Battery health analysis method, device, equipment, storage medium and program product

Abstract

The present invention discloses a battery health analysis method, device, equipment, storage medium and program product, the method comprising: preprocessing original real vehicle data to obtain multiple groups of charging segment data, the charging segment data comprising charging data of multiple current stages, determining the battery health status labels corresponding to each current stage based on the multiple groups of charging segment data, obtaining battery characteristic information, the battery characteristic information comprising voltage characteristic information, cell inconsistency characteristic information and severe operating condition characteristic information, performing health analysis on the vehicle battery to be analyzed based on the battery health status labels and battery characteristic information of each current stage, performing feature analysis based on the battery characteristic information of multiple dimensions, thereby avoiding the problem of inaccurate characterization caused by single-dimensional analysis, effectively improving the correlation between the characteristics and the battery health, effectively reducing the health analysis error of the vehicle battery, and realizing rapid and accurate evaluation of the vehicle battery health.

Description

Technical Field

[0001] The present invention relates to the field of vehicle battery technology, and in particular to a battery health analysis method, device, equipment, storage medium and program product. Background Art

[0002] Step rate conditions (i.e. step charging) are different from the current conventional constant current-constant voltage (CC-CV) charging mode. Step charging often includes multiple different constant current segments. Because it can significantly improve charging efficiency, the step charging mode is becoming more and more widely used. In the current state of health (SOH) evaluation method for real vehicle power batteries, the analysis is mainly carried out in a certain battery state of charge (SOC) range (40%-90%). This SOH evaluation method is no longer applicable to the step charging mode, resulting in inaccurate battery health analysis for step charging conditions. Summary of the invention

[0003] The main purpose of the present invention is to provide a battery health analysis method, device, equipment, storage medium and program product, aiming to solve the technical problem that the battery health assessment in the prior art cannot be applied to the step charging condition, resulting in inaccurate battery health analysis under the step charging condition.

[0004] To achieve the above object, the present invention provides a battery health analysis method, which comprises the following steps:

[0005] Preprocessing the original real vehicle data to obtain multiple sets of charging segment data, wherein the charging segment data includes charging data of multiple current stages;

[0006] Determine a battery health status label corresponding to each current stage based on the multiple sets of charging segment data;

[0007] Acquire battery characteristic information, wherein the battery characteristic information includes voltage characteristic information, cell inconsistency characteristic information, and severe operating condition characteristic information;

[0008] The health analysis of the vehicle battery to be analyzed is performed based on the battery health status label and battery characteristic information of each current stage.

[0009] Optionally, determining the battery health status label corresponding to each current stage based on the multiple sets of charging segment data includes:

[0010] Acquire charging parameters of each current stage based on the multiple sets of charging segment data;

[0011] Determine the original capacity label of each current stage according to the charging parameter;

[0012] Filter out valid capacity labels that meet preset label conditions from the original capacity labels;

[0013] The battery health status label corresponding to each current stage is determined according to the effective capacity label and the initial charging capacity label, and the initial charging capacity label is the capacity label of each current stage when the vehicle battery to be analyzed is in an initial state.

[0014] Optionally, the filtering out effective capacity labels that meet preset label conditions from the original capacity labels includes:

[0015] Determining the number of charging segments of the charging segment data and the number of tags of the original capacity tag;

[0016] Determining a sample utilization rate in each current stage based on the number of charging segments and the number of tags;

[0017] Determine the maximum capacity and the minimum capacity of each current stage according to the original capacity label;

[0018] Determining the discreteness of each current stage based on the maximum capacity and the minimum capacity;

[0019] Filter out effective capacity labels that meet preset label conditions from the original capacity labels according to the sample utilization and the dispersion.

[0020] Optionally, obtaining battery characteristic information includes:

[0021] Obtain voltage probability density data of the vehicle battery during the aging process and voltage data corresponding to the voltage probability density peak;

[0022] Acquiring voltage characteristic information of a vehicle battery based on the voltage probability density data and voltage data corresponding to the voltage probability density peak value;

[0023] Determining inconsistency data of each current stage based on the multiple sets of charging segment data;

[0024] Acquire cell inconsistency feature information of the vehicle battery according to the inconsistency data, wherein the cell inconsistency feature information includes cell voltage inconsistency feature information and cell temperature inconsistency feature information;

[0025] Acquire discharge information of the vehicle battery under a preset severe working condition based on the multiple sets of charging segment data;

[0026] Acquire the severe operating condition characteristic information of the vehicle battery according to the discharge information.

[0027] Optionally, the preprocessing of the original real vehicle data to obtain multiple sets of charging segment data includes:

[0028] Clean the original real vehicle data for abnormal data and obtain the data to be processed;

[0029] Filtering out initial data satisfying a preset state condition from the data to be processed;

[0030] Cutting the initial data into charging segments;

[0031] Determine whether there is data missing in the initial data after the charging segment is cut;

[0032] If there is missing data, the initial data after the charging segment is cut is filled with missing data to obtain multiple sets of charging segment data;

[0033] If there is no data missing, the initial data after the charging segment is cut is used as the charging segment data.

[0034] Optionally, the health analysis of the vehicle battery to be analyzed based on the battery health status label and battery characteristic information at each current stage includes:

[0035] Obtain the mapping relationship between the battery health status label and the battery characteristic information at each current stage;

[0036] Building a regression model based on the mapping relationship;

[0037] Obtain target battery characteristic information of the vehicle battery to be analyzed;

[0038] The target battery characteristic information is input into the regression model for health analysis to obtain the health analysis result of the vehicle battery to be analyzed.

