Impedance anomaly evaluation method and system based on single voltage consistency

Abstract

The embodiment of the invention relates to the technical field of Internet of Vehicles big data analysis, and discloses an impedance anomaly evaluation method and system based on single voltage consistency, and the method comprises the steps: obtaining historical charging data of a target vehicle model and historical driving data corresponding to the historical charging data; performing fragment extraction on the historical charging data to obtain target charging fragment data; based on the target charging fragment data, calculating a voltage deviation value of each single battery in the target vehicle type; and performing impedance anomaly evaluation on the target vehicle model based on the historical driving data and the voltage deviation value. By applying the technical scheme of the invention, the rationality and accuracy of the impedance anomaly evaluation of the target vehicle model can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of battery health assessment, and specifically to an impedance anomaly evaluation method and system based on the consistency of single-cell voltages. Background Art

[0002] With the popularization of new energy vehicles, as the core component, the health state of the power battery has become increasingly prominent in affecting the vehicle performance. However, the battery health assessment in related technologies often only focuses on the capacity attenuation of the battery, while ignoring the increase in the internal resistance of the battery. For new energy vehicles, the increase in internal resistance will not only affect the peak output ability of the vehicle, but also reduce the cycle life of the battery, thereby affecting the reliability and safety of the whole vehicle. Summary of the Invention

[0003] In view of the above problems, the embodiments of the present invention provide an impedance anomaly evaluation method and system based on the consistency of single-cell voltages, which are used to solve the problem of inaccurate battery health assessment in related technologies.

[0004] According to one aspect of the embodiments of the present invention, an impedance anomaly evaluation method and system based on the consistency of single-cell voltages are provided. The method includes obtaining historical charging data of a target vehicle model and corresponding historical driving data; extracting segments from the historical charging data to obtain target charging segment data; calculating the voltage deviation values of each battery cell in the target vehicle model based on the target charging segment data; and performing an impedance anomaly evaluation on the target vehicle model based on the historical driving data and the voltage deviation values.

[0005] In an alternative embodiment, performing an impedance anomaly evaluation on the target vehicle model based on the historical driving data and the voltage deviation values includes:

[0006] Determining the voltage deviation threshold interval corresponding to each battery cell based on the historical driving data;

[0007] Determining the voltage consistency score of each battery cell based on the voltage deviation threshold interval;

[0008] Performing an impedance anomaly evaluation on the target vehicle model based on the voltage consistency score.

[0009] In an alternative embodiment, determining the voltage deviation threshold interval corresponding to each battery cell based on the historical driving data includes:

[0010] Determining the release time of the target vehicle model based on the historical driving data;

[0011] If the release time is greater than or equal to the target time, performing statistical analysis on the voltage deviation values to obtain the voltage deviation standard deviation of each battery cell;

[0012] Determine the voltage deviation threshold interval corresponding to each battery cell based on the voltage deviation value and the standard deviation of the voltage deviation.

[0013] In an alternative embodiment, perform statistical analysis on the voltage deviation values to obtain the standard deviation of the voltage deviation of each battery cell, including:

[0014] Determine the current mileage segment of the target vehicle model based on historical driving data;

[0015] Perform statistical analysis on the voltage deviation values based on the current mileage segment to obtain the average voltage deviation of each battery cell;

[0016] Obtain the standard deviation of the voltage deviation of the battery cell based on the voltage deviation value and the average voltage deviation.

[0017] In an alternative embodiment, determining the voltage deviation threshold interval corresponding to each battery cell based on historical driving data further includes:

[0018] If the market launch time is less than the target time, obtain the initial voltage deviation threshold and the final voltage deviation threshold of the target vehicle model;

[0019] Determine the driving voltage deviation threshold corresponding to each battery cell based on historical driving data, the initial voltage deviation threshold, and the final voltage deviation threshold;

[0020] Determine the voltage deviation threshold interval corresponding to each battery cell based on the driving voltage deviation threshold and the target deviation coefficient.

[0021] In an alternative embodiment, perform segment extraction on historical charging data to obtain target charging segment data, including:

[0022] Perform single-cell current sampling and state-of-charge sampling on each battery cell based on historical charging data to obtain the current value at each current sampling moment and the state-of-charge value at each charge sampling moment;

[0023] Match the charge sampling moment with the current sampling moment, and perform interpolation processing on the state-of-charge value based on the matching result to obtain the processed charging segment data;

[0024] Perform segment extraction on the processed charging segment data to obtain the target charging segment data.

[0025] In an alternative embodiment, matching the charge sampling moment with the current sampling moment and performing interpolation processing on the state-of-charge value based on the matching result to obtain the processed charging segment data includes:

[0026] Obtain the charge sampling moment closest to the current sampling moment to obtain the target charge sampling moment;

[0027] Based on the state of charge value corresponding to the target charge sampling moment, obtain the state of charge interpolation;

[0028] Perform interpolation processing on the state of charge value based on the state of charge interpolation to obtain an interpolation data processing segment;

[0029] Perform data cleaning on the interpolation data processing segment to obtain the charging segment processed data.

[0030] In an alternative embodiment, based on the target charging segment data, calculate the voltage deviation value of each battery cell in the target vehicle model, including:

[0031] Perform current change sampling of the battery cells on the target charging segment data to obtain the data frame corresponding to the moment with the largest total current change during any charging process of the target vehicle model;

[0032] Calculate the single-cell voltage and voltage average value of each battery cell under the data frame;

[0033] Based on the difference between the single-cell voltage and the voltage average value, obtain the voltage deviation value of each battery cell in the target vehicle model.

