CN115494399A - Intelligent identification method for individual difference risks of new energy automobile battery system - Google Patents

Intelligent identification method for individual difference risks of new energy automobile battery system Download PDF

Info

Publication number
CN115494399A
CN115494399A CN202211296735.4A CN202211296735A CN115494399A CN 115494399 A CN115494399 A CN 115494399A CN 202211296735 A CN202211296735 A CN 202211296735A CN 115494399 A CN115494399 A CN 115494399A
Authority
CN
China
Prior art keywords
data
risk
cell
difference
battery
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
CN202211296735.4A
Other languages
Chinese (zh)
Inventor
杨若浩
刘惠强
徐明禹
钟灵杰
姜国翠
钟波
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.)
Chongqing Telecommunication System Integration Co ltd
Original Assignee
Chongqing Telecommunication System Integration 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 Chongqing Telecommunication System Integration Co ltd filed Critical Chongqing Telecommunication System Integration Co ltd
Priority to CN202211296735.4A priority Critical patent/CN115494399A/en
Publication of CN115494399A publication Critical patent/CN115494399A/en
Pending legal-status Critical Current

Links

Images

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]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • 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
    • 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

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

A cell difference risk intelligent identification method of a new energy automobile battery system is characterized in that six items of data are provided according to SOC, a charging state, a highest voltage cell code, a cell voltage highest value, a lowest voltage cell code and a cell voltage lowest value specified by national standard GB/T32960, and a cell monomer with extreme difference and occurrence of the extreme difference is counted to construct a difference matrix and structure difference characteristics; accumulating the range matrix in an observation window to eliminate the influence of an abnormal value; the average value in the historical influence window is used for highlighting the abnormal change of the consistency of the proceeding party; constructing a safety risk signal, and calculating to obtain a safety risk characteristic vector; and constructing a logistic regression model to realize intelligent identification of the safety risk. The method has the advantages of high real-time performance, simple requirement on data and capability of realizing difference quantification of each battery and intelligent identification of safety risks.

