Battery data processing method, retired battery cleaning equipment and storage medium

Abstract

The embodiment of the invention provides a battery data processing method, retired battery cleaning equipment and a storage medium. The method comprises the following steps: acquiring historical acquisition data of a retired battery; determining abnormal data and normal data of the decommissioned battery from the historical collected data; the abnormal data comprises repeated data and conflict data; and cleaning the repeated data and the conflict data, and obtaining target performance data of the retired battery based on the cleaned data and the normal data. The method is used for achieving the effect of improving the accuracy of battery data cleaning.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery data processing method, a retired battery cleaning device and a storage medium. Background Art

[0002] As new energy vehicles become more and more popular, the development of power battery-related technologies that provide power for new energy vehicles has also attracted more attention, especially the retirement and cascade utilization of power batteries. For the cascade utilization of retired power batteries, they are usually selected to be used as a whole package in the form of battery modules or battery packs, which reduces the cost of cascade utilization.

[0003] The whole pack utilization strategy for retired power batteries usually requires obtaining historical operating data information of the battery pack to conduct a comprehensive assessment of the battery's performance, safety, value, etc. Based on this, the data needs to be cleaned to obtain valuable data.

[0004] However, the existing data cleaning methods at least have the problem of inaccurate battery data cleaning of retired power batteries. Summary of the invention

[0005] The embodiments of the present application provide a battery data processing method, a retired battery cleaning device and a storage medium, so as to achieve the effect of improving the accuracy of battery data cleaning.

[0006] In a first aspect, an embodiment of the present application provides a battery data processing method, the method comprising:

[0007] Obtain historical collection data of retired batteries;

[0008] Determine abnormal data and normal data of retired batteries from historically collected data; abnormal data includes duplicate data and conflicting data;

[0009] Duplicate data and conflicting data are cleaned, and target performance data of retired batteries are obtained based on the cleaned data and normal data.

[0010] In a possible implementation, determining abnormal data of retired batteries from historically collected data includes:

[0011] Obtain multiple data items with associated relationships from historically collected data;

[0012] Obtain data change information corresponding to each data item in multiple data items;

[0013] In the case that the data change information of the multiple data items is different, the battery data in the multiple data items are determined as conflicting data.

[0014] In a possible implementation, determining abnormal data of retired batteries from historically collected data includes:

[0015] Get the data items corresponding to the same message time;

[0016] If there are duplicate data items, the data items are determined to be duplicate data.

[0017] In a possible implementation, the abnormal data further includes blank data, invalid data and outlier data; and the method further includes:

[0018] Use blank data to replace invalid data and outlier data to obtain updated blank data;

[0019] The updated blank data is cleaned, and the target performance data of the retired battery is obtained based on the cleaned data and normal data.

[0020] In a possible implementation, the updated blank data is cleaned, and target performance data of the retired battery is obtained based on the cleaned data and normal data, including:

[0021] Get the percentage of updated blank data in abnormal data;

[0022] When the data proportion is greater than a preset proportion threshold, data interpolation is performed on the blank data, and the target performance data of the retired battery is obtained based on the data after data interpolation and the normal data.

[0023] In a possible implementation, data interpolation is performed on blank data, including:

[0024] When the data type of the blank data item corresponding to the blank data is non-numeric data, obtaining an associated data item that has an associated relationship with the blank data item;

[0025] According to the data change information of the associated data items, data interpolation is performed on the blank data items;

[0026] When the data type of the blank data item corresponding to the blank data is numerical data, the discrete blank data item is interpolated in the nearest place, and the continuous blank data item is interpolated in the linear place.

[0027] In a possible implementation, after obtaining the data proportion of the updated blank data in the abnormal data, the method further includes:

[0028] When the data ratio is less than or equal to the ratio threshold, delete the blank data.

[0029] In a possible implementation, duplicate data and conflicting data are cleaned, and target performance data of retired batteries is obtained based on the cleaned data and normal data, including:

[0030] Keep one of the data items corresponding to the duplicate data, and delete the other data items corresponding to the duplicate data;

[0031] The conflicting data is marked to obtain marked conflicting data; the marked conflicting data is used to indicate that the conflicting data is to be corrected;

[0032] Based on the corrected conflicting data, the retained duplicate data and the normal data, the target performance data of the retired battery is obtained.

[0033] In a second aspect, an embodiment of the present application provides a retired battery cleaning device, including: a memory, a processor;

[0034] Memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory, so that the processor executes various possible implementations of the method as described above.

[0036] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement various possible implementation methods of the method as described above.

[0037] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements various possible implementation methods of the above method when executed by a processor.

