CN117269784A - Battery abnormality detection method, device, equipment and storage medium - Google Patents

Battery abnormality detection method, device, equipment and storage medium Download PDF

Info

Publication number
CN117269784A
CN117269784A CN202311452116.4A CN202311452116A CN117269784A CN 117269784 A CN117269784 A CN 117269784A CN 202311452116 A CN202311452116 A CN 202311452116A CN 117269784 A CN117269784 A CN 117269784A
Authority
CN
China
Prior art keywords
battery
detected
abnormal
reference curve
remote monitoring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311452116.4A
Other languages
Chinese (zh)
Inventor
黄俭标
姚欣跃
常毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GAC Aion New Energy Automobile Co Ltd
Original Assignee
GAC Aion New Energy Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GAC Aion New Energy Automobile Co Ltd filed Critical GAC Aion New Energy Automobile Co Ltd
Priority to CN202311452116.4A priority Critical patent/CN117269784A/en
Publication of CN117269784A publication Critical patent/CN117269784A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)
  • Tests Of Electric Status Of Batteries (AREA)

Abstract

The embodiment of the invention provides a battery abnormality detection method, device, equipment and storage medium, and relates to the technical field of electric automobiles. The battery abnormality detection method includes: acquiring a remote monitoring data set from a big data platform, and generating a reference curve according to battery characteristic data in the remote monitoring data set; and judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve, and obtaining an abnormal detection result. The embodiment of the invention can realize continuous abnormality detection of the battery to be detected, discover the abnormal battery as early as possible, and effectively ensure the technical effect of safe operation of the electric automobile.

Description

Battery abnormality detection method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of electric automobiles, in particular to a battery abnormality detection method, a device, equipment and a storage medium.
Background
With the rapid increase of new energy market share, the storage capacity of the pure electric vehicle is increased, and the failure frequency of the power battery is increased. When the battery management system reports faults, serious problems occur to the power battery, and the performance of the whole vehicle is affected.
At present, a bus tool is generally used at the after-sale end to read the historical fault code of the power battery and the battery characteristic data during collection to detect the abnormality of the battery, so that the battery characteristic information during fault occurrence cannot be obtained in real time. Considering that the power battery is declined from performance to failure to meet the safe operation requirement of the power system, a period of time is often required to elapse, and how to discover an abnormal battery early before serious problems occur in the power battery so as to effectively ensure the safe operation of the electric automobile becomes a great problem to be solved in the current urgent need.
Disclosure of Invention
The embodiment of the invention aims to provide a battery abnormality detection method, device, equipment and storage medium, which are used for realizing continuous abnormality detection of a battery to be detected, discovering an abnormal battery as soon as possible and effectively ensuring the technical effect of safe operation of an electric automobile.
In a first aspect, an embodiment of the present invention provides a method for detecting battery abnormality, including:
acquiring a remote monitoring data set from a big data platform, and generating a reference curve according to battery characteristic data in the remote monitoring data set;
and judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve, and obtaining an abnormal detection result.
In the implementation process, the battery characteristic data in the remote monitoring data set is extracted to perform abnormal detection on the battery to be detected by acquiring the remote monitoring data set from the big data platform, the battery characteristic data can be monitored for a long time by using the big data remote monitoring technology, and the normal battery and the abnormal battery can be accurately distinguished based on the recent battery characteristic data, so that the continuous abnormal detection on the battery to be detected is realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, before the acquiring the remote monitoring dataset from the big data platform, the method further comprises:
and acquiring the operation data of each battery cell in each electric automobile power battery pack in real time through a remote monitoring big data system, and uploading all the operation data to the big data platform as remote monitoring data.
In the implementation process, the operation data of each battery monomer in each electric automobile power battery pack is collected in real time through the remote monitoring big data system and is uploaded to the big data platform as remote monitoring data, so that the operation data of a large number of batteries can be monitored remotely in real time, and the big data platform is ensured to store the operation data of a large number of batteries with the same type as the battery to be detected.
Further, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes:
screening all battery charging currents meeting a first preset condition from the remote monitoring data set, and determining battery charging capacity and battery driving mileage corresponding to each battery charging current;
and combining the battery charging capacity and the battery driving mileage corresponding to all the battery charging currents, and generating a first reference curve by taking the battery charging capacity and the battery driving mileage corresponding to one battery charging current as a point coordinate.
In the implementation process, the first reference curve is generated by extracting the battery characteristic data of the battery charging capacity from the remote monitoring data set, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the battery charging capacity, so that the abnormal detection of the battery to be detected is continuously carried out, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, based on the reference curve, judging whether the battery to be detected is an abnormal battery according to the characteristic data of the battery to be detected, so as to obtain an abnormal detection result, which specifically includes:
Determining a battery charging capacity corresponding to the driving mileage of the battery to be detected as a reference battery charging capacity based on the first reference curve;
when the charging capacity of the battery to be detected is larger than or equal to the charging capacity of the reference battery, judging that the battery to be detected is a normal battery;
and when the charging capacity of the battery to be detected is smaller than the charging capacity of the reference battery, judging that the battery to be detected is an abnormal battery.
