Battery thermal management method and system based on intelligent control

Abstract

The present invention relates to the field of thermal management technology, specifically to a battery thermal management method and system based on intelligent control, including the following steps: based on the data collected by the temperature sensor, a support vector machine is used to sort and calibrate the real-time temperature data of the battery pack, identify the battery cells that need thermal load adjustment, and evaluate the current and cooling resource requirements, perform thermal load adjustment, and generate a thermal load adjustment configuration. The present invention effectively improves the accuracy and adaptability of battery thermal management by applying support vector machines and online gradient boosting, and ensures that the battery cells operate at the optimal temperature by real-time analysis and adjustment of the battery temperature, significantly improving the charging and discharging efficiency and safety of the battery. By dynamically adjusting the cooling process, the battery can maintain the best state under various operating conditions, reduce energy loss, and improve overall performance. Through continuous learning and self-optimization, the ability to predict future changes is enhanced, making thermal management more proactive.

Description

Technical Field

[0001] The present invention relates to the field of thermal management technology, and in particular to a battery thermal management method and system based on intelligent control. Background Art

[0002] The field of thermal management technology focuses on maintaining the temperature of equipment and systems during operation, ensuring that they operate within the optimal temperature range to improve performance, safety and efficiency. This field covers a variety of applications from microelectronic devices to large industrial systems. Especially in battery technology, the battery's thermal management system is designed to regulate the temperature of battery cells and modules, and keep the battery at an ideal operating temperature through heat dissipation or heating to prevent overheating or overcooling. It is critical to improving the battery's charging and discharging efficiency, extending its life, and preventing thermal runaway. Thermal management includes passive heat dissipation, active cooling systems (such as liquid cooling or air cooling systems), and thermal isolation measures.

[0003] Among them, battery thermal management methods focus on how to effectively control and regulate heat in battery systems. Batteries generate heat during discharge and charging. If not controlled, overheating will lead to degradation of battery performance and even safety risks. The purpose is to keep the battery operating within the optimal operating temperature range through reasonable heat distribution and removal, thereby improving battery efficiency, output stability and service life. This is particularly important in the fields of electric vehicles, portable electronic devices and energy storage systems.

[0004] Traditional methods mostly rely on preset programs, lack real-time data processing capabilities, and have difficulty adapting to changing operating conditions. For example, batteries overheat quickly under high-load operation. Traditional cooling systems cannot be adjusted immediately due to response delays, resulting in reduced battery performance or increased risks. Passive heating technology in low-temperature environments is inefficient and cannot effectively increase battery temperature, affecting battery performance and life, causing the battery management system to perform poorly in extreme or non-standard operating environments, increasing maintenance costs and potential safety risks. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a battery thermal management method and system based on intelligent control.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a battery thermal management method based on intelligent control, comprising the following steps:

[0007] S1: Based on the data collected by the temperature sensor, the support vector machine is used to sort and calibrate the real-time temperature data of the battery pack, identify the battery cells that need thermal load adjustment, evaluate the current and cooling resource requirements, adjust the thermal load, and generate the thermal load adjustment configuration;

[0008] S2: Based on the heat load adjustment configuration, monitor the temperature change after adjustment, record the temperature data of the battery unit before and after adjustment, analyze and verify the adjustment effect, and generate a thermal effect evaluation record;

[0009] S3: Based on the thermal effect evaluation record, analyze the performance of the battery pack under differentiated operating conditions, extract key adjustment parameters, feed back to the temperature control system, and automatically update the temperature difference adjustment parameters using online gradient boosting to generate parameter update records;

[0010] S4: Based on the parameter update record, adjust the working mode of the battery pack, change the current distribution and cooling process, record the adjusted working mode data, perform long-term monitoring, and evaluate the impact on battery life and performance to generate thermal management performance data.

