CN112330176A - Lithium battery copper bar loosening fault diagnosis and prediction method - Google Patents
Lithium battery copper bar loosening fault diagnosis and prediction method Download PDFInfo
- Publication number
- CN112330176A CN112330176A CN202011280975.6A CN202011280975A CN112330176A CN 112330176 A CN112330176 A CN 112330176A CN 202011280975 A CN202011280975 A CN 202011280975A CN 112330176 A CN112330176 A CN 112330176A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- early warning
- copper bar
- energy density
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/05—Accumulators with non-aqueous electrolyte
- H01M10/052—Li-accumulators
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention discloses a lithium battery copper bar loosening fault diagnosis and prediction method, which comprises the following steps: (1) data preprocessing; (2) and index construction: the index construction stage mainly comprises the steps of preprocessing results through vehicle original data and data; (3) and excavating fault early warning points: the fault early warning point mining means that some index change rules before the copper bar loosening fault is outbreak are obtained through learning of known copper bar loosening fault data; (4) and model application: and in the model application stage, the new data of the vehicles of the same type are calculated, and then the failure energy density data of the vehicles are compared with the early warning value to determine whether to carry out early warning or not. According to the invention, whether the lithium battery copper bar has a fault in a future period of time is judged by acquiring the state quantities in the past and the present operation processes, so that a corresponding solution is found in advance.
Description
Technical Field
The invention relates to a lithium battery copper bar loosening fault diagnosis and prediction method.
Background
The internal structure of the power battery of the new energy vehicle is that the single batteries are connected in series and in parallel to form an integral power battery, and the power battery is connected with the single batteries through copper bars. The phenomenon that the voltage value of the monomer is changed abnormally and the temperature of the monomer cell is abnormal can occur after the fault of the copper bar. The copper bar is loosened and faulted, which easily causes the abnormity of the charging and discharging process and limits the function of the power battery (the charging depends on the highest monomer voltage, and the discharging depends on the lowest monomer voltage); local current is easy to be overlarge, the temperature of the single battery core is abnormal, and the inside of the power battery is burnt when the temperature is serious.
In conclusion, the invention designs a lithium battery copper bar loosening fault diagnosis and prediction method based on new energy vehicle monitoring platform data.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a lithium battery copper bar loosening fault diagnosis and prediction method, which judges whether the lithium battery copper bar breaks down in a period of time in the future by acquiring the state quantities in the past and the current operation process, thereby finding out a corresponding solution in advance.
In order to achieve the purpose, the invention is realized by the following technical scheme: a lithium battery copper bar loosening fault diagnosis and prediction method comprises the following steps:
1. data pre-processing
In the data preprocessing stage, a curve (hereinafter referred to as a threshold curve) formed by threshold values of voltage deviation of the single battery under different conditions of current, temperature of the single battery and residual SOC is calculated and obtained mainly by analyzing the voltage, the current, the temperature of the single battery and the residual SOC of the single battery in the vehicle data;
2. index construction
The index construction stage mainly comprises the steps of preprocessing results through vehicle original data and data;
3. fault early warning point excavation
The fault early warning point mining means that some index change rules before the copper bar loosening fault is outbreak are obtained through learning of known copper bar loosening fault data.
4. Model application
And in the model application stage, the new data of the vehicles of the same type are calculated, and then the failure energy density data of the vehicles are compared with the early warning value to determine whether to carry out early warning or not.
(1) The specific process of the data processing is as follows: calculating the mean value of the voltage of the single battery
Wherein n is the number of the single batteries of the vehicle, m is the number of records under the specified condition, and Vij I is the voltage value of the ith single battery for recording j
(2) Calculating the deviation of the cell voltage from the mean voltage (hereinafter referred to as voltage deviation)
(3) Calculating the accumulated times of the deviation, and calculating the accumulated times according to voltage deviation groups, wherein the calculation formula of the accumulated times of the given voltage deviation is as follows:
where Vt is a given voltage deviation value.