In the implementation process, the to-be-detected battery is subjected to outlier analysis based on the first reference curve generated according to the battery characteristic data of the battery charging capacity, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the abnormal detection of the to-be-detected battery is continuously realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes:
screening all groups of battery dynamic pressure differences meeting a second preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to the average value of the battery dynamic pressure differences of each group;
And combining battery off-line time or battery driving mileage corresponding to the average value of all the battery dynamic pressure differences, and generating a second reference curve by taking the average value of one group of the battery dynamic pressure differences and the corresponding battery off-line time or battery driving mileage as a point coordinate.
In the implementation process, the battery characteristic data of the dynamic pressure difference of the battery is extracted from the remote monitoring data set to generate the second reference curve, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the dynamic pressure difference of the battery, so that the abnormal detection of the battery to be detected is continuously carried out, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, based on the reference curve, judging whether the battery to be detected is an abnormal battery according to the characteristic data of the battery to be detected, so as to obtain an abnormal detection result, which specifically includes:
based on the second reference curve, determining an average value of battery dynamic pressure differences corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery dynamic pressure difference;
when the dynamic pressure difference of the battery to be detected is smaller than or equal to the dynamic pressure difference of the reference battery, judging that the battery to be detected is a normal battery;
And when the dynamic pressure difference of the battery to be detected is larger than the dynamic pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
In the implementation process, the to-be-detected battery is subjected to outlier analysis based on the second reference curve generated according to the battery characteristic data of the battery dynamic pressure difference, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the abnormal detection of the to-be-detected battery is continuously realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes:
screening all battery static pressure differences meeting a third preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to each battery static pressure difference;
and generating a third reference curve by taking one battery static pressure difference and the corresponding battery off-line duration or battery driving mileage as a point coordinate in combination with all battery off-line durations or battery driving mileage corresponding to the battery static pressure differences.
In the implementation process, the battery characteristic data of the battery static pressure difference is extracted from the remote monitoring data set to generate the third reference curve, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the battery static pressure difference, so that the abnormal detection of the battery to be detected is continuously carried out, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Further, based on the reference curve, judging whether the battery to be detected is an abnormal battery according to the characteristic data of the battery to be detected, so as to obtain an abnormal detection result, which specifically includes:
based on the third reference curve, determining a battery static pressure difference corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery static pressure difference;
when the static pressure difference of the battery to be detected is smaller than or equal to the static pressure difference of the reference battery, judging that the battery to be detected is a normal battery;
and when the static pressure difference of the battery to be detected is larger than the static pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
In the implementation process, the to-be-detected battery is subjected to outlier analysis based on the third reference curve generated according to the battery static pressure difference, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the abnormal detection of the to-be-detected battery is continuously realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In a second aspect, an embodiment of the present invention provides a battery abnormality detection apparatus including:
The reference curve generation module is used for acquiring a remote monitoring data set from the big data platform and generating a reference curve according to battery characteristic data in the remote monitoring data set;
and the battery abnormality detection module is used for judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve to obtain an abnormality detection result.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor and the processor, when executing the computer program, implements the battery anomaly detection method as described above.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, wherein the computer readable storage medium includes a stored computer program; wherein the apparatus in which the computer-readable storage medium is controlled to execute the battery abnormality detection method as described above when the computer program is run.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments of the present invention will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a battery abnormality detection method according to a first embodiment of the present invention;
FIG. 2 is a schematic view of a first reference curve of an example of an alternative embodiment of the first embodiment of the present invention;
FIG. 3 is a schematic diagram of a second reference curve of an example of an alternative embodiment of the first embodiment of the present invention;
FIG. 4 is a schematic view of a third reference curve of an example of an alternative embodiment of the first embodiment of the present invention;
fig. 5 is a schematic structural diagram of a battery abnormality detection device according to a second embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.
It should be noted that: in the description of the present invention, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance. Meanwhile, step numbers herein are only for convenience of explanation of the embodiments of the present invention, and are not used as limiting the order of execution of the steps. The method provided by the embodiment of the invention can be executed by the related terminal equipment, and the following description uses the electric automobile processor as an execution main body.
Referring to fig. 1, fig. 1 is a flowchart of a battery abnormality detection method according to a first embodiment of the present invention. The first embodiment of the present invention provides a battery abnormality detection method, including steps S101 to S102:
s101, acquiring a remote monitoring data set from a big data platform, and generating a reference curve according to battery characteristic data in the remote monitoring data set;
s102, based on the reference curve, judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected, and obtaining an abnormal detection result.