Description

Intelligent identification method for individual difference risks of new energy automobile battery system
Technical Field
The invention relates to the technical field of power batteries, in particular to an intelligent identification method for a monomer difference risk of a new energy automobile battery system.
Background
Accidents, especially fire accidents, of new energy automobiles (electric vehicles) are mostly caused by the failure of power batteries. In practical application, the internal state of the battery pack can be analyzed by monitoring and acquiring various indexes through a BMS (battery management system), and then safety early warning and risk assessment of the new energy automobile are realized.
In automobile application, a plurality of independent battery monomers are connected in series to form a storage battery pack, each battery monomer is used as a minimum monitoring unit in the battery pack, deterioration of the internal state of the battery pack is often shown through inconsistency of performance among the battery monomers, and therefore analysis of the risk state of the battery pack can be achieved through analysis of whether the performance of the battery monomers is consistent. Because each battery monomer is limited by the process, the internal resistance, the resistance value of the connection part, the internal impurities and the like of each battery are different, the initial state of each battery monomer is different when the battery monomer leaves a factory, but the inconsistency is determined by the inherent physicochemical property of the battery monomer, and the inconsistency can be considered to be stable and can not cause accidents generally. At present, the commonly used method for analyzing the consistency of battery cells in a battery pack includes: the method comprises an information entropy method for analyzing the voltage toggle instability of a single battery, an internal resistance method for identifying internal short circuit based on equivalent circuit model calculation, a characteristic analysis method for constructing an analysis model by supervised machine learning based on a large number of examples, and the like.
Disclosure of Invention
The invention aims to provide an intelligent identification method for the monomer difference risk of a new energy automobile battery system, aiming at the defects of the prior art, and the intelligent identification method is high in real-time performance, simple in data requirement and capable of realizing difference quantification and intelligent identification of safety risk of each battery.
The technical scheme of the invention is as follows: a method for intelligently identifying individual difference risks of a new energy automobile battery system comprises the following specific steps:
1) Data acquisition: real-time acquisition of six operating parameters soc of vehicle in operation i (battery level at time i), status i (charge-discharge state at time i), umax i (maximum voltage value at time i), umin i (lowest voltage value at time i), smax i (highest cell number at time i), smin i (the voltage lowest monomer serial number at the moment i), wherein the data are time-varying data with time scales;
2) Structuring of battery cell inconsistency characteristics: defining a range matrix A m×n ：
A m×n ＝(a ij )∈R m×n
Wherein
Figure BDA0003902997990000021
Wherein m represents the number of battery cells in the battery pack, n represents the number of valid data, a ij Elements representing the ith row and the jth column of the range matrix, R m×n A real number matrix representing m rows and n columns;
3) Quantification of cell inconsistency:
3-1) setting a filter f according to the historical data;
3-2) convolving the range matrix with a filter f to obtain a difference matrix D for reflecting the current inconsistency of the battery pack m×n = cov (a, f), calculation formula as follows,
Figure BDA0003902997990000022
in the formula, d ij Elements representing the ith row and jth column of the difference matrix, f i Denotes the ith element of the filter, a i+1-k,j Representing the elements of the ith +1-k row and the jth column of the range matrix, and l representing the length of a historical observation window;
4) Identifying abnormal changes in the inconsistency of the battery cells: the scaling of the difference matrix is realized based on the mean value and the standard deviation of L pieces of data in the historical influence window to obtain a relative difference matrix D', the calculation formula is as follows,
Figure BDA0003902997990000031
of formula (II) to' ij Elements representing the ith row and jth column of the relative difference matrix, D ij Representing a difference matrix, x ij Means, S, representing L pieces of data within a historical influence window ij Representing the standard deviation of L pieces of data in a historical influence window;
5) Constructing a characteristic signal of security risk of inconsistency: setting a safety risk signal at the jth moment of the ith cell as a according to the sampling frequency Fs ij Extracting the mean value mu of the safety risk signal ij Standard deviation σ ij Kurtosis K ij Mean value of rectification
Figure BDA0003902997990000034
Form factor
Figure BDA0003902997990000033
Crest factor
Figure BDA0003902997990000035
Information entropy H (a) ij ) To obtain its safety risk characteristic alpha ij Wherein: :
a ij ＝(D′ i,j-600*Fs+1 ,D′ i,j-600*Fs+2 ,…,D′ i,j )，
Figure BDA0003902997990000036
6) Risk intelligent identification of battery system safety risk: the safety risk characteristics 3 hours before the accident of the problem battery cell of the accident vehicle are used as a risk training set, the battery cell of the normal vehicle and the safety risk characteristics of the normal telecommunication of the accident vehicle are used as the safety training set, and a nonlinear logistic regression classification model is trained, so that the risk intelligent identification of the safety risk of the battery system is realized.
Further, in step 3-1), the filter f is a first-order half gaussian filter with a length of 2l and a standard deviation of σ =2l/3.75, and the calculation formula is as follows,