[0039] In addition, to achieve the above object, the present invention also provides a battery health analysis device, the battery health analysis device comprising:

[0040] A preprocessing module, used to preprocess the original real vehicle data to obtain multiple sets of charging segment data, wherein the charging segment data includes charging data of multiple current stages;

[0041] A label calculation module, used to determine the battery health status label corresponding to each current stage based on the multiple groups of charging segment data;

[0042] A feature analysis module, used to obtain battery feature information, wherein the battery feature information includes voltage feature information, cell inconsistency feature information and severe operating condition feature information;

[0043] The health analysis module is used to perform health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information at each current stage.

[0044] In addition, to achieve the above-mentioned objectives, the present application also proposes a battery health analysis device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the battery health analysis method as described above.

[0045] In addition, to achieve the above objectives, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the battery health analysis method described above are implemented.

[0046] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the battery health analysis method described above are implemented.

[0047] The present invention obtains multiple groups of charging segment data by preprocessing original real vehicle data, and the charging segment data includes charging data of multiple current stages; determines the battery health status label corresponding to each current stage based on the multiple groups of charging segment data; obtains battery characteristic information, and the battery characteristic information includes voltage characteristic information, battery cell inconsistency characteristic information and severe operating condition characteristic information; performs health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information of each current stage; because the present invention realizes the cutting of charging data by preprocessing original real vehicle data; obtains charging data of multiple current stages, and calculates battery health status labels based on multiple groups of charging segment data, thereby ensuring the accuracy of label calculation; obtains battery characteristic information of different dimensions, and performs feature analysis based on multiple dimensions, thereby avoiding the problem of inaccurate representation caused by single-dimensional analysis, effectively improving the correlation between features and battery health, effectively reducing the health analysis error of vehicle batteries, and realizing rapid and accurate evaluation of vehicle battery health. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 It is a structural schematic diagram of a battery health analysis device in a hardware operating environment involved in an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of a first embodiment of a battery health analysis method according to the present invention;

[0052] Figure 3 This is a flow chart of a second embodiment of a battery health analysis method according to the present invention;

[0053] Figure 4 A schematic diagram of a flow chart of a third embodiment of a battery health analysis method according to the present invention;

[0054] Figure 5 The PDF variation curve of the vehicle battery at different aging stages in the third embodiment of the battery health analysis method of the present invention;

[0055] Figure 6 A schematic diagram of a flow chart of a fourth embodiment of a battery health analysis method according to the present invention;

[0056] Figure 7 This is a schematic diagram of the current comparison of the original real vehicle data before and after preprocessing;

[0057] Figure 8 This is a schematic diagram of voltage comparison of the original real vehicle data before and after preprocessing;

[0058] Fig. 9 A schematic diagram of a battery health status label sample in the current phase of the battery health analysis method of the present invention;

[0059] Fig.10 A schematic diagram of calculation results of voltage characteristic information of the battery health analysis method of the present invention;

[0060] Fig.11 A schematic diagram of calculation results of cell inconsistency characteristic information of the battery health analysis method of the present invention;

[0061] Fig.12 A schematic diagram of calculation results of the severe operating condition characteristic information of the battery health analysis method of the present invention;

[0062] Fig.13 This is a structural block diagram of the first embodiment of the battery health analysis device of the present invention.

[0063] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0065] Reference Figure 1 , Figure 1A schematic diagram of the structure of a battery health analysis device in a hardware operating environment according to an embodiment of the present invention.

[0066] like Figure 1 As shown, the battery health analysis device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (RandomAccess Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0067] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the battery health analysis device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0068] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a battery health analysis program.

[0069] exist Figure 1 In the battery health analysis device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the battery health analysis device of the present invention can be set in the battery health analysis device, and the battery health analysis device calls the battery health analysis program stored in the memory 1005 through the processor 1001, and executes the battery health analysis method provided in the embodiment of the present invention.

[0070] The embodiment of the present invention provides a battery health analysis method, referring to Figure 2 , Figure 2 FIG. 4 is a flow chart of a first embodiment of a battery health analysis method according to the present invention.

[0071] In this embodiment, the battery health analysis method includes the following steps:

[0072] Step S10: pre-processing the original real vehicle data to obtain multiple groups of charging segment data.

[0073] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes a battery health analysis device (hereinafter referred to as the analysis device) as an example to illustrate this embodiment and the following embodiments.

[0074] It should be noted that the charging segment data includes charging data of multiple current stages. The above current stages can be multiple different constant current segments in the step rate charging condition. For example: using the actual operating data of a new energy vehicle, the vehicle is charged from 0% SOC to full charge in accordance with the 110A, 95A, 46A, and 14A step current modes. Since the user's electrical behavior habits are relatively random, the actual charging mode may include one or more step currents.

[0075] It should be noted that the original real vehicle data can be the actual historical vehicle operation data collected by the analysis equipment. The analysis equipment can collect the operation data of multiple vehicles in advance, such as the vehicle data, drive motor data, and rechargeable energy storage device data of each vehicle, including 24 data types such as data time, vehicle speed, vehicle status, total voltage, and total current.

[0076] It is understandable that the above preprocessing may be to process the original real vehicle data by means of data screening, data cutting, etc., so as to retain valid charging data and cut the charging data into multiple groups of charging segment data.