[0011] The present invention is improved in that the steps of identifying the battery cell requiring thermal load adjustment are specifically as follows:

[0012] S111: Based on the data collected by the temperature sensor, continuously monitor the battery pack, collect real-time temperature readings of the battery cells, and generate a real-time temperature data set;

[0013] S112: Based on the real-time temperature data set, feature extraction is performed using a support vector machine, using the formula:

[0014]

[0015] Calculate the temperature score for each battery cell , get the sorted temperature data, where Represents the sensitivity weight of each battery cell temperature anomaly, which is used to amplify the square term of the temperature reading. represents the adjustment factor used to correct the effect of low temperature readings. Real-time temperature readings for each battery cell, is the number of battery cells;

[0016] S113: Analyze the sorted temperature data, identify battery cells whose temperatures exceed a threshold, and determine a list of battery cells that require thermal load adjustment.

[0017] The present invention is improved in that the step of obtaining the heat load adjustment configuration is specifically as follows:

[0018] S121: For the battery cells that require thermal load adjustment, analyze the temperature data and historical temperature data, according to the formula:

[0019]

[0020] and

[0021]

[0022] Evaluate the current requirements of each unit and cooling resource requirements , perform heat load adjustment and obtain heat load adjustment configuration, where, is the required power, is the voltage, and are the current and target temperatures, is the mass of the battery cell, is the specific heat capacity.

[0023] The present invention is improved in that the steps of obtaining the thermal effect evaluation record are specifically as follows:

[0024] S211: Based on the thermal load adjustment configuration, continuously capture the initial temperature of each battery cell, extract the temperature data before adjustment, and generate an initial temperature data set;

[0025] S212: Based on the initial temperature data set, monitor the temperature change, using the formula:

[0026]

[0027] Calculate the average temperature difference to get the adjusted temperature data, where: represents the average temperature change, For the The adjusted temperature of the data points, For the The temperature before adjustment of the data point, is the total number of data points;

[0028] S213: Based on the adjusted temperature data, the temperature adjustment effect is analyzed and verified to obtain a thermal effect evaluation record.

[0029] The present invention is improved in that the analysis steps of the performance of the battery pack under differentiated operating conditions are specifically as follows:

[0030] S311: extracting performance and temperature data of the battery pack based on the thermal effect evaluation record and arranging them into a preliminary performance data set;

[0031] S312: Statistical analysis is performed on the preliminary performance data set using the formula:

[0032]

[0033] Get key performance fluctuation data, among which, represents the sample standard deviation, Indicates Battery performance data points, is the sample mean, is the sample size;

[0034] S313: Based on the key performance fluctuation data, evaluate the performance of the battery pack under differentiated operating conditions to obtain a battery pack performance evaluation log.

[0035] The present invention is improved in that the automatic updating step of the temperature difference adjustment parameter is specifically as follows:

[0036] S321: Update the temperature difference adjustment parameter of the temperature control system according to the extracted key adjustment parameter, using the formula:

[0037]

[0038] Get new temperature difference adjustment parameters ,in, is the historical temperature difference adjustment parameter, represents the average temperature change, is the adjustment coefficient, which is used to adjust the sensitivity of the parameter according to the temperature difference;

[0039] S322: Based on the new temperature difference adjustment parameter, the temperature difference adjustment parameter is automatically updated by using online gradient boosting to obtain a parameter update record.

[0040] The present invention is improved in that the steps of changing the current distribution and cooling process are specifically as follows:

[0041] S411: based on the parameter update record, extract the current distribution and cooling data of the current battery pack to generate a basic configuration;

[0042] S412: According to the basic configuration, the current distribution and cooling process are changed again, using the formula:

[0043]

[0044] Optimize battery thermal management and energy efficiency to achieve expected energy consumption ,in, Represents the current value of the battery cell, is the resistance of the battery cell, represents the cooling flow rate, and is the adjustment factor used to balance the effects of current and cooling efficiency.

[0045] The present invention is improved in that the step of obtaining the thermal management performance data is specifically as follows:

[0046] S421: Collect the adjusted current distribution and cooling process data, record the operating parameters and battery response information, and obtain the working mode data;

[0047] S422: Long-term monitoring of the working mode data is performed to continuously track key performance indicators, including changes in temperature, current, and voltage of the battery, using the formula:

[0048]

[0049] Get battery performance stability ,in, is the performance data point during the monitoring period, is the average value of the monitoring data, is the number of monitoring cycles;

[0050] S423: Based on the battery performance stability, evaluate the impact on battery life and performance, and generate thermal management performance data.

