Vehicle power battery thermal management method and system

Abstract

The present invention provides a vehicle power battery thermal management method, comprising: real-time collection of the vehicle's position, time, power battery voltage, current, and temperature data during driving and uploading them to the cloud. Data cleaning is performed on the dynamic data uploaded by the vehicle to remove variable values ​​that exceed a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model. A cooling start-up temperature prediction model is established. The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the current route of the vehicle; the battery temperature change curve is input into the cooling start-up temperature prediction model, with the goal of the battery temperature reaching a safety threshold at the end of the trip, to obtain the cooling start-up temperature and start-up time for this target trip. The battery temperature reaches the safety threshold at the end of the trip, ensuring that the maximum power battery temperature of the vehicle is lower than or equal to the safety threshold at the end of this driving cycle.

Description

Technical Field

[0001] The present invention relates to the field of thermal management of electric vehicle power batteries, and in particular to a vehicle power battery thermal management method and system. Background Art

[0002] During use, the temperature of power batteries fluctuates, rising and falling. A thermal management system is needed to heat or cool the power batteries and maintain temperature control, ensuring they operate within a comfortable temperature range and maximize performance. However, heating or cooling batteries requires energy. Heating can be achieved through methods such as motor stalling, but cooling relies solely on the battery's own stored energy. This energy consumption significantly impacts vehicle range. In today's world of range anxiety, optimizing cooling energy consumption is particularly important.

[0003] Existing technologies that optimize battery thermal management methods using vehicle historical data focus on optimizing the power battery cooling entry and exit temperature thresholds in different scenarios. Although this has played a certain role, it has not fundamentally eliminated the waste of power battery cooling energy, and there is still room for improvement in reducing cooling energy consumption. Summary of the Invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the present invention provides a vehicle power battery thermal management method, comprising:

[0005] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0006] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0007] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0008] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0009] Furthermore, data cleaning includes cell voltage filtering, voltage default value exclusion, battery module temperature filtering, current value filtering, SOC value filtering, vehicle mileage filtering, integrity filtering and logic filtering.

[0010] Furthermore, cell voltage filtering removes voltage data outside the range [0, 5V]; voltage default value exclusion removes data with a cell voltage of 0 or the default value (3.65V is used as an example in this embodiment); battery module temperature filtering removes data outside the range [-40°C, 210°C]; current filtering removes data outside the range [-1500A, 1500A]; SOC filtering removes data outside the range [0, 100%]; vehicle mileage filtering removes data outside the range [0, 1000000km]; integrity filtering removes data with missing cell voltage values; and logic filtering removes data with valid current values, changes in SOC or mileage, but unchanged cell voltage values. Eliminating obviously erroneous data effectively prevents errors in subsequent data processing.

[0011] Furthermore, battery thermal management parameters can be obtained through the power battery traceability platform, including static parameters such as power battery material system, grouping method, number of batteries, peak current and cooling water flow.

[0012] Furthermore, the battery temperature prediction model includes the following calculation formula:

[0013]

[0014] I(t)≤I max

[0015] Among them, T pre (t) is the predicted curve of battery temperature changing with time, I(t) is the real-time current, I max is the peak current, P generation (I(t),r i , t) is the real-time heat generation power, m is the number of batteries in the battery pack, M is the mass of the battery, and C is the equivalent specific heat capacity.

[0016] Furthermore, the battery cooling start temperature prediction model is established including:

[0017] The battery initial temperature, current time, season information and road condition information are input into the battery temperature prediction model. The maximum battery temperature is used as the output, and the optimization goal is that the maximum battery temperature reaches the safety threshold at the end time. A cooling start temperature prediction model is established through a neural network or support vector machine algorithm.

[0018]

[0019]

[0020] The actual maximum battery temperature at the end of the user's trip is used as feedback for the cooling start-up temperature prediction model, and the model parameters are dynamically tuned to continuously improve the prediction accuracy of the cooling start-up temperature.