[0034] In an alternative embodiment, based on the historical driving data and the voltage deviation value, perform impedance anomaly evaluation on the target vehicle model, further including:

[0035] Based on the historical charging data, determine the initial capacity retention rate and the corresponding mileage attenuation rate of each battery cell;

[0036] Perform data cleaning on the initial capacity retention rate through the mileage reduction rate to obtain the target capacity retention rate;

[0037] Perform statistical analysis on the voltage deviation value to obtain the voltage deviation standard deviation of each battery cell;

[0038] Based on the historical driving data, perform statistical analysis on the capacity retention rate, voltage deviation value, and voltage deviation standard deviation respectively to obtain statistical analysis features;

[0039] Based on the statistical analysis features, perform impedance anomaly evaluation on the target vehicle model.

[0040] According to another aspect of the embodiments of the present invention, there is provided an impedance anomaly evaluation system based on the consistency of single-cell voltages, including: a data acquisition module for acquiring the historical charging data of the target vehicle model and the historical driving data corresponding to the historical charging data; a segment extraction module for performing segment extraction on the historical charging data to obtain the target charging segment data; a deviation calculation module for calculating the voltage deviation value of each battery cell in the target vehicle model based on the target charging segment data; and an anomaly evaluation module for performing impedance anomaly evaluation on the target vehicle model based on the historical driving data and the voltage deviation value.

[0041] According to another aspect of the embodiments of the present invention, a vehicle is provided, including: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete mutual communication through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operations of the foregoing method and system for evaluating impedance abnormality based on the consistency of single-cell voltages.

[0042] According to still another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which at least one executable instruction is stored, and the executable instruction causes a vehicle / device to execute the operations of the foregoing method and system for evaluating impedance abnormality based on the consistency of single-cell voltages.

[0043] According to yet another aspect of the embodiments of the present invention, a computer program product is provided, including computer instructions for causing a computer to execute the method and system for evaluating impedance abnormality based on the consistency of single-cell voltages according to the first aspect or any corresponding embodiment thereof described above.

[0044] The technical solution provided by the embodiments of the present invention obtains historical charging data of a target vehicle model and historical driving data corresponding to the historical charging data, extracts segments from the historical charging data to obtain target charging segment data that can accurately reflect the performance of battery cells; calculates the voltage deviation values of each battery cell based on the target charging segment data to quantify the voltage inconsistency between battery cells; and combines the historical driving data, comprehensively considers the long-term operating state of the battery, and evaluates the impedance abnormality of the target vehicle model, which not only improves the accuracy of battery health assessment, but also can timely detect potential impedance abnormality problems of the battery, providing a strong guarantee for the safe operation of new energy vehicles.

[0045] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to be able to understand the technical means of the embodiments of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the embodiments of the present invention more obvious and understandable, the following specifically describes the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings are only used to illustrate the embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0047] Figure 1 A flowchart showing a method for evaluating impedance abnormality based on the consistency of single-cell voltages provided by the present invention is shown;

[0048] Figure 2 An interpolation processing diagram showing a method for evaluating impedance abnormality based on the consistency of single-cell voltages provided by the present invention is shown;

[0049] Figure 3 Another schematic flow chart showing an impedance anomaly evaluation method based on the consistency of monomer voltages provided by the present invention is shown;

[0050] Figure 4 The first voltage deviation threshold schematic diagram of an impedance anomaly evaluation method based on the consistency of monomer voltages provided by the present invention is shown;

[0051] Figure 5 The second voltage deviation threshold schematic diagram of an impedance anomaly evaluation method based on the consistency of monomer voltages provided by the present invention is shown;

[0052] Figure 6 The structural schematic diagram of an impedance anomaly evaluation system based on the consistency of monomer voltages provided by the present invention is shown;

[0053] Figure 7 The structural schematic diagram of a vehicle provided by the present invention is shown. Detailed implementation manners

[0054] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0055] In the related art, the evaluation of battery health often only focuses on the capacity attenuation of the battery, while ignoring the increase in the internal resistance of the battery. However, for new energy vehicles, the increase in internal resistance will not only affect the peak output ability of the vehicle, but also reduce the cycle life of the battery, thereby affecting the reliability and safety of the whole vehicle.

[0056] Based on this, the embodiments of the present invention provide an impedance anomaly evaluation method based on the consistency of monomer voltages. By obtaining the historical charging data of the target vehicle model and the corresponding historical driving data, segment extraction is performed on the historical charging data to obtain target charging segment data that can accurately reflect the performance of battery monomers; based on the target charging segment data, the voltage deviation values of each battery monomer are calculated to quantify the voltage inconsistency between battery monomers; and in combination with the historical driving data, considering the long-term operating state of the battery, an impedance anomaly evaluation is performed on the target vehicle model, which not only improves the accuracy of battery health evaluation, but also can timely detect potential impedance anomaly problems of the battery, providing a strong guarantee for the safe operation of new energy vehicles.

[0057] Figure 1 The flow chart of the first embodiment of an impedance anomaly evaluation method and system based on the consistency of monomer voltages of the present invention is shown. This method is executed by a vehicle. As Figure 1 shown, this method includes the following steps:

[0058] Step 110, obtain the historical charging data of the target vehicle model and the historical driving data corresponding to the historical charging data.

[0059] As above, by obtaining the historical charging data of the target vehicle model and the historical driving data corresponding to the historical charging data, it provides necessary data support for the subsequent impedance anomaly analysis and processing of the cell voltage consistency.

[0060] Specifically, the historical charging data and historical driving data of the target vehicle model can be obtained in the form of a data interface, and the data interface includes but is not limited to the vehicle CAN bus interface, OBD interface or wireless data transmission interface. The historical charging data includes but is not limited to parameters such as the data acquisition time, vehicle status, charging status, charging start time, charging end time, charging temperature, charging current, charging voltage, cell voltage list, state of charge and capacity retention rate of the historical charging data and historical driving data; the historical driving data includes but is not limited to parameters such as driving mileage, driving time, average speed, acceleration and braking frequency.

