Battery thermal management method and system and computer readable storage medium

Abstract

The invention discloses a battery thermal management method and system and a computer readable storage medium, which are applied to the technical field of thermal management, and the method comprises the following steps: obtaining battery pack operation data, the battery pack operation data comprising battery cell temperature information and battery pack heat dissipation information; storing the operation data of the battery pack to form historical data; presetting a temperature prediction model based on a preset machine learning algorithm and historical data; generating a current temperature curve based on the battery pack operation data and the temperature prediction model; and if it is determined that the battery pack has a thermal runaway trend based on the current temperature curve, controlling the thermal management controller to perform temperature control. The temperature of the battery cell is monitored through the operation data of the battery cell of the battery pack, the temperature curve is generated according to the temperature prediction model, the thermal runaway trend is performed according to the temperature curve, the thermal management controller can be actively controlled to perform temperature control when the temperature of the battery is abnormal or before the thermal runaway trend occurs, and the thermal management accuracy of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of thermal management technology, and in particular to a battery thermal management method, system, and computer-readable storage medium. Background Art

[0002] Battery thermal management plays a crucial role in electric and hybrid vehicles. The performance, lifespan, and safety of lithium-ion batteries are highly dependent on the stability of their operating temperature. Operating the battery at high temperatures can easily lead to electrolyte decomposition, battery expansion, and even thermal runaway, potentially causing safety incidents. In low-temperature environments, the battery's electrochemical reaction efficiency decreases, significantly reducing battery life and charging efficiency. Therefore, thermal management not only improves the battery's energy efficiency and charge-discharge performance in various environments, but also extends battery life and ensures vehicle safety. It is a key technology for achieving high reliability and performance in electric vehicles.

[0003] Existing battery management methods typically use a single thermistor to collect temperature data from a group of several battery cells and transmit it to the battery management system. The battery management system collects and monitors temperature data, and when it detects abnormally high temperatures, it controls the fan or water pump to run at high speed to achieve cooling. Alternatively, the battery management system uses the cloud to predict historical temperature data. While this method can achieve effective thermal management, the temperature data needs to be transmitted to the local vehicle for control after being predicted in the cloud. This data transmission can lead to poor thermal management accuracy due to the long distance between locations. Summary of the Invention

[0004] The present invention provides a battery thermal management method, system and computer-readable storage medium to improve the accuracy of vehicle thermal management.

[0005] In order to solve the above technical problems, the present invention provides a battery thermal management method, comprising:

[0006] Acquiring battery pack operating data, wherein the battery pack operating data includes battery cell temperature information and battery pack heat dissipation information;

[0007] Storing the battery pack operating data to form historical data;

[0008] Presetting a temperature prediction model based on a preset machine learning algorithm and the historical data;

[0009] Generate a current temperature curve based on the battery pack operating data and the preset temperature prediction model;

[0010] If it is determined based on the current temperature curve that the battery pack has a thermal runaway trend, the thermal management controller is controlled to perform temperature control.

[0011] The present invention monitors the temperature of battery cells using battery pack cell operating data, locally storing the battery pack operating data and forming historical data. A temperature prediction model is then pre-set based on the local historical data, generating a temperature curve based on the temperature prediction model. Thermal runaway trends are then analyzed based on the temperature curve. This allows the thermal management controller to proactively control the temperature when abnormal battery temperatures occur or before thermal runaway trends occur. Locally storing battery heat dissipation data and cell temperature data allows for local data access, avoiding delays associated with cloud-based data transmission and prediction. Furthermore, the accuracy of temperature predictions is improved through the use of a pre-set machine learning algorithm and the pre-set temperature prediction model based on historical data, thereby enhancing the accuracy of vehicle thermal management.

[0012] Furthermore, the cell temperature information includes a cell temperature value; and after obtaining the battery pack operation data, the method further includes:

[0013] When the battery core temperature value has a temperature abnormality, the thermal management controller is controlled to perform temperature control.

[0014] The present invention immediately performs temperature control when an abnormality occurs in the battery core temperature value, thereby making vehicle thermal management more timely, improving dual-path thermal management for the vehicle, and further improving the accuracy of vehicle thermal management.

[0015] Furthermore, the battery cell temperature information also includes the battery cell voltage value, the battery cell current value and the battery cell internal resistance value; the battery pack heat dissipation information includes the battery pack water outlet temperature value and the battery pack water inlet temperature value; the preset temperature prediction model based on the preset machine learning algorithm and the historical data includes:

[0016] Build an initial temperature rise prediction model and an initial heat dissipation prediction model based on a preset machine learning algorithm;

[0017] The initial temperature rise prediction model is trained based on the battery cell temperature value, the battery cell voltage value, the battery cell current value, and the battery cell internal resistance value to obtain a temperature rise prediction model;

[0018] Training the initial heat dissipation prediction model based on the battery core temperature value, the battery pack water outlet temperature value, and the battery pack water inlet temperature value to obtain a heat dissipation prediction model;

[0019] The temperature prediction model is constructed based on the temperature rise prediction model and the heat dissipation prediction model.