[0051] A battery thermal management system based on intelligent control, the system comprising:

[0052] The temperature analysis module collects data collected by the temperature sensor, sorts and calibrates the real-time temperature data of the battery pack using a support vector machine, identifies the battery cells that require thermal load adjustment, evaluates the required current and cooling resources, and generates a thermal load adjustment configuration;

[0053] The thermal load adjustment module monitors the temperature change after adjustment based on the thermal load adjustment configuration, records the temperature data of the battery unit before and after adjustment, analyzes and verifies the adjustment effect, and generates a thermal effect evaluation record;

[0054] The performance evaluation module analyzes the performance of the battery pack under differentiated operating conditions based on the thermal effect evaluation record, extracts key adjustment parameters, feeds back to the temperature control system, automatically updates the temperature difference adjustment parameters using online gradient boosting, and generates parameter update records;

[0055] The working mode optimization module adjusts the working mode of the battery pack based on the parameter update record, changes the current distribution and cooling process, optimizes the battery performance and life, and generates working mode update data;

[0056] The performance monitoring module updates data based on the working mode, performs long-term monitoring, evaluates the impact of thermal management on battery life and performance, verifies the effectiveness of thermal management, and generates thermal management performance data.

[0057] Compared with the prior art, the advantages and positive effects of the present invention are:

[0058] In the present invention, the accuracy and adaptability of battery thermal management are effectively improved by applying support vector machines and online gradient boosting. By real-time analysis and adjustment of battery temperature, the battery cells are ensured to operate at the optimal temperature, which significantly improves the charging and discharging efficiency and safety of the battery. By dynamically adjusting the cooling process, the battery can maintain the best state under various operating conditions, reduce energy loss, and improve overall performance. Through continuous learning and self-optimization, the ability to predict future changes is enhanced, making thermal management more proactive. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flow chart of a battery thermal management method based on intelligent control proposed by the present invention;

[0060] Figure 2 A flow chart for identifying a battery cell that requires thermal load adjustment in the present invention;

[0061] Figure 3 A flow chart for obtaining the heat load adjustment configuration in the present invention;

[0062] Figure 4 A flow chart for obtaining thermal effect evaluation records in the present invention;

[0063] Figure 5 is a flow chart for analyzing the performance of the battery pack under differentiated operating conditions in the present invention;

[0064] Figure 6 This is a flow chart of automatic updating of temperature difference adjustment parameters in the present invention;

[0065] Figure 7 A flowchart of the changes in the current distribution and cooling process of the present invention;

[0066] Figure 8 This is a flow chart for obtaining thermal management performance data in the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0068] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0069] Example

[0070] See also Figure 1 The present invention provides a technical solution: a battery thermal management method based on intelligent control, comprising the following steps:

[0071] S1: Based on the data collected by the temperature sensor, the support vector machine is used to sort and calibrate the real-time temperature data of the battery pack, identify the battery cells that need thermal load adjustment, evaluate the current and cooling resource requirements, adjust the thermal load, and generate the thermal load adjustment configuration;

[0072] S2: Based on the heat load adjustment configuration, monitor the temperature change after adjustment, record the temperature data of the battery unit before and after adjustment, analyze and verify the adjustment effect, and generate a thermal effect evaluation record;

[0073] S3: Based on the thermal effect evaluation records, analyze the performance of the battery pack under differentiated operating conditions, extract key adjustment parameters, feed them back to the temperature control system, and use online gradient boosting to automatically update the temperature difference adjustment parameters and generate parameter update records;

[0074] S4: Based on the parameter update records, adjust the operating mode of the battery pack, change the current distribution and cooling process, record the adjusted operating mode data, conduct long-term monitoring, and evaluate the impact on battery life and performance to generate thermal management performance data.

