CN115951231A - Automobile power battery fault early warning method based on single battery voltage correlation - Google Patents
Automobile power battery fault early warning method based on single battery voltage correlation Download PDFInfo
- Publication number
- CN115951231A CN115951231A CN202310239436.5A CN202310239436A CN115951231A CN 115951231 A CN115951231 A CN 115951231A CN 202310239436 A CN202310239436 A CN 202310239436A CN 115951231 A CN115951231 A CN 115951231A
- Authority
- CN
- China
- Prior art keywords
- voltage
- single battery
- time
- battery
- time window
- 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
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Abstract
The invention provides an automobile power battery fault early warning method based on single battery voltage correlation, which comprises the following steps: acquiring voltage data of each single battery of the vehicle based on the time sequence after data cleaning; determining the length of a time window, acquiring voltage data of each single battery in the current window, and calculating the voltage correlation coefficient sum of each single battery and other single batteries at each moment based on a sliding window by using a correlation coefficient algorithm; and (3) performing statistics on the voltage correlation coefficients of the single batteries by using a Z score of a statistical tool, obtaining abnormal voltage coefficients A of the single batteries at each moment based on a sliding window, setting an abnormal coefficient fault judgment threshold, and realizing power battery voltage inconsistency fault early warning based on the abnormal coefficients of the voltage correlation coefficients of the single batteries. The invention has the advantages of data simplification and easy acquisition, can realize real-time early warning of the thermal runaway fault of the vehicle, and can position the single battery with the fault.
Description
Technical Field
The invention belongs to the technical field of automobile power batteries, and particularly relates to an automobile power battery fault early warning method based on single battery voltage correlation.
Background
Under the dual pressure of environmental pollution and energy crisis, energy conservation and emission reduction become common responsibilities of countries in the world, and new energy automobiles represented by electric automobiles become the first choice of future transportation tools. The power battery system is used as a key and core component of the electric automobile, and the safety and the reliability of the power battery system directly influence the comprehensive performance of the electric automobile to a great extent. The lithium ion battery is the most widely used energy storage element in the new energy automobile industry at present by virtue of the advantages of high power, high energy density, long cycle life, low self-discharge rate and the like. However, in recent years, as a lithium ion battery system fails under extreme operating conditions and harsh environments, and thus a fire accident is occurring, safety thereof is receiving more and more attention. Safety accidents characterized by thermal runaway occur occasionally, and hidden dangers are brought to the life and property safety of the public.
Thermal runaway of electric vehicles has uncertainty, and the possibility of thermal runaway occurs during charging at rest, during driving, and during parking. In addition, the method is also sudden, and no obvious abnormality is detected by the monitoring data and the background data of the battery management system before thermal runaway occurs. Therefore, early warning of thermal runaway of the power battery of the electric automobile is very important for ensuring the safety of the electric automobile.
At present, the research on the thermal runaway early warning method of the battery mainly focuses on a power battery system fault diagnosis method developed based on laboratory conditions or a model simulation test carried out by using related software. Such research is often large in calculation amount, low in diagnosis accuracy, poor in universality of diagnosis targets, insufficient in robustness characteristics of noise from a system and an environment and system uncertainty, and not ideal in actual application effect on electric vehicles. Therefore, a fault diagnosis method with high accuracy and high reliability for a power battery system of a real vehicle is yet to be developed to improve the safety of the electric vehicle.
Based on the method, the automobile power battery fault early warning method based on the voltage correlation of the single battery is provided.
Disclosure of Invention
The invention provides a method for early warning the fault of an automobile power battery based on the voltage correlation of a single battery, aiming at overcoming the defects in the prior art, and aims to solve the problems in the background art.