[0020] The present invention integrates the cell temperature, voltage, current, internal resistance and battery pack inlet and outlet temperature information to train temperature rise prediction models and heat dissipation prediction models. It uses multi-dimensional data to more comprehensively simulate the thermal behavior of the battery system, enhance the model's predictive capability, help identify potential thermal runaway risks in advance, and achieve accurate feedforward thermal management.

[0021] Furthermore, generating a current temperature curve based on the battery cell temperature data and a preset temperature prediction model includes:

[0022] Based on the battery cell temperature information and the temperature rise prediction model of the preset temperature prediction model, generating a temperature rise curve within a preset time period;

[0023] Based on the battery heat dissipation information and the preset temperature prediction model, the heat dissipation prediction model generates a temperature heat dissipation curve within a preset time period;

[0024] The temperature rise curve and the temperature heat dissipation curve are used as the current temperature curve.

[0025] The present invention constructs a temperature rise curve and a temperature heat dissipation curve respectively, so that the temperature rise curve and the temperature heat dissipation curve predict the temperature rise trend and temperature heat dissipation of the battery within a preset time period, thereby realizing thermal runaway risk judgment.

[0026] Furthermore, if it is determined based on the current temperature curve that the battery has a thermal runaway trend, then controlling the thermal management controller to perform temperature control includes:

[0027] Obtaining a total heat dissipation value based on the temperature heat dissipation curve, and obtaining a total temperature rise value based on the temperature rise curve;

[0028] The accumulated heat is obtained based on the total temperature rise value and the total heat dissipation value. When the accumulated heat is greater than a preset heat threshold, it is determined that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control.

[0029] The present invention determines the total heat dissipation value within a preset time period through a temperature heat dissipation curve, and determines the total temperature rise value through a temperature rise curve, thereby obtaining the cumulative heat within the time period. Since the cumulative heat indicates the total heat rise value of the battery within the time period, when the total heat value exceeds a preset heat threshold, it is considered that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control to avoid thermal runaway accidents.

[0030] Furthermore, the determining that the battery cell temperature data has a temperature anomaly, and then controlling the thermal management controller to perform temperature control, includes:

[0031] When the cell temperature value of any cell in the current cell temperature information is greater than a preset temperature threshold, it is determined that the battery has a temperature abnormality, and the thermal management controller is controlled to perform temperature control.

[0032] The present invention monitors the temperature of each battery cell by setting a temperature threshold. When an abnormality is detected, the temperature is immediately controlled to avoid the risk of thermal runaway caused by battery overheating.

[0033] Furthermore, controlling the thermal management controller to perform temperature control includes:

[0034] Generate water pump control signal and compressor control signal;

[0035] controlling the thermal management controller to turn on the water pump fan based on the water pump control signal;

[0036] The thermal management controller is controlled to adjust the cooling speed of the compressor based on the compressor control signal.

[0037] The present invention generates a water pump control signal and a compressor control signal respectively, thereby controlling the thermal management controller to regulate the water pump fan and the compressor, thereby realizing the coordinated adjustment of the water cooling and air cooling mechanisms, and effectively improving the energy efficiency ratio and dynamic response performance of the thermal management control.

[0038] Furthermore, it also includes:

[0039] A temperature sensor is provided at each battery cell in the battery pack, and the temperature information of the battery cell is obtained based on the temperature sensor.

[0040] The present invention installs a temperature sensor at each battery cell and collects the temperature data of any battery cell instead of the average temperature of a single group to monitor the temperature of each battery cell in real time, thereby realizing refined battery cell temperature monitoring in the battery pack, improving the resolution and accuracy of temperature monitoring, enabling thermal management control to more accurately perceive local overheating risks, realizing finer-grained thermal management control, and avoiding safety hazards caused by insufficient temperature sampling coverage.

[0041] In a second aspect, the present invention provides a vehicle thermal management system, characterized in that it includes: an acquisition board, a vehicle domain controller and a thermal management controller;

[0042] The acquisition board is used to obtain battery pack operation data, wherein the battery pack operation data includes battery cell temperature information and battery pack heat dissipation information;

[0043] The vehicle domain controller is used to store the battery pack operating data to form historical data; preset a temperature prediction model based on a preset machine learning algorithm and the historical data; generate a current temperature curve based on the battery pack operating data and the preset temperature prediction model; and control the thermal management controller to perform temperature control if it is determined based on the current temperature curve that the battery pack has a thermal runaway trend.