Illustratively, a large amount of remote monitoring data is stored on the big data platform, wherein all remote monitoring data comprise operation data of each battery cell in each electric automobile power battery pack acquired in real time.
According to the actual application requirement, all remote monitoring data acquired in any time period are called from a big data platform to obtain a remote monitoring data set, battery characteristic data in the remote monitoring data set are extracted, and a reference curve is generated according to the battery characteristic data.
The method comprises the steps of obtaining characteristic data of a battery to be detected, judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on a reference curve, and obtaining an abnormal detection result, so that a user can be prompted to maintain the battery to be detected and recall the battery to be detected when the battery to be detected is judged to be the abnormal battery, serious problems such as thermal runaway and the like caused by continuous decline of the performance of the battery to be detected are avoided, and safe operation of an electric automobile is effectively guaranteed.
According to the embodiment of the invention, the battery characteristic data in the remote monitoring data set is extracted to perform abnormality detection on the battery to be detected by acquiring the remote monitoring data set from the big data platform, the battery characteristic data can be monitored for a long time by applying the big data remote monitoring technology, and the normal battery and the abnormal battery are accurately distinguished based on the recent battery characteristic data, so that the continuous abnormality detection on the battery to be detected is realized, the abnormal battery is found as early as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an alternative embodiment, before the acquiring the remote monitoring dataset from the big data platform, the method further comprises: and acquiring the operation data of each battery cell in each electric automobile power battery pack in real time through a remote monitoring big data system, and uploading all the operation data as remote monitoring data to a big data platform.
As an example, the operation data of each battery cell in each electric automobile power battery pack is collected in real time through a remote monitoring big data system, and all the operation data are uploaded to a big data platform as remote monitoring data. All operation data comprise battery charging current, battery charging voltage, battery charging temperature, battery dynamic pressure difference, battery static pressure difference and the like at all times in the whole life cycle of the electric automobile.
According to the embodiment of the invention, the operation data of each battery monomer in each electric automobile power battery pack is collected in real time through the remote monitoring big data system and is uploaded to the big data platform as remote monitoring data, so that the operation data of a large number of batteries can be monitored remotely in real time, and the big data platform is ensured to store a large number of operation data of batteries with the same type as the battery to be detected.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all battery charging currents meeting a first preset condition from a remote monitoring data set, and determining battery charging capacity and battery driving mileage corresponding to each battery charging current; and combining the battery charging capacities and the battery driving mileage corresponding to all the battery charging currents, and generating a first reference curve by taking the battery charging capacity and the battery driving mileage corresponding to one battery charging current as a point coordinate.
As an example, the first preset condition is preset according to actual application requirements. And screening all battery charging currents meeting the first preset condition from the remote monitoring data set.
For example, assume that the first preset condition is: select a certain time t 1 Lower battery charging current C t1 > 0, and at the same time t 1 Lower battery charging voltage U t1 At (U) 1 ，U 2 ) Inner, same time t 1 Battery charging temperature K t1 At (K) 1 ，K 2 ) A battery charging current in, wherein U 1 For a first preset voltage, U 2 At a second preset voltage, a second preset voltageThe set voltage is greater than the first preset voltage, K 1 For a first preset temperature, K 2 And for the second preset temperature, if the second preset temperature is greater than the first preset temperature, selecting the starting time of the remote monitoring data set, determining the ending time of the remote monitoring data set, traversing all remote monitoring data from the starting time to the ending time in the remote monitoring data set, screening all battery charging currents meeting the first preset condition, and determining the sampling interval between each battery charging current.
When all battery charging currents are screened out, carrying out ampere-time integration on each battery charging current to obtain battery charging capacity corresponding to the battery charging current, and combining sampling intervals among the battery charging currents to obtain battery driving mileage corresponding to the battery charging current, so as to determine the battery charging capacity and the battery driving mileage corresponding to each battery charging current.
In order to enhance the accuracy of the subsequent outlier detection of the abnormal battery, an off-line circulation test mode is adopted, battery charging capacity and battery driving mileage corresponding to all battery charging currents are combined, the battery charging capacity and the battery driving mileage corresponding to one battery charging current are used as a point coordinate, wherein the battery driving mileage corresponding to the battery charging current can be used as an abscissa value, the battery charging capacity corresponding to the battery charging current is used as an ordinate value, and a curve of the battery charging capacity changing along with the battery driving mileage is calibrated off-line, so that a first reference curve is generated.
The charging capacity of the battery is selected as the battery characteristic data, so that the charging characteristic values of the battery under the conditions of low SOC (state of charge), medium SOC and high SOC can be obtained, and the effective characteristic values can be obtained in different user scenes. The battery characteristic data of the battery charging capacity is more accurate and effective when the battery is slowly charged by 3.3kW and 7kW, and can be distinguished according to the battery charging temperature gradient, so that the influence of the ambient temperature on the battery charging capacity is eliminated.