In order to solve the technical problems, the invention adopts the technical scheme that: the automobile power battery fault early warning method based on the voltage correlation of the single battery comprises the following steps:
s1, acquiring voltage data of each single battery of the vehicle based on time sequence after data cleaning,
the method specifically comprises the following steps:
s11, firstly, cleaning the voltage signal of the power battery monomer of the vehicle, deleting empty data and data larger than 5V in the data, and then selecting the data;
s12, extracting voltage data of each single battery of the vehicle based on the time sequence, and constructing a voltage data set U as follows:
wherein, U is a voltage data set of all the single batteries based on a time sequence;
u i is voltage data of No. i single battery based on time series;
k is the number of the single batteries in the power battery pack;
s2, determining the length of a time window, acquiring voltage data of each single battery in the current window, and calculating the voltage correlation coefficient sum of each single battery and other single batteries at each moment based on a sliding window by using a correlation coefficient algorithm;
s3, performing Z fraction on the voltage correlation coefficient of each single battery obtained in the S2 by using a statistical tool, and obtaining a voltage abnormal coefficient A of each single battery at each moment based on a sliding window;
s4: and setting an abnormal coefficient fault judgment threshold, and realizing power battery voltage inconsistency fault early warning based on the abnormal coefficient of the voltage correlation coefficient of each single battery.
Further, S2 specifically includes the following steps:
Wherein the content of the first and second substances,is greater than or equal to at moment>Time of day;
s22, constructingIs reached at moment>At the moment in time the voltage data set of the individual cell->:
Wherein, the first and the second end of the pipe are connected with each other,is the first->A cell voltage data set at each time window, device for selecting or keeping>;
The voltage values of the ith row and the jth single battery under the h time window are represented;
s23, calculating the sum of voltage correlation coefficients of the j unit cell and other unit cells in the h time windowComprises the following steps:
wherein it is present>The voltage correlation coefficient of the jth single battery and the Kth single battery under the h time window is obtained;
s24, voltage data set in h time windowThe voltage correlation coefficient of the single battery is as follows:
s25, calculating the sum of the voltage correlation coefficients of each single battery and other single batteries under all time windows according to S23-S24 as follows:
wherein n is the number of time windows.
Further, S3 specifically includes the following steps:
s31, calculating the voltage abnormity coefficient of the j unit battery based on the Z fraction under the h time windowComprises the following steps:
wherein the content of the first and second substances,is the average correlation coefficient value of all the cell voltages in the h time window;
is the standard deviation of all cell voltage correlation coefficient values under the h-th time window;
s32, voltage abnormity coefficients of all single batteries based on Z fraction in h time windowComprises the following steps:
s33, calculating voltage abnormity coefficients A of all the single batteries based on the Z fraction under all the time windows according to S31-S32, wherein the voltage abnormity coefficients A are as follows:
further, S4 specifically includes the following steps:
s41, setting an abnormal coefficient fault judgment threshold value Z;
s42, performing threshold value judgment on the abnormal coefficient values of the correlation coefficients of all the single batteries under all the time windows, and if the abnormal coefficient values do not exceed the threshold values, indicating that the vehicle has no risk of thermal runaway power battery failure;
if the threshold value is exceeded, the risk of thermal runaway power battery failure is indicated, the corresponding single battery code is recorded, and the alarm time is determined.
Compared with the prior art, the invention has the following advantages:
the voltage data of the single battery of the electric automobile is used, and the method has the advantage of data simplification; moreover, the voltage data of the single battery is real-time operation data of the electric automobile, and the method has the advantage of easy acquisition; secondly, the invention is not influenced by the voltage value of the single battery, and does not need to carry out classification analysis according to the running working condition and the charging and discharging working condition of the vehicle; the invention can realize real-time early warning of the thermal runaway fault of the vehicle and can position the single battery with the fault.
Drawings
Fig. 1 is a flow chart of the electric vehicle power battery fault early warning based on real vehicle data according to the present invention:
FIG. 2 is voltage data of each unit cell of the vehicle based on time series in the embodiment of the present invention;
FIG. 3 is a voltage relationship value of a single battery under each time window in the embodiment of the present invention;
fig. 4 is the voltage abnormality coefficient values of the unit cells at the respective time windows in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in fig. 1, the present invention provides a technical solution: the automobile power battery fault early warning method based on the voltage correlation of the single battery comprises the following steps:
s1, acquiring voltage data of each single battery of the vehicle based on time sequence after data cleaning,
the method specifically comprises the following steps:
s11, firstly, cleaning the voltage signal of the power battery monomer of the vehicle, deleting empty data and data larger than 5V in the data, and then selecting the data;
s12, extracting voltage data of each single battery of the vehicle based on the time sequence, and constructing a voltage data set U as follows:
wherein, U is a voltage data set of all the single batteries based on a time sequence;
u i is voltage data of No. i single battery based on time series;
k is the number of the single batteries in the power battery pack.