[0044] In a third aspect, the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the battery thermal management method. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic flow chart of a battery thermal management method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of vehicle battery pack temperature collection provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the architecture of a vehicle domain controller provided by an embodiment of the present invention;

[0048] Figure 4 A functional distribution architecture diagram of a battery thermal management method provided by an embodiment of the present invention;

[0049] Figure 5 A schematic diagram of a thermal runaway judgment influencing factor for battery thermal management provided by an embodiment of the present invention;

[0050] Figure 6 A flow chart for constructing a temperature rise prediction model provided by an embodiment of the present invention;

[0051] Figure 7 A flowchart for constructing a heat dissipation prediction model provided by an embodiment of the present invention;

[0052] Figure 8 Another flowchart of a battery thermal management method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0054] The terms "first," "second," and the like in the specification, claims, and drawings of this application are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0055] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] Example 1

[0057] See also Figure 1 , Figure 1 A schematic flow chart of a battery thermal management method provided by an embodiment of the present invention. The embodiment of the present invention provides a battery thermal management method, including steps 101 to 105, as follows:

[0058] Step 101: Obtain battery pack operating data, where the battery pack operating data includes cell temperature information and battery pack heat dissipation information;

[0059] Please refer to Figure 2 , Figure 2 A schematic diagram of vehicle battery pack temperature collection provided by an embodiment of the present invention.

[0060] In this embodiment, the entire vehicle architecture includes a PACK power battery pack, a vehicle domain controller, and a thermal management controller. The vehicle domain controller is connected to the PACK power battery pack and the thermal management controller, respectively. The PACK power battery pack includes several parallel-connected battery modules, each of which contains several series-connected battery cells. The PACK power battery pack also includes a data acquisition board for collecting battery cell temperature data.

[0061] Please refer to Figure 3 , Figure 3 A schematic diagram of the architecture of a vehicle domain controller provided by an embodiment of the present invention.

[0062] In this embodiment, a distributed, high-performance vehicle domain controller (VDC) architecture is adopted. The vehicle domain controller uses the NXP S32G series SoC, which includes multiple high-performance cores and high-security cores, with sufficient computing power and high-level functional safety features. The VDC is equipped with more than 4GB of DDR and 16GB of Flash, as well as EMMC storage, which are used to store runtime variables and historical thermal management data, respectively, to support the training and online prediction of localized machine learning models. The Flash module is used to store VDC application software. During the power-on process, the VDC application software in the flash is loaded into the DDR for execution. The DDR is used to store temporary variables, application programs, etc. generated during product operation to ensure the normal operation of the product. The EMMC is used to store historical and current thermal management data, and the stored historical data is used for predictive judgment of thermal management. The use of more than 4GB of DDR and 16GB of FLASH ensures large-capacity storage. It also has multi-channel communication, including Ethernet, CAN, LIN and other communications, to ensure efficient and high-speed communication with the entire vehicle.

[0063] In this embodiment, it also includes:

[0064] A temperature sensor is provided at each cell in the battery pack to obtain the cell temperature information based on the temperature sensor.

[0065] In this embodiment, a temperature sensor is installed in each battery cell to monitor the temperature of each battery cell in real time. The temperature of each battery cell is collected by a data acquisition board in the battery pack and the collected temperature data is sent to the vehicle domain controller via CAN.

[0066] In this embodiment, a temperature sensor is installed at each battery cell. The temperature data of any battery cell is collected instead of the average temperature of a single group to monitor the temperature of each battery cell in real time, thereby realizing refined battery cell temperature monitoring in the battery pack. The resolution and accuracy of temperature monitoring are improved, so that thermal management control can more accurately perceive the risk of local overheating, realize finer-grained thermal management control, and avoid safety hazards caused by insufficient temperature sampling coverage.

[0067] Please refer to Figure 4 , Figure 4 A functional distribution architecture diagram of a battery thermal management method provided by an embodiment of the present invention.

[0068] In this embodiment, the acquisition board periodically or on demand reads data from each battery cell temperature sensor, water outlet and water inlet temperature sensors, and battery cell voltage, current and internal resistance measuring devices; and sends battery pack heat dissipation information such as battery cell temperature value, voltage value, current value, internal resistance value, and water inlet and outlet water temperature value to the vehicle domain controller through the CAN bus.