[0075] The thermal load adjustment configuration includes temperature threshold settings and load distribution ratios. The thermal effect evaluation records include temperature response curves, effect improvement points, and performance comparison data. The parameter update records include update frequency, adjustment accuracy, and response time. The thermal management performance data include energy consumption statistics, cooling efficiency, and stability indicators.

[0076] See also Figure 2 , the steps for identifying the battery cells that require thermal load adjustment are as follows:

[0077] S111: Based on the data collected by the temperature sensor, continuously monitor the battery pack, collect real-time temperature readings of the battery cells, and generate a real-time temperature data set;

[0078] By real-time monitoring of battery cells, according to the formula Calculate the temperature reading of the battery cell, where Real-time temperature readings for each battery cell, Represents a battery cell At the monitoring time The temperature readings, Represents the number of monitoring times.

[0079] By collecting temperature readings of the battery cells at different points in time , and averaging the data can get a more stable temperature reading, reducing the impact of occasional high or low temperatures. In one monitoring cycle, the battery cell The temperatures at three different time points were 30°C, 32°C and 31°C, i.e. , monitoring times :

[0080]

[0081] The results showed that the battery cells The temperature reading during the monitoring period was 31°C, providing a basis for the next step of data analysis and processing.

[0082] S112: Based on the real-time temperature data set, feature extraction is performed using a support vector machine using the formula:

[0083]

[0084] Calculate the temperature score for each battery cell , get the sorted temperature data, where Represents the sensitivity weight of each battery cell temperature anomaly, which is used to amplify the square term of the temperature reading. represents the adjustment factor used to correct the effect of low temperature readings. Real-time temperature readings for each battery cell, is the number of battery cells;

[0085] For a battery cell, ℃, weight parameter , , the calculation process is as follows:

[0086]

[0087]

[0088] The score reflects the temperature risk assessment of the battery cell under given conditions, with a high score indicating that the battery cell temperature is high and further verification or intervention is required.

[0089] S113: analyzing the sorted temperature data, identifying battery cells whose temperatures exceed a threshold, and determining a list of battery cells that require thermal load adjustment;

[0090] Sort the results by temperature, according to the formula , calculate the battery cells that exceed the temperature threshold, where, Real-time temperature readings for each battery cell, represents the temperature threshold, Represents a list of battery cells that require thermal load adjustment;

[0091] set up , ,but:

[0092]

[0093] This result indicates that the temperature of the battery cell exceeds the set threshold and thermal load adjustment is required.

[0094] See also Figure 3 , the specific steps for obtaining the heat load adjustment configuration are:

[0095] S121: For the battery cells that require thermal load adjustment, analyze the temperature data and historical temperature data, according to the formula:

[0096]

[0097] and

[0098]

[0099] Evaluate the current requirements of each unit and cooling resource requirements , perform heat load adjustment and obtain heat load adjustment configuration, where, is the required power, is the voltage, and are the current and target temperatures, is the mass of the battery cell, is the specific heat capacity;

[0100] If a battery cell requires 100W of power to operate at 10V, substitute the values ​​into the formula:

[0101]

[0102] The battery cell requires 10 amps of current to operate properly, which is the basis for evaluating whether the battery cell current capacity is sufficient or whether the system needs to be adjusted to accommodate this current demand.

[0103] If the mass of the battery cell is 2kg, the specific heat capacity is , the current temperature is 45℃, and the target temperature is 35℃, then:

[0104]

[0105] The results show that in order to reduce the battery cell temperature from the current 45°C to the target temperature of 35°C, 18,000 joules of energy are required for cooling.