[0021] Among them, T s is the temperature safety threshold affected by the material system, P cool (L) is the heat dissipation power affected by the cooling water flow rate, t max is the end time of this trip, t cool is the cooling start time, T coolpre is the cooling start temperature.

[0022] Furthermore, the vehicle route is obtained through the vehicle's current position, current time and target location; the target location is obtained based on the navigation results when the user uses navigation; when the user does not use navigation, the user's travel records are obtained through vehicle historical data, and the frequency of recently frequently used target locations is statistically analyzed to generate a target location set. Based on the frequency of the target locations, the probability of reaching different target locations from the current position is calculated, and a list of possible destinations is generated according to the screening rules, and sorted from high to low according to probability.

[0023] Furthermore, we counted recent user travel records, analyzed the frequency of frequently visited destinations, and the frequency matrix between two destinations. When the user did not use navigation, the specific calculation formula for the probability of reaching different destinations from the current location was as follows:

[0024]

[0025] ω+μ=1

[0026] Among them, x i is the current position, x k is the target location, f pre (x i →x k ) represents the probability of reaching the target location from the current location, k≤num and k≠i, num is the total number of all possible target locations, Indicates that from x i Arrive at xk The statistical frequency of Represents reaching x from any possible destination k The sum of the frequencies of Indicates that from x i The sum of the frequencies of going to any other possible destinations, represents the sum of the frequencies of reaching all target locations, t represents the three time labels of a day, namely working hours, off-get off work hours and other times, day represents the type label of each day, namely working days and non-working days, and ω represents the target location x k The weight of the probability of being reached, μ represents the distance from the current location x i Departure and arrival at destination x k The weight of the probability.

[0027] Further filters to generate a list of possible destinations include:

[0028] According to the calculated results of the probability of reaching the target location, the target locations are sorted from high to low to generate a first target location list; the first target location list filters the calculated results of the probability of reaching the target location f pre (x i →x k )≥θ to generate a second target location list, and θ is calibrated according to actual conditions; the second target location list filters the top three target locations to generate a third target location list.

[0029] Furthermore, the battery temperature change curve prediction includes:

[0030] Based on the target locations in the third target location list, query historical records to determine the most likely path, travel time, road condition information, historical peak current, and SOC change; substituted the above information and the current initial value of the battery temperature into the temperature prediction model to obtain the predicted value of the battery temperature change curve.

[0031] Furthermore, the determination of the cooling start temperature and start time includes:

[0032] The battery temperature change curve corresponding to the target location in the third target location list is input into the cooling start temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the recommended cooling start temperature and start time for this target trip are obtained.

[0033] Furthermore, the cooling temperature and time are sent to the user. After confirmation, the vehicle controller updates the cooling temperature threshold. A recommended method is to push this information to the vehicle's dashboard. The location and estimated time corresponding to the cooling temperature are marked on the most likely path between the current and target locations, and a sound prompt is played to alert the user.

[0034] Further, the predicted target location is dynamically adjusted according to the route and traffic congestion conditions, the starting temperature and starting time of this trip are calculated in real time, and the cooling start temperature threshold of the vehicle controller is updated according to the preset cooling threshold update strategy.

[0035] Further, the cooling threshold update includes:

[0036] When the cooling start temperature threshold newly calculated by the cloud is lower than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice ≥t0, then observe n consecutive w cooling start temperature threshold calculation periods. If the fluctuations of the recommended cooling start temperatures in n w cooling start temperature threshold calculation periods satisfy then update the cooling start temperature threshold of the vehicle controller, otherwise do not update.

[0037] When the cooling start temperature threshold newly calculated by the cloud is lower than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice <t0, then take the average value of the cooling start temperatures in ε consecutive cooling start temperature threshold calculation periods to update the cooling start temperature threshold of the vehicle controller.

[0038] When the cooling start temperature threshold newly calculated by the cloud is higher than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice ≥t0, then observe n consecutive w cooling start temperature threshold calculation periods. If the fluctuations of the recommended cooling start temperatures in n w cooling start temperature threshold calculation periods satisfy [[ID=四十一]]则 update the cooling start temperature threshold of the vehicle controller, otherwise do not update.