[0038] The battery data processing method, retired battery cleaning device and storage medium provided in the embodiment of the present application identify abnormal duplicate data and conflicting data from the historical collected data of retired batteries, and clean the duplicate data and conflicting data. After cleaning, the target performance data of retired batteries is obtained together with normal data. In this way, the duplicate data and conflicting data are more consistent with the data collection situation of retired batteries, thereby improving the accuracy of cleaning the collected data of retired batteries, and further improving the accuracy of the performance data of retired batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 Schematic diagram of the battery data processing method provided in this application Figure 1 ;

[0041] Figure 2 Schematic diagram of the battery data processing method provided in this application Figure 2 ;

[0042] Figure 3 Schematic diagram of the battery data processing method provided in this application Figure 3 ;

[0043] Figure 4 Schematic diagram of the battery data processing method provided in this application Figure 3 ;

[0044] Figure 5 Schematic diagram of the battery data processing method provided in this application Figure 5 ;

[0045] Figure 6 A flowchart of the steps of identifying and cleaning abnormal data contained in a data set provided by the present application;

[0046] Figure 7 A flowchart of the steps of identifying and classifying abnormal data provided in this application;

[0047] Figure 8 A schematic diagram of the process of interpolating blank values ​​provided in this application;

[0048] Fig. 9 A schematic diagram of the structure of the battery data processing device provided in this application;

[0049] Fig.10 A schematic diagram of the structure of the retired battery cleaning equipment provided for this application.

[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the present application clearer, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation methods described in the following exemplary embodiments do not represent all implementation methods consistent with the present application. On the contrary, they are merely examples of devices and implementation methods consistent with some aspects of the present application as detailed in the attached claims. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a series of units, systems, products or devices are not necessarily limited to those units clearly listed, but may include units that are not clearly listed or inherent to these products or devices.

[0053] As new energy vehicles become more and more popular, the development of power battery-related technologies that provide power for new energy vehicles has also attracted more attention, especially the retirement and recycling of power batteries.

[0054] For the cascade utilization of retired power batteries, it is usually chosen to utilize the whole package in the form of battery modules or battery packs, which reduces the cost of cascade utilization. The production of some battery products for cascade utilization is achieved by disassembling all retired power battery packs to the single-cell level, and then sorting and reorganizing the single-cell level. Although the consistency of retired batteries is guaranteed under the appropriate sorting strategy, it will inevitably consume a lot of manpower and material resources, which greatly weakens the reuse value of retired batteries for cascade utilization. Therefore, the whole-package utilization strategy for the cascade utilization of power batteries is usually chosen, and it is usually necessary to obtain the historical operating data information of the battery pack in order to conduct a comprehensive evaluation of the battery's performance, safety, value, etc.

[0055] How to obtain the required information from massive historical big data is a key link in realizing big data applications. However, these historical data are not only huge in quantity, but also of poor quality. Data will be affected by noise, errors, and loss during sampling and transmission. Only after data cleaning can valuable data be obtained. To determine the data cleaning method, it is necessary to first clarify the purpose and needs. However, most of the existing data cleaning methods have a wide range of applications or are not thoroughly cleaned. They cannot be used for big data cleaning of power battery cascade utilization, resulting in inaccurate battery data cleaning of retired power batteries.

[0056] In view of the above background, it can be seen that in the related art, there is a technical problem of inaccurate battery data cleaning.

[0057] The battery data processing method provided in the present application solves the technical problem of how to improve the accuracy of battery data cleaning by determining duplicate data and conflicting data so that the cleaned data is more consistent with the data of retired batteries.

[0058] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0059] Figure 1 Schematic diagram of the battery data processing method provided in this application Figure 1 ,like Figure 1 As shown, this embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes S101 to S103, wherein:

[0060] S101. Obtain historical collection data of retired batteries.

[0061] Among them, retired batteries refer to retired power batteries. Power batteries can be batteries that provide power for vehicles, and can be battery packs, battery groups, single cells, etc. Historically collected data can be data collected during the use of power batteries. Historically collected data can be data stored for power batteries.

[0062] For example, the terminal can obtain the historical collected data of the retired battery to be cleaned from the battery database. The historical collected data can be further used as the data to be cleaned, and the performance data of the retired battery can be obtained after cleaning the historical collected data. The performance data can be used to further analyze the performance of the retired battery.

[0063] S102. Determine abnormal data and normal data of retired batteries from historically collected data; the abnormal data includes duplicate data and conflicting data.

[0064] Among them, abnormal data refers to battery data collected with abnormal conditions. Abnormal data may include duplicate data, conflicting data, blank data, invalid data, and outlier data. As an example, duplicate data refers to completely repeated data item data. For example, at the same data collection time, two sets of data collected are exactly the same data, then the two sets of data can be considered duplicate data. Conflicting data can be two sets of conflicting data. For example, if the data item corresponding to the "charging state" is displayed as "uncharged state", but the data item corresponding to the "SOC" at the corresponding time is gradually increasing, it is considered that the data item corresponding to the "charging state" conflicts with the data item corresponding to the "SOC".