S2, determining the length of a time window, acquiring voltage data of each single battery in the current window, and calculating the sum of voltage correlation coefficients of each single battery and other single batteries at each moment based on a sliding window by using a correlation coefficient algorithm;
the method specifically comprises the following steps:
Wherein, the first and the second end of the pipe are connected with each other,is greater than or equal to at moment>Time of day;
s22, constructing fromTime of day to>At the moment in time the voltage data set of the individual cell->:
Wherein the content of the first and second substances,is the first->The cell voltage data set at each time window, device for selecting or keeping>;
The voltage values of the ith row and the jth single battery under the h time window are represented;
s23, calculating the sum of voltage correlation coefficients of the j unit cell and other unit cells in the h time windowComprises the following steps:
wherein the content of the first and second substances,the voltage correlation coefficient of the j-th single battery and the K-th single battery under the h-th time window is obtained;
s24, voltage data set in h time windowIs not only a sheetThe voltage correlation coefficient of the bulk battery is as follows:
s25, calculating the sum of the voltage correlation coefficients of each single battery and other single batteries under all time windows according to S23-S24 as follows:
wherein n is the number of time windows.
S3, obtaining the voltage abnormal coefficient A of each single battery at each moment on the basis of a sliding window by using a statistical tool Z score of the voltage correlation coefficient of each single battery obtained in the S2;
the method specifically comprises the following steps:
s31, calculating the voltage abnormity coefficient of the j unit battery based on the Z fraction under the h time windowComprises the following steps:
wherein, the first and the second end of the pipe are connected with each other,is the average correlation coefficient value of all the cell voltages in the h-th time window;
is the standard deviation of all cell voltage correlation coefficient values under the h-th time window;
s32, voltage abnormity coefficients of all single batteries based on Z fraction in h time windowComprises the following steps:
s33, calculating voltage abnormity coefficients A of all the single batteries based on the Z fraction under all the time windows according to the steps S31-S32 as follows:
s4: setting an abnormal coefficient fault judgment threshold value, and realizing power battery voltage inconsistency fault early warning based on the abnormal coefficient of each single battery voltage correlation coefficient, wherein the method specifically comprises the following steps:
s41, setting an abnormal coefficient fault judgment threshold value Z;
s42, performing threshold value judgment on the abnormal coefficient values of the correlation coefficients of all the single batteries in all the time windows, and if the abnormal coefficient values do not exceed the threshold values, indicating that the vehicle has no risk of thermal runaway power battery failure;
if the threshold value is exceeded, the risk of thermal runaway power battery failure is indicated, the corresponding single battery code is recorded, and the alarm time is determined.
Fig. 2 is voltage data of each battery cell of a thermal runaway accident vehicle in time series, wherein the thermal runaway occurs when the vehicle has severe water diving at the last stage, and the vehicle is in a normal state before the thermal runaway accident vehicle. Taking the length of the time window =100, fig. 3 shows the voltage correlation coefficient value of each unit cell. Setting a threshold value Z =, and fig. 4 is abnormal coefficient value data of the voltage correlation coefficient of each unit cell;
it can be seen that the voltage abnormality coefficient value of a certain single battery exceeds-5 at the beginning, which indicates that the vehicle is at risk of thermal runaway, and the voltage abnormality coefficient value of the No. 86 single battery exceeds-5 after positioning the battery as No. 29 single battery and a few seconds later.
After 46 minutes, the vehicle had thermal runaway.
In conclusion, the electric vehicle power battery thermal runaway early warning method based on real vehicle data can well achieve early warning of vehicle thermal runaway faults, locate the faulty battery and the occurrence time, and cannot generate false alarm when the vehicle has no thermal runaway faults.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (4)
1. The automobile power battery fault early warning method based on the voltage correlation of the single battery is characterized by comprising the following steps of:
s1, acquiring voltage data of each single battery of the vehicle based on time sequence after data cleaning,
the method specifically comprises the following steps:
s11, firstly, cleaning the voltage signal of the power battery monomer of the vehicle, deleting empty data and data larger than 5V in the data, and then selecting the data;
s12, extracting voltage data of each single battery of the vehicle based on the time sequence, and constructing a voltage data set U as follows:
wherein U is a time series based voltage data set of all the cells;
u i is voltage data of No. i single battery based on time series;
k is the number of the single batteries in the power battery pack;
s2, determining the length of a time window, acquiring voltage data of each single battery in the current window, and calculating the sum of voltage correlation coefficients of each single battery and other single batteries at each moment based on a sliding window by using a correlation coefficient algorithm;
s3, performing Z fraction on the voltage correlation coefficient of each single battery obtained in the S2 by using a statistical tool, and obtaining a voltage abnormal coefficient A of each single battery at each moment based on a sliding window;
s4: and setting an abnormal coefficient fault judgment threshold, and realizing power battery voltage inconsistency fault early warning based on the abnormal coefficient of the voltage correlation coefficient of each single battery.
2. The automobile power battery fault early warning method based on single battery voltage correlation as claimed in claim 1, wherein S2 specifically comprises the following steps:
Wherein, the first and the second end of the pipe are connected with each other,is greater than or equal to at moment>Time of day;
s22, constructing fromTime of day to>At the moment in time the voltage data set of the individual cell->:
Wherein the content of the first and second substances,is a first->The cell voltage data set at each time window, device for selecting or keeping>;
The voltage values of the ith row and the jth single battery under the h time window are represented;
s23, calculating the sum of voltage correlation coefficients of the jth single battery and other single batteries under the h time windowComprises the following steps:
wherein the content of the first and second substances,the voltage correlation coefficient of the jth single battery and the Kth single battery under the h time window is obtained;
s24, voltage data set in h time windowThe voltage correlation coefficient of the single battery is as follows:
s25, calculating the sum of the voltage correlation coefficients of each single battery and other single batteries under all time windows according to S23-S24 as follows:
wherein n is the number of time windows.
3. The automobile power battery fault early warning method based on single battery voltage correlation as claimed in claim 2, wherein S3 specifically comprises the following steps:
s31, calculating the voltage abnormity coefficient of the j unit battery based on the Z fraction under the h time windowComprises the following steps:
wherein the content of the first and second substances,is the average correlation coefficient value of all the cell voltages in the h-th time window;
is the standard deviation of all cell voltage correlation coefficient values under the h-th time window;
s32, voltage abnormity coefficients of all single batteries based on Z fraction in h time windowComprises the following steps:
s33, calculating voltage abnormity coefficients A of all the single batteries based on the Z fraction under all the time windows according to the steps S31-S32 as follows:
4. the automobile power battery fault early warning method based on single battery voltage correlation as claimed in claim 3, wherein S4 specifically comprises the following steps:
s41, setting an abnormal coefficient fault judgment threshold value Z;
s42, performing threshold value judgment on the abnormal coefficient values of the correlation coefficients of all the single batteries in all the time windows, and if the abnormal coefficient values do not exceed the threshold values, indicating that the vehicle has no risk of thermal runaway power battery failure;
if the threshold value is exceeded, the risk of thermal runaway power battery failure is indicated, the corresponding single battery code is recorded, and the alarm time is determined.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310239436.5A CN115951231A (en) | 2023-03-14 | 2023-03-14 | Automobile power battery fault early warning method based on single battery voltage correlation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310239436.5A CN115951231A (en) | 2023-03-14 | 2023-03-14 | Automobile power battery fault early warning method based on single battery voltage correlation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115951231A true CN115951231A (en) | 2023-04-11 |