[0061] Step 120, perform segment extraction on the historical charging data to obtain target charging segment data.

[0062] As above, by performing segment extraction on the historical charging data, it is convenient to accurately evaluate the performance of the battery cells based on the obtained target charging segment data.

[0063] In an optional implementation manner, when performing segment extraction on the historical charging data to obtain target charging segment data, single-cell current sampling and state-of-charge sampling can be performed on each battery cell based on the historical charging data to obtain the current value at each current sampling moment and the state-of-charge value at the state-of-charge sampling moment; match the state-of-charge sampling moment with the current sampling moment, and perform interpolation processing on the state-of-charge value based on the matching result to obtain the processed charging segment data; perform segment extraction on the processed charging segment data to obtain the target charging segment data.

[0064] In an optional implementation manner, when matching the state-of-charge sampling moment with the current sampling moment and performing interpolation processing on the state-of-charge value based on the matching result to obtain the processed charging segment data, the state-of-charge sampling moment closest to the current sampling moment can be obtained first to obtain the target state-of-charge sampling moment; obtain the state-of-charge interpolation based on the state-of-charge value corresponding to the target state-of-charge sampling moment; perform interpolation processing on the state-of-charge value based on the state-of-charge interpolation to obtain the interpolated data processing segment; perform data cleaning on the interpolated data processing segment to obtain the processed charging segment data.

[0065] To Figure 2For example, select the state of charge value SOC at the target charge sampling moment (SOC sampling time) close to the interpolation frame current value acquisition time, that is, the current sampling moment (current acquisition time), such as SOC6 as the state of charge interpolation (interpolation value). At this time, it is necessary to verify the state of charge interpolation. If SOC6 ≤ (I1×Δt / 60 / 60) / C 额 , it is considered that the state of charge interpolation is valid. Here, I1 represents the current value of the previous frame of the interpolation frame, Δt is the current acquisition time interval (for example, 30 seconds), and C 额 is the rated capacity of the battery cell. To prevent deviation value mutations caused by incorrect reporting of voltage, current, and temperature data due to system failures and affect the accuracy of the evaluation results, the over-threshold range can be set according to the measurement ranges of the signal collection probes for each field. For example, if the measurement range of the single-cell voltage probe is [0, 5], then the data in (-∞, 0) ∪ (5, +∞) is marked as over-threshold and cleaned. In addition, considering that the influence degrees of the current magnitude and different state of charge value intervals on the DC resistance DCR are different, to reduce the influence of the difference between the single cell and the system average state, the charging segment data in the parking charging state can be used, and the state of charge value at the end of charging should be within the range of [80%, 100%].

[0066] In an alternative embodiment, segment extraction is performed on the charging segment processing data to obtain the target charging segment data, which can also be based on a preset segment extraction rule. For example, parameters such as the length of the segment and the overlapping ratio between segments can be set to ensure that the extracted segments can comprehensively and accurately reflect the performance of the battery cell at different charging stages. By segmenting the charging segment processing data, multiple target charging segment data can be obtained, providing a basis for subsequent calculation of the voltage deviation of the single cell.

[0067] In an alternative embodiment, to ensure the accuracy of the extracted target charging segment data, the segment extraction result can also be verified. For example, the voltage deviation value of each target charging segment data can be calculated and compared with a preset voltage deviation threshold. If the voltage deviation value of the target charging segment data exceeds the preset range, the segment extraction is performed again until the target charging segment data that meets the requirements is obtained.

[0068] Step 130, based on the target charging segment data, calculate the voltage deviation value of each battery cell in the target vehicle model.

[0069] As above, by calculating the voltage deviation value of each battery cell in the target vehicle model based on the target charging segment data, the voltage inconsistency between battery cells is quantified, providing a key indicator for subsequent impedance anomaly evaluation.

[0070] In an alternative embodiment, when calculating the voltage deviation values of each battery cell in the target vehicle model based on the target charging segment data, the current change of each battery cell in the target charging segment data can be sampled first to obtain the data frame corresponding to the moment with the largest total current change during any charging process of the target vehicle model; calculate the individual voltage and voltage average value of each battery cell under the data frame; and based on the difference between the individual voltage and the voltage average value, obtain the voltage deviation values of each battery cell in the target vehicle model.

[0071] Specifically, first, obtain the data frame j with the largest current change during the i-th charging, and record the individual voltage of each battery cell (or parallel module) and the voltage average value Then, calculate the voltage deviation of each battery cell (or parallel module) That is, by subtracting to obtain The data frame j with the largest current change can be determined by comparing the current value differences between adjacent frames and taking the maximum value of the absolute values. Among them, when determining the voltage average value , after the data frame corresponding to the moment with the largest total current change during any charging process of the target vehicle model, the maximum and minimum values of n voltage values in the data frame j can be excluded, and then the average value of the remaining voltage values is calculated and used as the voltage average value under this data frame, which can reduce the influence of the initial performance differences between battery cells or abnormal cells on the voltage average value and improve the accuracy of voltage deviation calculation.

[0072] Step 140, perform an impedance abnormality evaluation on the target vehicle model based on the historical driving data and the voltage deviation values.

[0073] Among them, the voltage consistency score can reflect the degree of inconsistency of the voltages between battery cells. The higher the score, the better the voltage consistency between battery cells. Based on the voltage consistency score, an impedance abnormality evaluation can be performed on the target vehicle model, so as to timely discover potential impedance abnormality problems of the battery and provide a strong guarantee for the safe operation of new energy vehicles.