[0065] Exemplarily, the terminal can identify and analyze the historically collected data to obtain normal data without errors and abnormal data with abnormalities of the retired battery. The abnormal data may include duplicate data and conflicting data. Further, the abnormal data including duplicate data and conflicting data can be cleaned to obtain the cleaned data. In this way, the present application can identify and analyze the duplicate data and conflicting data of retired batteries, thereby ensuring the comprehensive cleaning of the abnormal data of retired batteries and improving the accuracy of battery data cleaning of retired batteries.

[0066] Optionally, blank data, invalid data, outlier data, etc. can be identified from historically collected data, and the above-mentioned different types of abnormal data can be cleaned separately to obtain cleaned data, which can be used as performance data of retired batteries for performance analysis.

[0067] S103, performing cleaning processing on duplicate data and conflicting data, and obtaining target performance data of retired batteries based on the cleaned data and normal data.

[0068] The target performance data may be data used to perform performance analysis on retired batteries. The target performance data refers to normal battery data.

[0069] Exemplarily, the terminal can clean the duplicate data and conflicting data separately. For example, the terminal can retain one of the duplicate data and delete the other duplicate data to obtain the data cleaned for the duplicate data; the terminal marks the conflicting data, and the user can confirm the error of the marked conflicting data and correct it to obtain the data cleaned for the conflicting data. In this way, the present application can clean the identified duplicate data and conflicting data, and can clean the abnormal data of retired batteries more comprehensively, which is more in line with the data cleaning situation of retired batteries, thereby improving the accuracy of cleaning the abnormal data of retired batteries.

[0070] In this embodiment, the battery data processing method provided by the present application identifies abnormal duplicate data and conflicting data from the historical data collected from retired batteries, and cleans the duplicate data and conflicting data. After cleaning, the target performance data of the retired batteries is obtained together with the normal data. In this way, the duplicate data and conflicting data are more consistent with the data collection situation of the retired batteries, thereby improving the accuracy of cleaning the collected data of the retired batteries, and further improving the accuracy of the performance data of the retired batteries.

[0071] In an exemplary embodiment, Figure 2 Schematic diagram of the battery data processing method provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment Figure 1Based on the embodiment, the step S102 is described in detail, and abnormal data of retired batteries is determined from historically collected data, including S201 to S203, wherein:

[0072] S201, acquiring multiple data items having an associated relationship from historically collected data;

[0073] S202, obtaining data change information corresponding to each data item in a plurality of data items;

[0074] S203: When the data change information of the multiple data items is different, the battery data in the multiple data items are determined as conflicting data.

[0075] The association relationship may be a relationship determined according to a correlation coefficient. The data item may be a data set collected according to the data type. For example, for a battery pack obtained by connecting 8 single cells in series, the record format of the "single cell voltage" item is: [3.471, 3.474, 3.472, 3.468, 3.456, 3.448, 3.477, 3.469], that is, one of the data items corresponding to the "single cell voltage" is [3.471, 3.474, 3.472, 3.468, 3.456, 3.448, 3.477, 3.469]. The data change information may be trend information of data change. For example, if the battery power gradually increases, the data change information refers to the increase in battery power.

[0076] Exemplarily, the terminal may determine the association relationship between multiple data types, for example, the association relationship may be determined by a correlation coefficient, and the correlation coefficient may be a Pearson correlation coefficient, a Spearman correlation coefficient, a Kendall rank correlation coefficient, etc. The terminal may determine the data change information corresponding to each data item among multiple data items with an association relationship. If the data change information of multiple data items is the same, it can be considered that there is no conflict between the multiple data items, that is, the multiple data items are not conflicting data. If the data change information of multiple data items is different, it can be considered that the battery data in the multiple data items is conflicting data.

[0077] Optionally, whether the data is conflicting can be determined by judging whether the corresponding data in the associated data items are contradictory. If there is a contradiction, it is determined to be conflicting data. The terminal can determine whether there is a contradiction between the data by establishing an association relationship between the associated data items. The establishment of the association relationship can be performed at the offline end, and the correlation between any two data items is calculated by the Pearson correlation coefficient. The calculation method is: in and σ x , σ yThey are the average value and standard deviation of two data items respectively. When 0.8 < r < 1.0, it is considered that there is a very strong correlation between the two data items, and an association relationship is established between them. For example, there is a strong correlation between the "charging status" item and the "SOC" item. When SOC i -SOC i-1 > 0, the "charging status" item in the row where SOC i is located should be displayed as "charging". If the "charging status" item is displayed as "not charging", but the "SOC" during the corresponding period is gradually increasing, it is considered that the data of the "charging status" item conflicts with the corresponding data of the "SOC" item. Since it is often impossible to directly determine which of the two data items is incorrect in the case of conflicting data, it is necessary to identify and mark it first, and then process it manually.

[0078] In this embodiment, by obtaining multiple data items with an association relationship, and the data change information corresponding to each data item among the multiple data items with an association relationship; when the data change information of the multiple data items is different, the battery data among the multiple data items can be determined as conflicting data. Thus, conflicting data can be effectively determined, thereby improving the accuracy of cleaning the collected data of retired batteries, and further improving the accuracy of the performance data of retired batteries.

