Methods and systems for monitoring battery pack health status

Abstract

This application provides a method and system for monitoring the health status of a battery pack. The method includes: acquiring the voltage difference between the maximum and minimum voltages of the cells within an electric vehicle battery pack; determining an alarm value based on the voltage difference, wherein the alarm value is a composite value of the following factors: the slope of the average voltage difference of the cells over a past preset time period, the predicted average voltage difference of the cells over a future preset time period, and the minimum voltage difference of the cells; and generating a predictive maintenance notification for the electric vehicle battery pack when the alarm value exceeds a threshold.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle technology, and in particular to a method and system for monitoring the health status of battery packs. Background Technology

[0002] Today, with increasing public concern about environmental issues, more and more people are accepting new energy vehicles (NEVs). NEVs include electric vehicles (EVs), hybrid electric vehicles (HEVs), and plug-in hybrid electric vehicles (PHEVs). NEVs can transmit real-time vehicle data to internet cloud servers for remote monitoring and data collection. Therefore, over time, NEV models have accumulated a vast amount of data. Hidden within this data are valuable clues about the performance and health of NEVs, especially regarding the battery pack, a crucial component of NEVs.

[0003] These valuable data can be used to develop effective methods for monitoring the health status of new energy vehicle battery packs.

[0004] It should be noted that the content disclosed in the background section of this application is only for enhancing the understanding of the background of this application, and is not and should not be construed as an endorsement of prior art known to those skilled in the art or any form of implication. Summary of the Invention

[0005] Embodiments of this application provide a method and system for monitoring the health status of battery packs, aiming to address the problem of how to establish an effective method for monitoring the health status of new energy vehicle battery packs.

[0006] According to one embodiment of this application, a method for monitoring the health status of a battery pack is provided. The method includes: acquiring the voltage difference between the maximum and minimum voltages of cells within an electric vehicle battery pack; determining an alarm value based on the voltage difference, wherein the alarm value is a composite value of the following factors: the slope of the average voltage difference of the cells over a past preset time period, the predicted average voltage difference of the cells over a future preset time period, and the minimum voltage difference of the cells; and generating a predictive maintenance notification for the electric vehicle battery pack when the alarm value is greater than a threshold.

[0007] In an exemplary embodiment, before acquiring the voltage difference between the maximum and minimum voltages among the cells in the electric vehicle battery pack, the method further includes: reporting voltage-related data of each cell in the electric vehicle battery pack via onboard sensors and / or the CAN bus of the electric vehicle.

[0008] In an exemplary embodiment, calculating the alarm value based on the voltage difference includes: analyzing the time series of voltage-related data of each cell in the battery pack through a cloud-based server or in-vehicle computing device to obtain the alarm value.

[0009] In an exemplary embodiment, the alarm value is a weighted average of the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell.

[0010] In an exemplary embodiment, the alarm value L within a given time period d The calculation formula is as follows:

[0011] L d =W1*L1+W2*L2+W3*L3, W1+W2+W3=1;

[0012] Wherein, L1, L2, and L3 represent the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell, respectively; W1, W2, and W3 are the non-negative weighting coefficients of L1, L2, and L3, respectively.

[0013] In the exemplary embodiment, W1, W2, and W3 are determined according to the type of battery pack.

[0014] In an exemplary embodiment, the method further includes: based on the alarm value L d Obtain the current alarm value, wherein the current alarm value is a weighted average of alarm values ​​over a preset number of time periods.

[0015] In an exemplary embodiment, the current alarm value L p The calculation formula is as follows:

[0016]

[0017] Where N represents the number of sampling periods contained in the backtracking window, w n This represents the weighting coefficient for the Nth sampling period.

[0018] In an exemplary embodiment, the method further includes: optimizing the threshold based on whether the electric vehicle battery pack currently has error reports or not.

[0019] In an exemplary embodiment, after generating a predictive maintenance notification for the electric vehicle battery pack when the alarm value is greater than a threshold, the method further includes: sending the predictive maintenance notification to a designated terminal.