f＝(f 1 ,f 2 ,…,f l ) In which
Figure BDA0003902997990000032
In the formula, l is a set historical observation window length and is used for observing historical data in the observation window at a certain time.
Further, in step 4), the mean and standard deviation of the L pieces of data in the history influence window are calculated according to the following formula,
Figure BDA0003902997990000041
Figure BDA0003902997990000042
where L represents the historical impact window length, avg m×n Means, S, representing L pieces of data within a historical influence window m×n Indicating the standard deviation of the L pieces of data within the historical impact window.
Further, in step 5), the safety risk characteristics of the ith cell at the jth moment include a mean value, a standard deviation, a kurtosis, a rectified mean value, a wave form factor, a peak value factor and an information entropy, which are calculated according to the following formula,
Figure BDA0003902997990000043
Figure BDA0003902997990000044
Figure BDA0003902997990000045
Figure BDA0003902997990000046
Figure BDA0003902997990000047
Figure BDA0003902997990000048
Figure BDA0003902997990000049
wherein D' represents a difference matrix, a ij And the safety risk signal at the jth moment of the ith battery cell is represented.
Adopt above-mentioned technical scheme's beneficial effect:
1. the method has low requirement on data: the calculation can be carried out only by using national standard data, the data acquisition frequency is not required to be high, the data is not required to be strict and continuous, and the safety early warning accurate to the battery cell can be realized without a single voltage value.
2. The method can realize difference quantification on the single battery: the process of constructing the difference matrix realizes the quantification of the inconsistency inside the battery pack, and the size of each element in the matrix is the quantified inconsistency of each battery cell.
3. The method is based on a statistical model, and is simple to realize: in the feature extraction stage, a large amount of machine learning is not needed, and the model can be brought into for risk identification after the mathematical calculation is carried out on the original data in the production environment.
4. The method can perform real-time calculation: when the difference value of each moment is calculated, only the historical data of the historical observation window L and the historical influence window L before the moment is needed.
The invention is further described with reference to the drawings and the specific embodiments in the following description.
Drawings
FIG. 1 is a broken line analysis diagram of a fault vehicle in the embodiment of the method;
FIG. 2 is a broken line analysis diagram of a normal vehicle in the embodiment of the method;
FIG. 3 is a flow chart of the implementation steps of the method.
Detailed Description
The battery pack generates stable inconsistency of battery monomers due to inherent physicochemical properties, the battery pack usually shows that voltage extreme values appear on a plurality of fixed battery monomers on the data characteristics of parameters, the size of range difference generally accords with Gaussian distribution, and the analysis of the abnormal state in the battery pack is to analyze the abnormal change of the inconsistency of the battery monomers in the battery pack, namely to identify the extreme value battery monomers newly appearing along with time sequence and the abnormal increase of the range difference.
Referring to fig. 1 to 3, an intelligent identification method for a cell difference risk of a new energy automobile battery system supplies six items of data according to SOC, a charging state, a highest voltage cell code, a highest cell voltage value, a lowest voltage cell code and a lowest cell voltage value specified by national standard GB/T32960, and calculates range and cell monomer occurring range, constructs a difference matrix, and structures difference characteristics; accumulating the range matrix in an observation window to eliminate the influence of an abnormal value; the average value in the historical influence window is used for highlighting the abnormal change of the consistency of the proceeding party; constructing a safety risk signal, and calculating to obtain a safety risk characteristic vector; and constructing a logistic regression model to realize intelligent identification of the safety risk.
The method comprises the following specific steps:
1) Data acquisition: real-time acquisition of six operating parameters soc of vehicle in operation i (battery level at time i), status i (charge/discharge state at time i), umax i (maximum voltage value at time i), umin i (minimum voltage value at time i), smax i (highest cell number at time i), smin i (the lowest cell number of the voltage at the time i), the above data are all time-varying data with time scales.
2) Structuring the battery cell inconsistency characteristics: defining a range matrix A m×n ：
A m×n ＝(a ij )∈R m×n
Wherein
Figure BDA0003902997990000061
Wherein m represents the number of battery cells in the battery pack, n represents the number of valid data, a ij Elements representing the ith row and the jth column of the range matrix, R m×n Representing a real number.
3) Quantification of cell inconsistency:
3-1) setting a historical observation window length l for historical data in an observation window when an observation mode is available, constructing a first-order half-Gaussian filter with the length of 2l and the standard deviation of sigma =2l/3.75, and calculating the formula as follows,
f＝(f 1 ,f 2 ,…,f l ) In which
Figure BDA0003902997990000062
Because a difference matrix needs to be constructed by referring to values of each moment and the previous l-1 moments, and the closer the current moment is, the higher the weight is, a Gaussian filter with the length of 2l is constructed, and the left half part of the Gaussian filter is taken as the weight;
3-2) convolving the range matrix with a filter f to obtain a difference matrix D for reflecting the current inconsistency of the battery pack m×n = cov (a, f), calculation formula as follows,
Figure BDA0003902997990000071
in the formula, d ij Elements representing the ith row and jth column of the difference matrix, f i Denotes the ith element of the filter, a i+1-k,j The elements in the j-th row from the i +1-k of the range matrix are shown, and l represents the length of the historical observation window.
4) Identifying abnormal changes in the inconsistency of the battery cells:
4-1) setting the length L of a history influence window, and calculating the average value and the standard deviation of L pieces of effective data in the window, wherein the calculation formula is as follows:
Figure BDA0003902997990000072
Figure BDA0003902997990000073
where L represents the historical impact window length, avg m×n Means representing the L pieces of data within a historical influence window, d i+1-k,j Elements representing the ith + 1-kth row and jth column of the disparity matrix, S m×n Standard deviation, σ, representing L pieces of data within a historical influence window ij Elements representing standard deviation ith row and jth column;
4-2) realizing the scaling of the difference matrix based on the mean value and the standard deviation of L pieces of data in the historical influence window, subtracting the corresponding mean value from the value of each difference matrix, and adding 3 times of standard deviation to obtain a relative difference matrix D', wherein the calculation formula is as follows,
Figure BDA0003902997990000074
in the formula (II), d' ij Elements representing the ith row and jth column of the relative difference matrix, d ij Representing a difference matrix, x ij Means, S, representing L pieces of data within a historical influence window ij Indicating the standard deviation of L pieces of data in the historical influence window.
5) Constructing a characteristic signal of the security risk of the inconsistency: setting the safety risk signal of the ith battery cell at the jth moment as alpha according to the data sampling frequency ij Calculating the signal characteristics of the safety risk signals;
according to the statistical law, the reason of most of the fire accidents is that the individual battery cells are subjected to internal short circuit and are easily subjected to two working conditions of discharging at the second SOC and charging at the high SOC, so that the two working conditions are combinedObtaining the signal characteristics, SOC and charge-discharge state of the safety risk signal of the battery cell to obtain the safety risk characteristic vector alpha of the safety risk signal ij 。
6) Risk intelligent identification of battery system safety risk: the safety risk characteristics 3 hours before the accident electric core accident of the accident vehicle are used as a risk training set, the safety risk characteristic vectors of the electric core of the normal vehicle and the normal electric core of the accident vehicle are used as the safety training set, and a logistic regression classification model is trained, so that the risk intelligent identification of the safety risk of the battery system is realized.
Embodiment 1, the intelligent identification and analysis of the individual difference risk of the new energy automobile battery system are as follows:
1. acquiring data of the full life cycle of a new energy automobile accident vehicle and a normal vehicle of a certain vehicle type with a fire accident, wherein the vehicle type is known to have 120 single batteries, the data acquisition frequency Fs is 0.1Hz, and the operation parameters of the vehicle type include: battery charge soc at time i i I time of charge/discharge status i Maximum voltage value umax at time i i Minimum voltage value umin at time i i I highest cell number smax at time i i Voltage lowest cell number smin at time i i ；
2. Construction of a range matrix A m×n ；
3. Empirically set the observation window to 10 minutes, then set l =10 × 60 × fs =60, resulting in a filter f;
4. according to A m×n And Fs to obtain a difference matrix D m×n ；
5. According to experience, setting a historical influence window to be 7 days, wherein the vehicle uses the vehicle for about 2 hours each day, then setting L =7 × 2 × 60 × Fs =5040, and calculating to obtain a mean value matrix Avg;
6. calculating to obtain a relative difference matrix D ' according to a formula, drawing a broken line statistical graph according to the D ', wherein the abscissa of the broken line graph represents time (Unix timestamp), the ordinate is the value of the difference matrix D ', each broken line corresponds to one single battery of a battery pack, and the single battery is respectively analyzed for an accident vehicle and a normal vehicle,
as shown in fig. 1: the difference value of the battery cells of the vehicle No. 45 and No. 74 is abnormally increased before an accident, as shown in FIG. 2, the inconsistency of the vehicle is stable, no sudden change occurs, and the difference value is small, and the difference can be expressed by calculating the statistical characteristic and the informatics characteristic of the signal;
7. constructing a safety risk signal based on 30 minutes of each battery cell at each moment and 30 × 60 × fs =180relative difference values, calculating a mean value, a standard deviation, a kurtosis, a rectified mean value, a wave form factor, a peak value factor and an information entropy of the signal according to a formula, and combining the SOC and the charging and discharging state at the corresponding moment to obtain a safety risk feature vector;
8. the safety risk characteristic 3 hours before the problem battery cell accident of multiple accident vehicles of the same vehicle type is used as a risk training set, the safety risk characteristic vectors of the battery cells of multiple normal vehicles of the same vehicle type and the normal battery cells of the accident vehicles are used as a safety training set, a logistic regression classification model is trained, and the intelligent risk identification of the safety risk of the battery system is further realized based on the obtained model.

Claims (4)

1. The intelligent identification method for the monomer difference risk of the new energy automobile battery system is characterized by comprising the following specific steps of:
1) Data acquisition: real-time acquisition of six operating parameters soc of vehicle in operation i (battery level at time i), status i (charge-discharge state at time i), umax i (maximum voltage value at time i), umin i (lowest voltage value at time i), smax i (highest cell number at time i), smin i (the voltage lowest monomer serial number at the moment i), wherein the data are time-varying data with time scales;
2) Structuring of battery cell inconsistency characteristics: defining a range matrix A m×n ：
A m×n ＝(a ij )∈R m×n
Wherein
Figure FDA0003902997980000011
Wherein m represents the number of battery cells in the battery pack,n represents the number of valid data, a ij Elements representing the ith row and the jth column of the range matrix, R m×n A real number matrix representing m rows and n columns;
3) Quantification of cell inconsistency:
3-1) setting a filter f according to the historical observation window l;
3-2) convolving the range matrix with a filter f to obtain a difference matrix D for reflecting the current inconsistency of the battery pack m×n = cov (a, f), calculation formula as follows,
Figure FDA0003902997980000012
in the formula (d) ij Elements representing the ith row and jth column of the difference matrix, f i Denotes the ith element of the filter, a i+1-k,j Representing the elements of the ith +1-k row and the jth column of the range matrix, and l representing the length of a historical observation window;
4) And identifying abnormal change of the inconsistency of the battery cells: the scaling of the difference matrix is realized based on the mean value and the standard deviation of L pieces of data in the historical influence window to obtain a relative difference matrix D', the calculation formula is as follows,
Figure FDA0003902997980000021
of formula (II) to' ij Elements representing the ith row and jth column of the relative difference matrix, D ij Represents a difference matrix, x ij Means, S, representing L pieces of data within a historical influence window ij Representing the standard deviation of L pieces of data in a historical influence window;
5) Constructing a characteristic signal of the security risk of the inconsistency: setting a safety risk signal of the ith battery cell at the jth moment as a according to the sampling frequency Fs ij Extracting the mean value mu of the safety risk signal ij Standard deviation σ ij Kurtosis K ij Mean value of rectification
Figure FDA0003902997980000022
Form factor
Figure FDA0003902997980000023
Crest factor
Figure FDA0003902997980000024
Information entropy H (a) ij ) And combining the SOC and the charge-discharge state at the moment to obtain a safety risk characteristic vector alpha of the battery ij Wherein: :
a ij ＝(D′ i,j-600*Fs+1 ,D′ i,j-600*Fs+2 ,…,D′ i,j )，
Figure FDA0003902997980000025
6) Risk intelligent identification of battery system safety risk: the safety risk characteristics 3 hours before the accident of the problem battery cell of the accident vehicle are used as a risk training set, the battery cell of the normal vehicle and the safety risk characteristics of the normal telecommunication of the accident vehicle are used as the safety training set, and a logistic regression classification model is trained, so that the risk intelligent identification of the safety risk of the battery system is realized.
2. The intelligent identification method for the cell difference risk of the new energy automobile battery system according to claim 1, characterized in that: in step 3-1), the filter f is a first-order half gaussian filter with a length of 2l and a standard deviation of σ =2l/3.75, and the calculation formula is as follows,
f＝(f 1 ,f 2 ,…,f l ) Wherein
Figure FDA0003902997980000026
In the formula, l is a set historical observation window length and is used for observing historical data in the observation window at a certain time.
3. The intelligent identification method for the cell difference risk of the new energy automobile battery system according to claim 1, characterized in that: in the step 4), the mean value and the standard deviation of L pieces of data in the historical influence window are calculated according to the following formula,
Figure FDA0003902997980000031
Figure FDA0003902997980000032
where L represents the historical impact window length, avg m×n Means, S, representing L pieces of data within a historical influence window m×n Indicating the standard deviation of the L pieces of data within the historical impact window.
4. The intelligent identification method for the monomer difference risk of the new energy automobile battery system according to claim 1, characterized in that: in step 5), the safety risk characteristics of the ith cell at the jth moment include a mean value, a standard deviation, a kurtosis, a rectified mean value, a wave form factor, a peak value factor and an information entropy, and are calculated according to the following formula,
Figure FDA0003902997980000033
Figure FDA0003902997980000034
Figure FDA0003902997980000035
Figure FDA0003902997980000036
Figure FDA0003902997980000037
Figure FDA0003902997980000038
Figure FDA0003902997980000039
wherein D' represents a difference matrix, a ij And the safety risk signal at the jth moment of the ith battery cell is represented.
CN202211296735.4A 2022-10-21 2022-10-21 Intelligent identification method for individual difference risks of new energy automobile battery system Pending CN115494399A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211296735.4A CN115494399A (en) 2022-10-21 2022-10-21 Intelligent identification method for individual difference risks of new energy automobile battery system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211296735.4A CN115494399A (en) 2022-10-21 2022-10-21 Intelligent identification method for individual difference risks of new energy automobile battery system