[0079] Optionally, the step of S102 to determine the abnormal data of the retired battery from the historical collected data includes:

[0080] S204, obtaining the data items corresponding to the same message time;

[0081] S205, if there are duplicate data items, determining the data items as duplicate data.

[0082] Among them, the message time can be the timestamp of receiving data or the timestamp of collecting battery data. It can be understood that when collecting data of power batteries, battery data with timestamps should be obtained, and the message time can be determined according to the timestamp. The data item can be a data set containing the collected battery data.

[0083] Exemplarily, the terminal can determine whether there are duplicate data items among the data items within the same message time. If there are exactly duplicate data items, the duplicate data items can be considered as duplicate data. If there are no duplicate data items within the same message time, it can be considered that there is no duplicate data within this message time.

[0084] Optionally, the terminal identifies the data items with the same message time from the historical collected data and determines whether there are exactly the same data items. If there are at least two exactly the same data items, these at least two data items can be determined as duplicate data.

[0085] In this embodiment, by determining whether there are repeated data items in the data items within the same message time, the repeated data can be effectively screened out, and the repeated data can be further cleaned. Screening out the repeated data and cleaning it is beneficial to improve the accuracy of battery data cleaning of retired batteries, which is more in line with the data cleaning situation of power batteries.

[0086] In an exemplary embodiment, Figure 3 Schematic diagram of the battery data processing method provided in this application Figure 3 ,like Figure 3 As shown, in this embodiment Figure 1 Based on the embodiment, the battery data processing method is described in detail, the abnormal data also includes blank data, invalid data and outlier data; the method also includes:

[0087] S301. Use blank data to replace invalid data and outlier data to obtain updated blank data.

[0088] S302: Clean the updated blank data, and obtain target performance data of the retired battery based on the cleaned data and normal data.

[0089] Among them, blank data can be missing data, or lost data caused by loss of acquisition signal. Invalid data refers to data outside the preset valid range. Usually, data outside the preset range can become invalid data, which will affect the judgment of retired battery performance. Outlier data can be data that exceeds the outlier standard, and the outlier standard can be the 3σ criterion.

[0090] Exemplarily, the terminal may use blank values ​​to replace invalid data and outlier data to obtain updated blank data, so that blank data, invalid data and outlier data can be effectively processed. The terminal may clean the updated blank data to obtain data cleaned for the blank data. As an example, the terminal may obtain target performance data of retired batteries based on data cleaned for blank data, data cleaned for duplicate data, data cleaned for conflicting data, and normal data.

[0091] Optionally, for the data value of the data item, it can be determined whether the data value is within a preset range, and if it is not within the preset range, it can be determined as an "invalid value". For different data items, data description requirements should be specified to determine the valid value range of the data.

[0092] For outlier data, we can judge whether the data is within the 3σ range. If it is not within the 3σ range, it can be determined as an "outlier". The 3σ criterion, also known as the Rheinland criterion, is based on three times the standard deviation of the collected data under a given confidence probability (generally 99.7%). Data exceeding this standard is considered an outlier. The calculation method is: arithmetic mean Standard Deviation When the collected data meets the following requirements: When x i is an "outlier".

[0093] In practical applications, by using blank data to replace invalid data and outlier data, invalid data and outlier data can be effectively processed, and by cleaning the updated blank data, the blank data of retired batteries can be processed in a targeted manner, which is conducive to accurately cleaning the data of retired batteries.

[0094] Optionally, the updated blank data is cleaned, and target performance data of the retired battery is obtained based on the cleaned data and normal data, including:

[0095] Get the percentage of updated blank data in abnormal data;

[0096] When the data proportion is greater than a preset proportion threshold, data interpolation is performed on the blank data, and the target performance data of the retired battery is obtained based on the data after data interpolation and the normal data.

[0097] The data proportion refers to the proportion of the data, which can be a percentage. The proportion threshold can be a threshold set for the data proportion.

[0098] Exemplarily, the terminal can determine the proportion of the updated blank data in the abnormal data to obtain the data proportion corresponding to the blank data. The terminal can determine the preset proportion threshold for blank data, and can judge the data proportion of blank data based on the preset proportion threshold. If the data proportion is greater than the preset proportion threshold, the blank data can be interpolated to obtain new battery data, and further, the target performance data of the retired battery can be obtained based on the data after the data interpolation processing for the blank table data and the normal data. In this way, the blank data can be effectively cleaned to avoid excessive blank data being deleted, resulting in inaccurate performance analysis of retired batteries, thereby improving the accuracy of data cleaning for retired batteries.

[0099] In practical applications, by obtaining the data ratio of updated blank data in abnormal data, the blank data can be interpolated when the data ratio is greater than the preset ratio threshold, and the blank data can be effectively cleaned, thereby improving the accuracy of data cleaning for retired batteries.