Family
ID=87282818
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310239436.5A Pending CN115951231A (en) | 2023-03-14 | 2023-03-14 | Automobile power battery fault early warning method based on single battery voltage correlation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115951231A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116736140A (en) * | 2023-08-08 | 2023-09-12 | 启垠科技(深圳)有限公司 | Energy storage type rapid charging fault monitoring method and system based on energy storage self-detection |
CN116968556A (en) * | 2023-07-26 | 2023-10-31 | 北京科技大学 | Power and energy storage battery fault diagnosis method based on fuzzy entropy |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112924870A (en) * | 2021-04-12 | 2021-06-08 | 上海电享信息科技有限公司 | Method for evaluating inconsistency of battery |
CN114583301A (en) * | 2022-04-29 | 2022-06-03 | 国网浙江省电力有限公司电力科学研究院 | Power station thermal runaway early warning method and system based on safety characteristic parameter representation system |
CN114942387A (en) * | 2022-07-20 | 2022-08-26 | 湖北工业大学 | Real data-based power battery fault online detection method and system |
CN115257379A (en) * | 2022-08-05 | 2022-11-01 | 长安大学 | Electric vehicle power battery thermal runaway early warning method based on real vehicle data |
-
2023
- 2023-03-14 CN CN202310239436.5A patent/CN115951231A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112924870A (en) * | 2021-04-12 | 2021-06-08 | 上海电享信息科技有限公司 | Method for evaluating inconsistency of battery |
CN114583301A (en) * | 2022-04-29 | 2022-06-03 | 国网浙江省电力有限公司电力科学研究院 | Power station thermal runaway early warning method and system based on safety characteristic parameter representation system |
CN114942387A (en) * | 2022-07-20 | 2022-08-26 | 湖北工业大学 | Real data-based power battery fault online detection method and system |
CN115257379A (en) * | 2022-08-05 | 2022-11-01 | 长安大学 | Electric vehicle power battery thermal runaway early warning method based on real vehicle data |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116968556A (en) * | 2023-07-26 | 2023-10-31 | 北京科技大学 | Power and energy storage battery fault diagnosis method based on fuzzy entropy |
CN116736140A (en) * | 2023-08-08 | 2023-09-12 | 启垠科技(深圳)有限公司 | Energy storage type rapid charging fault monitoring method and system based on energy storage self-detection |
CN116736140B (en) * | 2023-08-08 | 2023-10-20 | 启垠科技(深圳)有限公司 | Energy storage type rapid charging fault monitoring method and system based on energy storage self-detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Voltage fault diagnosis and prognosis of battery systems based on entropy and Z-score for electric vehicles | |
CN115951231A (en) | Automobile power battery fault early warning method based on single battery voltage correlation | |
Gan et al. | Data-driven fault diagnosis of lithium-ion battery overdischarge in electric vehicles | |
CN102749588B (en) | Method for fault diagnosis on basis of storage battery state of charge (SOC) and state of health (SOH) | |
CN114559819B (en) | Electric automobile battery safety early warning method based on signal processing | |
CN110376530B (en) | Device and method for detecting short circuit in battery | |
CN110940921A (en) | Multi-fault diagnosis method and system of lithium ion battery string based on correction variance | |
CN103698713A (en) | Method for assessing SOH (state of health) of lithium ion battery | |
CN111257753B (en) | Battery system fault diagnosis method | |
CN107528095B (en) | Low tension battery failure prediction method based on new energy vehicle storing card data | |
CN109406929B (en) | On-line monitoring alarm device for open circuit in storage battery pack of transformer substation | |
CN112345955B (en) | Multi-fault online diagnosis method and system for power battery | |
CN107045104B (en) | Online estimation method for capacity of lithium titanate battery | |
CN106300548A (en) | A kind of battery intelligent management system | |
CN105203968A (en) | Lead-acid battery residual energy on-line measuring system | |
CN114487856A (en) | Thermal runaway early warning method and system for battery replacement station | |
CN114942386A (en) | Power battery fault online detection method and system | |
Kim et al. | Outlier mining-based fault diagnosis for multiceli lithium-ion batteries using a low-priced microcontroller | |
CN115257379A (en) | Electric vehicle power battery thermal runaway early warning method based on real vehicle data | |
CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
CN105717458B (en) | A kind of on-line real-time measuremen method of the internal resistance of cell | |
CN109884553B (en) | Real-time online diagnosis method and system for internal resistance consistency of super-capacitor energy storage power supply | |
CN108535653B (en) | Storage battery internal resistance estimation method and device | |
CN115469226A (en) | Real-time safety early warning method for electric vehicle power battery based on operation big data | |
CN115656837A (en) | Fault prediction method for series-connected battery |
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 |