(4) Calculating the cumulative percentage of the deviation (hereinafter referred to as cumulative percentage)
(5) Calculating a threshold curve: and obtaining voltage deviation threshold values under different conditions according to the condition that the accumulated percentage is larger than the specified threshold value, and forming a threshold value curve.
The index construction constructs the following indexes:
(1) accumulating mileage;
(2) failure energy density: counting the number of times that the voltage deviation of the single battery exceeds the voltage deviation threshold value within the range of every hundred kilometers, wherein the calculation formula is as follows:
the concrete implementation process of the fault early warning point excavation is as follows:
(1) and (3) mileage interval division: dividing the distance according to the length of one hundred kilometers, namely, the distance is 0-100 and belongs to a 100km interval, and the distance is 101-200 and belongs to a 200km interval;
(2) calculating the fault energy density of the specified battery in each mileage interval;
(3) calculating the fault energy density change rate: the fault energy density ratio of the current mileage interval to the last mileage interval;
(4) calculating an interval of which the first fault energy density change rate is greater than a specified threshold value, and taking a point in the interval as a fault early warning point;
(5) and taking the fault energy density value of the fault early warning point as an early warning value.
The specific process of the model application is as follows:
(1) and (3) mileage interval division: dividing the data into a plurality of sections according to the length of one hundred kilometers;
(2) calculating the fault energy density of the specified battery in each mileage interval;
(3) and when the fault energy density data is larger than the early warning value, sending out a fault early warning, otherwise, considering the fault energy density data to be normal.
The invention has the beneficial effects that: according to the invention, whether the lithium battery copper bar has a fault in a future period of time is judged by acquiring the state quantities in the past and the present operation processes, so that a corresponding solution is found in advance.
Drawings
The invention is described in detail below with reference to the drawings and the detailed description;
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a flow chart of data preprocessing of the present invention;
fig. 3 is a graph of a voltage deviation threshold distribution under charge and discharge current after fitting of a problematic battery of the present invention in year 2015 and month 1 to date;
FIG. 4 is a graph of the fault energy density of a faulty battery of the present invention;
fig. 5 is a graph of the fault energy density of a normal battery of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
Referring to fig. 1 to 2, the following technical solutions are adopted in the present embodiment: a lithium battery copper bar loosening fault diagnosis and prediction method comprises the following steps:
1. data pre-processing
In the data preprocessing stage, a curve (hereinafter referred to as a threshold curve) formed by threshold values of voltage deviation of the single battery under different conditions of current, temperature of the single battery and residual SOC is calculated and obtained mainly by analyzing the voltage, the current, the temperature of the single battery and the residual SOC of the single battery in the vehicle data, and the specific process is as follows:
1) calculating the mean value of the voltage of the single battery
Wherein n is the number of the single batteries of the vehicle, m is the number of records under the specified condition, and Vij is the voltage value of the ith single battery for recording j
2) Calculating the deviation of the cell voltage from the mean voltage (hereinafter referred to as voltage deviation)
Calculating the accumulated times of the deviation, and calculating the accumulated times according to voltage deviation groups, wherein the calculation formula of the accumulated times of the given voltage deviation is as follows:
wherein, the given voltage deviation value is given.
3) Calculating the cumulative percentage of the deviation (hereinafter referred to as cumulative percentage)
Calculating a threshold curve: and obtaining voltage deviation threshold values under different conditions according to the fact that the accumulated percentage is larger than the specified threshold value to form a threshold value curve, wherein the graph in FIG. 3 is an example of the threshold value curve under different charging and discharging current conditions.
2. Index construction
In the index construction stage, the following indexes are constructed mainly through vehicle original data and data preprocessing results:
accumulated mileage
Failure energy density: counting the number of times that the voltage deviation of the single battery exceeds the voltage deviation threshold value within the range of every hundred kilometers, wherein the calculation formula is as follows:
3. fault early warning point excavation
The fault early warning point mining means that some index change rules before the copper bar loosening fault is outbreak are obtained through learning of known copper bar loosening fault data. The specific implementation process is as follows:
and (3) mileage interval division: dividing the distance according to the length of one hundred kilometers, namely, the distance is 0-100 and belongs to a 100km interval, and the distance is 101-200 and belongs to a 200km interval;
calculating the fault energy density of the specified battery in each mileage interval;
calculating the fault energy density change rate: and the fault energy density ratio of the current mileage interval to the last mileage interval.
Calculating the interval of which the first failure energy density change rate is greater than a specified threshold value, and taking the point of the interval as a failure early warning point
And taking the fault energy density value of the fault early warning point as an early warning value.
4. Model application
And in the model application stage, the new data of the vehicles of the same type are calculated, and then the failure energy density data of the vehicles are compared with the early warning value to determine whether to carry out early warning or not. The specific process is as follows:
1) and (3) mileage interval division: dividing the data into a plurality of sections according to the length of one hundred kilometers;
2) calculating the fault energy density of the specified battery in each mileage interval;
3) and when the fault energy density data is larger than the early warning value, sending out a fault early warning, otherwise, considering the fault energy density data to be normal.
Fig. 4 is a fault energy density curve for a faulty battery, which exceeds the warning value at 12900 of the curve and issues a fault warning according to the method described above. (actual conditions of the battery failed at 15600 km.)
Fig. 5 is a fault energy density curve for a normal cell, where the data does not exceed the warning value and is considered normal, according to the method described above.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A lithium battery copper bar loosening fault diagnosis and prediction method is characterized by comprising the following steps:
(1) data preprocessing
In the data preprocessing stage, a curve formed by threshold values of voltage deviation of the single battery under different current, single battery temperature and residual SOC conditions is calculated through analyzing the voltage, the current, the single battery temperature and the residual SOC of the single battery in the vehicle data;
(2) index construction
The index construction stage mainly comprises the steps of preprocessing results through vehicle original data and data;
(3) and excavation of fault early warning points
The fault early warning point mining means that some index change rules before the copper bar loosening fault is outbreak are obtained through learning of known copper bar loosening fault data;
(4) model application
And in the model application stage, the new data of the vehicles of the same type are calculated, and then the failure energy density data of the vehicles are compared with the early warning value to determine whether to carry out early warning or not.
2. The lithium battery copper bar loosening fault diagnosis and prediction method according to claim 1, wherein the specific process of data processing is as follows:
(1) calculating the mean value of the voltage of the single battery
Wherein n is the number of single batteries of the vehicle, m is the number of records under specified conditions,
recording the voltage value of the ith single battery of j;
(2) calculating the deviation of the monomer voltage and the average voltage;
(3) calculating the accumulated times of the deviation, and calculating the accumulated times according to voltage deviation groups, wherein the calculation formula of the accumulated times of the given voltage deviation is as follows:
wherein the content of the first and second substances,
given voltage deviation values;
(4) calculating the percentage of accumulated times of deviation;
(5) calculating a threshold curve: and obtaining voltage deviation threshold values under different conditions according to the condition that the accumulated percentage is larger than the specified threshold value, and forming a threshold value curve.
3. The lithium battery copper bar loosening fault diagnosis and prediction method according to claim 1, wherein the index construction is as follows:
(1) accumulating mileage;
(2) failure energy density: counting the number of times that the voltage deviation of the single battery exceeds the voltage deviation threshold value within the range of every hundred kilometers, wherein the calculation formula is as follows:
4. the lithium battery copper bar loosening fault diagnosis and prediction method according to claim 1, wherein the specific implementation process of the fault early warning point excavation is as follows:
(1) and (3) mileage interval division: dividing the distance according to the length of one hundred kilometers, namely, the distance is 0-100 and belongs to a 100km interval, and the distance is 101-200 and belongs to a 200km interval;
(2) calculating the fault energy density of the specified battery in each mileage interval;
(3) calculating the fault energy density change rate: the fault energy density ratio of the current mileage interval to the last mileage interval;
(4) calculating an interval of which the first fault energy density change rate is greater than a specified threshold value, and taking a point in the interval as a fault early warning point;
(5) and taking the fault energy density value of the fault early warning point as an early warning value.