[0039] When the cooling start temperature threshold newly calculated by the cloud is higher than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice <t0, do not update the cooling start temperature threshold of the vehicle controller.

[0040] Among them, t0 is the time required for the temperature to change by a specified temperature during normal vehicle driving, and this value is obtained by statistical analysis of the vehicle's historical trip records. t current is the current time, t adviceis the recommended time to start cooling, T coolpre (i) is the predicted value of the cooling start temperature at the i-th moment, n w is t current -t advice ≥t0 observation window width, ε is t current -t advice <t0 observation window width, δ is the allowable range of fluctuations in the predicted cooling start temperature within the observation window width, and the value range of this value is determined according to the temperature sampling accuracy.

[0041] A vehicle power battery thermal management system is also provided, which uses the above method and includes: a vehicle-end execution system, a cloud computing system, and a vehicle-cloud communication system.

[0042] The vehicle-end execution system includes: a data acquisition module for real-time acquisition of data such as the position, time, power battery voltage, current, temperature, etc. of the vehicle during driving; a thermal management execution module for receiving parameters sent from the cloud and executing the thermal management strategy to control the battery temperature within a comfortable range.

[0043] The cloud computing system includes: a data cleaning module for eliminating data that exceeds the threshold range and does not conform to logical changes; a temperature prediction module for real-time prediction of the change in battery temperature; a cooling start temperature prediction module for predicting the cooling entry temperature and time of the thermal management system for this trip.

[0044] The vehicle-cloud communication system includes: a data upload module for uploading the collected signals to the cloud big data platform according to the specified coding rules.

[0045] Furthermore, the vehicle-end execution system further includes a user prompt module for receiving and displaying a cooling start temperature suggestion instruction; the cloud computing system further includes a user prompt sending module for sending a cooling start temperature suggestion instruction to the user; the vehicle-cloud communication system further includes a user prompt sending module for updating the cooling start temperature threshold of the vehicle-end controller.

[0046] The present invention eliminates the problem of waste of cooling energy of the power battery and maximally saves the energy of the power battery. On the premise of ensuring safety, the battery is maintained within a relatively high temperature range, improving the power performance of the power battery and providing a surging power experience.

[0047] The present invention may also be able to dynamically adjust the cooling start temperature threshold according to the user's usage habits. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a schematic diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0050] Example 1:

[0051] The vehicle power battery thermal management method of this embodiment includes:

[0052] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0053] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0054] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0055] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0056] Example 2:

[0057] The vehicle power battery thermal management method of this embodiment includes:

[0058] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0059] Data cleaning includes cell voltage filtering, voltage default value exclusion, battery module temperature filtering, current value filtering, SOC value filtering, vehicle mileage filtering, integrity filtering and logic filtering.

[0060] Preferably, cell voltage filtering removes voltage data outside the range [0, 5V]; voltage default value exclusion removes data with a cell voltage of 0 or the default value; battery module temperature filtering removes data outside the range [-40°C, 210°C]; current value filtering removes data outside the range [-1500A, 1500A]; SOC value filtering removes data outside the range [0, 100%]; vehicle mileage filtering removes data outside the range [0, 1000000km]; integrity filtering removes data with missing cell voltage values; and logic filtering removes data with valid current values, changes in SOC or mileage, but unchanged cell voltage values. Eliminating obviously erroneous data can effectively prevent errors in subsequent data processing.

[0061] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0062] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0063] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0064] Example 3:

[0065] The vehicle power battery thermal management method of this embodiment includes:

[0066] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0067] Battery thermal management parameters can be obtained through the power battery traceability platform, including static parameters such as power battery material system, grouping method, number of batteries, peak current and cooling water flow.