[0074] In an alternative embodiment, when performing an impedance abnormality evaluation on the target vehicle model based on the historical driving data and the voltage deviation values, the voltage deviation threshold interval corresponding to each battery cell can be determined first based on the historical driving data; then, based on the voltage deviation threshold interval, the voltage consistency score of each battery cell can be determined; and finally, an impedance abnormality evaluation can be performed on the target vehicle model based on the voltage consistency score.

[0075] In an alternative embodiment, when determining the voltage deviation threshold interval corresponding to each battery cell based on historical driving data, the market launch time of the target vehicle model can be determined based on the historical driving data; if the market launch time is greater than or equal to the target time, statistical analysis is performed on the voltage deviation values to obtain the standard deviation of the voltage deviation of each battery cell; based on the voltage deviation values and the standard deviation of the voltage deviation, the voltage deviation threshold interval corresponding to each battery cell is determined.

[0076] In an alternative embodiment, when performing statistical analysis on the voltage deviation values to obtain the standard deviation of the voltage deviation of each battery cell, the current mileage segment of the target vehicle model can be determined based on the historical driving data; statistical analysis is performed on the voltage deviation values based on the current mileage segment to obtain the average value of the voltage deviation of each battery cell; based on the voltage deviation values and the average value of the voltage deviation, the standard deviation of the voltage deviation of the battery cell is obtained.

[0077] Specifically, the formula for obtaining the standard deviation of the voltage deviation of the battery cell based on the voltage deviation values and the average value of the voltage deviation is:

[0078]

[0079] Wherein, is the standard deviation of the voltage deviation, is the voltage deviation value, is the average value of the voltage deviation, and m is the number of voltage probes.

[0080] Specifically, for a vehicle model that has been launched, has a large market share, and some vehicles have reached the end of their service life, is used as the voltage deviation threshold interval, r is the adjustment coefficient, and the interval is scored and assigned values. The score corresponding to the maximum voltage deviation value (single-cell voltage deviation value) in the battery system falling into the voltage deviation threshold interval is used as the impedance abnormality evaluation result of the target vehicle model, as shown in Table 1.

[0081] Table 1 The first impedance abnormality evaluation result of the target vehicle model

[0082]

[0083] In a specific embodiment, when determining the voltage deviation threshold interval, factors such as driving mileage, driving time, and average speed in the historical driving data can also be comprehensively considered. For example, for battery cells with a longer driving mileage and a longer driving time, the voltage deviation threshold interval can be set relatively loosely to reflect the natural attenuation after long-term operation of the battery. On the contrary, for battery cells with a shorter driving mileage and less driving time, the voltage deviation threshold interval can be set relatively strictly to ensure that the battery maintains good performance in the initial stage.

[0084] When determining the voltage consistency score, a linear scoring method or a non-linear scoring method can be adopted. The linear scoring method directly gives the corresponding score according to the relationship between the voltage deviation value and the voltage deviation threshold range. The non-linear scoring method can consider factors such as the change rate and change trend of the voltage deviation value to give a more detailed score. For example, when the voltage deviation value continues to increase or the change rate is relatively fast, a lower score can be given to warn of potential impedance abnormality problems.

[0085] When evaluating the impedance abnormality of the target vehicle model based on the voltage consistency score, different scoring levels can be set, such as excellent, good, average, poor, extremely poor, etc. For the target vehicle model with a lower scoring level, further detection and analysis should be carried out in a timely manner to determine the specific cause of the impedance abnormality and take corresponding repair measures. At the same time, the impedance abnormality evaluation results can also be correlated with the historical charging data and historical driving data of the target vehicle model to explore deeper battery performance degradation laws and maintenance strategies.

[0086] The impedance abnormality evaluation method based on the monomer voltage consistency in the embodiments of the present invention obtains the historical charging data of the target vehicle model and the corresponding historical driving data; extracts fragments from the historical charging data to obtain the target charging fragment data; calculates the voltage deviation values of each battery monomer in the target vehicle model based on the target charging fragment data; and evaluates the impedance abnormality of the target vehicle model based on the historical driving data and the voltage deviation values, thereby improving the rationality and accuracy of the impedance abnormality evaluation of new energy vehicles.

[0087] Figure 3 The flowchart of another embodiment of the impedance abnormality evaluation method and system based on the monomer voltage consistency of the present invention is shown, and this method is executed by the vehicle. As Figure 3 shown, the method includes the following steps:

[0088] Step 310, obtain the historical charging data of the target vehicle model and the corresponding historical driving data.

[0089] For details, please refer to Figure 1 step 110 of the embodiment shown, which will not be elaborated here.

[0090] Step 320, extract fragments from the historical charging data to obtain the target charging fragment data.

[0091] For details, please refer to Figure 1 step 120 of the embodiment shown, which will not be elaborated here.

[0092] Step 330, calculate the voltage deviation values of each battery monomer in the target vehicle model based on the target charging fragment data.

[0093] For details, please refer toFigure 1 Step 130 of the illustrated embodiment will not be elaborated here.

[0094] Step 340: Determine the voltage deviation threshold interval corresponding to each battery cell based on historical driving data.

[0095] Specifically, the above step 340 includes:

[0096] Step 3401: If the market launch time is less than the target time, obtain the initial voltage deviation threshold and the final voltage deviation threshold of the target vehicle model.

[0097] As described above, by obtaining the initial voltage deviation threshold and the final voltage deviation threshold of the target vehicle model when the market launch time is less than the target time, the driving voltage deviation threshold corresponding to each battery cell is determined based on the initial voltage deviation threshold and the final voltage deviation threshold.

[0098] Step 3402: Determine the driving voltage deviation threshold corresponding to each battery cell based on historical driving data, the initial voltage deviation threshold, and the final voltage deviation threshold.

[0099] As described above, by determining the driving voltage deviation threshold corresponding to each battery cell based on historical driving data, the initial voltage deviation threshold, and the final voltage deviation threshold, the performance state of the battery at different usage stages can be more accurately reflected.

[0100] Step 3403: Determine the voltage deviation threshold interval corresponding to each battery cell based on the driving voltage deviation threshold and the target deviation coefficient.

[0101] As described above, by determining the voltage deviation threshold interval corresponding to each battery cell based on the driving voltage deviation threshold and the target deviation coefficient, the setting of the voltage deviation threshold interval can be further refined to adapt to the performance changes of different battery cells at different usage stages and conditions. The target deviation coefficient can be preset or dynamically adjusted according to factors such as the type, specification, and usage environment of the battery cell to ensure the rationality and accuracy of the voltage deviation threshold interval.

[0102] In specific implementation, a time window can be set, such as the first N years after the vehicle is launched, as the initial stage, and a relatively strict initial voltage deviation threshold is adopted. As time goes by, it gradually transitions to the final voltage deviation threshold to reflect the natural attenuation of the battery performance. At the same time, the driving voltage deviation threshold can be dynamically adjusted according to factors such as the driving mileage and driving time in the historical driving data to more accurately evaluate the health status of the battery.

[0103] For example, for newly launched vehicle models, since the amount of data is small and it is difficult to set evaluation criteria through statistical methods, the maximum initial voltage deviation threshold at the initial stage of a new vehicle is set with reference to design requirements, expert experience, and similar vehicle models or battery systems, that is, the initial voltage deviation threshold. And the maximum initial voltage deviation threshold of the battery system at the end of its life, that is, the end-stage voltage deviation threshold. Assume that the maximum voltage deviation has a linear relationship with the cumulative mileage. Then, when the current mileage segment (driven mileage) is y XOL the maximum system voltage deviation at this time, that is, the driving voltage deviation threshold is The corresponding voltage deviation threshold interval is as Figure 4 shown. Since the actual pressure difference change does not have a linear relationship with the mileage increase, data statistics can be used to obtain the target deviation coefficient, that is, the correction coefficient A, and update the calculation formula corresponding to the driving voltage deviation threshold, so as to obtain:

[0104]

[0105] Step 350: Based on the voltage deviation threshold interval, perform an impedance abnormality evaluation on the target vehicle model.

[0106] Specifically, for newly launched vehicle models, use as the voltage deviation threshold interval, and assign scores to the voltage deviation threshold interval. Use the score corresponding to the maximum voltage deviation (single-cell voltage deviation value) in the battery system falling into the voltage deviation threshold interval as the impedance abnormality evaluation result of the target vehicle model, as shown in Table 2.

[0107] Table 2 The second impedance abnormality evaluation result of the target vehicle model

[0108]

[0109] In an alternative embodiment, when performing an impedance abnormality evaluation on the target vehicle model based on historical driving data and voltage deviation values, the initial capacity retention rate and the corresponding mileage attenuation rate of each battery cell can also be determined based on historical charging data; the initial capacity retention rate is data-cleaned through the mileage reduction rate to obtain the target capacity retention rate; statistical analysis is performed on the voltage deviation values to obtain the voltage deviation standard deviation of each battery cell; based on historical driving data, statistical analysis is performed on the capacity retention rate, voltage deviation values, and voltage deviation standard deviation respectively to obtain statistical analysis features; based on the statistical analysis features, an impedance abnormality evaluation is performed on the target vehicle model. The statistical analysis features can include but are not limited to the change trend of the capacity retention rate, the distribution of voltage deviation values, the degree of dispersion of the voltage deviation standard deviation, etc. These features can comprehensively reflect the performance status of the battery cell under different usage stages and conditions, providing more accurate data support for the impedance abnormality evaluation.

[0110] In specific implementation, the initial capacity retention rate and the corresponding mileage attenuation rate of each battery cell can be determined based on historical charging data. The initial capacity retention rate refers to the capacity retention of the battery cell in the initial stage (such as the initial stage of a new car launch), while the mileage attenuation rate reflects the trend that the capacity of the battery cell gradually decreases as the driving mileage increases. Then, data cleaning can be performed on the initial capacity retention rate through the mileage reduction rate to obtain a more accurate target capacity retention rate. The mileage reduction rate refers to the deviation between the actual driving mileage and the theoretical driving mileage due to factors such as battery performance attenuation and changes in the use environment. By correcting the initial capacity retention rate, a target capacity retention rate that can better reflect the actual performance of the battery can be obtained. Then, statistical analysis is performed on the voltage deviation values to obtain the standard deviation of the voltage deviation of each battery cell. The standard deviation of the voltage deviation reflects the degree of dispersion of the voltage inconsistency between battery cells and is one of the important indicators for evaluating the stability of battery performance. Finally, based on historical driving data, statistical analysis is performed on the capacity retention rate, voltage deviation value, and standard deviation of the voltage deviation respectively to obtain statistical analysis features. These features can be used to construct an impedance anomaly evaluation model to achieve the impedance anomaly evaluation of the target vehicle model. By comprehensively considering multiple statistical analysis features, the health status of the battery can be evaluated more accurately, potential impedance anomaly problems can be detected in a timely manner, and strong guarantee can be provided for the safe operation of new energy vehicles.