[0106] See also Figure 4 , the specific steps for obtaining thermal effect assessment records are as follows:

[0107] S211: Based on the heat load adjustment configuration, continuously capture the initial temperature of each battery cell, extract the temperature data before adjustment, and generate an initial temperature data set;

[0108] S212: Based on the initial temperature data set, monitor the temperature change using the formula:

[0109]

[0110] Calculate the average temperature difference to get the adjusted temperature data, where: represents the average temperature change, For the The adjusted temperature of the data points, For the The temperature before adjustment of the data point, is the total number of data points;

[0111] S213: Analyze and verify the temperature adjustment effect based on the adjusted temperature data to obtain a thermal effect evaluation record;

[0112] There are three data points The temperatures before and after adjustment are , , , , , ,but:

[0113]

[0114] result It indicates that after the adjustment measures, the average temperature increased by 3°C, indicating that the heat load adjustment produced an actual temperature change effect.

[0115] See also Figure 5 , the analysis steps of the battery pack performance under differentiated operating conditions are as follows:

[0116] S311: Based on the thermal effect evaluation records, extract the performance and temperature data of the battery pack and organize them into a preliminary performance data set;

[0117] Extract the performance and temperature data of the battery pack from the thermal effect evaluation record, according to the formula Calculate the degree of data dispersion, where Represents the degree of data dispersion, Representative Battery performance data points, Represents the expectation or mean of the data;

[0118] The data points obtained from the thermal effects evaluation record are , expected value ,but:

[0119]

[0120] The degree of dispersion of the data is 2, indicating the deviation of the data point from the average value. The results are helpful to further analyze the stability and performance of the battery under different environmental conditions.

[0121] S312: Perform statistical analysis on the preliminary performance data set using the formula:

[0122]

[0123] Get key performance fluctuation data, among which, represents the sample standard deviation, Indicates Battery performance data points, is the sample mean, is the sample size;

[0124] Collect battery performance data points 22℃, 23℃ and 21℃, ℃, number of samples , the calculation process is as follows:

[0125]

[0126] It means that the standard deviation of the battery performance data during the measurement period is 1°C, which indicates the degree of fluctuation in the performance of the battery pack under the test conditions.

[0127] S313: Based on the key performance fluctuation data, evaluate the performance of the battery pack under differentiated operating conditions to obtain a battery pack performance evaluation log;

[0128] Using key performance fluctuation data to evaluate the performance of the battery pack under differentiated operating conditions, according to the formula Calculate the performance evaluation index, where stands for Performance Evaluation Index, Represents the sum of key performance fluctuation data, Represents the number of conditions tested, designed to quantify the overall performance of the battery pack under different operating conditions;

[0129] The total amount of key performance fluctuation data monitored , the number of test conditions ,but:

[0130]

[0131] Indicates that the performance evaluation index of the battery pack is 2. This value can be used to compare the performance differences between different battery packs or under different operating conditions, thereby guiding future optimization and adjustment strategies.

[0132] See also Figure 6 , the automatic update steps of the temperature difference adjustment parameters are as follows:

[0133] S321: Update the temperature difference adjustment parameters of the temperature control system according to the extracted key adjustment parameters, using the formula:

[0134]

[0135] Get new temperature difference adjustment parameters ,in, is the historical temperature difference adjustment parameter, represents the average temperature change, is the adjustment coefficient, which is used to adjust the sensitivity of the parameter according to the temperature difference;

[0136] set up is 5 degrees, the measured is 3 degrees, is 0.5. The calculation process is as follows:

[0137]

[0138] =5.87 represents a parameter value that has been calculated and optimized, and this value will be used to actually adjust the temperature control system to ensure that its performance responds to changes in ambient temperature more accurately and efficiently.

[0139] S322: Based on the new temperature difference adjustment parameter, the temperature difference adjustment parameter is automatically updated by using online gradient boosting to obtain a parameter update record;

[0140] According to the formula Calculate the updated average temperature difference adjustment parameter, where: represents the updated average temperature difference adjustment parameter, Represents the new temperature difference adjustment parameter, Represents the total number of parameters;

[0141] The formula is used to calculate the average value of all updated temperature difference adjustment parameters to evaluate the broad effect of system adjustment. For example, if the new parameter value set is , and the total number of parameters ,but:

[0142]

[0143] Calculation results show that the updated average temperature difference adjustment parameter is 6.7. This value helps evaluate the adjustment effect of the overall system and ensures that the temperature control system adjustment achieves the expected consistency and efficiency.