[0069] In this embodiment, a three-level modular architecture of "acquisition board - vehicle domain controller (VDC) - thermal management controller" is adopted, and efficient and reliable data and control instruction interaction is achieved through the CAN bus. The acquisition board arranges a thermistor voltage divider circuit at each battery cell and the onboard MCU (such as STM32 series) periodically samples the temperature, voltage, current, internal resistance and other parameters of the single battery cell through multiple ADCs, and then encapsulates the data into CAN messages and uploads them to the vehicle domain controller; VDC is based on high-performance SoC (such as NXPS32G) to deframe and read the multi-feature operation data uploaded by the acquisition board in real time, not only performing temperature threshold alarms and high and low temperature processing,

[0070] In this embodiment, a machine learning model stored in locally stored high-capacity DDR / Flash / eMMC memory is used to perform online predictions of temperature rise and heat dissipation under current operating conditions. The accumulated heat, the difference between the total temperature rise and the total heat dissipation, is calculated to determine thermal runaway trends. When the accumulated heat exceeds a preset threshold or a temperature anomaly occurs in any battery cell, the VDC generates control signals for the water pump speed and compressor cooling rate, which are transmitted via CAN to the thermal management controller. Upon receiving these signals, the thermal management controller drives actuators such as the water pump, fan, solenoid valve, and compressor, providing real-time feedback on the execution status, forming a closed-loop temperature regulation system. This distributed thermal management solution combines precise cell-level monitoring, localized online prediction, and rapid closed-loop control, significantly improving the safety and performance stability of electric / hybrid vehicle power battery packs under multiple operating conditions.

[0071] In this embodiment, the cell temperature information includes the cell temperature value; after obtaining the battery pack operation data, it also includes:

[0072] When the battery cell temperature value is abnormal, the thermal management controller is controlled to perform temperature control.

[0073] In this embodiment, by immediately performing temperature control when there is an abnormality in the battery cell temperature value, the vehicle thermal management is made more timely, and dual-path thermal management is improved for the vehicle, further improving the accuracy of the vehicle thermal management.

[0074] Step 102: Storing the battery pack operating data to form historical data;

[0075] In this embodiment, the VDC stores the collected operating data in the EMMC in time series to form a rich historical database for subsequent machine learning model updates and online predictions.

[0076] In this embodiment, the battery pack operation data is stored locally and formed into historical data, and then a temperature prediction model is preset based on the local historical data. By locally storing the battery heat dissipation data and battery cell temperature data, local data call is realized to avoid the delay problem caused by cloud data transmission and cloud prediction.

[0077] Step 103: Preset a temperature prediction model based on a preset machine learning algorithm and historical data;

[0078] Please refer to Figure 5 , Figure 5 A schematic diagram of thermal runaway judgment influencing factors for battery thermal management provided by an embodiment of the present invention.

[0079] In this embodiment, the judgment of battery thermal runaway is driven by two major prediction sub-models: a temperature rise prediction model and a heat dissipation prediction model. The temperature rise prediction model uses the current battery cell temperature as the initial input and combines real-time current, voltage, and internal resistance information to calculate the heat generation rate per unit time; the heat dissipation prediction model uses the inlet and outlet temperature difference and the coolant flow rate (determined by the water pump speed) as the main parameters to evaluate the cooling system's heat dissipation capacity within the same time window. The system compares the temperature rise curve output by the temperature rise prediction model with the heat dissipation curve output by the heat dissipation prediction model, and calculates the integral difference between the two curves - the accumulated net heat; when this value exceeds the preset safety threshold, it is determined that the battery pack is at risk of thermal runaway, and the corresponding cooling or alarm control strategy is triggered.

[0080] In this embodiment, the battery cell temperature information also includes the battery cell voltage value, the battery cell current value, and the battery cell internal resistance value; the battery pack heat dissipation information includes the battery pack water outlet temperature value and the battery pack water inlet temperature value; based on the preset machine learning algorithm and historical data, a preset temperature prediction model is provided, including:

[0081] Build an initial temperature rise prediction model and an initial heat dissipation prediction model based on a preset machine learning algorithm;

[0082] The initial temperature rise prediction model is trained based on the battery cell temperature value, the battery cell voltage value, the battery cell current value and the battery cell internal resistance value to obtain the temperature rise prediction model;

[0083] The initial heat dissipation prediction model is trained based on the battery cell temperature value, the battery pack water outlet temperature value, and the battery pack water inlet temperature value to obtain a heat dissipation prediction model;

[0084] A temperature prediction model is constructed based on the temperature rise prediction model and the heat dissipation prediction model.

[0085] In this embodiment, the temperature prediction model includes a temperature rise prediction model and a heat dissipation prediction model.

[0086] In this embodiment, the pre-collected calibration test data and the offline training platform are used to construct the initial temperature rise prediction model and the initial heat dissipation prediction model using regression or deep learning algorithms.

[0087] Please refer to Figure 6 , Figure 6 A flow chart for constructing a temperature rise prediction model provided by an embodiment of the present invention.