According to the embodiment of the invention, the first reference curve is generated by extracting the battery characteristic data of the battery charging capacity from the remote monitoring data set, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the battery charging capacity, so that the abnormal detection of the battery to be detected is continuously carried out, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: determining a battery charging capacity corresponding to a driving range of a battery to be detected as a reference battery charging capacity based on a first reference curve; when the charging capacity of the battery to be detected is larger than or equal to the charging capacity of the reference battery, judging that the battery to be detected is a normal battery; and when the charging capacity of the battery to be detected is smaller than the charging capacity of the reference battery, judging that the battery to be detected is an abnormal battery.
As an example, when the first reference curve is generated, battery charge capacities corresponding to different battery mileage may be determined according to the first reference curve.
And acquiring the driving mileage of the battery to be detected, and determining the battery charging capacity corresponding to the driving mileage of the battery to be detected as the reference battery charging capacity based on the first reference curve.
And acquiring the charging capacity of the battery to be detected, directly comparing the charging capacity of the battery to be detected with the charging capacity of the reference battery, judging that the battery to be detected is a normal battery when the charging capacity of the battery to be detected is greater than or equal to the charging capacity of the reference battery, and judging that the battery to be detected is an abnormal battery when the charging capacity of the battery to be detected is less than the charging capacity of the reference battery.
Considering that the normal battery and the abnormal battery are distinguished directly by the charge capacity of the reference battery on the first reference curve, the problem of inaccurate detection may exist, or the ratio of the charge capacity of the battery to be detected to the charge capacity of the reference battery may be calculated first, then the ratio of the charge capacity of the battery to be detected to the charge capacity of the reference battery is compared with a preset ratio range, for example (97%, 103%), when the ratio of the charge capacity of the battery to be detected to the charge capacity of the reference battery is within the preset ratio range, the battery to be detected is judged to be the normal battery, and when the ratio of the charge capacity of the battery to be detected to the charge capacity of the reference battery is not within the preset ratio range, the battery to be detected is judged to be the abnormal battery.
For example, assuming that the first reference curve is as shown in fig. 2, an outlier analysis is performed on the battery to be detected based on the first reference curve, and the normal battery and the abnormal battery are rapidly and accurately distinguished. The battery with abnormal charging capacity under the same driving mileage can be screened out by adopting a Laida criterion, an isolated forest method or other abnormal detection algorithms.
According to the embodiment of the invention, the to-be-detected battery is subjected to outlier analysis based on the first reference curve generated according to the battery characteristic data of the battery charging capacity, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the continuous to-be-detected battery is subjected to abnormal detection, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all groups of battery dynamic pressure differences meeting a second preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to the average value of the battery dynamic pressure differences of all groups; and combining battery off-line time or battery driving mileage corresponding to the average value of all the battery dynamic pressure differences, and generating a second reference curve by taking the average value of one group of battery dynamic pressure differences and the corresponding battery off-line time or battery driving mileage as a point coordinate.
As an example, the second preset condition is preset according to actual application requirements. And screening dynamic pressure differences of all battery packs meeting the second preset condition from the remote monitoring data set.
For example, assume that the second preset condition is: selecting a certain time t in the process of AC slow charging 2 Battery charging current C t2 At (I) 1 ，I 2 ) In, and battery charging voltage U t2 At (U) 3 ，U 4 ) A preset number of dynamic cell pressure differences in the battery, wherein I 1 For a first preset current, I 2 For a second preset current, a secondThe preset current is greater than the first preset current, (I) 1 ，I 2 ) Can be set as a battery charging current interval corresponding to 7KW alternating current slow charge, U 3 For a third preset voltage, U 4 For a fourth preset voltage, the fourth preset voltage is greater than the third preset voltage, (U) 3 ，U 4 ) The method comprises the steps of setting a voltage of a battery pack platform to be +/-3V or a voltage of 95% SOC to be +/-3V, selecting a starting time of a remote monitoring data set, determining a terminating time of the remote monitoring data set, traversing all remote monitoring data from the starting time to the terminating time in the remote monitoring data set, screening all groups of battery dynamic pressure differences meeting a second preset condition, and determining sampling intervals among the groups of battery dynamic pressure differences.
When screening out all the battery dynamic pressure differences, calculating the average value of the battery dynamic pressure differences of each battery to obtain the average value of the battery dynamic pressure differences of each battery, and combining the sampling intervals among the battery dynamic pressure differences to obtain the battery off-line duration or the battery driving mileage corresponding to the average value of the battery dynamic pressure differences of each battery, thereby determining the battery off-line duration or the battery driving mileage corresponding to the average value of the battery dynamic pressure differences of each battery.