[0077] It should be noted that the charging segment data may be the step rate charging condition data of the vehicle, each set of charging segment data corresponds to one charging condition, and each set of charging segment data includes charging data of multiple current stages in the step rate charging condition.

[0078] In a specific implementation, the analysis device can collect data from one or more vehicles based on a collection interval (for example, a collection interval of 20 seconds), collect historical vehicle data of the vehicles, and obtain charging data of the vehicles under multiple historical charging conditions by preprocessing the historical vehicle data.

[0079] Step S20: determining a battery health status label corresponding to each current stage based on the multiple sets of charging segment data.

[0080] It should be noted that the battery health status label can be a battery health status label, that is, a SOH (State of Health) label. The battery health status label can indicate the battery aging degree corresponding to each current stage, or reflect the battery life status.

[0081] In some embodiments, the analysis device may determine the remaining capacity percentage of each current stage based on the ratio between the current maximum charge capacity and the initial maximum charge capacity of each current stage, thereby determining the battery health status label corresponding to each current stage.

[0082] Step S30: Obtain battery characteristic information.

[0083] It should be noted that the battery characteristic information includes voltage characteristic information, battery cell inconsistency characteristic information and severe operating condition characteristic information.

[0084] It can be understood that the above-mentioned voltage characteristic information can be the voltage probability density characteristic information of the battery during the aging process. As the battery ages more, its probability density peak and the voltage corresponding to the peak are changing. The analysis equipment can perform characteristic analysis based on the probability density peak and the voltage corresponding to the peak during the battery aging process to obtain the voltage characteristic information.

[0085] It should be noted that as the battery usage time increases, the inconsistency between different cells in the battery will also damage the health of the battery system. Therefore, the analysis equipment can analyze the inconsistency characteristics of the battery cells through the temperature difference information in each charging segment of the battery to obtain the cell inconsistency characteristic information.

[0086] It is understandable that the severe operating condition characteristic information may be characteristic information of the battery under severe operating conditions. The aforementioned severe operating conditions may include deep discharge conditions, abnormally high temperature conditions, and abnormally low temperature conditions. Deep discharge and abnormally high and low temperature conditions will accelerate the aging rate of the battery system. The analysis device may perform severe operating condition characteristic analysis based on the charge and discharge data of the battery under severe operating conditions to obtain severe operating condition characteristic information.

[0087] Step S40: Perform health analysis on the vehicle battery to be analyzed based on the battery health status label and battery characteristic information at each current stage.

[0088] It should be noted that the analysis device can perform analysis (such as regression analysis) based on the battery health status label and battery characteristic information of each current stage, and evaluate the battery health status of the vehicle battery to be analyzed based on the analysis results.

[0089] Furthermore, in order to accurately evaluate the battery health status, the above step S40 includes:

[0090] Obtain the mapping relationship between the battery health status label and the battery characteristic information at each current stage;

[0091] Building a regression model based on the mapping relationship;

[0092] Obtain target battery characteristic information of the vehicle battery to be analyzed;

[0093] The target battery characteristic information is input into the regression model for health analysis to obtain the health analysis result of the vehicle battery to be analyzed.

[0094] It should be noted that the regression model may be a machine learning model of numerical regression. The target battery characteristic information may be characteristic information of the vehicle battery to be analyzed, and the target battery characteristic information may include voltage characteristic information, cell inconsistency characteristic information, and adverse operating condition characteristic information of the vehicle battery to be analyzed.

[0095] It can be understood that at each current stage n, the analysis device can construct a numerical regression model (which can be extended to a machine learning model) according to the following formula, where SOHn is the battery health status label calculated at different current stages, To calculate the battery characteristic information in three dimensions at different current stages.

[0096]

[0097] It should be noted that the vehicle battery to be analyzed may be a battery of unknown health status, and therefore the charging segment data of the vehicle battery to be analyzed is also unknown. The analysis device can extract the target battery characteristic information of the vehicle battery to be analyzed (including voltage characteristic information, cell inconsistency characteristic information and harsh operating condition characteristic information of the vehicle battery to be analyzed), and input the target battery characteristic information into the regression model to obtain the health analysis result of the vehicle battery to be analyzed.

[0098] It can be understood that if the battery health status label screened out from the charging data of the vehicle battery to be analyzed only involves one current stage, the target battery characteristic information of the vehicle battery to be analyzed is input into the regression model to directly output the SOH (battery health status) analysis result.

[0099] If the battery health status label screened out by the charging data of the vehicle battery to be analyzed involves multiple current stages, a SOH analysis result is output for each current stage, and then the average weighted sum of the SOH analysis results of multiple current stages is performed to obtain the final health analysis result, referring to the following formula, where is the average weighting coefficient. For example, if 2 step currents are included, the average weighting coefficient is 1 / 2; if 3 step currents are included, the average weighting coefficient is 1 / 3, and so on.