[0088] In this embodiment, the core parameters of the battery cell operation are first collected synchronously, including the battery cell temperature (thermal quantity), voltage (electrical quantity), current and resistance (circuit characteristic quantity); then, based on Ohm's law and Joule's heat formula, the theoretical heat generation (Q = I 2 RT) to establish a dynamic equation for cell heat generation. The measured cell temperature and voltage data were then correlated with the theoretical heat generation in multiple dimensions. Through experimental calibration, a dynamic response curve (actual cell temperature versus estimated heat generation) was generated, revealing the mapping relationship between temperature changes and electrothermal parameters. Finally, through data fitting and model optimization, the correlation curve was converted into a predictive single cell temperature rise model, providing a quantitative basis for the design and safety assessment of battery thermal management systems.

[0089] In this embodiment, during the temperature rise prediction model training process, by inputting sample data such as battery cell temperature value, battery cell voltage value, battery cell current value and battery cell internal resistance value, the initial temperature rise prediction model is fine-tuned locally in the VDC or in the cloud to obtain the final temperature rise prediction model.

[0090] Please refer to Figure 7 , Figure 7 A flowchart for constructing a heat dissipation prediction model provided by an embodiment of the present invention.

[0091] In this embodiment, the core parameters of the battery cell operation are first collected synchronously, including the battery cell temperature (thermal quantity), voltage (electrical quantity), current and resistance (circuit characteristic quantity); then, based on Ohm's law and Joule's heat formula, the theoretical heat generation (Q = I 2 RT) to establish a dynamic equation for cell heat generation. Subsequently, a multi-dimensional correlation between measured cell temperature and voltage data and theoretical heat generation was performed. Through experimental calibration, a dynamic response curve (actual cell temperature versus estimated heat generation) was generated, revealing the mapping relationship between temperature changes and electrothermal parameters. Finally, through data fitting and model optimization, the correlation curve was converted into a temperature rise prediction model with predictive capabilities, providing a quantitative basis for the design and safety assessment of battery thermal management systems.

[0092] In this embodiment, four basic parameters, namely, battery cell temperature, water outlet temperature, water inlet temperature and water pump drive speed, are collected to form the original data set of the thermodynamic system. Subsequently, the heat exchange efficiency of the cooling circuit (the temperature difference ΔT before and after) is determined by the difference between the inlet and outlet temperatures, and the water flow rate per unit time is derived in combination with the water pump drive speed to quantify the dynamic transmission characteristics of the cooling medium. Modeling is then carried out using a hyperbola: on the one hand, a relationship curve between the water pump speed and the coolant temperature change (speed-temperature relationship curve) is established to reveal the influence of power regulation on thermal balance; on the other hand, a composite curve of battery cell temperature, speed and temperature parameters is integrated (single battery cell temperature, speed and temperature curve) to analyze the thermal response mechanism of individual battery cells under variable working conditions. Finally, through multi-source data fusion and curve parameter optimization, the correlation analysis results are integrated into a single battery cell heat dissipation model with predictive capabilities, realizing a closed-loop deduction from real-time parameter monitoring to future thermal state evolution, providing a quantitative decision-making basis for precise temperature control strategies.

[0093] In this embodiment, during the heat dissipation prediction model training process, the initial heat dissipation prediction model is updated online by inputting the battery cell temperature value, water outlet temperature, water inlet temperature, and current water pump speed and water channel aperture information to obtain the final heat dissipation prediction model.

[0094] In this embodiment, the cell temperature, voltage, current, internal resistance and battery pack inlet and outlet temperature information are integrated to train the temperature rise prediction model and the heat dissipation prediction model. The thermal behavior of the battery system is simulated more comprehensively through multi-dimensional data, and the prediction capability of the model is enhanced. This helps to identify potential thermal runaway risks in advance and achieve accurate feedforward thermal management.

[0095] Step 104: Generate a current temperature curve based on the battery pack operating data and the temperature prediction model;

[0096] In this embodiment, based on the battery cell temperature data and the preset temperature prediction model, a current temperature curve is generated, including:

[0097] Generate a temperature rise curve within a preset time period based on the battery cell temperature information and a preset temperature prediction model;

[0098] Generate a temperature heat dissipation curve within a preset time period based on battery heat dissipation information and a preset temperature prediction model;

[0099] The temperature rise curve and the temperature heat dissipation curve are used as the current temperature curve.

[0100] In this embodiment, based on the real-time collected battery cell temperature information, the temperature rise prediction model is called to output the temperature rise curve within the preset time period; based on the real-time collected heat dissipation information and water pump speed signal, the heat dissipation prediction model is called to output the temperature heat dissipation curve within the preset time period.

[0101] In this embodiment, by constructing a temperature rise curve and a temperature heat dissipation curve respectively, the temperature rise curve and the temperature heat dissipation curve predict the temperature rise trend and temperature heat dissipation of the battery within a preset time period, thereby realizing thermal runaway risk judgment.