Based on the maximum dynamic pressure difference allowed by the battery monomer, such as an industry standard of 50mV, or the maximum capacity difference of the tail end, the average value of all the battery dynamic pressure differences and the corresponding battery off-line duration or battery driving mileage are combined, the average value of a group of battery dynamic pressure differences and the corresponding battery off-line duration or battery driving mileage are taken as a point coordinate, wherein the battery off-line duration or battery driving mileage corresponding to the average value of a group of battery dynamic pressure differences can be taken as an abscissa value, and the average value group of a group of battery dynamic pressure differences is taken as an ordinate value, so as to generate a second reference curve.
The dynamic pressure difference of the battery is selected as battery characteristic data, the charging characteristic values of the battery under low SOC, medium SOC and high SOC can be obtained, the high SOC and the low SOC are used as degradation screening intervals, and abnormal batteries are screened by tightening.
According to the embodiment of the invention, the second reference curve is generated by extracting the battery characteristic data of the dynamic pressure difference of the battery from the remote monitoring data set, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the dynamic pressure difference of the battery, so that the abnormal detection of the battery to be detected is continuously carried out, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: based on the second reference curve, determining an average value of the dynamic pressure differences of the battery corresponding to the offline time length or the driving mileage of the battery to be detected as a reference dynamic pressure difference of the battery; when the dynamic pressure difference of the battery to be detected is smaller than or equal to the dynamic pressure difference of the reference battery, judging that the battery to be detected is a normal battery; and when the dynamic pressure difference of the battery to be detected is larger than the dynamic pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
As an example, when the second reference curve is generated, an average value of the battery dynamic pressure difference corresponding to different battery off-line durations or battery mileage may be determined according to the second reference curve.
Acquiring the offline time length or the driving mileage of the battery to be detected, and determining an average value of the dynamic pressure differences of the battery corresponding to the offline time length or the driving mileage of the battery to be detected as a reference dynamic pressure difference of the battery based on a second reference curve.
The method comprises the steps of obtaining dynamic pressure difference of a battery to be detected, comparing the dynamic pressure difference of the battery to be detected with the dynamic pressure difference of a reference battery, judging that the battery to be detected is a normal battery when the dynamic pressure difference of the battery to be detected is smaller than or equal to the dynamic pressure difference of the reference battery, and judging that the battery to be detected is an abnormal battery when the dynamic pressure difference of the battery to be detected is larger than the dynamic pressure difference of the reference battery.
For example, assuming that the second reference curve is as shown in fig. 3, an outlier analysis is performed on the battery to be detected based on the second reference curve, and the normal battery and the abnormal battery are rapidly and accurately distinguished.
According to the embodiment of the invention, the to-be-detected battery is subjected to outlier analysis based on the second reference curve generated according to the battery characteristic data of the battery dynamic pressure difference, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the continuous to-be-detected battery abnormality detection is realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all battery static pressure differences meeting a third preset condition from the remote monitoring data set, and determining battery off-line duration or battery driving mileage corresponding to each battery static pressure difference; and combining battery off-line time or battery driving mileage corresponding to all the battery static pressure differences, and generating a third reference curve by taking one battery static pressure difference and corresponding battery off-line time or battery driving mileage as a point coordinate.
As an example, the third preset condition is preset according to actual application requirements. And screening all battery static pressure differences meeting the third preset condition from the remote monitoring data set.
For example, assume that the third preset condition is: the electric automobile stands for a preset standing time period, for example, after the continuous data-free uploading time of the electric automobile reaches 30 minutes, the first frame of signal is powered on by the whole automobile at high voltage, the battery static pressure difference in a preset SOC interval, for example (50% SOC and 60% SOC) is selected, then the starting time of a remote monitoring data set is selected, the ending time of the remote monitoring data set is determined, all remote monitoring data from the starting time to the ending time in the remote monitoring data set are traversed, all the battery static pressure differences meeting a third preset condition are screened, and meanwhile sampling intervals among all the battery static pressure differences are determined.
When all the battery static pressure differences are screened out, combining sampling intervals among the battery static pressure differences for each battery static pressure difference to obtain battery offline time or battery driving mileage corresponding to the battery static pressure differences, so as to determine the battery offline time or the battery driving mileage corresponding to the battery static pressure differences.
Based on the maximum static pressure difference allowed by the battery unit, such as industry standard 30mV, or the maximum capacity difference of the tail end, combining all the battery static pressure differences and corresponding battery off-line time periods or battery driving mileage, taking one battery static pressure difference and corresponding battery off-line time period or battery driving mileage as a point coordinate, wherein the battery off-line time period or battery driving mileage corresponding to one battery static pressure difference can be taken as an abscissa value, and one battery static pressure difference can be taken as an ordinate value, so as to generate a third reference curve.
The static pressure difference of the battery is selected as battery characteristic data, the charging characteristic values of the battery under low SOC, medium SOC and high SOC can be obtained, the high SOC and the low SOC are used as degradation screening intervals, and abnormal batteries are screened by tightening.