[0144] See also Figure 7 , the specific steps of changing the current distribution and cooling process are:

[0145] S411: extracting the current distribution and cooling data of the current battery pack based on the parameter update record, and generating a basic configuration;

[0146] Among them, based on the parameter update record, the current distribution and cooling system data of the battery pack are extracted according to the formula Calculate the basic configuration, where represents the total configuration index, For the The value of the parameter, is the corresponding configuration weight, Represents the total number of parameters;

[0147] Assume that the battery pack consists of three main parameters, whose values ​​are The corresponding configuration weight is ,but:

[0148]

[0149] The result shows that based on the existing parameters and weight configuration, the overall configuration index is 90, reflecting the overall configuration efficiency of the battery pack's current distribution and cooling system.

[0150] S412: Based on the basic configuration, the current distribution and cooling process are changed again, using the formula:

[0151]

[0152] Optimize battery thermal management and energy efficiency to achieve expected energy consumption ,in, Represents the current value of the battery cell, is the resistance of the battery cell, represents the cooling flow rate, and is the adjustment factor, used to balance the effects of current and cooling efficiency;

[0153] Monitored current For 15 amps, the resistor 0.5 ohm, cooling flow is 20, the adjustment coefficient is 0.05, is 0.1;

[0154] Substitute the parameter values ​​into the formula for calculation:

[0155]

[0156] The result shows that the expected energy consumption is 7.625 under the current regulation coefficient and working conditions. The calculation helps to analyze the energy consumption under specific parameters and adjust the current distribution and cooling process accordingly to achieve higher energy efficiency and safety standards.

[0157] See also Figure 8 , the specific steps for obtaining thermal management performance data are:

[0158] S421: Collect adjusted current distribution and cooling process data, record operating parameters and battery response information, and obtain working mode data;

[0159] According to the formula Calculate the instantaneous power output of the battery during the adjustment process, where, Represents the total power of the battery, Representative The voltage at each measuring point, Represents the corresponding current value;

[0160] The battery pack is monitored to have three measurement points at a specific time point, and the voltage and current values ​​are:

[0161]

[0162]

[0163]

[0164] The total power is calculated as follows:

[0165]

[0166]

[0167]

[0168] The results show the total power output of the battery pack at a given moment, providing basic data for further analysis of battery performance.

[0169] S422: Monitor the working mode data for a long time and continuously track key performance indicators, including the temperature, current and voltage changes of the battery, using the formula:

[0170]

[0171] Get battery performance stability , providing quantitative data support for battery life and performance evaluation, including: is the performance data point during the monitoring period, is the average value of the monitoring data, is the number of monitoring cycles;

[0172] Over a period of time, the following voltage data (in V) were monitored:

[0173] Performance Data Points ;

[0174] Calculate the average voltage :

[0175]

[0176] Calculate battery performance stability :

[0177]

[0178]

[0179]

[0180]

[0181]

[0182] The results show that the average variability of the voltage during the monitoring period is 0.0424, which reflects the high stability of the battery performance and helps to analyze the behavior and life prediction of the battery under different working conditions.

[0183] S423: Based on the battery performance stability, evaluate the impact on battery life and performance, and generate thermal management performance data;

[0184] Through data analysis, the capacity decay of each battery cycle is compared with the expected performance to evaluate its health status and expected lifespan. Predict the performance degradation of the battery after continuous use, where Indicates The battery capacity after a charge and discharge cycle, is the initial capacity, is the decay constant, is the number of charge and discharge cycles;

[0185] If the initial battery capacity is , the decay constant , after 100 charge and discharge cycles, the battery capacity is calculated as follows:

[0186]

[0187] It shows that after 100 charge and discharge cycles, the capacity of the battery will be reduced to about 36.79Wh, that is, the battery retains about 36.79% of its original capacity, which is crucial for analyzing the battery's service life and planning replacement cycles.