[0102] In this embodiment, based on the current temperature curve, it is determined that the battery has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control, including:

[0103] Obtaining a total heat dissipation value based on a temperature heat dissipation curve, and obtaining a total temperature rise value based on a temperature rise curve;

[0104] The accumulated heat is obtained based on the total temperature rise value and the total heat dissipation value. When the accumulated heat is greater than the preset heat threshold, it is determined that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control.

[0105] In this embodiment, the total temperature rise is calculated by calculating the integral value of the temperature rise curve, and the total heat dissipation is calculated by calculating the integral value of the temperature heat dissipation curve, thereby obtaining the cumulative heat, which is calculated as follows: cumulative heat = total temperature rise - total heat dissipation.

[0106] In this embodiment, when the accumulated heat is greater than a preset heat threshold, it is determined that the battery pack has a thermal runaway tendency.

[0107] In this embodiment, the total heat dissipation value within a preset time period is determined by the temperature heat dissipation curve, and the total temperature rise value is determined by the temperature rise curve, so as to obtain the cumulative heat within the time period. Since the cumulative heat indicates the total heat rise value of the battery within the time period, when the total heat value exceeds the preset heat threshold, it is considered that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control to avoid thermal runaway accidents.

[0108] Step 105: Determine based on the current temperature curve that the battery pack has a thermal runaway trend, and then control the thermal management controller to perform temperature control.

[0109] In this embodiment, if it is determined that the battery cell temperature data has a temperature anomaly, the thermal management controller is controlled to perform temperature control, including:

[0110] When the cell temperature value of any cell in the current cell temperature information is greater than a preset temperature threshold, it is determined that the battery has a temperature abnormality, and the thermal management controller is controlled to perform temperature control.

[0111] In this embodiment, when a temperature anomaly is detected or a thermal runaway trend is predicted, the VDC adjusts the thermal management controller according to the following control signal, first generating a control signal and then performing a cooling operation according to the control, thereby achieving battery thermal management.

[0112] In this embodiment, the temperature of each battery cell is monitored by setting a temperature threshold. When an abnormality is detected, the temperature is immediately controlled to avoid the risk of thermal runaway caused by battery overheating.

[0113] In this embodiment, controlling the thermal management controller to perform temperature control includes:

[0114] Generate water pump control signal and compressor control signal;

[0115] controlling the thermal management controller to turn on the water pump fan based on the water pump control signal;

[0116] The thermal management controller is controlled based on the compressor control signal to adjust the cooling speed of the compressor.

[0117] In this embodiment, the required water pump speed and compressor cooling rate are calculated based on the degree of thermal runaway and operating conditions, generating water pump and compressor control signals. These signals are then transmitted to the thermal management controller via CAN. Based on these signals, the thermal management controller increases the water pump or fan speed, or adjusts the compressor cooling rate, achieving rapid cooling.

[0118] In this embodiment, the degree of thermal runaway, that is, the heat generation rate inside the battery, can be calculated by accumulating heat.

[0119] In this embodiment, a thermal balance relationship is established by combining the degree of thermal runaway with the current operating conditions (current, inlet and outlet water temperatures, ambient temperature, etc.), and the required water pump speed and compressor cooling rate are calculated based on the thermal balance relationship.

[0120] In this embodiment, by generating a water pump control signal and a compressor control signal respectively, the thermal management controller is controlled to regulate the water pump fan and the compressor, thereby realizing the coordinated adjustment of the water cooling and air cooling mechanisms, and effectively improving the energy efficiency and dynamic response performance of the thermal management control.

[0121] Please refer to Figure 8 , Figure 8 Another flowchart of a battery thermal management method provided by an embodiment of the present invention.

[0122] In this embodiment, thermal management utilizes a closed-loop management mechanism that combines data-driven and predictive control. The specific process can be divided into three phases: data acquisition, status assessment, and proactive control. After thermal management is initiated, the acquisition board first collects real-time battery temperature data and transmits it to the vehicle domain controller, synchronizing basic thermal status data with the cloud. The controller then applies threshold judgment to the received temperature data. If a temperature anomaly is detected, it immediately sends a cooling command to the thermal management controller, triggering the water pump and compressor to coordinate and accelerate cooling. If the temperature is within the normal range, the data is stored and a temperature runaway prediction algorithm is activated. This algorithm uses historical data modeling to analyze future temperature trends. During the prediction phase, the system continuously monitors thermal runaway risk parameters. If the prediction model determines that the temperature is about to exceed the safety threshold, it issues a preemptive control command to the thermal management controller, triggering the refrigeration system to proactively intervene. This dual closed-loop architecture of "real-time monitoring - immediate control" and "trend prediction - proactive control" achieves full-cycle temperature management, from abnormal response to preventive adjustments, ensuring that the battery system always operates within the optimal thermal safety range.

[0123] In this embodiment, battery cell temperature monitoring is achieved through the use of battery pack cell operating data. This data is stored locally and converted into historical data. A temperature prediction model is then pre-set based on this local historical data, generating a temperature curve based on the temperature prediction model. Thermal runaway trends are then analyzed based on the temperature curve. This allows the thermal management controller to proactively control the temperature when abnormal battery temperatures occur or before thermal runaway trends emerge. Locally storing battery heat dissipation data and cell temperature data allows for local data access, avoiding delays associated with cloud-based data transmission and prediction. Furthermore, the accuracy of temperature predictions is improved through the use of a pre-set machine learning algorithm and a pre-set temperature prediction model based on historical data, thereby enhancing the accuracy of vehicle thermal management.

[0124] The embodiment of the present invention further provides a vehicle thermal management system, comprising: an acquisition board, a vehicle domain controller, and a thermal management controller;

[0125] The acquisition board is used to obtain battery pack operating data, including cell temperature information and battery pack heat dissipation information;

[0126] The vehicle domain controller is used to store the battery pack operating data to form historical data; based on the preset machine learning algorithm and historical data, a preset temperature prediction model is preset; based on the battery pack operating data and the preset temperature prediction model, the current temperature curve is generated; based on the current temperature curve, if it is determined that the battery pack has a thermal runaway trend, the thermal management controller is controlled to perform temperature control.

[0127] In this embodiment, the cell temperature information includes the cell temperature value; after obtaining the battery pack operating data, it also includes, through the vehicle domain controller:

[0128] When the battery cell temperature value is abnormal, the thermal management controller is controlled to perform temperature control.

[0129] In this embodiment, the battery cell temperature information also includes the battery cell voltage value, the battery cell current value, and the battery cell internal resistance value; the battery pack heat dissipation information includes the battery pack water outlet temperature value and the battery pack water inlet temperature value; based on the preset machine learning algorithm and historical data, a preset temperature prediction model is provided, including:

[0130] Build an initial temperature rise prediction model and an initial heat dissipation prediction model based on a preset machine learning algorithm;

[0131] The initial temperature rise prediction model is trained based on the battery cell temperature value, the battery cell voltage value, the battery cell current value and the battery cell internal resistance value to obtain the temperature rise prediction model;

[0132] The initial heat dissipation prediction model is trained based on the battery cell temperature value, the battery pack water outlet temperature value, and the battery pack water inlet temperature value to obtain a heat dissipation prediction model;

[0133] A temperature prediction model is constructed based on the temperature rise prediction model and the heat dissipation prediction model.

[0134] In this embodiment, the vehicle domain controller is used to generate a current temperature curve based on the battery cell temperature data and a preset temperature prediction model, including:

[0135] Generate a temperature rise curve within a preset time period based on the battery cell temperature information and the temperature rise prediction model;

[0136] Generate a temperature heat dissipation curve within a preset time period based on battery heat dissipation information and heat dissipation prediction model;

[0137] The temperature rise curve and the temperature heat dissipation curve are used as the current temperature curve.

[0138] In this embodiment, the vehicle domain controller is configured to determine, based on the current temperature curve, that the battery has a thermal runaway trend, and then control the thermal management controller to perform temperature control, including:

[0139] Obtaining a total heat dissipation value based on a temperature heat dissipation curve, and obtaining a total temperature rise value based on a temperature rise curve;

[0140] The accumulated heat is obtained based on the total temperature rise value and the total heat dissipation value. When the accumulated heat is greater than the preset heat threshold, it is determined that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control.

[0141] In this embodiment, the vehicle domain controller is configured to determine that the battery cell temperature data has a temperature anomaly and then control the thermal management controller to perform temperature control, including:

[0142] When the cell temperature value of any cell in the current cell temperature information is greater than a preset temperature threshold, it is determined that the battery has a temperature abnormality, and the thermal management controller is controlled to perform temperature control.

[0143] In this embodiment, controlling the thermal management controller to perform temperature control includes:

[0144] Generate water pump control signal and compressor control signal;

[0145] controlling the thermal management controller to turn on the water pump fan based on the water pump control signal;

[0146] The thermal management controller is controlled based on the compressor control signal to adjust the cooling speed of the compressor.

[0147] In this embodiment, it also includes:

[0148] A temperature sensor is provided at each cell in the battery pack to obtain the cell temperature information based on the temperature sensor.

[0149] In an embodiment of the present invention, a terminal device is also provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned vehicle thermal management method is implemented.

[0150] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned vehicle thermal management method.

[0151] For example, a computer program may be divided into one or more modules, one or more of which are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0152] The terminal device may be a computing device such as a desktop computer, laptop, PDA, or cloud server. The terminal device may include, but is not limited to, a processor, memory, and display. Those skilled in the art will appreciate that the aforementioned components are merely examples of terminal devices and do not constitute a limitation of the terminal device. The terminal device may include more or fewer components, or a combination of certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, and the like.