5. The method for diagnosing and predicting the loosening fault of the copper bar of the lithium battery as claimed in claim 1, wherein the concrete process of the model application is as follows:
(1) and (3) mileage interval division: dividing the data into a plurality of sections according to the length of one hundred kilometers;
(2) calculating the fault energy density of the specified battery in each mileage interval;
(3) and when the fault energy density data is larger than the early warning value, sending out a fault early warning, otherwise, considering the fault energy density data to be normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011280975.6A CN112330176A (en) | 2020-11-17 | 2020-11-17 | Lithium battery copper bar loosening fault diagnosis and prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011280975.6A CN112330176A (en) | 2020-11-17 | 2020-11-17 | Lithium battery copper bar loosening fault diagnosis and prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112330176A true CN112330176A (en) | 2021-02-05 |
Family
ID=74319202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011280975.6A Withdrawn CN112330176A (en) | 2020-11-17 | 2020-11-17 | Lithium battery copper bar loosening fault diagnosis and prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330176A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114062943A (en) * | 2021-10-21 | 2022-02-18 | 合肥国轩高科动力能源有限公司 | Lithium ion battery system polarization abnormity early warning method and system |
-
2020
- 2020-11-17 CN CN202011280975.6A patent/CN112330176A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114062943A (en) * | 2021-10-21 | 2022-02-18 | 合肥国轩高科动力能源有限公司 | Lithium ion battery system polarization abnormity early warning method and system |
| CN114062943B (en) * | 2021-10-21 | 2024-02-09 | 合肥国轩高科动力能源有限公司 | Polarization abnormality early warning method and system for lithium ion battery system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110133508B (en) | Safety early warning method for power battery of electric automobile | |
| CN112092675B (en) | Battery thermal runaway early warning method, system and server | |
| CN113064939B (en) | New energy vehicle three-electric system safety feature database construction method | |
| CN112327167B (en) | Battery capacity diving risk assessment method and system | |
| CN110045291B (en) | Lithium battery capacity estimation method | |
| CN110806508B (en) | Data-based method for evaluating contact resistance change of high-voltage circuit | |
| CN115384311A (en) | Method, system, vehicle and storage medium for diagnosing insulation fault of power battery | |
| CN115366683A (en) | Fault diagnosis strategy for new energy automobile power battery multi-dimensional model fusion | |
| CN115372828A (en) | Battery cell consistency evaluation method based on charging segment data and unsupervised algorithm | |
| CN113866641A (en) | Fault detection method and device for lithium ion battery | |
| CN112330176A (en) | Lithium battery copper bar loosening fault diagnosis and prediction method | |
| CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
| CN116736142B (en) | Method, system and device for early warning of health condition of battery pack | |
| CN115958957B (en) | Method and system for predicting charging overheat faults of power battery of electric automobile | |
| CN116256642A (en) | Lithium iron phosphate battery fault diagnosis method suitable for sparse data | |
| CN115128468A (en) | Chemical energy storage battery PHM undervoltage fault prediction method | |
| CN113240002A (en) | Internet of vehicles big data preprocessing system, device and method | |
| CN117341476B (en) | Battery differential pressure fault early warning method and system | |
| CN115561658B (en) | Power battery abnormal cell monitoring method based on data slicing | |
| CN115389948B (en) | Method for establishing health state evaluation model of power battery of battery replacement station | |
| CN117103997A (en) | Battery thermal runaway risk detection method considering discharge data of battery system | |
| Xu et al. | Prediction of Lithium-ion Battery Remaining Useful Life Based on Long Short Term Memory | |
| CN117590269A (en) | Comprehensive health state evaluation method of battery system based on charge sparse big data | |
| Gong et al. | Data-driven lithium-ion battery remaining life prediction on actual operating vehicles | |
| Cheng et al. | A method for battery fault diagnosis and early warning combining isolated forest algorithm and sliding window |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210205 |
|
| WW01 | Invention patent application withdrawn after publication |