[0020] According to another embodiment of this application, a system for monitoring the health status of a battery pack is provided. The system includes: an acquisition module for acquiring the voltage difference between the maximum and minimum voltages of cells within an electric vehicle battery pack; a calculation module for calculating an alarm value based on the voltage difference, wherein the alarm value is a composite value of the following factors: the slope of the average voltage difference between cells over a past preset time period, the predicted average voltage difference between cells over a future preset time period, and the minimum voltage difference between cells; and a generation module for generating a predictive maintenance notification for the electric vehicle battery pack when the alarm value exceeds a threshold.

[0021] In an exemplary embodiment, the alarm value is a weighted average of the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell.

[0022] In an exemplary embodiment, the alarm value L within a given time period d The calculation formula is as follows:

[0023] L d =W1*L1+W2*L2+W3*L3, W1+W2+W3=1;

[0024] Wherein, L1, L2, and L3 represent the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell, respectively; W1, W2, and W3 are the non-negative weighting coefficients of L1, L2, and L3, respectively.

[0025] In the exemplary embodiment, W1, W2, and W3 are determined according to the type of battery pack.

[0026] In an exemplary embodiment, the acquisition module further includes: based on the alarm value L d Obtain the current alarm value, wherein the current alarm value is a weighted average of alarm values ​​over a preset number of time periods.

[0027] In an exemplary embodiment, the current alarm value L p The calculation formula is as follows:

[0028]

[0029] Where N represents the number of sampling periods contained in the backtracking window, w n This represents the weighting coefficient for the Nth sampling period.

[0030] In an exemplary embodiment, the system further includes an optimization module for optimizing the threshold based on whether the electric vehicle battery pack currently has error reports or not.

[0031] In an exemplary embodiment, the system further includes a sending module for sending the predictive maintenance notification to a designated terminal.

[0032] According to one embodiment of this application, a non-volatile computer-readable storage medium is provided, which stores a program that, when executed by a computer, implements the method steps described in the above embodiment.

[0033] According to one embodiment of this application, an electric vehicle is provided. The electric vehicle includes the system described in the above embodiments for monitoring the health status of a battery pack.

[0034] The embodiments described above in this application obtain alarm values ​​by analyzing relevant voltage difference data of the battery pack. Based on these alarm values, various degradation trends of abnormal battery packs can be detected, providing early warnings for original equipment manufacturers, distributors, and end customers. Furthermore, distributors can perform troubleshooting and predictive maintenance as needed to extend battery life and reduce warranty costs. Attached Figure Description

[0035] The accompanying drawings described herein provide a further understanding of this application and form part of this application. The illustrative embodiments and descriptions of this application are for illustrative purposes only and are not intended to limit the scope of this application.

[0036] Figure 1 This is a flowchart of a method for monitoring the health status of a battery pack according to an embodiment of this application;

[0037] Figure 2 This is a flowchart of a method for monitoring the health status of a battery pack according to another embodiment of this application;

[0038] Figure 3 This is a schematic diagram comparing the alarm distribution between error reporting groups and non-error reporting groups according to an embodiment of this application;

[0039] Figure 4 The ROC curve of the alarm model provided according to an embodiment of this application;

[0040] Figure 5 This is a structural block diagram of a system for monitoring the health status of a battery pack according to an embodiment of this application;

[0041] Figure 6 This is a structural block diagram of a system for monitoring the health status of a battery pack, according to another embodiment of this application;

[0042] Figure 7 This is a structural block diagram of an electric vehicle provided according to an embodiment of this application. Detailed Implementation

[0043] The present application will now be described in detail with reference to the accompanying drawings and embodiments. It should be understood that the preferred embodiments described below are for illustration and explanation only and are not intended to limit the present invention.

[0044] Example 1

[0045] To establish an effective battery pack health monitoring method, this embodiment provides a data-driven battery pack health monitoring method based on the voltage-related data of each cell within the battery pack. For example... Figure 1 As shown, the method includes the following steps.

[0046] Step S102: Obtain the voltage difference between the maximum and minimum voltages between the cells in the electric vehicle battery pack.

[0047] Step S104: Calculate the alarm value based on the voltage difference, wherein the alarm value is a comprehensive value of the following factors: the slope of the average voltage difference of the cell in the past preset time period, the predicted average voltage difference of the cell in the future preset time period, and the minimum voltage difference of the cell.

[0048] Step S106: When the alarm value is greater than the threshold, generate a predictive maintenance notification for the electric vehicle battery pack.

[0049] After the above steps, the relevant voltage difference data of the battery pack is analyzed to obtain alarm values. Based on these alarm values, various degradation trends of abnormal battery packs can be detected, providing early warnings for original equipment manufacturers, distributors, and end customers. Furthermore, distributors can perform troubleshooting and predictive maintenance as needed to extend battery life and reduce warranty costs.

[0050] In an exemplary embodiment, prior to step S102, the method may further include the following step: reporting voltage-related data of each cell in the electric vehicle battery pack via on-board sensors and / or the CAN bus of the electric vehicle.

[0051] For example, voltage sensors connected to each battery cell can be used to measure the battery voltage. This allows measurements to be taken while the vehicle is in use. The reliability of the data measured by the voltage sensors can be further improved by measuring the battery voltage in real time for one or more seconds within a preset sampling period.

[0052] In an exemplary embodiment, step S104 may further include the following steps: analyzing the time series of voltage-related data of each cell in the battery pack through a cloud-based server or in-vehicle computing device to obtain an alarm value.

[0053] In an exemplary embodiment, the alarm value is a weighted average of the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within a preset future time period, and the minimum voltage difference of the battery cell.

[0054] In an exemplary embodiment, the method further includes the following step: obtaining a current alarm value based on an alarm value, wherein the current alarm value is a weighted average of alarm values ​​over a preset number of time periods.

[0055] In an exemplary embodiment, the method further includes the step of optimizing a threshold based on whether the electric vehicle battery pack currently has error reports or not.

[0056] In an exemplary embodiment, after step S106, the method further includes the step of sending a predictive maintenance notification to a designated terminal.

[0057] Example 2

[0058] This embodiment provides an alarm model. The alarm model can be used to analyze relevant data stored in a cloud server and generate predictive maintenance automatic notifications for battery packs of different types of new energy vehicles (e.g., electric vehicles, hybrid vehicles, plug-in hybrid vehicles, etc.). Battery life can be extended for a better user experience, and warranty costs can be significantly reduced if troubleshooting and predictive maintenance are performed immediately after an early warning notification is issued. The method provided in this application achieves the highest level of predictive maintenance and user satisfaction, avoiding the poor user experience and high warranty costs associated with passive maintenance.

[0059] Figure 2 A flowchart of an example of this application is shown. It should be noted that... Figure 2 The method shown applies to all types of new energy vehicles; the plug-in hybrid electric vehicle (PHEV) here is just an example. Figure 2 As shown, the process includes the following steps.

[0060] In step S202, based on historical data analysis of the time series of individual cell voltages of a plug-in hybrid electric vehicle (which has reported multiple battery pack failures), the difference between the maximum and minimum voltages between cells within the battery pack is an important indicator for determining the health status of the battery pack.

[0061] For a battery pack to function properly, the voltage difference between the cells must generally be kept within a very small range. When the voltage difference between the cells continues to increase, abnormal degradation of the battery pack can be observed in some vehicles, and the battery capacity may decrease abnormally. It has been shown that abnormal degradation trends in the battery pack can be corrected through BMS software updates and subsequent regular charging.

[0062] In step S204, based on the above observations, the daily alarm value L can be determined according to the statistical data of the daily voltage difference between the battery cells of each vehicle during driving. d It is the combined value of the following three factors.

[0063] The first factor is the slope of the daily average voltage difference between cells over a certain period. For example, this slope could be a time series trend of the daily average voltage difference between cells over the past 30 days.

[0064] The second factor is the prediction of the future daily average voltage difference between cells based on the current inter-cell voltage difference and the time series trend. For example, the daily average voltage difference between cells in the next 30 days can be predicted based on the current inter-cell voltage difference and the time series trend of the inter-cell voltage difference over the past 30 days.

[0065] The third factor is the minimum daily voltage difference between cells. Multiple daily voltage differences between cells can be measured and collected, from which the minimum daily voltage difference between cells can be selected.

[0066] It should be noted that in this embodiment, "daily" is just an example and not a limitation. It can be other time periods, such as every hour, every N hours, or every N days.

[0067] In this embodiment, different thresholds can be defined for the above three factors according to the needs of different vehicle battery types, and the ratio between the actual value and the threshold can be defined as different alarm factors, namely L1, L2, and L3. For example, the daily alarm value L d It can be determined by the weighted average of the three alarm factors mentioned above, and the calculation formula is as follows:

[0068] L d =w1*L1+w2*L2+w3*L3 (1)

[0069] w1+w2+w3=1 (2)

[0070] In step S206, for each type of vehicle, its current alarm value L p This can be determined by a normalized weighted average of daily alert values ​​over a period of time (e.g., the last N days). For example, the last day has a weight of 1, and the weight decays exponentially in the days preceding the last day. For example, the current alert value L... p It can be determined according to the following formula:

[0071]

[0072] In step S208, all vehicles that have driven in the past N days can be ranked according to the current alarm value. Alarm values ​​that are higher than a certain threshold can be identified as emergency warnings, and dealers are advised to pay attention and maintain them immediately.

[0073] The alarm model results provided in this embodiment are verified by battery pack error reports. The alarm value for the day the user reports a battery pack failure to the dealer can be calculated and compared with the current alarm values ​​of all active vehicles.

[0074] Figure 3 This is a diagram comparing the distribution of alarm values ​​between groups with and without error reports. For example... Figure 3 As shown, for the PHEV studied, the alarm value distribution is significantly different between vehicles with and without error reports. For vehicles with error reports, the median alarm value is approximately 1. For vehicles without error reports, the median alarm value is approximately 0.25.

[0075] according to Figure 3 The results show that 0.5 can be defined as the threshold between the normal alarm group and the abnormal alarm group. The corresponding alarm model has a true positive rate of 83%, a false negative rate of 17%, and a false positive rate of 22%.

[0076] When the thresholds for the normal group and the abnormal group are different, different true positive rates and false positive rates are obtained, and the resulting ROC curves are as follows: Figure 4 As shown, an area under the ROC curve (AUC) > 0.8 indicates that the alarm model is effective.

[0077] In this embodiment, the weights in formulas (1) and (2) were trained and optimized. The same applies to the weights in the attenuation scheme formula (3). In one embodiment, parameters are selected based on training data from vehicles with and without error reports to maximize the AUC value.

[0078] Through the description of the above operating modes, those skilled in the art will clearly understand that the methods in the embodiments can be implemented by combining software and the required general-purpose hardware platform, or of course, by hardware. However, in many cases, the former is the preferred implementation method. Based on this understanding, the technical solutions of this application that are substantially beneficial to conventional technology can be embodied in the form of a software product. This computer software product is stored in a storage medium (e.g., read-only memory / random access memory, disk, and optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, computer, server, network device, etc.) to execute the methods in the various embodiments of this application.

[0079] Example 3

[0080] This embodiment further provides a system for monitoring the health status of a battery pack. This system can be applied to cloud-based servers or in-vehicle computing devices to implement the above embodiments in a preferred manner. Further details are omitted here. For example, the term "module" below can refer to a combination of software and / or hardware that implements a specific function. The devices described in the following embodiments are preferably implemented by software, but can also be implemented by hardware or a combination of software and hardware.

[0081] Figure 5 This is a structural block diagram of a system for monitoring the health status of a battery pack, according to an embodiment of this application. Figure 5 As shown, system 100 includes:

[0082] The acquisition module 10 is used to acquire the voltage difference between the maximum and minimum voltages between the cells in the battery pack of an electric vehicle.

[0083] The calculation module 20 is used to calculate an alarm value based on the voltage difference, wherein the alarm value is a comprehensive value of the following factors: the slope of the average voltage difference of the cells in the past preset time period, the predicted average voltage difference of the cells in the future preset time period, and the minimum voltage difference of the cells.

[0084] The generation module 30 is used to generate a predictive maintenance notification for the electric vehicle battery pack when the alarm value is greater than the threshold.

[0085] Figure 6 This is another structural block diagram of a system for monitoring the health status of a battery pack, according to an embodiment of this application.

[0086] like Figure 6 As shown, the system also includes:

[0087] Optimization module 40 is used to optimize the threshold based on whether the electric vehicle battery pack currently has error reports or not.

[0088] The sending module 50 is used to send predictive maintenance notifications to designated terminals.

[0089] In this embodiment, the system can be implemented in a cloud-based server or onboard computing device. It can analyze time series data provided by onboard sensors and / or the CAN bus to identify all vehicles exhibiting unhealthy degradation trends and generate automatic predictive maintenance warnings for battery packs of different types of new energy vehicles (such as EVs, HEVs, PHEVs, etc.). It ensures that all actively operating battery packs operate within a healthy voltage differential range and detects any potential imbalances or unhealthy degradation trends in the battery packs at an early stage. Once a reasonable vehicle warning threshold is determined, "maintenance required" warnings can be sent directly to the original equipment manufacturer (OEM), dealers, and users in various ways to facilitate early troubleshooting and predictive maintenance, thereby extending battery life and reducing warranty costs for OEMs.

[0090] Example 4

[0091] According to this embodiment, a non-volatile computer-readable storage medium is provided, which stores a program that, when executed by a computer, performs the following steps.

[0092] Step S1: Obtain the voltage difference between the maximum and minimum voltages between the cells in the electric vehicle battery pack.

[0093] Step S2: Calculate the alarm value based on the voltage difference, where the alarm value is a comprehensive value of the following factors: the slope of the average voltage difference of the cell in the past preset time period, the predicted average voltage difference of the cell in the future preset time period, and the minimum voltage difference of the cell.

[0094] Step S3: When the alarm value is greater than the threshold, generate a predictive maintenance notification for the electric vehicle battery pack.

[0095] In exemplary embodiments, the storage medium includes, but is not limited to, various media capable of storing program code, such as a USB flash drive, read-only memory, random access memory, portable hard drive, magnetic disk, or optical disk.

[0096] Example 5

[0097] According to this embodiment, an electric vehicle is provided. For example... Figure 7 As shown, the electric vehicle includes the system for monitoring the health status of the battery pack described in the above embodiments. It should be noted that the electric vehicle in this embodiment can be different types of new energy vehicles (NEVs), such as electric vehicles (EVs), hybrid electric vehicles (HEVs), plug-in hybrid electric vehicles (PHEVs), etc.

[0098] In this embodiment, the system can analyze relevant data from the battery pack provided by onboard sensors and / or the CAN bus, and identify all vehicles exhibiting any unhealthy degradation trends, generating automatic predictive maintenance warnings for the new energy vehicle battery packs. It ensures that all actively operating battery packs operate within a healthy voltage differential range and detects any potential imbalances or unhealthy degradation trends in the battery packs at an early stage. Once reasonable vehicle warning thresholds are determined, warnings can be sent directly to the original equipment manufacturer (OEM), dealers, and users in various ways to facilitate early troubleshooting and predictive maintenance, thereby extending battery life and reducing OEM warranty costs.

[0099] Obviously, those skilled in the art will understand that the various modules or steps of this application can be executed by general-purpose computer devices. These modules or steps can be centralized on a single computer device or distributed across a network of multiple computer devices, and in one embodiment, they can be implemented by computer-executable program code. Therefore, the module or step can be stored in a storage device for execution by a computer device. In some cases, the steps shown or described may be executed in a different order than those described herein, or they may each form a separate integrated circuit module, or multiple modules or steps may form a single integrated circuit module for execution. Therefore, this application is not limited to any particular combination of hardware and software.

[0100] The above are merely exemplary embodiments of this application and are not intended to limit this application. Those skilled in the art will recognize that this application can be modified and varied in many ways. All modifications, equivalent substitutions, and improvements made in accordance with the spirit and principles of this application should be understood as falling within the protection scope of this application.

Claims

1. A method for monitoring the health status of a battery pack, characterized in that, include: Obtain the voltage difference between the maximum and minimum voltages between the cells in the battery pack of an electric vehicle; An alarm value is calculated based on the voltage difference, wherein the alarm value is a weighted average of the slope of the average voltage difference of the cell, the predicted average voltage difference of the cell within a preset time period, and the minimum voltage difference of the cell. When the alarm value is greater than the threshold, a predictive maintenance notification is generated for the electric vehicle battery pack.

2. The method according to claim 1, further comprising, before obtaining the voltage difference between the maximum and minimum voltages between the cells in the electric vehicle battery pack: The voltage-related data of each cell in the electric vehicle's battery pack are reported via the vehicle's onboard sensors and / or CAN bus.

3. The method according to claim 1, characterized in that, The calculation of the alarm value based on the voltage difference includes: Alarm values ​​are obtained by analyzing the time series of voltage-related data of each cell in the battery pack using cloud-based servers or in-vehicle computing devices.

4. The method according to claim 1, characterized in that, The alarm value L within a given time period d The calculation formula is as follows: L d = W1 * L1 + W2 * L2 + W3 * L3, W1 + W2 + W3 = 1; Wherein, L1, L2, and L3 represent the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell, respectively; W1, W2, and W3 are the non-negative weighting coefficients of L1, L2, and L3, respectively.

5. The method according to claim 4, characterized in that, The weighting coefficients W1, W2, and W3 are determined based on the type of battery pack.

6. The method according to claim 1, characterized in that, Also includes: Based on the alarm value L d Obtain the current alarm value, wherein the current alarm value is a weighted average of alarm values ​​over a preset number of time periods.

7. The method according to claim 6, characterized in that, The current alarm value L p The calculation formula is as follows: Where N represents the number of sampling periods contained in the backtracking window, w n This represents the weighting coefficient for the Nth sampling period.

8. The method according to claim 1, characterized in that, Also includes: The threshold is optimized based on whether the electric vehicle battery pack currently has error reports or not.

9. The method according to claim 1, characterized in that, It also includes the step of generating a predictive maintenance notification for the electric vehicle battery pack when the alarm value is greater than a threshold. Send the predictive maintenance notification to the designated terminal.

10. A system for monitoring the health status of a battery pack, comprising: The acquisition module is used to acquire the voltage difference between the maximum and minimum voltages between the cells in the battery pack of an electric vehicle. The calculation module is used to calculate the alarm value based on the voltage difference, wherein, The alarm value is a weighted average of the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within a preset time period, and the minimum voltage difference of the battery cell. A generation module is used to generate a predictive maintenance notification for the electric vehicle battery pack when the alarm value is greater than a threshold.

11. The system according to claim 10, characterized in that, The alarm value L within a given time period d The calculation formula is as follows: L d = W1 * L1 + W2 * L2 + W3 * L3, W1 + W2 + W3 = 1; Wherein, L1, L2, and L3 represent the slope of the average voltage difference of the battery cell, the predicted average voltage difference of the battery cell within the future preset time period, and the minimum voltage difference of the battery cell, respectively; W1, W2, and W3 are the non-negative weighting coefficients of L1, L2, and L3, respectively.

12. The system according to claim 11, characterized in that, The weighting coefficients W1, W2, and W3 are determined based on the type of battery pack.

13. The system according to claim 10, characterized in that, The acquisition module is also used for: Based on the alarm value L d Obtain the current alarm value, wherein the current alarm value is a weighted average of alarm values ​​over a preset number of time periods.

14. The system according to claim 13, characterized in that, The current alarm value L p The calculation formula is as follows: Where N represents the number of sampling periods contained in the backtracking window, w n This represents the weighting coefficient for the Nth sampling period.

15. The system according to claim 10, characterized in that, Also includes: An optimization module is used to optimize the threshold based on whether the electric vehicle battery pack currently has error reports or not.

16. The system according to claim 10, characterized in that, Also includes: The sending module is used to send the predictive maintenance notification to the designated terminal.

17. A non-volatile computer-readable storage medium, characterized in that, The non-volatile computer-readable storage medium stores a program that, when executed by a computer, implements the method as described in claim 1.

18. An electric vehicle, characterized in that, Including the system as described in claim 10.

Images