[0153] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting various parts of the entire terminal device using various interfaces and lines.

[0154] The memory can be used to store computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function (such as a sound playback function, a text conversion function, etc.); the data storage area can store data generated based on the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory can include high-speed random access memory and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0155] If the vehicle thermal management module is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. Computer-readable media can include any entity or device capable of carrying computer program code, recording media, USB flash drives, removable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunications signals, and software distribution media. Persons of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0156] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A battery thermal management method, characterized in that: include: Acquiring battery pack operating data, wherein the battery pack operating data includes battery cell temperature information and battery pack heat dissipation information; Storing the battery pack operating data to form historical data; Presetting a temperature prediction model based on a preset machine learning algorithm and the historical data; generating a current temperature curve based on the battery pack operating data and the temperature prediction model; If it is determined based on the current temperature curve that the battery pack has a thermal runaway trend, the thermal management controller is controlled to perform temperature control.

2. A battery thermal management method according to claim 1, characterized in that: The battery cell temperature information includes the battery cell temperature value; after obtaining the battery pack operation data, the method further includes: When the battery core temperature value has a temperature abnormality, the thermal management controller is controlled to perform temperature control.

3. A battery thermal management method according to claim 2, characterized in that: The battery cell temperature information also includes the battery cell voltage value, the battery cell current value and the battery cell internal resistance value; the battery pack heat dissipation information includes the battery pack water outlet temperature value and the battery pack water inlet temperature value; The preset temperature prediction model based on the preset machine learning algorithm and the historical data includes: Build an initial temperature rise prediction model and an initial heat dissipation prediction model based on a preset machine learning algorithm; The initial temperature rise prediction model is trained based on the battery cell temperature value, the battery cell voltage value, the battery cell current value, and the battery cell internal resistance value to obtain a temperature rise prediction model; Training the initial heat dissipation prediction model based on the battery core temperature value, the battery pack water outlet temperature value, and the battery pack water inlet temperature value to obtain a heat dissipation prediction model; The temperature prediction model is constructed based on the temperature rise prediction model and the heat dissipation prediction model.

4. A battery thermal management method according to claim 3, characterized in that: The generating of a current temperature curve based on the battery cell temperature data and a preset temperature prediction model includes: Based on the battery cell temperature information and the temperature rise prediction model, generating a temperature rise curve within a preset time period; generating a temperature heat dissipation curve within a preset time period based on the battery heat dissipation information and the heat dissipation prediction model; The temperature rise curve and the temperature heat dissipation curve are used as the current temperature curve.

5. A battery thermal management method according to claim 4, characterized in that: Determining that the battery has a thermal runaway trend based on the current temperature curve, and then controlling the thermal management controller to perform temperature control, includes: Obtaining a total heat dissipation value based on the temperature heat dissipation curve, and obtaining a total temperature rise value based on the temperature rise curve; The accumulated heat is obtained based on the total temperature rise value and the total heat dissipation value. When the accumulated heat is greater than a preset heat threshold, it is determined that the battery pack has a thermal runaway trend, and the thermal management controller is controlled to perform temperature control.

6. A battery thermal management method according to claim 1, characterized in that: The determining that the battery core temperature data has a temperature anomaly, and then controlling the thermal management controller to perform temperature control, includes: When the cell temperature value of any cell in the current cell temperature information is greater than a preset temperature threshold, it is determined that the battery has a temperature abnormality, and the thermal management controller is controlled to perform temperature control.

7. A battery thermal management method according to claim 1, characterized in that: The controlling of the thermal management controller to perform temperature control includes: Generate water pump control signal and compressor control signal; controlling the thermal management controller to turn on the water pump fan based on the water pump control signal; The thermal management controller is controlled to adjust the cooling speed of the compressor based on the compressor control signal.

8. A vehicle thermal management method according to any one of claims 1 to 7, characterized in that: Also includes: A temperature sensor is provided at each battery cell in the battery pack, and the temperature information of the battery cell is obtained based on the temperature sensor.

9. A vehicle thermal management system, characterized in that: include: Acquisition board, vehicle domain controller and thermal management controller; The acquisition board is used to obtain battery pack operation data, wherein the battery pack operation data includes battery cell temperature information and battery pack heat dissipation information; The vehicle domain controller is configured to store the battery pack operating data to form historical data; and to preset a temperature prediction model based on a preset machine learning algorithm and the historical data; Generate a current temperature curve based on the battery pack operating data and the preset temperature prediction model; If it is determined based on the current temperature curve that the battery pack has a thermal runaway trend, the thermal management controller is controlled to perform temperature control.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the battery thermal management method according to any one of claims 1 to 8.

Images