Publications (1)

Publication Number Publication Date
CN115494399A true CN115494399A (en) 2022-12-20

Family

ID=84474856

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211296735.4A Pending CN115494399A (en) 2022-10-21 2022-10-21 Intelligent identification method for individual difference risks of new energy automobile battery system

Country Status (1)

Country Link
CN (1) CN115494399A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117310543A (en) * 2023-11-29 2023-12-29 中国华能集团清洁能源技术研究院有限公司 Battery abnormality diagnosis method and device
CN117922301A (en) * 2024-03-25 2024-04-26 北京厚方科技有限公司 Battery power supply safety supervision system suitable for new energy automobile

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117310543A (en) * 2023-11-29 2023-12-29 中国华能集团清洁能源技术研究院有限公司 Battery abnormality diagnosis method and device
CN117922301A (en) * 2024-03-25 2024-04-26 北京厚方科技有限公司 Battery power supply safety supervision system suitable for new energy automobile
CN117922301B (en) * 2024-03-25 2024-05-24 北京厚方科技有限公司 Battery power supply safety supervision system suitable for new energy automobile

Similar Documents

Publication Publication Date Title
CN110161414B (en) Power battery thermal runaway online prediction method and system
CN115494399A (en) Intelligent identification method for individual difference risks of new energy automobile battery system
CN110794305B (en) Power battery fault diagnosis method and system
Tian et al. Consistency evaluation and cluster analysis for lithium-ion battery pack in electric vehicles
CN111584952B (en) Method and system for online evaluation of electrochemical cells of energy storage power station
CN113064939B (en) New energy vehicle three-electric system safety feature database construction method
CN112782591A (en) Lithium battery SOH long-term prediction method based on multi-battery data fusion
CN109375116B (en) Battery system abnormal battery identification method based on self-encoder
CN112255560B (en) Battery cell health degree prediction method
CN114734873B (en) Power battery monomer thermal runaway early warning method based on cloud online data
CN115366683A (en) Fault diagnosis strategy for new energy automobile power battery multi-dimensional model fusion
CN114509678B (en) Power battery thermal runaway prediction method based on big data
CN114580496A (en) Self-detection method for single fault of lithium ion battery
CN114646888A (en) Assessment method and system for capacity attenuation of power battery
CN116699407A (en) Power battery safety risk early warning method based on safety entropy
CN115656837A (en) Fault prediction method for series-connected battery
CN115424443A (en) Vehicle abnormity monitoring method based on driving data
CN115128468A (en) Chemical energy storage battery PHM undervoltage fault prediction method
CN112965001B (en) Power battery pack fault diagnosis method based on real vehicle data
CN115144753B (en) Echelon energy storage battery operation safety detection system, method and energy storage system
CN111983458B (en) Parallel battery optimal model judging and optimizing method
CN116908694B (en) SOH estimation method of household energy storage system
CN117341476B (en) Battery differential pressure fault early warning method and system
CN114781256B (en) Power battery thermal runaway risk assessment method based on cloud lifetime learning
CN115825755B (en) Method for evaluating consistency of voltages of battery cells of energy storage 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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: No.51, Daping Main Street, Yuzhong District, Chongqing 400042

Applicant after: Zhongdian Zhi'an Technology Co.,Ltd.

Address before: No.51, Daping Main Street, Yuzhong District, Chongqing 400042

Applicant before: CHONGQING TELECOMMUNICATION SYSTEM INTEGRATION CO.,LTD.