[0111] For example, please refer to Figure 5 , for a model that has been on the market, has a large market share, and some vehicles have reached the end of their service life, taking the model as a unit, statistical analysis is performed on the voltage deviation value distribution in different life stages (or mileage segments) of the battery system to obtain the standard deviation of the voltage deviation of each battery cell; based on historical charging data, the initial capacity retention rate and the corresponding mileage attenuation rate of each battery cell are determined; data cleaning is performed on the initial capacity retention rate through the mileage attenuation rate to obtain the target capacity retention rate; based on historical driving data, a statistical analysis feature matrix T is established for the capacity retention rate, voltage deviation value, and standard deviation of the voltage deviation respectively, where y is the cumulative driving mileage of the vehicle, SOH is the capacity retention rate (referring to the percentage of the remaining capacity to the initial capacity after a specific number of cycles or aging time of the battery, C n is the current remaining capacity of the system), is the voltage deviation value of each battery cell (or parallel module), is the mean value of the voltage deviation values of each battery cell (or parallel module), that is, the voltage deviation mean value, is the standard deviation of the voltage deviation of the battery cell (or parallel module), m is the number of voltage probes, and n is the number of charging segments corresponding to a capacity retention rate of 80%. Among them, the expression of the statistical analysis feature matrix is:

[0112]

[0113] For the cumulative driving mileage y, it is divided into granularity intervals of 5000 km, namely [0 km, 5000 km), [5000 km, 10000 km), [10000 km, 15000 km) and so on.

[0114] For the state of health (SOH) of capacity retention, considering that there are multiple single-vehicle results corresponding to the same mileage interval, due to different driving conditions and vehicle usage conditions, there are differences in the SOH of single vehicles. Therefore, it is necessary to clean and aggregate the results. The main purpose of cleaning is that the SOH is not a directly measured result, but is obtained by evaluating according to an algorithm model, and the accuracy of its result directly affects the statistical results of this model. First, clean the outliers of the capacity retention rate outside [40%, 100%], then clean the outliers of the capacity retention rate outside the mileage decay rate of [0% / Wkm, 10% / Wkm], and finally clean the remaining results using the interquartile range, and calculate the average value of the remaining results after cleaning as the SOH result in the statistical analysis feature matrix. Among them, the mileage decay rate R is the decay rate of the remaining capacity retention rate of the battery system with the increase of the vehicle driving mileage. The specific calculation method is as shown in the formula, where R is the battery mileage decay rate and is the capacity retention rate when the cumulative driving mileage is.

[0115]

[0116] For the voltage deviation value, first remove the outliers outside [0 mV, 1000 mV], then perform secondary cleaning using the interquartile range, and finally calculate the average of the remaining results after cleaning and use it as the output result

[0117] Based on historical driving data, perform statistical analysis on the capacity retention rate, voltage deviation value, and voltage deviation standard deviation after data cleaning respectively to obtain statistical analysis features; based on the statistical analysis features, evaluate the impedance abnormality of the target vehicle model.

[0118] In the process of specifically implementing the statistical analysis features, various statistical analysis methods can be used, including but not limited to mean analysis, variance analysis, trend analysis, correlation analysis, etc. Mean analysis can help understand the average level of the performance of battery monomers; variance analysis can reveal the degree of dispersion of the performance differences between battery monomers; trend analysis can show the change trend of battery performance over time and driving mileage; correlation analysis can help discover the correlation relationships between different performance indicators.

[0119] Through mean analysis, the average values of various statistical analysis features can be calculated to reflect the overall level of the performance of individual battery cells. Variance analysis is used to evaluate the degree of dispersion among the performances of individual battery cells, that is, the magnitude of inconsistency. A larger variance indicates a greater difference in performance among battery cells, which may imply problems with performance instability. Trend analysis observes the changing trend of battery performance by plotting the curves of statistical analysis features over time or driving mileage. This helps to discover the degradation law of battery performance and provides a basis for predicting battery life. Correlation analysis reveals the degree of association between different statistical analysis features by calculating the correlation coefficients. For example, the correlation analysis between the capacity retention rate and the voltage deviation value can help to understand the relationship between battery capacity degradation and voltage inconsistency.

[0120] Based on the statistical analysis features obtained from the above statistical analysis methods, an impedance anomaly evaluation model can be constructed. This model can comprehensively consider multiple statistical analysis features and use machine learning algorithms for training and verification to achieve accurate evaluation of impedance anomalies for the target vehicle model. In practical applications, the historical driving data, historical charging data, etc. of the vehicle model to be evaluated can be input into the model to obtain the impedance anomaly evaluation result. According to the evaluation result, the health status of the battery system can be evaluated, potential impedance anomaly problems can be detected in a timely manner, and strong guarantee can be provided for the safe operation of new energy vehicles.

[0121] In addition, during the implementation of impedance anomaly evaluation, expert experience and domain knowledge can also be combined to interpret and optimize the evaluation result. For example, statistical analysis features can be screened and weighted according to expert experience to improve the accuracy and reliability of the evaluation model. At the same time, the evaluation result can be explained and illustrated based on domain knowledge to provide more detailed fault diagnosis and repair suggestions for maintenance personnel.

[0122] Figure 6 The structural schematic diagram of an embodiment of an impedance anomaly evaluation system based on the consistency of individual cell voltages according to the present invention is shown. As Figure 6 shown, the device includes:

[0123] A data acquisition module 610, configured to acquire the historical charging data of the target vehicle model and the corresponding historical driving data;

[0124] A segment extraction module 620, configured to perform segment extraction on the historical charging data to obtain target charging segment data;

[0125] A deviation calculation module 630, configured to calculate the voltage deviation values of each battery cell in the target vehicle model based on the target charging segment data;

[0126] An anomaly evaluation module 640, configured to perform impedance anomaly evaluation on the target vehicle model based on the historical driving data and the voltage deviation values.

