Vehicle battery cell consistency risk prediction method and device, medium and product

Abstract

The invention provides a vehicle battery cell consistency risk prediction method and device, a medium and a product, and relates to the technical field of new energy vehicles. The method comprises the following steps: acquiring state parameter data of a single battery in a vehicle battery pack; performing data processing on the state parameter data to obtain first outlier data of the single batteries; according to the first outlier data, determining an outlier trend of the single battery in the recent set duration; and according to the outlier trend, predicting the consistency risk of the single battery and other batteries in the vehicle battery pack. Through the method, the consistency risk of the single battery and other batteries in the vehicle battery pack can be predicted, and the driving safety of a user is improved.

Description

Technical Field

[0001] The present application relates to the technical field of new energy vehicles, and in particular to a method, device, medium and product for predicting the consistency risk of vehicle battery cells. Background Art

[0002] The rapid development of new energy vehicles has made power battery technology a core area of ​​concern in the industry. In the power battery system, the consistency of battery cells directly affects the performance and life of the entire power battery system. When there are large performance differences between single cells, it will not only accelerate the aging of the battery pack and reduce the overall efficiency, but also increase safety hazards. Especially when the performance of individual single battery cells gradually deteriorates, it may lead to occasional failures, further increasing the risk of power battery fires. Therefore, how to predict the consistency risk of battery cells has become a key research direction for power battery safety technology.

[0003] At present, the vehicle-side battery management system (BMS) is usually used to monitor the status parameter data of the single battery in real time, such as voltage data and temperature data, to detect the consistency risk of the battery cell. Specifically, when the voltage or temperature of a single battery exceeds the preset threshold, the BMS will trigger an alarm signal to prompt the user that the battery has a consistency problem and needs to be inspected and repaired. However, this threshold-based alarm method is only applicable to situations where consistency risks have already appeared.

[0004] Therefore, there is an urgent need to provide a vehicle battery cell consistency risk prediction method to achieve early prediction of consistency risk and improve driving safety. Summary of the invention

[0005] The present application provides a vehicle battery cell consistency risk prediction method, equipment, medium and product to achieve early prediction of consistency risk and improve driving safety.

[0006] In a first aspect, the present application provides a vehicle battery cell consistency risk prediction method, comprising:

[0007] Obtaining status parameter data of single cells in a vehicle battery pack;

[0008] Performing data processing on the state parameter data to obtain first outlier data of the single battery;

[0009] Determine, based on the first outlier data, an outlier trend of the single battery within a recent set time period;

[0010] Based on outlier trends, predict the consistency risk of individual batteries and other batteries in the vehicle battery pack.

[0011] In a possible implementation, predicting the consistency risk of a single battery and other batteries in a vehicle battery pack according to the outlier trend includes:

[0012] Based on the outlier trend, determining second outlier data corresponding to the single battery with a relative outlier trend;

[0013] Based on the second outlier data, a consistency risk between the single battery and other batteries in the vehicle battery pack is determined.

[0014] In a possible implementation, determining second outlier data corresponding to a single battery with a relative outlier trend based on the outlier trend includes:

[0015] The outlier trend is input into the fitting prediction model to obtain the second outlier data of the relative outlier trend corresponding to the single battery. The fitting prediction model is used to capture the dynamic characteristics of the outlier trend and predict the outlier data of the relative outlier trend based on the dynamic characteristics.

[0016] In a possible implementation manner, the second outlier data includes multiple values ​​at different times, and determining the consistency risk between the single battery and other batteries in the vehicle battery pack according to the second outlier data includes:

[0017] Determine the rate of change of the values ​​of the second outlier data corresponding to adjacent moments;

[0018] If the rate of change is greater than or equal to the change threshold, determining whether the single battery has a charging behavior within a preset time period;

[0019] If there is charging behavior within the preset time period, determining that the change rate greater than or equal to the change threshold is an effective change rate;

[0020] Determine third outlier data corresponding to the effective change rate in the second outlier data;

[0021] Based on the third outlier data, a consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is determined.

[0022] In a possible implementation, determining the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack according to the third outlier data includes:

[0023] Obtain the duration of the effective change rate of the third outlier data;

[0024] An effective change rate whose duration is greater than or equal to the duration threshold is determined as an abnormal change rate;

[0025] Determine fourth outlier data corresponding to the abnormal change rate in the third outlier data;

[0026] Based on the fourth outlier data, a consistency risk prediction of the single battery and other batteries in the vehicle battery pack is determined.

[0027] In a possible implementation, determining the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack based on the fourth outlier data includes:

[0028] Based on the fourth outlier data, determining risk information of a single battery corresponding to the fourth outlier data that is greater than or equal to the outlier threshold;

[0029] Based on the risk information, determine the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack.

[0030] In a possible implementation, it further includes:

[0031] Output risk information;

[0032] And / or, output the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack.

[0033] In a possible implementation, obtaining state parameter data of a single battery in a vehicle battery pack includes:

[0034] Obtaining initial state parameter data of single cells in a vehicle battery pack;

[0035] The initial state parameter data is cleaned to obtain the state parameter data.

[0036] In a possible implementation, predicting the consistency risk of a single battery and other batteries in a vehicle battery pack according to the outlier trend includes:

[0037] The outlier trend is input into the filter, and the outlier trend is filtered to obtain filtered data;

[0038] During the filtering process, the phase response of the filter is analyzed to determine the nonlinear phase delay introduced by the filter;

[0039] Applying a compensation algorithm to phase compensate the filtered data to eliminate the nonlinear phase delay introduced by the filter and obtain the compensated outlier trend;

[0040] Predict the consistency risk of a single battery cell and other batteries in the vehicle battery pack based on compensated outlier trends.

[0041] In a second aspect, the present application provides a vehicle battery cell consistency risk prediction device, comprising:

[0042] An acquisition module, used to acquire state parameter data of a single battery in a vehicle battery pack;

[0043] A processing module, used for performing data processing on the state parameter data to obtain first outlier data of the single battery;

[0044] A determination module, used to determine the outlier trend of the single battery within a recent set time period according to the first outlier data;

[0045] The prediction module is used to predict the consistency risk of a single battery and other batteries in a vehicle battery pack based on the outlier trend.

[0046] In a possible implementation, the prediction module is specifically used for:

[0047] Based on the outlier trend, determining second outlier data corresponding to the single battery with a relative outlier trend;

[0048] Based on the second outlier data, a consistency risk between the single battery and other batteries in the vehicle battery pack is determined.

[0049] In a possible implementation manner, the determination module is specifically configured to:

[0050] The outlier trend is input into the fitting prediction model to obtain the second outlier data of the relative outlier trend corresponding to the single battery. The fitting prediction model is used to capture the dynamic characteristics of the outlier trend and predict the outlier data of the relative outlier trend based on the dynamic characteristics.

[0051] In a possible implementation, the second outlier data includes multiple values ​​at different times, and the determination module is specifically configured to:

[0052] Determine the rate of change of the values ​​of the second outlier data corresponding to adjacent moments;

[0053] If the rate of change is greater than or equal to the change threshold, determining whether the single battery has a charging behavior within a preset time period;

[0054] If there is charging behavior within the preset time period, determining that the change rate greater than or equal to the change threshold is an effective change rate;

[0055] Determine third outlier data corresponding to the effective change rate in the second outlier data;

[0056] Based on the third outlier data, a consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is determined.

[0057] In a possible implementation manner, the processing module is specifically used for:

[0058] Obtain the duration of the effective change rate of the third outlier data;

[0059] An effective change rate whose duration is greater than or equal to the duration threshold is determined as an abnormal change rate;

[0060] Determine fourth outlier data corresponding to the abnormal change rate in the third outlier data;

[0061] Based on the fourth outlier data, a consistency risk prediction of the single battery and other batteries in the vehicle battery pack is determined.

[0062] In a possible implementation manner, the processing module is specifically used for:

[0063] Based on the fourth outlier data, determining risk information of a single battery corresponding to the fourth outlier data that is greater than or equal to the outlier threshold;

[0064] Based on the risk information, the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is obtained.

[0065] In a possible implementation manner, the processing module is further configured to:

[0066] Output risk information;

[0067] And / or, output the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack.

[0068] In a possible implementation, the acquisition module is used to:

[0069] Obtaining initial state parameter data of single cells in a vehicle battery pack;

[0070] The initial state parameter data is cleaned to obtain the state parameter data.

[0071] In a possible implementation, the prediction module is specifically used for:

[0072] The outlier trend is input into the filter, and the outlier trend is filtered to obtain filtered data;

[0073] During the filtering process, the phase response of the filter is analyzed to determine the nonlinear phase delay introduced by the filter;

[0074] Applying a compensation algorithm to phase compensate the filtered data to eliminate the nonlinear phase delay introduced by the filter and obtain the compensated outlier trend;

[0075] Predict the consistency risk of a single battery cell and other batteries in the vehicle battery pack based on compensated outlier trends.

[0076] In a third aspect, the present application provides an electronic device, including: a memory, a processor;

[0077] Memory stores computer-executable instructions;

[0078] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0079] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the above first aspect and / or various possible implementations of the first aspect.

[0080] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed, implements the above first aspect and / or various possible implementations of the first aspect.

[0081] The vehicle battery cell consistency risk prediction method, device, medium and product provided in the present application relate to the field of new energy vehicle technology. The present application includes: obtaining the state parameter data of the single cell in the vehicle battery pack; performing data processing on the state parameter data to obtain the first outlier data of the single cell; determining the outlier trend of the single cell within the most recent set time according to the first outlier data; predicting the consistency risk of the single cell and other batteries in the vehicle battery pack according to the outlier trend. The present application determines the outlier data of the single cell, i.e., the first outlier data, by analyzing the state parameter data of the single cell in the vehicle battery pack, wherein the outlier data usually represents the outlier value in the battery state parameter data, and by analyzing these outliers, it is possible to determine the outlier trend of the single cell within the most recent set time; according to the outlier trend, it is possible to accurately predict the outlier data of the single cell in the future, thereby realizing the prediction of the consistency risk of the single cell and other batteries in the vehicle battery pack and improving the driving safety of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0083] Figure 1 Schematic diagram of the process of vehicle battery cell consistency risk prediction method provided in this application Figure 1 ;

[0084] Figure 2 A schematic diagram of an outlier trend curve provided in an embodiment of the present application;

[0085] Figure 3 A schematic diagram of determining problematic batteries based on rules provided in an embodiment of the present application;

[0086] Figure 4 An example diagram of a daily average secondary outlier change curve of a single cell voltage provided in an embodiment of the present application;

[0087] Figure 5 A schematic diagram of a battery cell consistency risk warning query interface provided in an embodiment of the present application;

[0088] Figure 6 The interface for querying the extreme values ​​of the single cell voltage and probe temperature provided in the embodiment of the present application;

[0089] Figure 7 A schematic diagram of the structure of a vehicle battery cell consistency risk prediction device provided in this application;

[0090] Figure 8 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0091] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0092] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0093] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0094] At present, the consistency risk prediction method of vehicle battery cells usually monitors the data of single cells, temperature, etc. in real time through the battery management system. Once the above data is detected to exceed the threshold, an alarm message is output. When the alarm message is found, the consistency failure is already serious and requires immediate maintenance. This method is only applicable to situations where consistency risks have already appeared, and the ability to achieve early prediction of consistency risks is limited.

[0095] In response to the above problems, an embodiment of the present application provides a method for predicting the consistency risk of vehicle battery cells. By analyzing the status parameter data of the single cells in the vehicle battery pack, the outlier data of the single cells are determined. For the convenience of distinction, they are called "first outlier data". By analyzing these first outlier data, the outlier trend of the single cells within the most recent set time period can be determined; based on the outlier trend, the future outlier data of the single cells can be accurately predicted, thereby realizing the prediction of the consistency risk of the single cells and other batteries in the vehicle battery pack, thereby improving user driving safety.

[0096] Figure 1 Schematic diagram of the process of vehicle battery cell consistency risk prediction method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0097] S101, obtaining status parameter data of single cells in a vehicle battery pack.

[0098] Among them, the state parameter data refers to the key indicators used to evaluate the performance and safety of the single battery in the vehicle battery pack. For example, the state parameter data includes but is not limited to: the maximum value of the battery single voltage, the minimum value of the battery single voltage, the list of battery single voltage values, the maximum value of the battery probe temperature, the minimum value of the battery probe temperature, the list of battery probe temperature values, and the remaining power of the single battery (State of Charge, referred to as SOC). For detailed information on the specific state parameter data, please refer to Table 1.

[0099] Furthermore, in the prior art, the GB / T 32960 data uploaded by the vehicle terminal is monitored and threshold analyzed, but the threshold analysis depends on the quality status of the state parameter data. When the state parameter data is abnormal, invalid, etc., the state parameter data will be inaccurate. Therefore, the state parameter data obtained in the embodiment of the present application can be processed data. Specifically, the state parameter data of the single cell in the vehicle battery pack is obtained, including: obtaining the initial state parameter data of the single cell in the vehicle battery pack; and performing data cleaning on the initial state parameter data to obtain the state parameter data. Among them, data cleaning aims to improve the quality and reliability of the state parameter data by detecting, correcting or deleting errors or irrelevant information in the state parameter data.

[0100] This means that in this example, invalid data needs to be identified from the complex initial state parameter data and removed from the initial state parameter data to improve the availability of the state parameter data. This example avoids the quality problems of the original initial state parameter data by selecting appropriate data fragments from the initial parameter data of the vehicle's entire life cycle, and will not be affected by abnormal individual frame data, which can improve the accuracy of the vehicle battery cell consistency risk prediction method.

[0101] Table 1 Status parameter data

[0102]

[0103] S102 , performing data processing on the state parameter data to obtain first outlier data of the single cell.

[0104] Data processing is performed on the state parameter data acquired in S101 to identify first outlier data of the single battery, that is, by analyzing the state parameter data, outliers that deviate significantly from normal data distribution are found.

[0105] Optionally, a statistical method or a machine learning algorithm is used to analyze the acquired state parameter data to identify abnormal values ​​that deviate significantly from normal data distribution, namely, first outlier data.

[0106] S103 . Determine the outlier trend of the single battery within a recent set time period according to the first outlier data.

[0107] After the first outlier data is determined, it is necessary to analyze the first outlier data to further identify the change pattern or development direction of the first outlier data, so as to determine the outlier trend of the single cell within the most recent set time period.

[0108] The outlier trend is used to evaluate the variation pattern of the first outlier data deviating from the normal range or average level within the recent set time period. The expression form of the outlier trend can be selected according to the actual situation, for example, by using a curve to display the outlier trend. Figure 2 Schematic diagram of an outlier trend curve provided in the embodiment of the present application. Figure 2 It can be seen that the curve shows whether the status parameter data of the single cell exceeds the specified threshold and whether the outlier data gradually increases. The risk of single cell consistency failure can be judged and predicted based on the above information, and early warning can be made based on the predicted risk.

[0109] The existing early warning technologies are based on the threshold judgment of the status parameter data of the single battery reported in real time by the vehicle end, and the rule logic is relatively simple, and only trigger alarms can be performed. When an alarm occurs, the single battery has already experienced a relatively serious single consistency failure, causing losses to after-sales maintenance.

[0110] Therefore, in some embodiments, the consistency risk of a single cell and other cells in the vehicle battery pack can be predicted by outlier trends, so that when a single cell is about to have a consistency failure, it can be repaired in advance to avoid a more serious failure of the single cell. For the specific principle, see step S104.

[0111] S104. Predict the consistency risk of the single battery and other batteries in the vehicle battery pack based on the outlier trend.

[0112] In this step, it can be understood that the change law or development direction of the first outlier data of the single cell is determined by the outlier trend, and the consistency risk of the single cell and other batteries in the vehicle battery pack is predicted according to the change law or development direction of the first outlier data. Among them, the consistency risk refers to the potential risk of the overall performance of the battery pack being reduced or failure caused by the gradual increase in the difference between the state parameter data of each single cell in the battery pack.

[0113] Furthermore, the above-mentioned outlier trend may be an outlier trend that has not been processed by filtering, or an outlier trend that has been processed by filtering.

[0114] When the outlier trend is a filtered outlier trend, the consistency risk of the single cell and other batteries in the vehicle battery pack is predicted according to the outlier trend, including: inputting the outlier trend into the filter, filtering the outlier trend, and obtaining filtered data; in the filtering process, analyzing the phase response of the filter to determine the nonlinear phase delay introduced by the filter; applying the compensation algorithm to phase compensate the filtered data to eliminate the nonlinear phase delay introduced by the filter, and obtaining the compensated outlier trend; based on the compensated outlier trend, predicting the consistency risk of the single cell and other batteries in the vehicle battery pack. Among them, the type of filter can be adjusted according to the actual situation, for example, the type of filter can be adjusted to a zero phase delay IIR filter.

[0115] The embodiment of the present application determines the first outlier data of the single cell battery by analyzing the status parameter data of the single cell battery in the vehicle battery pack, wherein the outlier data generally represents the abnormal value in the battery status parameter data, and by analyzing these abnormal values, the outlier trend of the single cell battery within the most recent set time period can be determined; based on the outlier trend, the future outlier data of the single cell battery can be accurately predicted, thereby realizing the prediction of the consistency risk between the single cell battery and other batteries in the vehicle battery pack, thereby improving the user's driving safety.

[0116] On the basis of the above embodiment, according to the outlier trend, the consistency risk of the single cell and other batteries in the vehicle battery pack is predicted, including: based on the outlier trend, determining the second outlier data corresponding to the relative outlier trend of the single cell; according to the second outlier data, determining the consistency risk of the single cell and other batteries in the vehicle battery pack.

[0117] In this embodiment, it can be understood that after determining the outlier trend, it is necessary to determine the second outlier data corresponding to the relative outlier trend of the single cell based on the outlier trend. That is to say, after determining the outlier trend, the embodiment of the present application further determines the outlier data present in the outlier trend, that is, the second outlier data. By determining the outlier trend, and then further determining the outlier data (the second outlier data) in the outlier trend, and determining the outlier data at least twice, the consistency risk of the single cell and other batteries in the vehicle battery pack can be predicted, which can further improve the prediction accuracy on the basis of achieving early prediction of consistency risk.

[0118] Optionally, based on the outlier trend, determining the second outlier data of the relative outlier trend corresponding to the single cell includes: inputting the outlier trend into a fitting prediction model to obtain the second outlier data of the relative outlier trend corresponding to the single cell, the fitting prediction model is used to capture the dynamic characteristics of the outlier trend, and predicting the outlier data of the relative outlier trend based on the dynamic characteristics. The second outlier data reflects the risk of further deterioration of the performance of the single cell.

[0119] The fitted prediction model can accurately predict the performance changes of single cells by using statistical methods or machine learning algorithms, such as regression analysis methods, that is, predicting the second outlier data. By identifying the second outlier data, it can be determined whether the single cell will significantly deviate from the overall performance level of the battery pack in the future, thereby evaluating its contribution to the consistency risk.

[0120] Optionally, the second outlier data includes values ​​at multiple different moments, and the consistency risk of the single battery and other batteries in the vehicle battery pack is determined based on the second outlier data, including: determining the rate of change of the values ​​corresponding to adjacent moments in the second outlier data; if the rate of change is greater than or equal to a change threshold, determining whether the single battery has charging behavior within a preset time period; if there is charging behavior within the preset time period, determining a rate of change greater than or equal to the change threshold as an effective rate of change; determining the third outlier data corresponding to the effective change rate in the second outlier data; and determining a predicted value of the consistency risk of the single battery and other batteries in the vehicle battery pack based on the third outlier data.

[0121] In this embodiment, it can be understood that after determining the second outlier data, it is necessary to determine the effective change rate from the change rate of the values ​​corresponding to adjacent moments in the second outlier data. Specifically, first determine the change rate of the values ​​corresponding to adjacent moments in the second outlier data, and judge whether the change rate is greater than or equal to the change threshold, wherein the change threshold can be set according to actual needs; if the change rate is greater than or equal to the change threshold, it is necessary to determine whether the single battery has a charging behavior within a preset time period, for example, determine the occurrence date of the third outlier data whose change rate is greater than or equal to the change threshold, and determine whether the single battery has a charging behavior within 7 days before the occurrence date; assuming that it is determined that overcharging behavior occurs within the preset time period, the change rate can be considered to be an effective change rate, and the flag bit 1 is output; assuming that it is determined that overcharging behavior does not occur within the preset time period, the change rate can be considered to be an invalid change rate.

[0122] Furthermore, whether the single cell battery is overcharged within a preset time period may be determined by the charging state of the battery.

[0123] After determining the third outlier data, the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack is determined according to the third outlier data. Determining the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack according to the third outlier data includes: obtaining the duration of the effective change rate of the third outlier data; determining the effective change rate with a duration greater than or equal to the duration threshold as the abnormal change rate; determining the fourth outlier data corresponding to the abnormal change rate in the third outlier data; and determining the consistency risk prediction of the single cell and other batteries in the vehicle battery pack according to the fourth outlier data.

[0124] This means that, in some embodiments, after determining the third outlier data, it is necessary to determine the fourth outlier data having an abnormal change rate from the third outlier data, wherein the abnormal change rate can be determined in the following manner: first, the duration of the effective change rate of the third outlier data is obtained; it is determined whether the duration is greater than or equal to a duration threshold, wherein the duration threshold can be adjusted according to actual conditions, for example, the duration threshold can be adjusted to 3 days; and the effective change rate whose duration is greater than or equal to the duration threshold is determined as the abnormal change rate.

[0125] The embodiment of the present application can accurately predict the consistency deviation between a single cell and other batteries and its impact on the overall performance of the battery pack by analyzing the outlier data of the abnormal change rate.

[0126] On the basis of the above embodiment, based on the fourth outlier data, determining the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack includes: determining the risk information of the single cell corresponding to the fourth outlier data greater than or equal to the outlier threshold based on the fourth outlier data; determining the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack based on the risk information. The outlier threshold can be adjusted according to actual conditions.

[0127] In this embodiment, it can be understood that the fourth outlier data is monitored and analyzed to identify whether the fourth outlier data reaches a preset outlier threshold. The risk information of the single cell corresponding to the fourth outlier data that reaches the preset outlier threshold is determined, and the risk information includes the state parameter data of the abnormality and the time when the abnormality occurs, etc.

[0128] For example, when the fourth outlier data includes a single cell voltage, it is necessary to detect whether the single cell voltage value is greater than or equal to 0.25V; and determine the risk information of the single cell corresponding to the fourth outlier data greater than or equal to 0.25V.

[0129] After determining the risk information, the potential impact on the consistency of the battery pack is quantified by analyzing the risk information, that is, the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is obtained.

[0130] Among them, based on the risk information, the specific implementation method of determining the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack can be selected according to the actual situation.

[0131] In one implementation, the consistency risk prediction value of a single battery and other batteries in a vehicle battery pack is determined based on the attributes of the risk information. For example, different weights are assigned to risk information with different attributes, and a weighted sum is performed. The corresponding consistency risk prediction value is output based on the summation result, where different summation results correspond to different consistency risk prediction values.

[0132] The embodiment of the present application can accurately predict the consistency risk of a single battery and other batteries in the vehicle battery pack by analyzing the fourth outlier data with an abnormal change rate.

[0133] Furthermore, the above-mentioned vehicle battery cell consistency risk prediction method also includes: outputting risk information; and / or outputting the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack. By outputting risk information and / or the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack, accurate monitoring and early warning of battery pack performance can be achieved.

[0134] Next, taking the state parameter data of the single cell voltage as an example, it is explained how to use the vehicle battery single cell consistency risk prediction method provided by the embodiment of the present application. Since the single cell has inconsistency when leaving the factory, the single cell has inconsistent voltage when discharged for a long time. Since the BMS has the function of passive balancing during charging, the voltage of each single cell will be kept near the same value as much as possible. However, if multiple charges cannot balance a single cell, it can be considered that the single cell is abnormal and has the risk of consistency failure. However, this method is only applicable to situations where consistency risks have already appeared.

[0135] Therefore, in order to identify the risk of power battery cell consistency failure in advance, the embodiment of the present application obtains the battery data reported by the vehicle terminal from the battery management system, processes the obtained data on a daily basis, and performs fitting of long-period outlier data, so as to obtain the outlier trend of the single cell several months in advance, thereby predicting the consistency failure of the single cell, and giving an early warning of the consistency failure, so as to arrange after-sales personnel to handle and solve it in advance. Specifically, the method includes the following steps:

[0136] 1. For each vehicle at a certain time of the day, pull the current list data of all single battery voltages of the vehicle;

[0137] 2. Calculate the daily average single cell voltage list value, and based on the list, find the outlier data of each single cell relative to the list average value;

[0138] 3. Make a curve of the daily deviation data for observation (if a vehicle has 90 single cells, then the vehicle has 90 curves, the y value of each curve is the outlier data of the single cell voltage, and the x value of each curve is the number of days). For the robustness of the data, the outlier data of the outlier data, that is, the secondary outlier, can be used to more effectively see the differences between the curves; and the outlier trend of the secondary outlier is filtered;

[0139] 4. According to the outlier trend after filtering, the problematic battery is judged based on the rule conditions, and a thermal runaway warning is issued for the entire vehicle. The rule conditions include the judgment of the abnormal change rate and the abnormal maximum value. Only when the above conditions are met can the problematic battery be judged.

[0140] Specifically: in the abnormal change rate judgment, the secondary outlier after filtering is judged. If a curve with an abnormal change rate is found, it is necessary to determine the date of its occurrence and determine whether there is any charging behavior before the occurrence of the secondary outlier. If there is no charging for more than 7 days, it is called an invalid change rate. If the effective change rate lasts for 3 days, it is considered an abnormal change rate judgment and the output flag is 1; in the abnormal maximum value judgment, if the maximum value of the secondary outlier after filtering exceeds 0.25V, it is considered to be an abnormal maximum value and the output flag is 1; if the flag output in the abnormal change rate judgment and the flag in the abnormal maximum value judgment are both 1, the battery with problems can be judged.

[0141] For detailed principles, please refer to Figure 3 , Figure 3 A schematic diagram of determining problematic batteries based on rules provided in an embodiment of the present application.

[0142] Taking a vehicle as an example, the above method can intuitively observe the daily average secondary outlier change curve of each single battery voltage, and observe whether there is an abnormality in the battery voltage of the vehicle throughout its life cycle through the curve. Figure 4 This is an example diagram of the daily average secondary outlier change curve of the single cell voltage provided in the embodiment of the present application. Figure 4 It can be seen that the vehicle had a single cell consistency failure in November 2020. From the figure, it can be directly observed that the secondary deviation of the daily average voltage of a certain single cell corresponding to the purple curve showed an abnormal increase near June 2020, proving that there is a problem with the battery. It is necessary to judge the abnormal battery based on rules, so as to warn of the risk of single cell voltage consistency failure.

[0143] Furthermore, the method provided in the embodiment of the present application can also collect statistics and alarm for the outlier trend of the outlier data of the status parameter data of the single cell battery, and provide feedback to after-sales personnel. At the same time, users can query according to the vehicle identification number (Vin for short), time and other information. Figure 5 This is a schematic diagram of a battery cell consistency risk warning query interface provided in an embodiment of the present application, wherein the cell number is the single cell battery number.

[0144] Furthermore, users can also query information such as single cell voltage and probe temperature extremes. Figure 6 This is the single cell voltage and probe temperature extreme value query interface provided in the embodiment of the present application.

[0145] In summary, the embodiments of the present application determine the outlier trend of daily single-cell battery status parameter data, use historical data for long-term early warning, promptly discover problems at the beginning of consistency failures, and issue early warnings for battery consistency risks to facilitate subsequent charging or balancing processes, thereby avoiding greater damage to the battery.

[0146] The following are embodiments of the device of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0147] Figure 7 The schematic diagram of the structure of the vehicle battery cell consistency risk prediction device provided in this application is as follows: Figure 7 As shown, the vehicle battery cell consistency risk prediction device 700 provided in this embodiment includes:

[0148] An acquisition module 701 is used to acquire state parameter data of a single cell in a vehicle battery pack;

[0149] A processing module 702 is used to perform data processing on the state parameter data to obtain first outlier data of the single battery;

[0150] A determination module 703 is used to determine the outlier trend of the single battery within a recent set time period according to the first outlier data;

[0151] The prediction module 704 is used to predict the consistency risk of the single battery and other batteries in the vehicle battery pack according to the outlier trend.

[0152] In a possible implementation, the prediction module 704 is specifically configured to:

[0153] Based on the outlier trend, determining second outlier data corresponding to the single battery with a relative outlier trend;

[0154] Based on the second outlier data, a consistency risk between the single battery and other batteries in the vehicle battery pack is determined.

[0155] In a possible implementation, the determination module 703 is specifically used to: input the outlier trend into the fitting prediction model to obtain the second outlier data corresponding to the relative outlier trend of the single cell, the fitting prediction model is used to capture the dynamic characteristics of the outlier trend, and predict the outlier data relative to the outlier trend based on the dynamic characteristics.

[0156] In one possible implementation, the second outlier data includes values ​​at multiple different moments, and the determination module 703 is specifically used to: determine the rate of change of values ​​corresponding to adjacent moments in the second outlier data; if the rate of change is greater than or equal to a change threshold, determine whether the single cell has charging behavior within a preset time period; if there is charging behavior within the preset time period, determine the rate of change greater than or equal to the change threshold as the effective rate of change; determine the third outlier data corresponding to the effective change rate in the second outlier data; and based on the third outlier data, determine the consistency risk prediction value of the single cell and other batteries in the vehicle battery pack.

[0157] In one possible implementation, the processing module 702 is specifically used to: obtain the duration of the effective change rate of the third outlier data; determine the effective change rate whose duration is greater than or equal to the duration threshold as an abnormal change rate; determine the fourth outlier data corresponding to the abnormal change rate in the third outlier data; and determine the consistency risk prediction of the single battery and other batteries in the vehicle battery pack based on the fourth outlier data.

[0158] In a possible implementation, the processing module 702 is specifically used to: determine, based on the fourth outlier data, risk information of a single cell corresponding to the fourth outlier data that is greater than or equal to an outlier threshold; and determine, based on the risk information, a consistency risk prediction value of the single cell and other batteries in the vehicle battery pack.

[0159] In a possible implementation, the processing module 702 is further configured to:

[0160] Output risk information; and / or output consistency risk prediction values ​​of the single battery and other batteries in the vehicle battery pack.

[0161] In a possible implementation, the acquisition module 701 is specifically used to:

[0162] Obtaining initial state parameter data of single cells in a vehicle battery pack;

[0163] The initial state parameter data is cleaned to obtain the state parameter data.

[0164] In a possible implementation, the prediction module is specifically used for:

[0165] The outlier trend is input into the filter, and the outlier trend is filtered to obtain filtered data;

[0166] During the filtering process, the phase response of the filter is analyzed to determine the nonlinear phase delay introduced by the filter;

[0167] Applying a compensation algorithm to phase compensate the filtered data to eliminate the nonlinear phase delay introduced by the filter and obtain the compensated outlier trend;

[0168] Predict the consistency risk of a single battery cell and other batteries in the vehicle battery pack based on compensated outlier trends.

[0169] The vehicle battery cell consistency risk prediction device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0170] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0171] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0172] Figure 8 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 8As shown, the electronic device 800 provided in the embodiment of the present application may include: a processor 801, and a memory 802 connected to the processor in communication, wherein:

[0173] Memory stores computer-executable instructions;

[0174] The processor executes the computer-executable instructions stored in the memory to implement the method described in the foregoing method embodiment.

[0175] It should be understood that the processor 801 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The memory 802 may include a high-speed random access memory (RAM), and may also include non-volatile storage NVM (non-volatile memory), such as at least one disk storage, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc.

[0176] Optionally, the electronic device 800 may further include a communication interface 803. In a specific implementation, if the communication interface 803, the memory 802 and the processor 801 are implemented independently, the communication interface 803, the memory 802 and the processor 801 may be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0177] Optionally, in a specific implementation, if the communication interface 803, the memory 802 and the processor 801 are integrated on a chip, the communication interface 803, the memory 802 and the processor 801 can communicate through an internal interface.

[0178] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the method described in any of the aforementioned embodiments.

[0179] It is understood that the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0180] An exemplary computer-readable storage medium is coupled to a processor so that the processor can read information from the computer-readable storage medium and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can be located in an ASIC. Of course, the processor and the computer-readable storage medium can also exist in an electronic device as discrete components.

[0181] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a computer-readable storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0182] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method described in any of the above embodiments when executed.

[0183] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0184] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0185] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0186] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0187] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A vehicle battery cell consistency risk prediction method, characterized in that: include: Obtaining status parameter data of single cells in a vehicle battery pack; Performing data processing on the state parameter data to obtain first outlier data of the single battery; Determining, according to the first outlier data, an outlier trend of the single battery within a recent set time period; According to the outlier trend, the consistency risk between the single battery and other batteries in the vehicle battery pack is predicted.

2. The method according to claim 1, characterized in that The predicting, based on the outlier trend, the consistency risk between the single battery and other batteries in the vehicle battery pack includes: Based on the outlier trend, determining second outlier data corresponding to the single cell relative to the outlier trend; The consistency risk between the single battery and other batteries in the vehicle battery pack is determined based on the second outlier data.

3. The method according to claim 2, characterized in that The determining, based on the outlier trend, second outlier data corresponding to the single battery and relative to the outlier trend comprises: The outlier trend is input into a fitting prediction model to obtain second outlier data corresponding to the single cell relative to the outlier trend. The fitting prediction model is used to capture the dynamic characteristics of the outlier trend and predict the outlier data relative to the outlier trend based on the dynamic characteristics.

4. The method according to claim 2, characterized in that: The second outlier data includes multiple values ​​at different times, and determining the consistency risk between the single battery and other batteries in the vehicle battery pack according to the second outlier data includes: Determine the rate of change of the values ​​of the second outlier data corresponding to adjacent moments; If the change rate is greater than or equal to the change threshold, determining whether the single battery has a charging behavior within a preset time period; If there is charging behavior within the preset time period, determining that the change rate greater than or equal to the change threshold is an effective change rate; Determine third outlier data corresponding to the effective change rate in the second outlier data; Based on the third outlier data, a consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is determined.

5. The method according to claim 4, characterized in that The step of determining the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack according to the third outlier data includes: Obtaining a duration of the effective change rate of the third outlier data; The effective change rate whose duration is greater than or equal to the duration threshold is determined as an abnormal change rate; Determine fourth outlier data corresponding to the abnormal change rate in the third outlier data; A consistency risk prediction of the single battery and other batteries in the vehicle battery pack is determined based on the fourth outlier data.

6. The method according to claim 5, characterized in that The step of determining the consistency risk prediction value of the single battery and other batteries in the vehicle battery pack based on the fourth outlier data includes: Based on the fourth outlier data, determining risk information of a single battery corresponding to the fourth outlier data that is greater than or equal to an outlier threshold; Based on the risk information, a consistency risk prediction value of the single battery and other batteries in the vehicle battery pack is determined.

7. The method according to claim 6, characterized in that Also includes: outputting the risk information; And / or, outputting a consistency risk prediction value of the single battery and other batteries in the vehicle battery pack.

8. The method according to any one of claims 1 to 7, characterized in that The step of obtaining the status parameter data of all single cells in the vehicle battery pack includes: Obtaining initial state parameter data of single cells in a vehicle battery pack; The initial state parameter data is cleaned to obtain state parameter data.

9. The method according to any one of claims 1 to 7, characterized in that The predicting, based on the outlier trend, the consistency risk between the single battery and other batteries in the vehicle battery pack includes: Inputting the outlier trend into a filter, filtering the outlier trend to obtain filtered data; During the filtering process, analyzing the phase response of the filter to determine the nonlinear phase delay introduced by the filter; Applying a compensation algorithm to perform phase compensation on the filtered data to eliminate the nonlinear phase delay introduced by the filter and obtain a compensated outlier trend; Based on the compensated outlier trend, the consistency risk between the single battery and other batteries in the vehicle battery pack is predicted.

10. A vehicle battery cell consistency risk prediction device, characterized in that: include: An acquisition module, used to acquire state parameter data of a single battery in a vehicle battery pack; A processing module, used for performing data processing on the state parameter data to obtain first outlier data of the single battery; A determination module, configured to determine an outlier trend of the single battery within a recent set time period according to the first outlier data; A prediction module is used to predict the consistency risk of the single battery and other batteries in the vehicle battery pack according to the outlier trend.

11. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed.

Images