charge first, then drive; B. Drive only; C. Drive first, then charge. (Since this temperature prediction mainly considers that the temperature will not rise within the next 60 minutes and does not consider the parking state, the specific modes can be extended according to the actual situation.)

[0056] The specific driving mode is determined based on the current vehicle speed and current. If the vehicle speed is 0 and the current output is negative, mode A is selected; otherwise, mode B or C is selected. If the initial processing time (ts) is greater than 60 minutes, mode B is selected; otherwise, mode C is selected. Alternatively, the driver can manually select and confirm the next driving mode.

[0057] For Mode A, the temperature prediction after 60 minutes can be divided into the following three parts:

[0058] The first part is the initial temperature of the battery; the second part is the temperature rise during charging, which is related to the current heat generation, cooling, and predicted charging time; the third part is the temperature rise during driving, where the output current is based on the most severe ramp conditions, the heat generation power is considered a constant, and the cooling power is based on maximum performance, which is related to the ambient temperature. Factors strongly correlated with the final predicted temperature include Xt1, Xt2, Xt3, Xt4, Xt5, and Xt7.

[0059] For Mode B, the temperature prediction after 60 minutes can be divided into the following three parts:

[0060] The first part is the initial temperature of the battery; the second part is the temperature rise during driving, which is related to current heat generation and cooling; factors strongly correlated with the final predicted temperature include Xt1, Xt4, and Xt5.

[0061] For Mode C, the temperature prediction after 60 minutes can be divided into the following three parts:

[0062] The first part is the initial temperature of the battery; the second part is the temperature rise during driving, which is related to the current heat generation, cooling, and predicted driving time; the third part is the temperature rise during charging, where the output current is based on the battery charging strategy, and the corresponding heat generation power is considered a constant; the cooling power is based on maximum performance and is related to the ambient temperature. Factors strongly correlated with the final predicted temperature include Xt1, Xt2, Xt3, Xt4, Xt5, and Xt6.

[0063] For different models, training is required using existing data. The aforementioned feature values ​​and the required average battery temperature can be obtained from vehicle data. Training can be performed by processing this information; setting an appropriate learning rate and number of iterations forces the model to focus on core parameters related to the underlying principles, guiding it to learn in a direction consistent with physical laws, ensuring that the final predicted value deviates from the actual value within an acceptable range. By combining these methods, the accuracy of the entire battery temperature prediction model can be continuously improved, enhancing the precision of the pre-cooling control method. The main steps are as follows: Figure 2 As shown.

[0064] The above method can predict the battery temperature within the next 60 minutes. Since there is a real value as a reference, a deviation range can be set. When the deviation is too large, the number of iterations, learning rate, hidden layer units, etc. can be changed until the model deviation reaches the set value range.

[0065] IV. Pre-cooling decision-making stage When it is determined that the battery temperature may reach the threshold temperature Ttreshold in the future and pre-cooling needs to be triggered, the minimum cooling power required to prevent the battery from overheating within the battery temperature prediction cycle is calculated in reverse. Based on the calculated minimum cooling power Qmin, the current cooling power is adjusted in reverse by controlling the execution module, adjusting the water pump speed, fan speed, compressor speed, and valve opening (usually to increase the current cooling power) in order to ensure that the battery temperature does not overheat in the future cycle.

[0066] IV. Feedback and Optimization Phase In practice, to improve the overall prediction accuracy of the model, it is necessary to continuously update the model with real data after the initial learning phase. This can be achieved by periodically adding newly collected data to the training set and updating the LSTM model parameters through transfer learning. Simultaneously, when the prediction error repeatedly exceeds a threshold, a data cleaning process is triggered to remove noisy data caused by sensor anomalies or sudden changes in operating conditions, thereby improving the model's generalization ability under complex operating conditions.

[0067] Secondly, this application also provides a battery pre-cooling thermal management control device. The battery pre-cooling thermal management control method includes: a battery temperature prediction module, which selects a corresponding pre-trained temperature prediction model based on the vehicle operation mode within the battery temperature prediction period, and predicts the battery temperature within the battery temperature prediction period.

[0068] The functions of each module in the battery pre-cooling thermal management control device correspond to the steps in the battery pre-cooling thermal management control method embodiment, and their functions and implementation processes will not be described in detail here.

[0069] Thirdly, embodiments of this application provide a battery pre-cooling thermal management control device, which can be a personal computer (PC), laptop computer, server, or other device with data processing capabilities.

[0070] Reference Figure 3 , Figure 3 This is a schematic diagram of the hardware structure of the battery pre-cooling thermal management control device involved in the embodiments of this application. In the embodiments of this application, the battery pre-cooling thermal management control device may include a processor, a memory, a communication interface, and a communication bus.

[0071] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0072] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting devices within the battery pre-cooling thermal management control device, as well as interfaces used for interconnecting the battery pre-cooling thermal management control device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0073] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0074] The processor can be a general-purpose processor, which can call the battery pre-cooling thermal management control program stored in the memory and execute the battery pre-cooling thermal management control method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the battery pre-cooling thermal management control program is called can be referred to in the various embodiments of the battery pre-cooling thermal management control method of this application, and will not be repeated here.

[0075] Those skilled in the art will understand that Figure 3 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0076] Fourthly, embodiments of this application also provide a readable storage medium.

[0077] The present application has a readable storage medium storing a battery pre-cooling thermal management control program, wherein when the battery pre-cooling thermal management control program is executed by a processor, it implements the steps of the battery pre-cooling thermal management control method as described above.

[0078] The method implemented when the battery pre-cooling thermal management control program is executed can be referred to in various embodiments of the battery pre-cooling thermal management control method of this application, and will not be repeated here.

[0079] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0080] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0081] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0082] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0083] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0085] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A battery pre-cooling thermal management control method, characterized in that, The battery pre-cooling thermal management control method includes: Based on the vehicle's operating mode during the battery temperature prediction period, a corresponding pre-trained temperature prediction model is selected to predict the battery temperature during the prediction period.

2. The battery pre-cooling thermal management control method as described in claim 1, characterized in that, The method based on the vehicle's operating mode within the battery temperature prediction period selects a pre-trained temperature prediction model to predict the battery temperature within the prediction period, including: If the vehicle's operating mode during the battery temperature prediction period is a charging-then-driving mode, then the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining charging time obtained based on the physical model are imported into the pre-trained temperature prediction model to predict the battery temperature during the battery temperature prediction period.

3. The battery pre-cooling thermal management control method as described in claim 2, characterized in that, Before selecting the corresponding pre-trained temperature prediction model to predict the battery temperature within the battery temperature prediction period based on the vehicle's operating mode during the battery temperature prediction cycle, the method further includes: The battery temperature prediction value is calculated based on the battery temperature rise during charging, the battery temperature rise during driving, and the initial battery temperature obtained from the physical model. This predicted battery temperature value is used as the output value of the training set of temperature prediction model one.

4. The battery pre-cooling thermal management control method as described in claim 2, characterized in that, The determination of the "charge first, then drive" mode includes: If the vehicle speed is zero and the battery output current is negative, it is determined to be in charge-then-drive mode.

5. The battery pre-cooling thermal management control method as described in claim 1, characterized in that, The method based on the vehicle's operating mode within the battery temperature prediction period selects a pre-trained temperature prediction model to predict the battery temperature within the prediction period, including: If the vehicle's operating mode during the battery temperature prediction period is driving mode only, the current battery temperature and the battery heat generation and cooling capacity obtained based on the physical model are imported into the pre-trained temperature prediction model 2 to predict the battery temperature during the battery temperature prediction period.

6. The battery pre-cooling thermal management control method as described in claim 5, characterized in that, The determination of the driving-only mode includes: If the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction period, it is determined to be in driving mode only.

7. The battery pre-cooling thermal management control method as described in claim 1, characterized in that, The method based on the vehicle's operating mode within the battery temperature prediction period selects a pre-trained temperature prediction model to predict the battery temperature within the prediction period, including: If the vehicle's operating mode during the battery temperature prediction period is a charging-then-driving mode, then the current battery temperature, current battery charge, ambient temperature, and the battery heat generation, battery cooling capacity, and remaining driving time between the vehicle and the target charging station, calculated based on the physical model, are imported into the pre-trained temperature prediction model 3 to predict the battery temperature during the battery temperature prediction period.

8. The battery pre-cooling thermal management control method as described in claim 7, characterized in that, The determination of the vehicle-first-charge mode includes: If the vehicle speed is zero and the battery output current is negative, or if the remaining driving time between the vehicle and the target charging station is greater than the battery temperature prediction cycle, it is determined to be a non-drive-before-charge mode. If the vehicle is determined to be in a non-driving-before-charging mode and the remaining driving time between the vehicle and the target charging station is less than or equal to the battery temperature prediction period, then the vehicle operation mode within the battery temperature prediction period is determined to be a driving-before-charging mode.

9. A battery pre-cooling thermal management control device, characterized in that, The battery precooling thermal management control device includes a processor, a memory, and a battery precooling thermal management control program stored in the memory and executable by the processor, wherein when the battery precooling thermal management control program is executed by the processor, it implements the steps of the battery precooling thermal management control method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a battery pre-cooling thermal management control program, wherein when the battery pre-cooling thermal management control program is executed by a processor, it implements the steps of the battery pre-cooling thermal management control method as described in any one of claims 1 to 8.

Images