[0127] In some alternative embodiments, the anomaly evaluation module 640 includes:

[0128] A threshold interval determination sub-module, configured to determine a voltage deviation threshold interval corresponding to each battery cell based on historical driving data;

[0129] A consistency score determination sub-module, configured to determine a voltage consistency score for each battery cell based on the voltage deviation threshold interval;

[0130] An impedance anomaly evaluation sub-module, configured to perform an impedance anomaly evaluation on the target vehicle model based on the voltage consistency score.

[0131] In some alternative embodiments, the threshold interval determination sub-module includes:

[0132] A market launch time determination unit, configured to determine the market launch time of the target vehicle model based on historical driving data;

[0133] A first deviation value statistical analysis unit, configured to perform a statistical analysis on the voltage deviation values to obtain the standard deviation of the voltage deviation of each battery cell if the market launch time is greater than or equal to the target time;

[0134] A first deviation threshold interval determination unit, configured to determine a voltage deviation threshold interval corresponding to each battery cell based on the voltage deviation values and the standard deviation of the voltage deviation.

[0135] In some alternative embodiments, the deviation value statistical analysis unit is specifically configured to determine the current mileage segment of the target vehicle model based on historical driving data; perform a statistical analysis on the voltage deviation values based on the current mileage segment to obtain the average value of the voltage deviation of each battery cell; and obtain the standard deviation of the voltage deviation of the battery cell based on the voltage deviation values and the average value of the voltage deviation.

[0136] In some alternative embodiments, the threshold interval determination sub-module further includes:

[0137] A first deviation value statistical analysis unit, configured to obtain the initial voltage deviation threshold and the final voltage deviation threshold of the target vehicle model if the market launch time is less than the target time;

[0138] A driving voltage deviation threshold unit, configured to determine a driving voltage deviation threshold corresponding to each battery cell based on historical driving data, the initial voltage deviation threshold, and the final voltage deviation threshold;

[0139] A first deviation threshold interval determination unit, configured to determine a voltage deviation threshold interval corresponding to each battery cell based on the driving voltage deviation threshold and the target deviation coefficient.

[0140] In some alternative embodiments, the segment extraction module 620 includes:

[0141] A data sampling sub-module, which is used to sample the individual current and state of charge of each battery cell based on historical charging data, so as to obtain the current value at each current sampling moment and the state of charge value at the charge sampling moment;

[0142] A data matching sub-module, which is used to match the charge sampling moment with the current sampling moment, and perform interpolation processing on the state of charge value based on the matching result to obtain charge segment processing data;

[0143] A segment extraction sub-module, which is used to extract segments from the charge segment processing data to obtain target charge segment data.

[0144] In some alternative embodiments, the data matching sub-module includes:

[0145] A state sampling unit, which is used to obtain the charge sampling moment closest to the current sampling moment to obtain the target charge sampling moment;

[0146] An interpolation obtaining unit, which is used to obtain a state of charge interpolation based on the state of charge value corresponding to the target charge sampling moment;

[0147] An interpolation processing unit, which is used to perform interpolation processing on the state of charge value based on the state of charge interpolation to obtain an interpolated data processing segment;

[0148] A data cleaning unit, which is used to clean the interpolated data processing segment to obtain charge segment processing data.

[0149] In some alternative embodiments, the deviation calculation module 630 includes:

[0150] A current change sampling sub-module, which is used to sample the current change of the battery cell for the target charge segment data, so as to obtain the data frame corresponding to the moment when the total current change is the largest during any charging process of the target vehicle model;

[0151] A single-cell voltage calculation sub-module, which is used to calculate the single-cell voltage and the average voltage of each battery cell under the data frame;

[0152] A voltage deviation value calculation sub-module, which is used to obtain the voltage deviation value of each battery cell in the target vehicle model based on the difference between the single-cell voltage and the average voltage.

[0153] In some alternative embodiments, the anomaly evaluation module is further configured to determine the initial capacity retention rate and the corresponding mileage attenuation rate of each battery cell based on historical charging data; perform data cleaning on the initial capacity retention rate through the mileage attenuation rate to obtain the target capacity retention rate; perform statistical analysis on the voltage deviation value to obtain the standard deviation of the voltage deviation of each battery cell; perform statistical analysis on the capacity retention rate, the voltage deviation value, and the standard deviation of the voltage deviation respectively based on historical driving data to obtain statistical analysis features; and perform impedance anomaly evaluation on the target vehicle model based on the statistical analysis features.

[0154] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding method embodiments described above, and will not be elaborated here.

[0155] Through the above system and its components, the technical solution provided by the embodiments of the present invention has the following advantages:

[0156] Figure 7 FIG. shows a schematic structural diagram of an embodiment of a vehicle provided by the present invention. The specific implementation of the vehicle is not limited in the specific embodiments of the present invention. The vehicle has the above-mentioned Figure 6 impedance anomaly evaluation system based on the consistency of single-cell voltages. The vehicle may include: a processor 702, a communication interface 704, a memory 706, and a communication bus 708.

[0157] Wherein: the processor 702, the communication interface 704, and the memory 706 communicate with each other through the communication bus 708. The communication interface 704 is used for network communication with other devices such as clients or other servers. The processor 702 is configured to execute the program 710, and specifically may execute the relevant steps in the above-mentioned method embodiments.

[0158] Specifically, the program 710 may include program code, and the program code includes computer-executable instructions.

[0159] The processor 702 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the vehicle may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0160] A memory 706 for storing a program 710. The memory 706 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0161] An embodiment of the present invention also provides a computer-readable storage medium storing at least one executable instruction, which, when running on a vehicle / impedance anomaly evaluation system based on cell voltage consistency, causes the vehicle / impedance anomaly evaluation system based on cell voltage consistency to execute the impedance anomaly evaluation method based on cell voltage consistency in any of the above method embodiments.

[0162] An embodiment of the present invention also provides a computer program product including computer instructions for causing a computer to execute the impedance anomaly evaluation method based on cell voltage consistency in the first aspect or any corresponding embodiment thereof.

[0163] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. In addition, embodiments of the present invention are not directed to any particular programming language.

[0164] In the specification provided herein, a large number of specific details are set forth. However, it can be understood that embodiments of the present invention may be practiced without these specific details. Similarly, in order to streamline the present invention and assist in understanding one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention above, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Among them, the claims following the specific implementation manners are hereby expressly incorporated into the specific implementation manners, where each claim itself serves as a separate embodiment of the present invention.

[0165] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into a module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive.

[0166] It should be noted that the above embodiments illustrate the present invention rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for evaluating impedance anomaly based on cell voltage consistency, characterized in that: The method comprises: Acquire historical charging data of a target vehicle type and historical driving data corresponding to the historical charging data; Extracting segments from the historical charging data to obtain target charging segment data; Calculating a voltage deviation value of each battery cell in the target vehicle model based on the target charging segment data; Based on the historical driving data and the voltage deviation value, an impedance abnormality evaluation is performed on the target vehicle model.

2. The method according to claim 1, characterized in that The performing impedance abnormality evaluation on the target vehicle model based on the historical driving data and the voltage deviation value includes: Determine a voltage deviation threshold interval corresponding to each battery cell based on the historical driving data; Determining a voltage consistency score of each of the battery cells based on the voltage deviation threshold interval; The target vehicle model is evaluated for impedance anomaly based on the voltage consistency score.

3. The method according to claim 2, characterized in that The determining the voltage deviation threshold interval corresponding to each battery cell based on the historical driving data includes: Determining the time to market of the target vehicle model based on the historical driving data; If the launch time is greater than or equal to the target time, statistically analyzing the voltage deviation value to obtain the voltage deviation standard deviation of each battery cell; Based on the voltage deviation value and the voltage deviation standard deviation, a voltage deviation threshold interval corresponding to each battery cell is determined.

4. The method according to claim 3, characterized in that The performing statistical analysis on the voltage deviation value to obtain the voltage deviation standard deviation of each battery cell includes: Determining a current mileage segment of the target vehicle type based on the historical driving data; Performing statistical analysis on the voltage deviation value based on the current mileage segment to obtain a mean voltage deviation value of each battery cell; Based on the voltage deviation value and the voltage deviation mean, a voltage deviation standard deviation of the battery cell is obtained.

5. The method according to claim 3, characterized in that: The step of determining the voltage deviation threshold interval corresponding to each battery cell based on the historical driving data further includes: If the launch time is less than the target time, obtaining the initial voltage deviation threshold and the final voltage deviation threshold of the target vehicle type; Determining a driving voltage deviation threshold corresponding to each battery cell based on the historical driving data, the initial voltage deviation threshold and the final voltage deviation threshold; Based on the running voltage deviation threshold and the target deviation coefficient, a voltage deviation threshold interval corresponding to each battery cell is determined.

6. The method according to claim 1, characterized in that The extracting segments from the historical charging data to obtain target charging segment data includes: Based on the historical charging data, the battery cells are subjected to single-cell current sampling and state-of-charge sampling to obtain the current value at each current sampling moment and the state-of-charge value at the charge sampling moment; Matching the charge sampling time with the current sampling time, and interpolating the state of charge value based on the matching result to obtain charging segment processing data; Perform segment extraction on the charging segment processing data to obtain target charging segment data.

7. The method according to claim 6, characterized in that The step of matching the charge sampling time with the current sampling time and interpolating the charge state value based on the matching result to obtain charging segment processing data includes: Obtaining a charge sampling time closest to the current sampling time to obtain a target charge sampling time; Obtaining a state of charge interpolation value based on the state of charge value corresponding to the target charge sampling time; performing interpolation processing on the state of charge value based on the state of charge interpolation to obtain an interpolation data processing segment; The interpolation data processing segment is cleaned to obtain the charging segment processing data.

8. The method according to claim 1, characterized in that The step of calculating the voltage deviation value of each battery cell in the target vehicle model based on the target charging segment data includes: Sampling the current change of the battery cell of the target charging segment data to obtain a data frame corresponding to the maximum total current change moment of the target vehicle model in any charging process; Calculating the cell voltage and the voltage average value of each battery cell in the data frame; Based on the difference between the single cell voltage and the voltage average value, a voltage deviation value of each battery cell in the target vehicle model is obtained.

9. The method according to claim 1, characterized in that: The performing impedance abnormality evaluation on the target vehicle model based on the historical driving data and the voltage deviation value further includes: Based on the historical charging data, determining the initial capacity retention rate of each battery cell and the corresponding mileage attenuation rate; Performing data cleaning on the initial capacity retention rate according to the mileage reduction rate to obtain a target capacity retention rate; Performing statistical analysis on the voltage deviation values ​​to obtain the voltage deviation standard deviation of each battery cell; Based on the historical driving data, statistical analysis is performed on the capacity retention rate, the voltage deviation value, and the voltage deviation standard deviation to obtain statistical analysis features; Based on the statistical analysis characteristics, the target vehicle model is evaluated for impedance anomaly.

10. An impedance anomaly evaluation system based on cell voltage consistency, characterized in that: The system comprises: A data acquisition module, used to acquire historical charging data of a target vehicle model and historical driving data corresponding to the historical charging data; A segment extraction module, used for extracting segments from the historical charging data to obtain target charging segment data; A deviation calculation module, used to calculate the voltage deviation value of each battery cell in the target vehicle model based on the target charging segment data; The abnormality evaluation module is used to perform impedance abnormality evaluation on the target vehicle model based on the historical driving data and the voltage deviation value.

Images