[0188] Battery thermal management system based on intelligent control, the system includes:

[0189] The temperature analysis module collects data collected by the temperature sensor, sorts and calibrates the real-time temperature data of the battery pack using a support vector machine, identifies the battery cells that require thermal load adjustment, evaluates the required current and cooling resources, and generates a thermal load adjustment configuration;

[0190] The thermal load regulation module monitors the temperature changes after adjustment based on the thermal load adjustment configuration, records the temperature data of the battery unit before and after adjustment, analyzes and verifies the adjustment effect, and generates thermal effect evaluation records;

[0191] The performance evaluation module analyzes the performance of the battery pack under differentiated operating conditions based on the thermal effect evaluation records, extracts key adjustment parameters, feeds them back to the temperature control system, automatically updates the temperature difference adjustment parameters using online gradient boosting, and generates parameter update records;

[0192] The working mode optimization module adjusts the working mode of the battery pack based on the parameter update record, changes the current distribution and cooling process, optimizes the battery performance and life, and generates working mode update data;

[0193] The performance monitoring module updates data based on the working mode, performs long-term monitoring, evaluates the impact of thermal management on battery life and performance, verifies the effectiveness of thermal management, and generates thermal management performance data.

[0194] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A battery thermal management method based on intelligent control, characterized in that: The following steps are involved: Based on the data collected by the temperature sensor, a support vector machine is used to sort and calibrate the real-time temperature data of the battery pack, identify the battery cells that need thermal load adjustment, evaluate the current and cooling resource requirements, adjust the thermal load, and generate the thermal load adjustment configuration; Based on the heat load adjustment configuration, monitor the temperature change after adjustment, record the temperature data of the battery unit before and after adjustment, analyze and verify the adjustment effect, and generate a thermal effect evaluation record; Based on the thermal effect evaluation record, the performance of the battery pack under differentiated operating conditions is analyzed, key adjustment parameters are extracted, fed back to the temperature control system, and the temperature difference adjustment parameters are automatically updated using online gradient boosting to generate parameter update records; The steps for obtaining the thermal effect assessment record are specifically as follows: Based on the thermal load adjustment configuration, continuously capture the initial temperature of each battery cell, extract the temperature data before adjustment, and generate an initial temperature data set; Based on the initial temperature data set, the temperature change is monitored using the formula: Calculate the average temperature difference to get the adjusted temperature data, where ΔTY represents the average temperature change, T after,i is the adjusted temperature of the ith data point, T before,i is the temperature of the i-th data point before adjustment, n r is the total number of data points; Based on the adjusted temperature data, analyzing and verifying the temperature adjustment effect to obtain a thermal effect evaluation record; The analysis steps of the battery pack performance under differentiated operating conditions are specifically as follows: Based on the thermal effect evaluation records, extract performance and temperature data of the battery pack and organize them into a preliminary performance data set; The preliminary performance data set was statistically analyzed using the formula: Get key performance fluctuation data, where SD represents the sample standard deviation, xd i represents the ith battery performance data point, is the sample mean, n d is the sample size; Based on the key performance fluctuation data, evaluate the performance of the battery pack under differentiated operating conditions to obtain a battery pack performance evaluation log; The automatic updating steps of the temperature difference adjustment parameters are specifically as follows: According to the extracted key adjustment parameters, the temperature difference adjustment parameters of the temperature control system are updated using the formula: Get the new temperature difference adjustment parameter PL new , where PL old is the historical temperature difference adjustment parameter, ΔTY represents the average temperature change, K L is the adjustment coefficient, which is used to adjust the sensitivity of the parameter according to the temperature difference; Based on the new temperature difference adjustment parameter, the temperature difference adjustment parameter is automatically updated by using online gradient boosting to obtain a parameter update record; According to the formula Calculate the updated average temperature difference adjustment parameter, where RS represents the updated average temperature difference adjustment parameter, PL new Represents the new temperature difference adjustment parameter, N j Represents the total number of parameters; Based on the parameter update records, the operating mode of the battery pack is adjusted, the current distribution and cooling process are changed, the adjusted operating mode data is recorded, long-term monitoring is performed, and the impact on battery life and performance is evaluated to generate thermal management performance data.