According to the embodiment of the invention, the battery characteristic data of the battery static pressure difference is extracted from the remote monitoring data set to generate the third reference curve, and the normal battery and the abnormal battery can be accurately distinguished based on the battery characteristic data of the battery static pressure difference, so that the abnormal detection of the battery to be detected is continuously realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: based on a third reference curve, determining a battery static pressure difference corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery static pressure difference; when the static pressure difference of the battery to be detected is smaller than or equal to the static pressure difference of the reference battery, judging that the battery to be detected is a normal battery; and when the static pressure difference of the battery to be detected is larger than the static pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
As an example, when the third reference curve is generated, the battery static pressure difference corresponding to different battery off-line durations or battery driving mileage may be determined according to the third reference curve.
Acquiring the offline time length or the driving mileage of the battery to be detected, and determining the battery static pressure difference corresponding to the offline time length or the driving mileage of the battery to be detected as the reference battery static pressure difference based on a third reference curve.
The method comprises the steps of obtaining the static pressure difference of a battery to be detected, comparing the static pressure difference of the battery to be detected with the static pressure difference of a reference battery, judging that the battery to be detected is a normal battery when the static pressure difference of the battery to be detected is smaller than or equal to the static pressure difference of the reference battery, and judging that the battery to be detected is an abnormal battery when the static pressure difference of the battery to be detected is larger than the static pressure difference of the reference battery.
For example, assuming that the third reference curve is as shown in fig. 4, an outlier analysis is performed on the battery to be detected based on the third reference curve, and the normal battery and the abnormal battery are rapidly and accurately distinguished.
According to the embodiment of the invention, the to-be-detected battery is subjected to outlier analysis based on the third reference curve generated according to the battery characteristic data of the battery static pressure difference, so that the normal battery and the abnormal battery can be rapidly and accurately distinguished, the continuous to-be-detected battery abnormality detection is realized, the abnormal battery is found as soon as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a battery abnormality detection device according to a second embodiment of the present invention. A second embodiment of the present invention provides a battery abnormality detection apparatus including: the reference curve generating module 201 is configured to acquire a remote monitoring data set from the big data platform, and generate a reference curve according to battery characteristic data in the remote monitoring data set; the battery abnormality detection module 202 is configured to determine whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected based on the reference curve, so as to obtain an abnormality detection result.
In an alternative embodiment, the reference curve generating module 201 is further configured to collect, in real time, operation data of each battery cell in each electric vehicle power battery pack through the remote monitoring big data system before the remote monitoring data set is obtained from the big data platform, and upload all the operation data as the remote monitoring data to the big data platform.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all battery charging currents meeting a first preset condition from a remote monitoring data set, and determining battery charging capacity and battery driving mileage corresponding to each battery charging current; and combining the battery charging capacities and the battery driving mileage corresponding to all the battery charging currents, and generating a first reference curve by taking the battery charging capacity and the battery driving mileage corresponding to one battery charging current as a point coordinate.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: determining a battery charging capacity corresponding to a driving range of a battery to be detected as a reference battery charging capacity based on a first reference curve; when the charging capacity of the battery to be detected is larger than or equal to the charging capacity of the reference battery, judging that the battery to be detected is a normal battery; and when the charging capacity of the battery to be detected is smaller than the charging capacity of the reference battery, judging that the battery to be detected is an abnormal battery.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all groups of battery dynamic pressure differences meeting a second preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to the average value of the battery dynamic pressure differences of all groups; and combining battery off-line time or battery driving mileage corresponding to the average value of all the battery dynamic pressure differences, and generating a second reference curve by taking the average value of one group of battery dynamic pressure differences and the corresponding battery off-line time or battery driving mileage as a point coordinate.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: based on the second reference curve, determining an average value of the dynamic pressure differences of the battery corresponding to the offline time length or the driving mileage of the battery to be detected as a reference dynamic pressure difference of the battery; when the dynamic pressure difference of the battery to be detected is smaller than or equal to the dynamic pressure difference of the reference battery, judging that the battery to be detected is a normal battery; and when the dynamic pressure difference of the battery to be detected is larger than the dynamic pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
In an alternative embodiment, the generating a reference curve according to the battery characteristic data in the remote monitoring data set specifically includes: screening all battery static pressure differences meeting a third preset condition from the remote monitoring data set, and determining battery off-line duration or battery driving mileage corresponding to each battery static pressure difference; and combining battery off-line time or battery driving mileage corresponding to all the battery static pressure differences, and generating a third reference curve by taking one battery static pressure difference and corresponding battery off-line time or battery driving mileage as a point coordinate.