[0068] Preferably, the battery temperature prediction model includes the following calculation formula:

[0069]

[0070] I(t)≤I max

[0071] Among them, T pre (t) is the predicted curve of battery temperature changing with time, I(t) is the real-time current, I max is the peak current, P generati o n (I(t),r i , t) is the real-time heat generation power, m is the number of batteries in the battery pack, M is the mass of the battery, and C is the equivalent specific heat capacity.

[0072] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0073] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0074] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0075] Example 4:

[0076] The vehicle power battery thermal management method of this embodiment includes:

[0077] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0078] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0079] The establishment of the battery cooling start temperature prediction model includes:

[0080] The battery initial temperature, current time, season information and road condition information are input into the battery temperature prediction model. The maximum battery temperature is used as the output, and the optimization goal is that the maximum battery temperature reaches the safety threshold at the end time. A cooling start temperature prediction model is established through a neural network or support vector machine algorithm.

[0081]

[0082]

[0083] The actual maximum battery temperature at the end of the user's trip is used as feedback for the cooling start-up temperature prediction model, and the model parameters are dynamically tuned to continuously improve the prediction accuracy of the cooling start-up temperature.

[0084] Among them, T s is the temperature safety threshold affected by the material system, P cool (L) is the heat dissipation power affected by the cooling water flow rate, t max is the end time of this trip, t coolis the cooling start time, T coolpre is the cooling start temperature.

[0085] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0086] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0087] Example 5:

[0088] The vehicle power battery thermal management method of this embodiment includes:

[0089] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0090] A cooling start-up temperature prediction model is established with battery cooling capacity, battery initial temperature, and battery temperature rise rate as input, battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time.

[0091] The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

[0092] The vehicle route is obtained through the vehicle's current position, current time and target location. The target location is obtained based on the navigation results when the user uses navigation. When the user does not use navigation, the user's travel history is obtained through vehicle historical data, and the frequency of recently frequently used target locations is statistically analyzed to generate a target location set. Based on the frequency of the target locations, the probability of reaching different target locations from the current position is calculated, and a list of possible destinations is generated according to the screening rules, and sorted from high to low according to probability.

[0093] Preferably, statistics are collected on recent user travel records, for example, within six months, and the frequency of recently frequently used destinations and the frequency matrix between two destinations are statistically analyzed as follows:

[0094]

[0095] When the user does not use navigation, the specific calculation formula for the probability of reaching different target locations from the current location is as follows:

[0096]

[0097] ω+μ=1

[0098] Among them, x i is the current position, x k is the target location, f pre (x i →x k ) represents the probability of reaching the target location from the current location, k≤num and k≠i, num is the total number of all possible target locations, Indicates that from x i Arrive at x k The statistical frequency of Represents reaching x from any possible destination k The sum of the frequencies of Indicates that from x i The sum of the frequencies of going to any other possible destinations, represents the sum of the frequencies of reaching all target locations, t represents the three time labels of a day, namely working hours, off-get off work hours and other times, day represents the type label of each day, namely working days and non-working days, and ω represents the target location x k The weight of the probability of being reached is preferably assigned a value of 0.8 or more, and μ represents the distance from the current location x i Departure and arrival at destination x k The probability weight is preferably assigned a value of 0.2 or less.

[0099] Further preferably, the screening for generating the possible destination list includes:

[0100] According to the calculated results of the probability of reaching the target location, the target locations are sorted from high to low to generate a first target location list; the first target location list filters the calculated results of the probability of reaching the target location f pre (x i →x k )≥θ to generate a second target location list, and θ is calibrated according to actual conditions; the second target location list filters the top three target locations to generate a third target location list.

[0101] In some embodiments, battery temperature variation curve prediction includes:

[0102] Based on the target locations in the third target location list, query historical records to determine the most likely path, travel time, road condition information, historical peak current, and SOC change; substituted the above information and the current initial value of the battery temperature into the temperature prediction model to obtain the predicted value of the battery temperature change curve.

[0103] In some embodiments, determining the cooling start temperature and start time includes:

[0104] The battery temperature change curve corresponding to the target location in the third target location list is input into the cooling start temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the recommended cooling start temperature and start time for this target trip are obtained.

[0105] At the end of the trip, the battery temperature reaches a safety threshold, ensuring that the vehicle's maximum power battery temperature at the end of the driving cycle is below or equal to the safety threshold (the safety threshold is determined by the battery material system and is above the cooling activation temperature). No cooling exit strategy is required, fundamentally eliminating the problem of power battery cooling energy waste and maximizing power battery energy conservation. At the same time, while ensuring safety, maintaining the battery at a higher temperature range improves the power performance of the power battery and provides a surging driving experience.

[0106] Example 6:

[0107] The vehicle power battery thermal management method of this embodiment includes:

[0108] Real-time data on the vehicle's location, time, power battery voltage, current, and temperature is collected and uploaded to the cloud. Signal collection can be based on either the GBT 32960 "Technical Specification for Electric Vehicle Remote Service and Management Systems" standard or corporate standards. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​outside a reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model.

[0109] Taking the battery cooling capacity, the initial battery temperature, and the battery temperature rise rate as inputs, taking the maximum battery temperature as the output, and taking the goal of the highest battery temperature reaching the safety threshold at the end time as the target constraint, a cooling start temperature prediction model is established.

[0110] Using the battery temperature prediction model, predict the battery temperature change curve based on the current battery temperature and the current vehicle route; input the battery temperature change curve into the cooling start temperature prediction model, and take the goal that the battery temperature reaches the safety threshold at the end of the trip to obtain the cooling start temperature and start time of this target trip.

[0111] Send the cooling start temperature and start time to the user. After the user confirms, synchronize it to the vehicle controller to update the cooling start temperature threshold. The recommended method can be set to push on the dashboard of the vehicle, mark the position corresponding to the cooling start temperature and the estimated time on the most likely path between the current position and the target position, and give a prompt sound reminder so that the user can notice.

[0112] Preferably, dynamically adjust the predicted target location according to the route and traffic congestion conditions, calculate the start temperature and start time of this trip in real-time, and update the cooling start temperature threshold of the vehicle controller according to the preset cooling threshold update strategy.

[0113] Preferably, the cooling threshold update includes:

[0114] When the cooling start temperature threshold newly calculated by the cloud is lower than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice ≥t0, then observe n consecutive w cooling start temperature threshold calculation cycles. If the fluctuations of the recommended cooling start temperatures in n [[ID=2二十二]] w cooling start temperature threshold calculation cycles satisfy then update the cooling start temperature threshold of the vehicle controller, otherwise do not update.

[0115] When the cooling start temperature threshold newly calculated by the cloud is lower than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t current -t advice <t0, then take the average value of the cooling start temperatures in ε consecutive cooling start temperature threshold calculation cycles to update the cooling start temperature threshold of the vehicle controller.

[0116] When the cooling start temperature threshold newly calculated by the cloud is higher than the cooling start temperature threshold stored in the vehicle terminal, and the current time from the recommended cooling start time satisfies t [[ID=4十四]] current -t advice ≥t0, then observe n consecutivew For a cooling start temperature threshold calculation period, if n w the recommended cooling start temperature fluctuations for n cooling start temperature threshold calculation periods satisfy then update the cooling start temperature threshold of the vehicle end controller; otherwise, do not update.

[0117] When the latest calculated cooling start temperature threshold by the cloud is higher than the cooling start temperature threshold stored at the vehicle end, and the current time satisfies t current -t advice <t0, do not update the cooling start temperature threshold of the vehicle end controller.

[0118] where t0 is the time required for the temperature to change by a specified temperature during normal vehicle driving, preferably 2°C, and this value is obtained by statistically analyzing the vehicle's historical trip records. t current is the current time, t advice is the recommended time for cooling start, T coolpre (i) is the predicted cooling start temperature value at the i-th moment, n w is t current -t advice ≥t0 is the observation window width (if the sampling period is 10s, preferably more than 10). ε is t current -t advice <t0 is the observation window width (if the sampling period is 10s, preferably 3 or less). δ is the allowable range of fluctuations in the predicted cooling start temperature value within the observation window width, and the value range of this value is determined according to the temperature sampling accuracy, preferably 0.01.

[0119] When the battery temperature reaches the safety threshold at the end of the trip, ensure that the maximum temperature of the power battery is lower than or equal to the safety threshold at the end of this driving cycle of the vehicle (the safety threshold is determined by the battery material system and is higher than the cooling start temperature). There is no need to formulate a cooling exit strategy, which fundamentally eliminates the problem of wasted cooling energy of the power battery and maximally saves the energy of the power battery. At the same time, on the premise of ensuring safety, the battery is maintained in a relatively high temperature range, improving the power performance of the power battery and providing a surging power experience.

[0120] Example 7:

[0121] Refer to Figure 1 , this example is a vehicle power battery thermal management system that uses the method in the above example and includes: a vehicle end execution system, a cloud computing system, and a vehicle-cloud communication system.

[0122] The vehicle-side execution system includes: a data acquisition module, which is used to collect real-time data such as the vehicle's location, time, power battery voltage, current, temperature, etc. during driving; a thermal management execution module, which is used to receive parameters sent from the cloud and execute thermal management strategies to control the battery temperature within a comfortable range.

[0123] The cloud computing system includes: a data cleaning module, which is used to eliminate data that exceeds the threshold range and does not conform to logical changes; a temperature prediction module, which is used to predict battery temperature changes in real time; and a cooling start-up temperature prediction module, which is used to predict the cooling entry temperature and time of the thermal management system during this trip.

[0124] The vehicle-cloud communication system includes: a data upload module, which is used to transfer the collected signals to the cloud big data platform according to specified coding rules.

[0125] Preferably, the vehicle-side execution system also includes a user prompt module for receiving and displaying a cooling start-up temperature recommendation instruction; the cloud computing system also includes a user prompt sending module for sending a cooling start-up temperature recommendation instruction to the user; the vehicle-cloud communication system also includes a user prompt sending module for updating the cooling start-up temperature threshold of the vehicle-side controller.

[0126] This invention eliminates the problem of power battery cooling energy waste, maximizes power battery energy conservation, maintains the battery at a higher temperature range while ensuring safety, improves the power performance of the power battery, and provides a surging power experience.

[0127] The present invention can also dynamically adjust the cooling start temperature threshold according to the user's usage habits.

[0128] For those skilled in the art, any modifications and changes made according to the above-mentioned embodiments of the present invention should be included in the scope of protection of the present invention without departing from the spirit of the present invention.

Claims

1. A vehicle power battery thermal management method, characterized in that include: The vehicle's location, time, power battery voltage, current, and temperature data are collected in real time during driving and uploaded to the cloud. The dynamic data uploaded by the vehicle is cleaned to remove variable values ​​that exceed the reasonable range, obtain battery thermal management parameters, and establish a battery temperature prediction model. The battery temperature prediction model includes the following calculation formula: I(t)≤I max Among them, T pre (t) is the predicted curve of battery temperature changing with time, I(t) is the real-time current, I max is the peak current, P generation (I(t), r i , t) is the real-time heat generation power, m is the number of batteries in the battery pack, M is the mass of the battery, and C is the equivalent specific heat capacity; A cooling start temperature prediction model is established with the battery cooling capacity, battery initial temperature, and battery temperature rise rate as inputs, the battery maximum temperature as output, and the target constraint that the battery maximum temperature reaches the safety threshold at the end time. The establishment of the battery cooling start temperature prediction model includes: The battery's initial temperature, current time, season, and road condition information are input into the battery temperature prediction model. The maximum battery temperature is used as the output, and the optimization goal is to achieve the maximum battery temperature reaching the safety threshold at the end of the cooling process. A cooling start temperature prediction model is established using a neural network or support vector machine algorithm. The actual maximum battery temperature at the end of a user's trip is used as feedback for the cooling start temperature prediction model, and the model parameters are dynamically tuned to continuously improve the cooling start temperature prediction accuracy. Among them, T s is the temperature safety threshold affected by the material system, P cool (L) is the heat dissipation power affected by the cooling water flow rate, t max is the end time of this trip, t cool is the cooling start time, T coolpre is the cooling start temperature; The battery temperature prediction model is used to predict the battery temperature change curve based on the current battery temperature and the vehicle's current route. The battery temperature change curve is input into the cooling start-up temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start-up temperature and start-up time for this target trip are obtained.

2. The vehicle power battery thermal management method according to claim 1, characterized in that: Data cleaning includes cell voltage filtering, voltage default value exclusion, battery module temperature filtering, current value filtering, SOC value filtering, vehicle mileage filtering, integrity filtering and logic filtering.

3. The vehicle power battery thermal management method according to claim 2, characterized in that: Cell voltage filtering deletes voltage data outside the range [0, 5V]. Voltage default value exclusion deletes data with a cell voltage of 0 or the default value. Battery module temperature filtering deletes data outside the range [-40°C, 210°C]. The current value is filtered to delete data outside [-1500A, 1500A]; The SOC value filter deletes data outside [0, 100%]; the vehicle mileage filter deletes data outside [0, 1000000km]; the integrity filter deletes data with missing cell voltage data values; the logic filter deletes data with valid current values, changes in SOC or mileage, but unchanged cell voltage values.

4. The vehicle power battery thermal management method according to claim 1, characterized in that: Battery thermal management parameters include power battery material system, grouping method, number of batteries, peak current and cooling water flow.

5. The vehicle power battery thermal management method according to claim 1, characterized in that: The vehicle route is obtained through the vehicle's current position, current time and target location. The target location is obtained based on the navigation results when the user uses navigation. When the user does not use navigation, the user's travel history is obtained through vehicle historical data, and the frequency of recently frequently used target locations is statistically analyzed to generate a target location set. Based on the frequency of the target locations, the probability of reaching different target locations from the current position is calculated, and a list of possible destinations is generated according to the screening rules, and sorted from high to low according to probability.

6. The vehicle power battery thermal management method according to claim 5, characterized in that: Collect statistics on recent user travel history, analyze the frequency of frequently visited destinations, and analyze the frequency matrix between two destinations. When the user does not use navigation, the specific formula for calculating the probability of reaching different destinations from the current location is as follows: ω+μ=1 Among them, x i is the current position, x k is the target location, f pre (x i →x k ) represents the probability of reaching the target location from the current location, k≤num and k≠i, num is the total number of all possible target locations, Indicates that from x i Arrive at x k The statistical frequency of Represents reaching x from any possible destination k The sum of the frequencies of Indicates that from x i The sum of the frequencies of going to any other possible destinations, represents the sum of the frequencies of reaching all target locations, t represents the three time labels of a day, namely working hours, off-get off work hours and other times, day represents the type label of each day, namely working days and non-working days, and ω represents the target location x k The weight of the probability of being reached, μ represents the distance from the current location x i Departure and arrival at destination x k The weight of the probability.

7. The vehicle power battery thermal management method according to claim 6, characterized in that: Filters used to generate a list of possible destinations include: According to the calculated results of the probability of reaching the target location, the target locations are sorted from high to low to generate a first target location list; the first target location list filters the calculated results of the probability of reaching the target location f pre (x i →x k )≥θ to generate a second target location list, and θ is calibrated according to actual conditions; the second target location list filters the top three target locations to generate a third target location list.

8. The vehicle power battery thermal management method according to claim 7, characterized in that: Battery temperature change curve prediction includes: Based on the target locations in the third target location list, query historical records to determine the most likely path, travel time, road condition information, historical peak current, and SOC change; substituted the above information and the current initial value of the battery temperature into the temperature prediction model to obtain the predicted value of the battery temperature change curve.

9. The vehicle power battery thermal management method according to claim 7, characterized in that: The determination of cooling start temperature and start time includes: The battery temperature change curve corresponding to the target location in the third target location list is input into the cooling start temperature prediction model. With the goal of the battery temperature reaching a safety threshold at the end of the trip, the cooling start temperature and start time of this target trip are obtained.

10. The vehicle power battery thermal management method according to any one of claims 1 to 9, characterized in that: The cooling start temperature and start time are sent to the user. After the user confirms, the cooling start temperature threshold is updated synchronously to the vehicle-side controller.

11. The vehicle power battery thermal management method according to claim 10, characterized in that: The predicted target location is dynamically adjusted according to the route and traffic congestion conditions, the start-up temperature and start-up time of this trip are calculated in real time, and the cooling start-up temperature threshold of the vehicle-side controller is updated according to the preset cooling threshold update strategy.

12. The vehicle power battery thermal management method according to claim 11, characterized in that: Cooldown threshold updates include: When the cooling start temperature threshold calculated by the cloud is lower than the cooling start temperature threshold stored on the vehicle, the current time to the cooling start time meets t current -t advice ≥t0, then observe the continuous n w Cooling start temperature threshold calculation cycle, if n w The cooling start temperature fluctuation of the cooling start temperature threshold calculation cycle meets the but To update the cooling start temperature threshold of the vehicle-side controller, otherwise it will not be updated; When the cooling start temperature threshold calculated by the cloud is lower than the cooling start temperature threshold stored on the vehicle, the current time to the cooling start time meets t current -t advice <t0, then take the average cooling start temperature of the consecutive cooling start temperature threshold calculation cycles Update the cooling start temperature threshold of the vehicle-side controller; When the cooling start temperature threshold calculated by the cloud is higher than the cooling start temperature threshold stored on the vehicle, the current time to the cooling start time meets t current -t advice ≥t0, then observe the continuous n w Cooling start temperature threshold calculation cycle, if n w The cooling start temperature fluctuation of the cooling start temperature threshold calculation cycle meets the but To update the cooling start temperature threshold of the vehicle-side controller, otherwise it will not be updated; When the cooling start temperature threshold newly calculated by the cloud is higher than the cooling start temperature threshold stored in the vehicle, and the current time satisfies t current -t advice <t0, do not update the cooling start temperature threshold of the vehicle controller; Among them, t0 is the time required for the temperature to change to the specified temperature during normal driving of the vehicle. This value is obtained from the historical travel records of the vehicle. current is the current time, t advice is the recommended time for cooling to start, T coolpre (i) is the predicted value of cooling start temperature at time i, n w It is t current -t advice ≥t0 observation window width, ε is t current -t advice <t0 observation window width, δ is the allowable range of fluctuation of the cooling start temperature prediction value within the observation window width, and the value range of this value is determined according to the temperature sampling accuracy.

13. A vehicle power battery thermal management system, characterized in that The method according to any one of claims 1 to 12, comprising: a vehicle-side execution system, a cloud computing system, and a vehicle-cloud communication system; The vehicle-side execution system includes: a data acquisition module for collecting real-time data on the vehicle's location, time, power battery voltage, current, and temperature during driving; a thermal management execution module for receiving parameters sent from the cloud and executing thermal management strategies to control the battery temperature within a comfortable range; The cloud computing system includes: a data cleaning module for eliminating data that exceeds the threshold range or does not conform to logical changes; a temperature prediction module for real-time prediction of battery temperature changes; and a cooling start temperature prediction module for predicting the cooling start temperature and time of the thermal management system during the current trip. The vehicle-cloud communication system includes: a data upload module, which is used to transfer the collected signals to the cloud big data platform according to specified coding rules.

14. The vehicle power battery thermal management system according to claim 13, characterized in that: The vehicle-side execution system also includes a user prompt module for receiving and displaying a cooling start-up temperature recommendation instruction; the cloud computing system also includes a user prompt sending module for sending a cooling start-up temperature recommendation instruction to the user; the vehicle-cloud communication system also includes a user prompt sending module for updating the cooling start-up temperature threshold of the vehicle-side controller.

Images