[0100] Optionally, data interpolation is performed for blank data, including:

[0101] When the data type of the blank data item corresponding to the blank data is non-numeric data, obtaining an associated data item that has an associated relationship with the blank data item;

[0102] According to the data change information of the associated data items, data interpolation is performed on the blank data items;

[0103] When the data type of the blank data item corresponding to the blank data is numerical data, the discrete blank data item is interpolated in the nearest place, and the continuous blank data item is interpolated in the linear place.

[0104] The associated data items refer to data items with associated relationships.

[0105] Exemplarily, if the data type of a blank data item with blank data is non-numeric data, that is, the data contained in the blank data item is not a numeric value, the terminal can determine the associated data item that is associated with the blank data item, and the associated data item can be a data item of numeric data or a data item of non-numeric data. The terminal can interpolate the blank data in the blank data item according to the data change information of the associated data item. For example, when the "charging status" item is displayed as "blank value", it can be filled according to the association rule between it and the "SOC" item. As an example, the association rule between the two is: when SOC i -SOC i-1 >0, SOC i The "Charging Status" item in the row should be filled in as "Charging", otherwise it should be filled in as "Not Charging". i-1 For SOC i The state of charge corresponding to the previous time, SOC refers to state of charge, that is, the state of charge.

[0106] If the data type of the blank data item with blank data is numeric data, the discrete blank data item can be interpolated at the nearest location, and the continuous blank data item can be interpolated linearly. For example, "numeric data" needs to be further subdivided into "discrete" and "continuous". The "discrete" data is filled by the "nearest interpolation" principle, and replaced with the last observation before the missing value or the observation after the missing value, and the two can take the one with the closest time series distance. As an example, the "highest voltage battery cell code" item or the "lowest temperature probe serial number" item, etc., since the sampling point corresponding to the voltage or temperature extreme value in a short period of time is often the same, the value with the closest time series distance to the data point in the data item is selected for filling. "Continuous" data can be filled by the "linear interpolation" principle. For example, the "highest value of battery cell voltage" item and the "lowest temperature value" item, etc., are calculated by fitting a first-order polynomial equation of the adjacent non-empty data before and after the data point in the data item. The calculation method is: construct a linear relationship for the local data in the data item that needs to be interpolated. After determining the k value, the filling value corresponding to the missing value at the middle moment can be obtained according to the linear relationship. and is the value of two adjacent times, t i and t i-1 for two adjacent times.

[0107] In practical applications, whether the data is blank or missing, if so, it is determined as a "blank value". Among them, for the single cell voltage collection item or the sampled temperature collection item, if the actual number of records is less than the number that should be recorded, the data is considered missing, but the "blank value" at this time can only choose to delete the row, and cannot choose the interpolation method, because it is impossible to determine which single cell or temperature probe the missing sampled data in the collection belongs to.

[0108] In this embodiment, by obtaining associated data items that have an associated relationship with blank data items when the data type of the blank data items corresponding to the blank data is non-numeric data; data interpolation can be performed on the blank data items according to data change information of the associated data items; and by performing local interpolation on discrete blank data items and linear interpolation on continuous blank data items when the data type of the blank data items corresponding to the blank data is numeric data, the data types of different blank data items can be cleaned in a targeted manner, the battery data can be cleaned more accurately, and the accuracy of performance data cleaning of retired batteries can be improved.

[0109] Optionally, after obtaining the data ratio of the updated blank data in the abnormal data, the method further includes:

[0110] When the data ratio is less than or equal to the ratio threshold, delete the blank data.

[0111] Exemplarily, if the data proportion is less than or equal to the proportion threshold, it means that there is only a small amount of blank data after the update. The terminal can delete the blank data, and there will be no impact or little impact on the performance analysis of the retired battery, which can be ignored. In this way, the steps for cleaning blank data can be reduced, and the cleaning efficiency of battery data of retired batteries can be improved.

[0112] In this embodiment, by deleting blank data when the data proportion is less than or equal to the proportion threshold, the blank data can be processed in a targeted manner, thereby improving the accuracy of data cleaning and also improving the efficiency of data cleaning.

[0113] In an exemplary embodiment, Figure 4 Schematic diagram of the battery data processing method provided in this application Figure 4 ,like Figure 4 As shown, in this embodiment Figure 1 Based on the embodiment, step S103 is described in detail. In step S103, duplicate data and conflicting data are cleaned, and target performance data of retired batteries are obtained based on the cleaned data and normal data, including S401 to S403, wherein:

[0114] S401: retain one of the data items corresponding to the duplicate data, and delete the other data items corresponding to the duplicate data.

[0115] S402: Mark the conflicting data to obtain marked conflicting data; the marked conflicting data is used to indicate that correction processing is to be performed on the conflicting data.

[0116] S403: Obtain target performance data of the retired battery based on the corrected conflicting data, the retained duplicate data, and the normal data.

[0117] Exemplarily, the terminal can process duplicate data. It can be understood that duplicate data means that multiple data items are exactly the same. In this way, only one of the data items can be retained, and the other duplicate data items can be deleted. In this way, the retained data items can be used as data after cleaning the duplicate data. The terminal can mark the conflicting data to obtain the marked conflicting data. The user can correct the marked conflicting data, and the terminal can obtain the corrected data for the conflicting data. The terminal can obtain the target performance data of the retired battery based on the corrected conflicting data, the data retained for the duplicate data, the data obtained after cleaning the blank data, and the normal data.

[0118] Optionally, the "conflict value" situation is relatively complex and changeable, and the terminal may temporarily mark it specially and perform manual cleaning.

[0119] In this embodiment, by retaining one of the data items corresponding to the duplicate data and deleting the other data items corresponding to the duplicate data, the duplicate data can be cleaned, and the conflicting data can be marked to obtain the marked conflicting data. The conflicting data can be cleaned to be more in line with the data collection situation of retired batteries, thereby improving the accuracy of cleaning the collected data of retired batteries, and further improving the accuracy of the performance data of retired batteries.

[0120] In an exemplary embodiment, Figure 5 Schematic diagram of the battery data processing method provided in this application Figure 5 , the method comprising:

[0121] S501. Obtain a historical operation data set of a vehicle to be cleaned.

[0122] Exemplarily, generally, operation data of the vehicle is collected and stored, which may at least include required real-time information collection items of new energy vehicles.

[0123] S502. Clarify cleaning requirements and objectives, retain test data items related to the power battery, and eliminate irrelevant items.

[0124] For example, some of the information collection items required for new energy vehicles are meaningless for the performance analysis and value assessment of power batteries. In order to reduce the amount of data processing, irrelevant data items, such as engine-related data, can be directly eliminated.

[0125] S503: Identify and clean abnormal data contained in the data set.

[0126] S504. Add or calculate other required data items as required to facilitate further processing and analysis of the data.

[0127] For example, the real-time acquisition items include the maximum and minimum values ​​of the single cell voltage and the temperature of a single probe, so data items such as the voltage extreme and standard deviation, temperature extreme and standard deviation can be added, which is conducive to the next step of data processing and analysis.

[0128] S505: Obtain a target performance data set of a final power battery.

[0129] Optionally, Figure 6 A flowchart of the steps of identifying and cleaning abnormal data contained in a data set provided in this application, such as Figure 6 As shown, in step S503, identifying and cleaning abnormal data contained in the data set includes:

[0130] S601. Acquire a power battery-related historical data set for which data collection items have been filtered.

[0131] S602: Determine whether all data items have been cleaned. If not, execute S603: analyze the next column of data items. If yes, execute S604: obtain the cleaned data set.

[0132] For the current data item, S605, determine whether the included data is normal, if not, execute S606, classify the abnormal data.

[0133] Different processing methods are adopted for the classified abnormal data. Among them, "blank value" is retained; S607, "invalid value" and "outlier value" are replaced by blank value.

[0134] S608. Keep one of the rows and delete the other rows. Optionally, keep one of the rows of "duplicate values" and delete the remaining duplicate data rows. Moreover, the identification and processing of "duplicate values" are only performed on the "message time" data item and skipped on other data items.

[0135] S609, special marking and manual processing. The "conflicting values" are more complex and changeable. They can be specially marked first, and then manually processed after all data cleaning is completed. Among them, blank value is regarded as one of the blank data, invalid value is regarded as one of the invalid data, invalid value is regarded as one of the duplicate data, and conflict value is regarded as one of the conflict data.

[0136] S610, calculate whether the proportion of "blank values" exceeds the threshold, if so, execute S611, interpolate the blank values, if not, execute S612, delete the row where the "blank value" is located.

[0137] Optionally, calculate the proportion of "blank values" to all data of the current data item and set a threshold. When the proportion of "blank values" is less than the threshold, it is considered that the amount of missing data is small and the impact on data analysis can be ignored. The deletion method is directly used to delete the row where the "blank value" is located. When the proportion of "blank values" is greater than or equal to the threshold, the "blank values" need to be interpolated to complete the data set.

[0138] Optionally, Figure 7 A flowchart of the steps of identifying and classifying abnormal data provided in this application is as follows: Figure 7 As shown, the identification and classification of abnormal data includes:

[0139] S701, analyzing all data in the data item;

[0140] S702. Determine whether the data is blank or missing. If so, go to S703 and mark it as a blank value. Determine whether the data is blank or missing. If so, it is determined as a "blank value". Among them, for the single-cell battery voltage set item or the sampling temperature set item, if the actual recorded quantity is less than the quantity that should be recorded, the data is considered missing. However, in this case, the "blank value" can only choose to delete the row where it is located, rather than the interpolation method, because it is impossible to determine which single-cell battery or temperature probe the missing sampling data in the set belongs to.

[0141] S704. Determine whether the data is within the pre-set range. If not, go to S705 and mark it as an invalid value. If it is not within the pre-set range, it can be determined as an "invalid value". For different data items, the description requirements of the data should be specified to determine the valid value range of the data.