[0100]

[0101] This embodiment obtains multiple groups of charging segment data by preprocessing the original real vehicle data, and the charging segment data includes charging data of multiple current stages; determines the battery health status label corresponding to each current stage based on the multiple groups of charging segment data; obtains battery characteristic information, and the battery characteristic information includes voltage characteristic information, battery cell inconsistency characteristic information and severe operating condition characteristic information; performs health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information of each current stage; because this embodiment realizes the segmentation of charging data by preprocessing the original real vehicle data; obtains charging data of multiple current stages, and calculates battery health status labels based on multiple groups of charging segment data, thereby ensuring the accuracy of label calculation; obtains battery characteristic information of different dimensions, and performs feature analysis based on multiple dimensions, thereby avoiding the problem of inaccurate representation caused by single-dimensional analysis, effectively improving the correlation between features and battery health, effectively reducing the health analysis error of vehicle batteries, and realizing rapid and accurate evaluation of vehicle battery health.

[0102] refer to Figure 3 , Figure 3 FIG. 4 is a flow chart of a second embodiment of a battery health analysis method according to the present invention.

[0103] Based on the above first embodiment, in this embodiment, step S20 further includes:

[0104] Step S201: acquiring charging parameters of each current stage based on the multiple sets of charging segment data.

[0105] It should be noted that each set of charging segment data may be composed of charging data under multiple current stages. The above charging parameters may include the charging current, charging time, SOC value at the start of charging and SOC value at the end of charging, etc., at each current stage.

[0106] Step S202: determining the original capacity label of each current stage according to the charging parameter.

[0107] It should be noted that the original capacity label may be a current capacity label at each current stage calculated based on the charging parameters at each current stage, and the original capacity label may indicate the current maximum charging capacity value corresponding to each current stage.

[0108] It can be understood that in order to avoid the calculation error of current to capacity, the present embodiment calculates the capacity according to the current at different stages (for example, the value fluctuation within ±10% can be considered as the current at the same stage), and calculates the battery capacity at different current steps based on the following formula, where: The current maximum charging capacity (i.e. the original capacity label), is the charging current, is the charging time, SOC2 and SOC1 are the SOC change values ​​at the start and end of charging respectively, wherein for the same step current, SOC2 and SOC1 should be consistent.

[0109]

[0110] Step S203: Filter out valid capacity labels that meet preset label conditions from the original capacity labels.

[0111] It should be noted that the effective capacity tag may be a tag with good capacity data quality among the original capacity tags, which can be used for effective battery health calculation. The above-mentioned preset tag condition may be high sample utilization and / or low discreteness.

[0112] It can be understood that by filtering out valid capacity labels from the original capacity labels, the amount of data analysis for health evaluation is reduced, the accuracy of health evaluation is improved, and the interference of invalid data is reduced.

[0113] Furthermore, in order to reduce the influence of abnormal current fluctuation and noise, improve data quality, and ensure analysis accuracy, the above step S203 may include:

[0114] Determining the number of charging segments of the charging segment data and the number of tags of the original capacity tag;

[0115] Determining a sample utilization rate in each current stage based on the number of charging segments and the number of tags;

[0116] Determine the maximum capacity and the minimum capacity of each current stage according to the original capacity label;

[0117] Determining the discreteness of each current stage based on the maximum capacity and the minimum capacity;

[0118] Filter out effective capacity labels that meet preset label conditions from the original capacity labels according to the sample utilization and the dispersion.

[0119] It is understandable that due to factors such as abnormal current fluctuations and sensor noise, not all of the original capacity labels initially calculated by the analysis device can be directly used for modeling. In order to improve data quality and ensure the accuracy of subsequent analysis, this embodiment can filter out effective capacity labels from the original capacity labels.

[0120] It should be noted that this embodiment can evaluate the capacity data calculated by current at different stages based on the two principles of "making full use of historical data and making the data more robust" and using two evaluation factors of "sample utilization rate + discreteness".

[0121] It should be noted that the sample utilization is calculated using the following formula, where M is the sample utilization, n is the number of capacity tags including the original capacity tags calculated based on the current of this stage, and N is the number of charging segments after preprocessing.

[0122]

[0123] It should be noted that the discreteness of each current stage can be calculated using the following formula, where R is the discreteness, Q max , Q min They are the maximum and minimum capacities calculated at each current stage respectively.

[0124]

[0125] In some embodiments, the preset label condition may be and / or When , it is considered that the capacity data corresponding to this current stage has good quality and can be used as an effective capacity label for subsequent effective SOH calculation.

[0126] Step S204: determining the battery health status label corresponding to each current stage according to the effective capacity label and the initial charging capacity label.

[0127] It should be noted that the initial charging capacity label is the capacity label of each current stage when the battery of the vehicle to be analyzed is in the initial state. The initial charging capacity label can be the initial maximum charging capacity value of each current stage when the battery of the vehicle to be analyzed is in the initial state without being used.

[0128] It is understandable that based on the filtered effective capacity data, the effective battery health status label can be calculated using the following formula, where: is the effective capacity label, that is, the capacity parameter represented by the effective capacity label of each current stage; Q1 is the initial charging capacity label, that is, the maximum charging capacity of each current stage in the initial state.

[0129]

[0130] This embodiment obtains the charging parameters of each current stage based on the multiple groups of charging segment data, determines the original capacity label of each current stage according to the charging parameters, screens out the effective capacity label that meets the preset label condition from the original capacity label, and determines the battery health status label corresponding to each current stage according to the effective capacity label and the initial charging capacity label, and the initial charging capacity label is the capacity label of each current stage when the battery of the vehicle to be analyzed is in the initial state; since this embodiment calculates the capacity label based on different current stages, the calculation error of the capacity due to different currents under step rate conditions is effectively avoided, and the invalid capacity labels caused by abnormal current fluctuations and sensor noise are effectively excluded by screening the capacity labels, thereby ensuring the accuracy of the battery health status label.

[0131] refer to Figure 4 , Figure 4 FIG. 4 is a flow chart of a third embodiment of a battery health analysis method according to the present invention.

[0132] Based on the above embodiments, in this embodiment, in step S30, the method further includes:

[0133] Step S301: Obtain voltage probability density data of a vehicle battery during an aging process and voltage data corresponding to a voltage probability density peak value.

[0134] It should be noted that during the aging process of vehicle batteries, the peak value of the voltage probability density (PDF) and the voltage corresponding to the peak value will change. Figure 5 , Figure 5 The PDF change curve of the battery at different aging stages. It can be seen from the figure that as the battery ages, the peak value of the probability density curve and the voltage corresponding to the peak value are increasing. The voltage probability density data is calculated according to the following formula.

[0135]

[0136] Step S302: Acquire voltage characteristic information of the vehicle battery based on the voltage probability density data and the voltage data corresponding to the voltage probability density peak value.

[0137] It can be understood that the voltage characteristic information is obtained by referring to the following formula, where PDF peak represents the voltage probability density peak (i.e. PDF peak), U MPDF represents the PDF peak voltage, is the voltage characteristic value.

[0138]

[0139] It should be noted that, referring to the following table, the following table is a comparison data table of the results of using different indicators to judge the degree of battery aging. The following table shows the comparison of the results of using different indicators to judge the degree of battery aging. It can be seen that due to the low sampling frequency of actual operation data, the collection of peak points is sometimes missed. For example, if states 2 and 3 are used alone to judge the degree of aging, it will be misjudged that the battery pack aging state 2 is more serious than the battery pack aging state 3; or for example, if states 4 and 5 are used alone to judge the degree of aging, it will be misjudged that the aging degree of state 4 is the same as that of state 5; and the eigenvalue increases monotonically with the increase of the number of cycles, which proves that compared with the traditional single PDF eigenvalue, the voltage-related eigenvalue proposed in this embodiment can effectively reduce the probability of misjudgment caused by excessive sampling period.

[0140]

[0141] Step S303: determining inconsistency data of each current stage based on the multiple sets of charging segment data.

[0142] It should be noted that the inconsistency data may be data of voltage inconsistency and temperature inconsistency in the same charging segment.

[0143] Step S304: acquiring cell inconsistency characteristic information of the vehicle battery according to the inconsistency data, wherein the cell inconsistency characteristic information includes cell voltage inconsistency characteristic information and cell temperature inconsistency characteristic information.

[0144] It is understandable that as the usage time increases, the inconsistency between different cells will also damage the health of the battery system. The cell inconsistency characteristic value is calculated according to the following formula, where U I is the cumulative voltage inconsistency, T I is the accumulated temperature inconsistency.

[0145]

[0146] In some embodiments, the above-mentioned cumulative voltage inconsistency U I It can be counted the number of times the maximum difference between the highest and lowest voltages of a single cell in the same charging segment exceeds 10%. The above cumulative temperature inconsistency T I It can be to count the number of times the maximum difference between the highest and lowest temperatures of a cell in the same charging segment exceeds 3°C.

[0147] Step S305: obtaining discharge information of the vehicle battery under preset severe working conditions based on the multiple sets of charging segment data.

[0148] It should be noted that the preset severe working conditions may include deep discharge conditions, abnormally high temperature conditions, and abnormally low temperature conditions. Deep discharge and abnormally high and low temperature conditions will accelerate the aging of the battery system. The analysis equipment can perform severe working condition feature analysis based on the charging and discharging data of the battery under severe working conditions to obtain severe working condition feature information.

[0149] Step S306: Acquire the severe operating condition characteristic information of the vehicle battery according to the discharge information.

[0150] It is understandable that deep discharge and abnormal high and low temperature conditions will accelerate the aging of the battery system. In this embodiment, the severe operating condition characteristic value of the vehicle battery can be calculated based on the following formula, where U L and T L They respectively represent the cumulative number of deep discharges (discharge cut-off voltage is lower than 15% of the total voltage) and the cumulative number of high and low temperature operating conditions (outside the optimal operating temperature of 20℃~45℃).

[0151]

[0152] This embodiment obtains voltage probability density data of a vehicle battery during an aging process and voltage data corresponding to a voltage probability density peak value, obtains voltage characteristic information of the vehicle battery based on the voltage probability density data and the voltage data corresponding to the voltage probability density peak value, determines inconsistency data of each current stage based on the multiple sets of charging segment data, obtains battery cell inconsistency characteristic information of the vehicle battery based on the inconsistency data, the battery cell inconsistency characteristic information includes battery cell voltage inconsistency characteristic information and battery cell temperature inconsistency characteristic information, obtains discharge information of the vehicle battery under preset severe working conditions based on the multiple sets of charging segment data, and obtains severe working condition characteristic information of the vehicle battery based on the discharge information.

[0153] refer to Figure 6 , Figure 6 FIG. 4 is a flow chart of a fourth embodiment of a battery health analysis method according to the present invention.

[0154] Based on the above embodiment, in this embodiment, the step S10 further includes:

[0155] Step S101: cleaning the original real vehicle data for abnormal data to obtain data to be processed.

[0156] It should be noted that abnormal data cleaning may include data with abnormal vehicle state matching (for example, data with non-monotonically increasing time data) and data with abnormal data values ​​(for example, sensor failure makes the data abnormally large or small).

[0157] It can be understood that in this embodiment, the original real vehicle data can be cleaned for abnormal data by using logical judgment to delete duplicate values, correct matching error data, and can also use the quartile box plot to eliminate over-limit data, where the quartile distance and upper and lower limit edges of the box plot refer to the following formula, where Q3 and Q1 are the upper and lower quartiles, respectively, and L up and L low Filter upper and lower limits respectively.

[0158]

[0159]

[0160]

[0161] Step S102: Filter out initial data satisfying a preset state condition from the data to be processed.

[0162] It should be noted that the preset state condition may be data that the vehicle state is "engine off" and / or "parking state" and the current is negative.

[0163] Step S103: cutting the initial data into charging segments.

[0164] It is understandable that the analysis device may divide the data in the initial data with a sampling time interval greater than 5 minutes into two charging segments, namely, a front and a back charging segment.

[0165] In some embodiments, the analysis device may delete charging segments having a sampling time of less than 2 minutes from the initial data.

[0166] Step S104: determining whether there is data missing in the initial data after the charging segment is cut;

[0167] Step S105: if there is data missing, the initial data after the charging segment is cut is filled with missing data to obtain multiple sets of charging segment data;

[0168] Step S106: If there is no data missing, the initial data after the charging segment is cut is used as the charging segment data.

[0169] It should be noted that the analysis device can determine whether the time interval between the previous and next data in the initial data after the charging segment is cut is greater than the sampling time. If so, the previous and next two rows of data need to be padded.

[0170] It is understandable that the analysis device can use the mean interpolation method for continuous values ​​such as "accumulated mileage" in the data. The calculation method is shown in the following formula, where To fill the gap, L2, L1, t2, and t1 are the cumulative mileage and data time of the first and last two rows of data, respectively, T is the sampling time, and ROUND is the rounding function.

[0171]

[0172] It should be noted that the analysis equipment can use the Lagrange interpolation method for fluctuating parameters such as voltage, current, SOC, and temperature. The calculation method is shown in the following formula, where y(t) is the middle data to be filled, and y(j) is the j known data before and after. is the Lagrangian operator.

[0173]

[0174] In some embodiments, the analysis device may collect data from one or more vehicles based on a collection interval (for example, a collection interval of 20 seconds), collect historical vehicle data of the vehicles, and obtain charging data of the vehicles under multiple historical charging conditions by preprocessing the historical vehicle data.

[0175] For example, refer to Figure 7 and Figure 8 , Figure 7 and Figure 8 They are the current comparison diagram and voltage comparison diagram of the original real vehicle data before and after preprocessing, where: Figure 7 The ordinate is current, the abscissa is time, Before filling represents the current data before preprocessing, and After filling represents the current data after preprocessing; Figure 8 The ordinate is voltage, the abscissa is time, Before filling represents the voltage data before preprocessing, and After filling represents the voltage data after preprocessing. After data preprocessing, 328 original charging segments are obtained. It can be seen that the four step currents (i.e., four current stages) of the vehicle are around 110A, 97A, 46A, and 14A, respectively, which are subsequently referred to as the first stage, the second stage, the third stage, and the fourth stage.

[0176] The analysis device calculates the battery health status labels at each current stage and finally selects 318 label samples from the first and second stages for subsequent feature extraction and battery health analysis. Fig. 9 , Fig. 9 Schematic diagram of battery health status label samples in the first and second stages, where: Fig. 9 The vertical axis represents the battery health status label (i.e. the percentage parameter of the battery health status), and the horizontal axis represents the vehicle mileage. The original fragment utilization rate is 97%, which avoids data waste to the greatest extent.

[0177] The analysis equipment obtains battery characteristic information. Taking the first stage as an example, three characteristic values ​​(voltage characteristic, cell inconsistency characteristic and bad working condition characteristic) are calculated respectively. Fig.10 , Fig.11 , Fig.12 ,in Fig.10 , Fig.11 , Fig.12 Schematic diagrams of calculation of voltage characteristic information, cell inconsistency characteristic information and severe working condition characteristic information, where μ is voltage characteristic information, ω is cell inconsistency characteristic information, γ is severe working condition characteristic information, Fig.10 , Fig.11 and Fig.12 The horizontal axis is the number of times the vehicle battery is charged (Charging Cycles).

[0178] The analysis equipment used the first 80% of the SOH labels (battery health status labels) and characteristic value data from the first and second phases to establish a regression model, and then used the remaining 20% ​​of the data to verify the model accuracy. The mean absolute error (MAE), mean error (MBE), root mean square deviation or root mean square error (RMSE), and goodness of fit (R2) errors were selected to evaluate the accuracy of the model assessment. MAE, MAPE, RSME, and R2 were 0.0101, 0.0106, 0.0134, and 0.7453, respectively.

[0179] This embodiment cleans the original real vehicle data for abnormal data to obtain data to be processed, screens out initial data that meets preset state conditions from the data to be processed, cuts the initial data into charging segments, and determines whether there is data missing in the initial data after the charging segment cutting. If there is data missing, the missing data is filled in the initial data after the charging segment cutting to obtain multiple groups of charging segment data; if there is no data missing, the initial data after the charging segment cutting is used as the charging segment data, thereby effectively reducing the negative impact of abnormal data and invalid data and improving data quality. By cutting the data into multiple charging segment data, the probability of misjudgment caused by excessive sampling period is effectively reduced, and the accuracy of battery health analysis is greatly improved.

[0180] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which a battery health analysis program is stored. When the battery health analysis program is executed by a processor, the steps of the battery health analysis method described above are implemented.

[0181] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0182] The computer-readable storage medium may be included in the battery health analysis device; or may exist independently without being assembled into the battery health analysis device.

[0183] In addition, an embodiment of the present invention further provides a computer program product, including a battery health analysis program, which implements the steps of the battery health analysis method described above when executed by a processor.

[0184] The specific implementation of the computer program product of the present invention is basically the same as the above-mentioned battery health analysis method embodiments, and will not be repeated here.

[0185] Reference Fig.13 , Fig.13 This is a structural block diagram of the first embodiment of the battery health analysis device of the present invention.

[0186] like Fig.13 As shown, the battery health analysis device proposed in the embodiment of the present invention includes:

[0187] A preprocessing module 10 is used to preprocess the original real vehicle data to obtain multiple sets of charging segment data, wherein the charging segment data includes charging data of multiple current stages;

[0188] A label calculation module 20, configured to determine a battery health status label corresponding to each current stage based on the multiple sets of charging segment data;

[0189] A feature analysis module 30, used to obtain battery feature information, wherein the battery feature information includes voltage feature information, cell inconsistency feature information, and severe operating condition feature information;

[0190] The health analysis module 40 is used to perform health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information at each current stage.

[0191] Furthermore, the label calculation module 20 is also used to obtain the charging parameters of each current stage based on the multiple groups of charging segment data; determine the original capacity label of each current stage according to the charging parameters; filter out the effective capacity labels that meet the preset label conditions from the original capacity labels; determine the battery health status label corresponding to each current stage according to the effective capacity label and the initial charging capacity label, and the initial charging capacity label is the capacity label of each current stage when the battery of the vehicle to be analyzed is in the initial state.

[0192] Furthermore, the label calculation module 20 is also used to determine the number of charging segments of the charging segment data and the number of labels of the original capacity label; determine the sample utilization rate of each current stage based on the number of charging segments and the number of labels; determine the maximum capacity and the minimum capacity of each current stage according to the original capacity label; determine the discreteness of each current stage based on the maximum capacity and the minimum capacity; and filter out valid capacity labels that meet preset label conditions from the original capacity labels according to the sample utilization and the discreteness.

[0193] Furthermore, the feature analysis module 30 is also used to obtain voltage probability density data of the vehicle battery during the aging process and voltage data corresponding to the voltage probability density peak; obtain voltage characteristic information of the vehicle battery based on the voltage probability density data and the voltage data corresponding to the voltage probability density peak; determine inconsistency data of each current stage based on the multiple sets of charging segment data; obtain battery cell inconsistency characteristic information of the vehicle battery according to the inconsistency data, the battery cell inconsistency characteristic information includes battery cell voltage inconsistency characteristic information and battery cell temperature inconsistency characteristic information; obtain discharge information of the vehicle battery under preset harsh working conditions based on the multiple sets of charging segment data; and obtain harsh working condition characteristic information of the vehicle battery according to the discharge information.

[0194] Furthermore, the preprocessing module 10 is also used to clean the original real vehicle data for abnormal data to obtain data to be processed; filter out initial data that meets preset state conditions from the data to be processed; cut the initial data into charging segments; determine whether there is data missing in the initial data after the charging segment cutting; if there is data missing, fill the missing data in the initial data after the charging segment cutting to obtain multiple groups of charging segment data; if there is no data missing, use the initial data after the charging segment cutting as the charging segment data.

[0195] Furthermore, the health analysis module 40 is also used to obtain the mapping relationship between the battery health status label and the battery characteristic information at each current stage; construct a regression model based on the mapping relationship; obtain the target battery characteristic information of the vehicle battery to be analyzed; input the target battery characteristic information into the regression model for health analysis, and obtain the health analysis result of the vehicle battery to be analyzed.

[0196] This embodiment obtains multiple groups of charging segment data by preprocessing the original real vehicle data, and the charging segment data includes charging data of multiple current stages; determines the battery health status label corresponding to each current stage based on the multiple groups of charging segment data; obtains battery characteristic information, and the battery characteristic information includes voltage characteristic information, battery cell inconsistency characteristic information and severe operating condition characteristic information; performs health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information of each current stage; because this embodiment realizes the segmentation of charging data by preprocessing the original real vehicle data; obtains charging data of multiple current stages, and calculates battery health status labels based on multiple groups of charging segment data, thereby ensuring the accuracy of label calculation; obtains battery characteristic information of different dimensions, and performs feature analysis based on multiple dimensions, thereby avoiding the problem of inaccurate representation caused by single-dimensional analysis, effectively improving the correlation between features and battery health, effectively reducing the health analysis error of vehicle batteries, and realizing rapid and accurate evaluation of vehicle battery health.

[0197] The battery health analysis device provided by the present application adopts the battery health analysis method in the above embodiment, which can solve the technical problems of battery health analysis. Compared with the prior art, the beneficial effects of the battery health analysis device provided by the present application are the same as the beneficial effects of the battery health analysis method provided by the above embodiment, and the other technical features in the battery health analysis device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0198] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0199] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0200] In addition, for technical details not fully described in this embodiment, reference can be made to the battery health analysis method provided in any embodiment of the present invention, and will not be repeated here.

[0201] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0202] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0203] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0204] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A battery health analysis method, characterized in that: The battery health analysis method comprises: Preprocessing the original real vehicle data to obtain multiple sets of charging segment data, wherein the charging segment data includes charging data of multiple current stages; Determine a battery health status label corresponding to each current stage based on the multiple sets of charging segment data; Acquire battery characteristic information, wherein the battery characteristic information includes voltage characteristic information, cell inconsistency characteristic information, and severe operating condition characteristic information; Perform health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information of each current stage; The step of determining the battery health status label corresponding to each current stage based on the multiple sets of charging segment data includes: Acquire charging parameters of each current stage based on the multiple sets of charging segment data; Determine an original capacity label of each current stage according to the charging parameter, wherein the original capacity label represents a current maximum charging capacity value corresponding to each current stage; Determining the number of charging segments of the charging segment data and the number of tags of the original capacity tag; Determining a sample utilization rate in each current stage based on the number of charging segments and the number of tags; Determine the maximum capacity and the minimum capacity of each current stage according to the original capacity label; Determining the discreteness of each current stage based on the maximum capacity and the minimum capacity; Filtering out effective capacity labels that meet preset label conditions from the original capacity labels according to the sample utilization rate and the discreteness; The battery health status label corresponding to each current stage is determined according to the effective capacity label and the initial charging capacity label, and the initial charging capacity label is the capacity label of each current stage when the vehicle battery to be analyzed is in an initial state.

2. The battery health analysis method according to claim 1, characterized in that: The obtaining of battery characteristic information includes: Obtain voltage probability density data of the vehicle battery during the aging process and voltage data corresponding to the voltage probability density peak; Acquiring voltage characteristic information of a vehicle battery based on the voltage probability density data and voltage data corresponding to the voltage probability density peak value; Determining inconsistency data of each current stage based on the multiple sets of charging segment data; Acquire cell inconsistency feature information of the vehicle battery according to the inconsistency data, wherein the cell inconsistency feature information includes cell voltage inconsistency feature information and cell temperature inconsistency feature information; Acquire discharge information of the vehicle battery under a preset severe working condition based on the multiple sets of charging segment data; Acquire the severe operating condition characteristic information of the vehicle battery according to the discharge information.

3. The battery health analysis method according to any one of claims 1 to 2, characterized in that: The original real vehicle data is preprocessed to obtain multiple sets of charging segment data, including: Clean the original real vehicle data for abnormal data and obtain the data to be processed; Filtering out initial data satisfying a preset state condition from the data to be processed; Cutting the initial data into charging segments; Determine whether there is data missing in the initial data after the charging segment is cut; If there is missing data, the initial data after the charging segment is cut is filled with missing data to obtain multiple sets of charging segment data; If there is no data missing, the initial data after the charging segment is cut is used as the charging segment data.

4. The battery health analysis method according to any one of claims 1 to 2, characterized in that: The health analysis of the vehicle battery to be analyzed based on the battery health status label and battery characteristic information of each current stage includes: Obtain the mapping relationship between the battery health status label and the battery characteristic information at each current stage; Building a regression model based on the mapping relationship; Obtain target battery characteristic information of the vehicle battery to be analyzed; The target battery characteristic information is input into the regression model for health analysis to obtain the health analysis result of the vehicle battery to be analyzed.

5. A battery health analysis device, characterized in that: The battery health analysis device comprises: A preprocessing module, used to preprocess the original real vehicle data to obtain multiple sets of charging segment data, wherein the charging segment data includes charging data of multiple current stages; A label calculation module, used to determine the battery health status label corresponding to each current stage based on the multiple groups of charging segment data; A feature analysis module, used to obtain battery feature information, wherein the battery feature information includes voltage feature information, cell inconsistency feature information and severe operating condition feature information; A health analysis module, used to perform health analysis on the battery of the vehicle to be analyzed based on the battery health status label and battery characteristic information of each current stage; Wherein, the label calculation module is also used for: Acquire charging parameters of each current stage based on the multiple sets of charging segment data; Determine an original capacity label of each current stage according to the charging parameter, wherein the original capacity label is a current maximum charging capacity value corresponding to each current stage; Determining the number of charging segments of the charging segment data and the number of tags of the original capacity tag; Determining a sample utilization rate in each current stage based on the number of charging segments and the number of tags; Determine the maximum capacity and the minimum capacity of each current stage according to the original capacity label; Determining the discreteness of each current stage based on the maximum capacity and the minimum capacity; Filtering out effective capacity labels that meet preset label conditions from the original capacity labels according to the sample utilization rate and the discreteness; The battery health status label corresponding to each current stage is determined according to the effective capacity label and the initial charging capacity label, and the initial charging capacity label is the capacity label of each current stage when the vehicle battery to be analyzed is in an initial state.

6. A battery health analysis device, characterized in that: The battery health analysis device comprises: a memory, a processor, and a battery health analysis program stored in the memory and executable on the processor, wherein the battery health analysis program is configured to implement the battery health analysis method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a battery health analysis program, and when the battery health analysis program is executed by a processor, the battery health analysis method according to any one of claims 1 to 4 is implemented.

8. A computer program product, characterized in that The computer program product comprises a battery health analysis program, and when the battery health analysis program is executed by a processor, the steps of the battery health analysis method according to any one of claims 1 to 4 are implemented.

Images