2. The battery thermal management method based on intelligent control according to claim 1, characterized in that: The steps for identifying the battery cell that needs thermal load adjustment are specifically as follows: Based on the data collected by the temperature sensor, the battery pack is continuously monitored, the real-time temperature readings of the battery cells are collected, and a real-time temperature data set is generated; Based on the real-time temperature data set, feature extraction is performed using a support vector machine, using the formula: Calculate the temperature score SVM_score of each battery cell to obtain the sorted temperature data, where a i Represents the sensitivity weight of each battery cell temperature anomaly, which is used to amplify the square term of the temperature reading, b i represents the adjustment factor used to correct the effect of low temperature readings, T i is the real-time temperature reading of each battery cell, where n is the number of battery cells; The sorted temperature data is analyzed to identify battery cells whose temperatures exceed a threshold value, and a list of battery cells requiring thermal load adjustment is determined.

3. The battery thermal management method based on intelligent control according to claim 1, characterized in that: The steps of obtaining the heat load adjustment configuration are specifically as follows: For battery cells that require thermal load adjustment, analyze the temperature data and historical temperature data, according to the formula: and Q cool =m×c×(T current -T target ) Estimate the current demand I of each unit required and cooling resource requirement Q cool , adjust the heat load and get the heat load adjustment configuration, where P needed is the required power, V is the voltage, T current and T target are the current and target temperatures, m is the mass of the battery cell, and c is the specific heat capacity.

4. The battery thermal management method based on intelligent control according to claim 1, characterized in that: The steps of changing the current distribution and cooling process are specifically as follows: Based on the parameter update record, extract the current distribution and cooling data of the current battery pack to generate a basic configuration; Based on the basic configuration, the current distribution and cooling process are re-changed, using the formula: EP=a P IP 2 R P +b P Q P Optimize the thermal management and energy efficiency of the battery to obtain the expected energy consumption EP, where IP represents the current value of the battery cell, R P is the resistance of the battery cell, Q P represents the cooling flow rate, α P and β P is the adjustment factor used to balance the effects of current and cooling efficiency.

5. The battery thermal management method based on intelligent control according to claim 1, characterized in that: The steps for obtaining the thermal management performance data are specifically as follows: Collecting the adjusted current distribution and cooling process data, recording operating parameters and battery response information, and obtaining working mode data; The working mode data is monitored for a long time, and key performance indicators are continuously tracked, including the temperature, current and voltage changes of the battery, using the formula: The battery performance stability RB is obtained, where XB j is the performance data point during the monitoring period, is the average value of the monitoring data, m is the number of monitoring cycles; Based on the battery performance stability, the impact on battery life and performance is evaluated and thermal management performance data is generated.

6. Battery thermal management system based on intelligent control, characterized in that: According to any one of claims 1 to 5, the battery thermal management method based on intelligent control is implemented, and the system comprises: The temperature analysis module collects data collected by the temperature sensor, sorts and calibrates the real-time temperature data of the battery pack using a support vector machine, identifies the battery cells that require thermal load adjustment, evaluates the required current and cooling resources, and generates a thermal load adjustment configuration; The thermal load adjustment module monitors the temperature change after adjustment based on the thermal load adjustment configuration, records the temperature data of the battery unit before and after adjustment, analyzes and verifies the adjustment effect, and generates a thermal effect evaluation record; The performance evaluation module analyzes the performance of the battery pack under differentiated operating conditions based on the thermal effect evaluation record, extracts key adjustment parameters, feeds back to the temperature control system, automatically updates the temperature difference adjustment parameters using online gradient boosting, and generates parameter update records; The working mode optimization module adjusts the working mode of the battery pack based on the parameter update record, changes the current distribution and cooling process, optimizes the battery performance and life, and generates working mode update data; The performance monitoring module updates data based on the working mode, performs long-term monitoring, evaluates the impact of thermal management on battery life and performance, verifies the effectiveness of thermal management, and generates thermal management performance data.

Images