In an optional embodiment, the determining, based on the reference curve, whether the battery to be detected is an abnormal battery according to the feature data of the battery to be detected, to obtain an abnormal detection result specifically includes: based on a third reference curve, determining a battery static pressure difference corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery static pressure difference; when the static pressure difference of the battery to be detected is smaller than or equal to the static pressure difference of the reference battery, judging that the battery to be detected is a normal battery; and when the static pressure difference of the battery to be detected is larger than the static pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. A third embodiment of the invention provides an electronic device 30 comprising a processor 301, a memory 302 and a computer program stored in the memory 302 and configured to be executed by the processor 301; the memory 302 is coupled to the processor 301, and the processor 301 executes a computer program to implement the battery abnormality detection method according to the first embodiment of the present invention.
The processor 301 may implement the method according to any embodiment included in the battery abnormality detection method according to the first embodiment of the present invention when reading the computer program from the memory 302 via the bus 303 and executing the computer program.
The processor 301 may process digital signals and may include various computing structures. Such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of instruction sets. In some examples, processor 301 may be a microprocessor.
Memory 302 may be used for storing instructions to be executed by processor 301 or data relating to the execution of instructions. Such instructions and/or data may include code to implement some or all of the functions of one or more of the modules described in embodiments of the present invention. The processor 301 of the embodiment of the present disclosure may be configured to execute instructions in the memory 302 to implement the battery abnormality detection method according to the first embodiment of the present invention. Memory 302 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memory known to those skilled in the art.
A fourth embodiment of the present invention provides a computer-readable storage medium including a stored computer program; the device where the computer readable storage medium is controlled to execute the battery abnormality detection method according to the first embodiment of the present invention when the computer program runs can achieve the same advantages as the method.
In summary, the embodiment of the invention provides a method, a device, equipment and a storage medium for detecting battery abnormality, where the method for detecting battery abnormality includes: acquiring a remote monitoring data set from a big data platform, and generating a reference curve according to battery characteristic data in the remote monitoring data set; and judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve, and obtaining an abnormal detection result. According to the embodiment of the invention, the battery characteristic data in the remote monitoring data set is extracted to perform abnormality detection on the battery to be detected by acquiring the remote monitoring data set from the big data platform, the battery characteristic data can be monitored for a long time by applying the big data remote monitoring technology, and the normal battery and the abnormal battery are accurately distinguished based on the recent battery characteristic data, so that the continuous abnormality detection on the battery to be detected is realized, the abnormal battery is found as early as possible, and the technical effect of safe operation of the electric automobile is effectively ensured.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (11)

1. A battery abnormality detection method, characterized by comprising:
acquiring a remote monitoring data set from a big data platform, and generating a reference curve according to battery characteristic data in the remote monitoring data set;
and judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve, and obtaining an abnormal detection result.
2. The battery anomaly detection method of claim 1, further comprising, prior to the acquiring the remote monitoring dataset from the big data platform:
and acquiring the operation data of each battery cell in each electric automobile power battery pack in real time through a remote monitoring big data system, and uploading all the operation data to the big data platform as remote monitoring data.
3. The battery abnormality detection method according to claim 1, wherein the generating a reference curve from the battery characteristic data in the remote monitoring data set specifically includes:
screening all battery charging currents meeting a first preset condition from the remote monitoring data set, and determining battery charging capacity and battery driving mileage corresponding to each battery charging current;
And combining the battery charging capacity and the battery driving mileage corresponding to all the battery charging currents, and generating a first reference curve by taking the battery charging capacity and the battery driving mileage corresponding to one battery charging current as a point coordinate.
4. The method for detecting abnormal battery according to claim 3, wherein the determining whether the battery to be detected is an abnormal battery based on the reference curve according to the characteristic data of the battery to be detected, to obtain an abnormal detection result, specifically comprises:
determining a battery charging capacity corresponding to the driving mileage of the battery to be detected as a reference battery charging capacity based on the first reference curve;
when the charging capacity of the battery to be detected is larger than or equal to the charging capacity of the reference battery, judging that the battery to be detected is a normal battery;
and when the charging capacity of the battery to be detected is smaller than the charging capacity of the reference battery, judging that the battery to be detected is an abnormal battery.
5. The battery abnormality detection method according to claim 1, wherein the generating a reference curve from the battery characteristic data in the remote monitoring data set specifically includes:
Screening all groups of battery dynamic pressure differences meeting a second preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to the average value of the battery dynamic pressure differences of each group;
and combining battery off-line time or battery driving mileage corresponding to the average value of all the battery dynamic pressure differences, and generating a second reference curve by taking the average value of one group of the battery dynamic pressure differences and the corresponding battery off-line time or battery driving mileage as a point coordinate.