[0142] S706. Determine whether the data is within the 3σ range. If it is not within the 3σ range, go to S707 and mark it as an outlier value, and it can be determined as an "outlier value". The 3σ criterion, also known as the Pauta criterion, is based on three times the standard deviation of the collected data at a given confidence probability (usually 99.7%). Data exceeding this standard is considered an outlier value. The calculation method is: arithmetic mean Standard deviation When the collected data satisfies: then x i is considered an "outlier value".

[0143] S708. Whether the data is completely repeated. If so, go to S709 and mark it as a duplicate value, and it is determined as a "duplicate value". It should be noted that the identification and processing of "duplicate values" are only carried out for the "message time" data item and skipped for other data items.

[0144] S710. Determine whether the data is contradictory. If so, go to S711 and mark it as a conflict value. If there is a contradiction, it is determined as conflict data. The terminal can establish an association relationship between related data items to determine whether there is a contradiction between the data. The establishment of the association relationship can be carried out offline. Calculate the correlation between any two data items through the Pearson correlation coefficient. The calculation method is: where and σ x and σ y are the mean and standard deviation of the two data items respectively. When 0.8 < r < 1.0, it is considered that there is a very strong correlation between the two data items, and an association relationship is established between them. For example, there is a strong correlation between the "charging state" item and the "SOC" item. When SOC i -SOC i-1 > 0, SOC iThe "Charging Status" item in the row should be displayed as "Charging". If the "Charging Status" item is displayed as "Not Charging", but the "SOC" of the corresponding period is gradually increasing, it is considered that the data of the "Charging Status" item conflicts with the data corresponding to the "SOC" item. Since it is often impossible to directly determine which of the two data items is wrong in the case of conflicting data, it is necessary to identify and mark them first, and then process them manually.

[0145] Optionally, Figure 8 A flow chart of the steps for interpolating blank values ​​provided for this application, such as Figure 8 As shown, blank values ​​are interpolated, including:

[0146] Determine the data type of the data item where the current "blank value" is located, which is divided into "non-numeric data" and "numeric data";

[0147] "Non-numeric data" is filled by "association rule interpolation". For example, when the "charging state" item is displayed as "blank value", it can be filled according to the association rule between it and the "SOC" item. The association rule between the two is: when SOC i -SOC i-1 >0, SOC i The "Charging Status" item in the row should be filled in with "Charging", otherwise it should be filled in with "Not Charging".

[0148] "Numerical data" needs to be further subdivided into "discrete" and "continuous".

[0149] "Discrete" data is filled using the "nearest interpolation" principle, replacing it with the last observed value before the missing value or the observed value after the missing value, whichever is closest in time series distance. For example, the "highest voltage battery cell code" item or the "lowest temperature probe serial number" item, since the sampling point corresponding to the voltage or temperature extreme value in a short period of time is often the same, the value in the data item with the closest time series distance to the data point is selected for filling.

[0150] "Continuous" data is filled by the "linear interpolation" principle. For example, the "highest value of battery cell voltage" and "lowest temperature value" items are calculated by fitting a first-order polynomial equation to the adjacent non-empty data before and after the data point in the data item. The calculation method is to construct a linear relationship between the local data in the data item that needs to be interpolated. After determining the k value, the filling value corresponding to the missing value at the middle moment can be obtained according to the linear relationship.

[0151] In this embodiment, based on the real-time data collection of new energy vehicles and the type of abnormal data that may appear, a method for identifying and processing abnormal data is proposed, and on this basis, new data items that can be obtained through simple logic or calculation are proposed to facilitate the next step of data processing and analysis; the data cleaning method adopted in this application tries to ensure that the implementation process is highly feasible, quick and simple while meeting data requirements.

[0152] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0153] Fig. 9 A schematic diagram of the structure of the battery data processing device provided in this application, such as Fig. 9 As shown, the battery data processing device 90 provided in this embodiment includes:

[0154] The data acquisition module 901 is used to acquire historical data of retired batteries.

[0155] The abnormality determination module 902 is used to determine abnormal data and normal data of retired batteries from historically collected data; the abnormal data includes duplicate data and conflicting data.

[0156] The data cleaning module 903 is used to clean duplicate data and conflicting data, and obtain target performance data of retired batteries based on the cleaned data and normal data.

[0157] In an exemplary embodiment, the abnormality determination module 902 is used to obtain multiple data items with an associated relationship from historical collected data; obtain data change information corresponding to each data item in the multiple data items; and when the data change information of the multiple data items is different, the battery data in the multiple data items is determined as conflicting data.

[0158] In an exemplary embodiment, the abnormality determination module 902 is used to obtain data items corresponding to the same message time; if there are repeated data items, the data items are determined as repeated data.

[0159] In an exemplary embodiment, the abnormal data also includes blank data, invalid data and outlier data. The data cleaning module 903 is used to replace the invalid data and outlier data with blank data to obtain updated blank data; clean the updated blank data, and obtain the target performance data of the retired battery based on the cleaned data and normal data.

[0160] In an exemplary embodiment, the data cleaning module 903 is used to obtain the data ratio of the updated blank data in the abnormal data; when the data ratio is greater than a preset ratio threshold, the blank data is interpolated, and the target performance data of the retired battery is obtained based on the data after data interpolation and the normal data.

[0161] In an exemplary embodiment, the data cleaning module 903 is used to obtain associated data items that have an associated relationship with the blank data items when the data type of the blank data items corresponding to the blank data is non-numeric data; perform data interpolation on the blank data items based on data change information of the associated data items; and perform local interpolation on discrete blank data items and linear interpolation on continuous blank data items when the data type of the blank data items corresponding to the blank data is numeric data.

[0162] In an exemplary embodiment, the data cleaning module 903 is further configured to delete blank data when the data proportion is less than or equal to a proportion threshold.

[0163] In an exemplary embodiment, the data cleaning module 903 is used to retain one of the data items corresponding to the duplicate data and delete the other data items corresponding to the duplicate data; mark the conflicting data to obtain marked conflicting data; the marked conflicting data is used to indicate that correction processing is performed on the conflicting data; based on the corrected conflicting data, the retained duplicate data and the normal data, the target performance data of the retired battery is obtained.

[0164] The battery data processing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in this embodiment.

[0165] Fig.10 This is a schematic diagram of the structure of the retired battery cleaning equipment provided in this application. Fig.10 As shown, the retired battery cleaning device 100 provided in this embodiment includes: at least one processor 1001 and a memory 1002. Optionally, the device 100 also includes a communication component 1003. The processor 1001, the memory 1002 and the communication component 1003 are connected via a bus 1004.

[0166] In a specific implementation process, at least one processor 1001 executes the computer-executable instructions stored in the memory 1002, so that at least one processor 1001 executes the above method.

[0167] The specific implementation process of the processor 1001 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0168] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0169] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0170] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0171] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0172] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0173] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0174] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0175] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0176] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0178] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0179] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0180] It should be noted that the user information (including but not limited to user device information, user personal information, vehicle information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0181] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A battery data processing method, characterized in that: The method comprises: Obtain historical collection data of retired batteries; Determining abnormal data and normal data of the retired battery from the historically collected data; the abnormal data includes duplicate data and conflicting data; The duplicate data and the conflicting data are cleaned, and the target performance data of the retired battery is obtained based on the cleaned data and normal data.

2. The method according to claim 1, characterized in that The determining, from the historically collected data, abnormal data of the retired battery includes: Acquire multiple data items having an associated relationship from the historically collected data; Obtaining data change information corresponding to each of the data items in the plurality of data items; In the case that the data change information of the multiple data items is different, the battery data in the multiple data items are determined as conflicting data.

3. The method according to claim 1, characterized in that The determining, from the historically collected data, abnormal data of the retired battery includes: Get the data items corresponding to the same message time; If there are repeated data items, the data items are determined to be repeated data.

4. The method according to claim 1, characterized in that: The abnormal data also includes blank data, invalid data and outlier data; the method also includes: Using blank data to replace the invalid data and the outlier data to obtain updated blank data; The updated blank data is cleaned, and the target performance data of the retired battery is obtained based on the cleaned data and normal data.

5. The method according to claim 4, characterized in that The step of cleaning the updated blank data and obtaining the target performance data of the retired battery based on the cleaned data and normal data includes: Obtaining the updated data ratio of the blank data in the abnormal data; When the data proportion is greater than a preset proportion threshold, data interpolation is performed on the blank data, and the target performance data of the retired battery is obtained based on the data after data interpolation and normal data.

6. The method according to claim 5, characterized in that The interpolating the blank data includes: When the data type of the blank data item corresponding to the blank data is non-numeric data, obtaining an associated data item that has an associated relationship with the blank data item; Performing data interpolation on the blank data item according to the data change information of the associated data item; In the case that the data type of the blank data item corresponding to the blank data is numerical data, the discrete blank data item is interpolated in the nearest place, and the continuous blank data item is interpolated in the linear place.

7. The method according to claim 5, characterized in that After obtaining the updated data proportion of the blank data in the abnormal data, the method further includes: When the data proportion is less than or equal to the proportion threshold, the blank data is deleted.

8. The method according to any one of claims 1 to 7, characterized in that The cleaning process of the duplicate data and the conflicting data, and obtaining the target performance data of the retired battery based on the cleaned data and the normal data, includes: retaining one of the data items corresponding to the duplicate data, and deleting the other data items corresponding to the duplicate data; Marking the conflicting data to obtain marked conflicting data; the marked conflicting data is used to indicate that correction processing is to be performed on the conflicting data; Based on the corrected conflicting data, the retained duplicate data and the normal data, the target performance data of the retired battery is obtained.

9. A retired battery cleaning device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

11. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images