6. The method for detecting abnormal cell according to claim 5, wherein the determining whether the cell to be detected is an abnormal cell based on the reference curve according to the feature data of the cell to be detected, to obtain an abnormal detection result, specifically comprises:
based on the second reference curve, determining an average value of battery dynamic pressure differences corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery dynamic pressure difference;
when the dynamic pressure difference of the battery to be detected is smaller than or equal to the dynamic pressure difference of the reference battery, judging that the battery to be detected is a normal battery;
and when the dynamic pressure difference of the battery to be detected is larger than the dynamic pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
7. The battery abnormality detection method according to claim 1, wherein the generating a reference curve from the battery characteristic data in the remote monitoring data set specifically includes:
screening all battery static pressure differences meeting a third preset condition from the remote monitoring data set, and determining battery offline time or battery driving mileage corresponding to each battery static pressure difference;
and generating a third reference curve by taking one battery static pressure difference and the corresponding battery off-line duration or battery driving mileage as a point coordinate in combination with all battery off-line durations or battery driving mileage corresponding to the battery static pressure differences.
8. The method for detecting abnormal cell according to claim 7, wherein the determining whether the cell to be detected is an abnormal cell based on the reference curve according to the feature data of the cell to be detected, to obtain an abnormal detection result, specifically comprises:
based on the third reference curve, determining a battery static pressure difference corresponding to the offline time length or the driving mileage of the battery to be detected as a reference battery static pressure difference;
when the static pressure difference of the battery to be detected is smaller than or equal to the static pressure difference of the reference battery, judging that the battery to be detected is a normal battery;
And when the static pressure difference of the battery to be detected is larger than the static pressure difference of the reference battery, judging that the battery to be detected is an abnormal battery.
9. A battery abnormality detection device, characterized by comprising:
the reference curve generation module is used for acquiring a remote monitoring data set from the big data platform and generating a reference curve according to battery characteristic data in the remote monitoring data set;
and the battery abnormality detection module is used for judging whether the battery to be detected is an abnormal battery or not according to the characteristic data of the battery to be detected based on the reference curve to obtain an abnormality detection result.
10. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor, and the processor, when executing the computer program, implements the battery abnormality detection method according to any one of claims 1 to 8.
11. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program; wherein the apparatus in which the computer-readable storage medium is controlled to execute the battery abnormality detection method according to any one of claims 1 to 8 when the computer program is run.
CN202311452116.4A 2023-11-02 2023-11-02 Battery abnormality detection method, device, equipment and storage medium Pending CN117269784A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311452116.4A CN117269784A (en) 2023-11-02 2023-11-02 Battery abnormality detection method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311452116.4A CN117269784A (en) 2023-11-02 2023-11-02 Battery abnormality detection method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117269784A true CN117269784A (en) 2023-12-22

Family

ID=89216149

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311452116.4A Pending CN117269784A (en) 2023-11-02 2023-11-02 Battery abnormality detection method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117269784A (en)

Similar Documents

Publication Publication Date Title
US11215679B2 (en) Method and apparatus for detecting micro short circuit of battery
EP2963433B1 (en) Method and apparatus for estimating state of battery
US11054481B2 (en) Multispectral impedance determination under dynamic load conditions
JP7483922B2 (en) Battery diagnostic device, battery diagnostic method, battery pack and automobile
CN108931725B (en) Method and device for detecting battery fault
CN111257764A (en) Method, system and device for monitoring battery short circuit
CN111999656B (en) Method and device for detecting short circuit in vehicle battery and electronic equipment
EP3992648A1 (en) Battery diagnosis device and method
CN111812529A (en) Aging thermal runaway test method for lithium ion battery under time-varying cycle working condition
CN113696786A (en) Battery equalization method and system
CN110874693A (en) Determination method, detection method and device for abnormal working condition of battery pack
CN115248379A (en) Power battery micro-short-circuit diagnosis method and system based on multi-scene fusion
CN114441979A (en) Voltage drop cell detection and cell health monitoring
JP2017016991A (en) Data extraction device, data extraction method and data extraction program
CN115951249B (en) Battery state monitoring method, system, electronic equipment and storage medium
KR20230161377A (en) Battery diagnosis apparatus, battery diagnosis method, battery pack, and vehicle including the same
CN117269784A (en) Battery abnormality detection method, device, equipment and storage medium
CN118033465B (en) Method and device for identifying battery self-discharge abnormality, vehicle and storage medium
CN118514570A (en) Method and device for monitoring internal resistance of battery of vehicle
CN118259187A (en) Monomer voltage acquisition processing method and system
KR20230168917A (en) Battery Parameter Estimation Method and Battery Parameter Acquisition Device
KR20240051014A (en) Battery diagnosis apparatus and method for detecting leakage current
CN116125311A (en) Battery short-circuit fault detection method, detection device, electronic equipment and storage medium
CN117907867A (en) Battery fault diagnosis method and device, computer equipment and storage medium
CN116794548A (en) Battery fault early warning and diagnosing method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination