CN114734873A - Power battery unit thermal runaway early warning method based on cloud online data - Google Patents

Power battery unit thermal runaway early warning method based on cloud online data Download PDF

Info

Publication number
CN114734873A
CN114734873A CN202210403841.1A CN202210403841A CN114734873A CN 114734873 A CN114734873 A CN 114734873A CN 202210403841 A CN202210403841 A CN 202210403841A CN 114734873 A CN114734873 A CN 114734873A
Authority
CN
China
Prior art keywords
matrix
thermal runaway
failure probability
dimensional
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
CN202210403841.1A
Other languages
Chinese (zh)
Inventor
杨世春
曹瑞
张正杰
林家源
王明悦
刘新华
李兴虎
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.)
Beihang University
Original Assignee
Beihang University
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 Beihang University filed Critical Beihang University
Priority to CN202210403841.1A priority Critical patent/CN114734873A/en
Publication of CN114734873A publication Critical patent/CN114734873A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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 relates to a power battery unit thermal runaway early warning method based on cloud online data, which comprises the following steps of: s1: extracting boundary characteristics of the battery module from the battery pack data collected by the cloud, and forming a high-dimensional matrix; s2: extracting a low-dimensional feature matrix of the high-dimensional matrix, calculating the current failure probability based on the low-dimensional feature matrix, comparing the current failure probability with a preset failure probability threshold value, and judging whether a thermal runaway risk exists at present; s3: when the thermal runaway risk is judged, calculating the contribution value of each dimension in the high-dimensional matrix to the failure probability, and determining the single battery corresponding to the boundary characteristic with the largest contribution of the failure probability as the high-risk single to be verified; s4: and analyzing the on-line voltage, temperature and SOC data of the high-risk monomer to be checked, and alarming according to the deviation degree value corresponding to three different levels. According to the method, the thermal runaway of the power single battery is early warned, so that the stability and the safety of the battery operation are improved.

Description

Power battery unit thermal runaway early warning method based on cloud online data
Technical Field
The invention belongs to the technical field of new energy automobile power batteries, and particularly relates to a power battery unit thermal runaway early warning method based on cloud online data.
Background
In the actual running of the electric automobile, along with the use of the electric automobile, the dynamic changes of severe road conditions, environmental temperature and load can cause the nonlinear reduction of the performance of a battery system, and further inevitably cause the problems of liquid leakage, insulation damage, internal micro short circuit and the like. The correlation between the current thermal runaway occurrence and the real-time working condition of the electric automobile is unknown, and the starting mechanism of the thermal runaway is not clear. Therefore, timely monitoring of the fault characteristics of the battery and evaluation of the health state of the battery are currently main means and important methods for preventing serious safety accidents such as spontaneous combustion, explosion and the like caused by further aging of the battery as far as possible. The real-time state monitoring and accurate fault diagnosis of the battery management system are realized, and further, the safety early warning is achieved in advance, so that the method has important practical significance.
The current methods for realizing fault alarm of the battery management system mainly comprise three types: a threshold-based determination method, a physical model-based determination method, and a data-driven model-based determination method. However, most of the verification and correction of the current thermal runaway early warning method are completed under laboratory data, and further development is needed in the face of the accuracy of real random working conditions. Along with the development of high in the clouds technique, board carries BMS data and can transmit in real time to the high in the clouds and store and calculate, on the basis of high in the clouds on-line data, combines intelligent algorithm to excavate big data, combines machine learning algorithm, realizes under the real-time operating mode, and the early warning of carrying on of battery thermal runaway risk ensures that electric motor car safe operation is very using value.
Disclosure of Invention
The technical problem to be solved is as follows:
aiming at the technical problems in the prior art, the invention provides a power battery monomer thermal runaway early warning method based on cloud end online data, which is used for realizing thermal runaway early warning and positioning of a battery monomer in the running process of a real vehicle based on the cloud end online data and various intelligent algorithms, and adopts the following technical scheme:
a power battery unit thermal runaway early warning method based on cloud online data comprises the following steps:
s1: extracting boundary characteristics of the battery module from battery pack data collected by a cloud in a certain period of time, and forming a high-dimensional matrix from the boundary characteristics of the battery module;
s2: reducing the dimension of the high-dimensional matrix through a machine learning algorithm, extracting a low-dimensional feature matrix of the high-dimensional matrix, calculating the current failure probability of each moment in the time period based on the low-dimensional feature matrix, and comparing the current failure probability with a preset failure probability threshold value to judge whether the thermal runaway risk exists at present;
s3: when the thermal runaway risk is judged, decompressing the low-dimensional matrix in the step S2, calculating the contribution value of each dimension in the high-dimensional matrix in the step S1 to the failure probability, and determining the single battery corresponding to the boundary feature with the largest failure probability contribution as the high-risk single to be verified;
s4: analyzing the on-line voltage, temperature and SOC data of the high-risk monomer to be checked, combining a deep learning battery state prediction model which is trained in advance, calculating the deviation degree of the on-line voltage, temperature and SOC data of the high-risk monomer to be checked in the current state and the prediction state, comparing the deviation degree value of the voltage, temperature and SOC data of the high-risk monomer to be checked with a preset three-level alarm threshold value, and alarming according to the deviation degree value corresponding to three different levels.
Further, in step S1, the parameter related to thermal runaway of the battery module includes a voltage neel coefficient of the single battery, a voltage change rate of the single battery, a differential value of voltage versus temperature of the single battery, a differential value of voltage versus state of charge of the single battery, a temperature change rate of the single battery, an internal short circuit internal resistance of the single battery, a voltage of the single battery, a temperature of the single battery, and a state of charge of the single battery.
Further, in step S1, the extracted boundary features are the extracted maximum, minimum, standard deviation, and range of the thermal runaway related parameters
Further, in step S2, the machine learning algorithm includes a linear dimensionality reduction PCA algorithm or a non-linear dimensionality reduction self-encoder algorithm.
Further, in step S2, the failure probability is determined by calculating Hotelling' S T of the low-dimensional matrix2The statistic and the SPE statistic are calculated, so that the comprehensive index is calculated
Figure BDA0003601025150000035
And regressed to a probability distribution
Figure BDA0003601025150000034
Obtaining the failure probability;
further, in step S2, the failure probability is calculated, specifically, Hotelling T2Calculating the statistic and the SPE statistic according to the normal battery training set dimension reduction process matrix;
wherein, Hotelling T2The statistics are calculated as follows:
Figure BDA0003601025150000031
in the formula, XiIs a matrix of i-module boundary features at a certain time, PkFor reducing dimension transformation matrix, the transformation matrix is composed of principal component feature vectors, and S is a training sample set
Figure BDA0003601025150000032
A diagonal matrix formed by principal component eigenvalues, wherein k is the number of principal components;
the SPE statistic is calculated as follows:
Figure BDA0003601025150000033
in the formula, XiA boundary feature matrix for i module at a certain time), PkA dimension reduction transformation matrix is adopted, I is an identity matrix, and k is the number of principal elements;
based on Hotelling T2Solving with SPE statistic according to the comprehensive index
Figure BDA0003601025150000041
The system failure rate function of the sample at the current moment can be obtained:
Figure BDA0003601025150000042
Figure BDA0003601025150000043
in the formula (I), the compound is shown in the specification,
Figure BDA0003601025150000044
δ2are respectively Hotelling T2In conjunction with the control limit of the SPE,
Figure BDA0003601025150000045
is a symmetric positive definite matrix, and integrates indexes
Figure BDA0003601025150000046
Conforming to probability distribution
Figure BDA0003601025150000047
Chi-square distribution with degree of freedom h and coefficient g, according to
Figure BDA0003601025150000048
The probability distribution function can obtain the current failure probability function
Figure BDA0003601025150000049
The failure probability h is calculated as follows:
Figure BDA00036010251500000410
Figure BDA00036010251500000411
further, in step S3, the calculation of the contribution value is different according to different dimension reduction methods, and for the linear dimension reduction method, the ratio of the module boundary feature to the low-dimensional feature exceeding the control limit is accumulated; and calculating the ratio of the decompressed low-dimensional fault dimension to different dimensions by using a nonlinear dimension reduction method.
The invention has the beneficial effects that:
1. and (3) information fusion judgment: the early warning mechanism of the invention does not perform comparison judgment aiming at a single variable, but performs judgment after information fusion and dimensionality reduction by combining with high-dimensional characteristic data of the module, thereby avoiding the influence of random error of the data of the single variable on the judgment and improving the robustness of the invention.
2. Multistage judgement, avoid the wrong report: in the invention, a multilayer judgment logic is set, the boundary parameters and the monomer core state quantity of the battery module are comprehensively evaluated, and statistical judgment is carried out in the failure rate mode, so that false alarm is avoided as much as possible, and the practical value is improved.
3. High accuracy: according to the method, data dimension reduction and fitting are performed on massive driving data of the cloud platform, retraining related to the model can be achieved based on cloud online data, and high accuracy of the method is guaranteed by combining a massive data set. .
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a work flow chart of a power battery unit thermal runaway early warning method based on cloud online data.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
S1: and carrying out boundary characteristic extraction on thermal runaway related parameter data of the battery module at a certain time interval collected by the cloud end to form a data high-dimensional matrix. The thermal runaway related parameters can comprise voltage neel coefficients of the single batteries, voltage change rates of the single batteries, differential values of voltage to temperature of the single batteries, differential values of voltage to state of charge of the single batteries, temperature change rates of the single batteries, internal short circuit internal resistance of the single batteries, voltage of the single batteries, temperature of the single batteries, state of charge of the single batteries and the like, wherein the boundary characteristics can take statistical parameters such as the maximum value, the next maximum value, the standard deviation, the extreme difference and the like of the thermal runaway related parameters.
S2: and reducing the dimension of the high-dimensional matrix through a machine learning algorithm, and extracting the low-dimensional features of the high-dimensional matrix. And calculating the current failure probability of each moment in the time period based on the low-dimensional feature matrix. And judging whether the thermal runaway risk exists currently or not according to a given failure probability threshold. The machine learning algorithm comprises a linear dimensionality reduction algorithm represented by PCA and a nonlinear deep learning dimensionality reduction algorithm represented by a self-encoder.
The low-dimensional features are set according to the required dimension reduction effect, the lowest dimension features are selected under the condition that the dimension reduction effect meets the actual requirement, for example, the low-dimensional features corresponding to information of which the ratio of the covariance matrix eigenvalue in the PCA algorithm is 90% (determined according to the actual dimension reduction requirement) is reserved; the self-encoder algorithm ensures the low-dimensional characteristics corresponding to reasonable loss functions before and after dimension reduction.
The failure probability calculation is performed by computing Hotelling's T of a low-dimensional matrix2Calculating the comprehensive index phi by the statistic and the SPE statistic and returning to the probability distribution
Figure BDA0003601025150000061
To (1) in particular Hotelling T2The calculation method of the statistic and the SPE statistic is calculated according to a normal battery training set dimension reduction process matrix, wherein Hotelling T2The statistics are calculated as follows:
Figure BDA0003601025150000062
in the formula, XiIs a matrix of i-module boundary features at a certain time, PkFor reducing dimension transformation matrix, the transformation matrix is composed of principal component feature vectors, and S is a training sample set
Figure BDA0003601025150000063
And k is the number of the pivot elements.
The pivot eigenvalue is a term known in the art, specifically, eigenvalues of a number corresponding to the matrix are selected according to dimension reduction, and the eigenvalues are selected in a descending order, and the pivot eigenvalue is a dimension reduction eigenvalue.
The SPE statistic is calculated as follows:
Figure BDA0003601025150000071
in the above formula, XiIs a matrix of i-module boundary features at a certain time, PkThe dimension reduction transformation matrix is a dimension reduction transformation matrix, I is an identity matrix, k is the number of pivot elements, and I refers to a certain moment.
Based on T2And solving SPE statistics, and obtaining a system failure rate function of the sample at the current moment according to the comprehensive index phi:
Figure BDA0003601025150000072
Figure BDA0003601025150000073
in the formula (I), the compound is shown in the specification,
Figure BDA0003601025150000074
δ2are respectively Hotelling T2In conjunction with the control limit of the SPE,
Figure BDA0003601025150000075
is a symmetrical positive definite matrix, and integrates indexes
Figure BDA0003601025150000076
Conforming to probability distribution
Figure BDA0003601025150000077
Chi-square distribution with degree of freedom h and coefficient g, according to
Figure BDA0003601025150000078
The probability distribution function can obtain the current failure probability function
Figure BDA0003601025150000079
The failure probability h is calculated as follows:
Figure BDA00036010251500000710
Figure BDA00036010251500000711
it should be noted that, the setting of the failure probability anomaly determination probability threshold is obtained by empirical judgment, and may be determined by existing data, such as the ratio of the data set to be normal.
S3: and when the thermal runaway risk is judged, calculating the contribution value of each dimension in the S1 high-dimensional matrix to the failure rate for the low-dimensional matrix proposed by the S2, and determining the battery cell corresponding to the module boundary feature with the maximum failure rate contribution. The monomer from which the dimension contributing the most is taken is marked as the high-risk monomer to be verified.
The calculation of the contribution value is different according to different dimension reduction algorithms, and the linear dimension reduction algorithm is used for performing accumulation calculation on the ratio of the boundary characteristic of the module to the low-dimensional characteristic exceeding the control limit; for the nonlinear dimensionality reduction algorithm, the occupation ratio of the decompressed low-dimensional fault dimensionality to different dimensionalities can be calculated.
S4: and analyzing the online voltage, temperature and SOC data of the battery monomer positioned in the S3, and calculating the deviation degree of the current state and the predicted state by combining a deep learning prediction model. And comparing the deviation degrees of the voltage, the temperature and the SOC of the monomer with a three-level alarm threshold value, and alarming according to the corresponding level of the deviation degrees.
The prediction model adopts a known prediction model and mainly covers the prediction of a recurrent neural network and a control equation, wherein the recurrent neural network is represented by LSTM and needs the advance training of a certain sample; the prediction of the control equation is carried out on the basis of parameter identification of a space state equation (represented by an equivalent circuit model); the two methods can also be fused to improve accuracy.
The three-level alarm threshold is preset according to different vehicle types and actual requirements.
The deep learning prediction model is used for predicting the state of a battery in the next second, the training process uses the data set of the type of the target vehicle, the data of the type of the target vehicle before the time t is used as model input, the data at the time t is used as model output, the time t is a sequence of 1 to the length of the data set, and the training set of the neural network is formed by utilizing the existing training method to finish the training of the neural network model.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.

Claims (7)

1. A power battery unit thermal runaway early warning method based on cloud online data is characterized by comprising the following steps:
s1: extracting battery module boundary characteristics of battery module data collected by a cloud terminal, and forming a high-dimensional matrix by using the battery module boundary characteristics;
s2: reducing the dimension of the high-dimensional matrix through a machine learning algorithm, extracting a low-dimensional feature matrix of the high-dimensional matrix, calculating the current failure probability of each moment in the time period based on the low-dimensional feature matrix, and comparing the current failure probability with a preset failure probability threshold value to judge whether the thermal runaway risk exists at present;
s3: when the thermal runaway risk is judged, decompressing the low-dimensional matrix in the step S2, calculating the contribution value of each dimension in the high-dimensional matrix in the step S1 to the failure probability, and determining the single battery corresponding to the boundary feature with the largest failure probability contribution as the high-risk single to be verified;
s4: analyzing the on-line voltage, temperature and SOC data of the high-risk monomer to be checked, combining a deep learning battery state prediction model which is trained in advance, calculating the deviation degree of the on-line voltage, temperature and SOC data of the high-risk monomer to be checked in the current state and the prediction state, comparing the deviation degree value of the voltage, temperature and SOC data of the high-risk monomer to be checked with a preset three-level alarm threshold value, and alarming according to the deviation degree value corresponding to three different levels.
2. The power battery cell thermal runaway early warning method based on cloud online data as claimed in claim 1, wherein in step S1, the battery module data includes parameters related to thermal runaway, specifically including a voltage neel coefficient of a cell, a voltage change rate of the cell, a cell voltage-to-temperature differential value, a cell voltage-to-state-of-charge differential value, a cell temperature change rate, an internal short circuit internal resistance of the cell, a cell voltage, a cell temperature, and a cell state-of-charge.
3. The cloud-based online data-based power battery unit thermal runaway early warning method according to claim 1 or claim 2, wherein in step S1, the extracted boundary features are the extracted maximum value, the next maximum value, the standard deviation and the extreme deviation of the thermal runaway related parameters.
4. The power battery unit thermal runaway early warning method based on cloud online data as claimed in claim 1, wherein in step S2, the machine learning algorithm comprises a linear dimensionality reduction PCA algorithm or a non-linear dimensionality reduction self-encoder algorithm.
5. The method of claim 1, wherein in step S2, the failure probability is calculated by computing Hotelling T of the low-dimensional matrix2The statistic and the SPE statistic are calculated, so that the comprehensive index is calculated
Figure FDA0003601025140000025
And regressed to a probability distribution
Figure FDA0003601025140000024
Obtaining the failure probability.
6. The power battery unit thermal runaway early warning method based on cloud online data as claimed in claim 5, wherein in step S2, the failure probability is calculated, specifically, Hotelling T2Calculating the statistic and the SPE statistic according to the normal battery training set dimension reduction process matrix;
wherein, Hotelling T2The statistics are calculated as follows:
Figure FDA0003601025140000021
in the formula, XiIs a matrix of i-module boundary features at a certain time, PkFor reducing dimension transformation matrix, the transformation matrix is composed of principal component feature vectors, and S is a training sample set
Figure FDA0003601025140000022
A diagonal matrix formed by principal component eigenvalues, wherein k is the number of principal components;
the SPE statistic is calculated as:
Figure FDA0003601025140000023
in the formula, XiA boundary feature matrix for i module at a certain time), PkIs a dimension reduction transformation matrix, I is a unit matrix, and k is the number of principal elements;
based on Hotelling T2Solving with SPE statistic according to the comprehensive index
Figure FDA0003601025140000031
The system failure rate function of the sample at the current moment can be obtained:
Figure FDA0003601025140000032
Figure FDA0003601025140000033
in the formula (I), the compound is shown in the specification,
Figure FDA0003601025140000034
δ2are respectively Hotelling T2In conjunction with the control limit of the SPE,
Figure FDA0003601025140000035
is a symmetrical positive definite matrix, and integrates indexes
Figure FDA0003601025140000036
Conforming to probability distribution
Figure FDA0003601025140000037
Chi-square distribution with degree of freedom h and coefficient g, according to
Figure FDA0003601025140000038
The probability distribution function can obtain the current failure probability function
Figure FDA0003601025140000039
The failure probability h is calculated as follows:
Figure FDA00036010251400000310
Figure FDA00036010251400000311
7. the method for early warning of thermal runaway of power battery cells based on cloud online data as claimed in claim 1, wherein in step S3, the calculation of the contribution value is different according to different dimension reduction methods, and for the linear dimension reduction method, the ratio of module boundary features to low-dimensional features exceeding control limits is cumulatively calculated; and calculating the ratio of the decompressed low-dimensional fault dimension to different dimensions by using a nonlinear dimension reduction method.
CN202210403841.1A 2022-04-18 2022-04-18 Power battery unit thermal runaway early warning method based on cloud online data Pending CN114734873A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210403841.1A CN114734873A (en) 2022-04-18 2022-04-18 Power battery unit thermal runaway early warning method based on cloud online data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210403841.1A CN114734873A (en) 2022-04-18 2022-04-18 Power battery unit thermal runaway early warning method based on cloud online data

Publications (1)

Publication Number Publication Date
CN114734873A true CN114734873A (en) 2022-07-12

Family

ID=82280896

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210403841.1A Pending CN114734873A (en) 2022-04-18 2022-04-18 Power battery unit thermal runaway early warning method based on cloud online data

Country Status (1)

Country Link
CN (1) CN114734873A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115840157A (en) * 2022-12-08 2023-03-24 斯润天朗(合肥)科技有限公司 Lithium battery electrical performance index coordination analysis system based on EOF analysis
CN116401585A (en) * 2023-04-19 2023-07-07 江苏果下科技有限公司 Energy storage battery failure risk assessment method based on big data

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115840157A (en) * 2022-12-08 2023-03-24 斯润天朗(合肥)科技有限公司 Lithium battery electrical performance index coordination analysis system based on EOF analysis
CN115840157B (en) * 2022-12-08 2023-08-22 斯润天朗(合肥)科技有限公司 Lithium battery electrical performance index coordination analysis system based on EOF analysis
CN116401585A (en) * 2023-04-19 2023-07-07 江苏果下科技有限公司 Energy storage battery failure risk assessment method based on big data
CN116401585B (en) * 2023-04-19 2023-11-10 江苏果下科技有限公司 Energy storage battery failure risk assessment method based on big data

Similar Documents

Publication Publication Date Title
CN114734873A (en) Power battery unit thermal runaway early warning method based on cloud online data
CN114559819B (en) Electric automobile battery safety early warning method based on signal processing
CN114801751B (en) Automobile battery fault prediction system based on data analysis
CN116154900B (en) Active safety three-stage prevention and control system and method for battery energy storage power station
CN112949060A (en) Lithium battery health state estimation and residual life prediction method under time-varying temperature
CN113459894A (en) Electric vehicle battery safety early warning method and system
CN115384311A (en) Method, system, vehicle and storage medium for diagnosing insulation fault of power battery
CN114839536A (en) Lithium ion battery health state estimation method based on multiple health factors
CN112363061A (en) Thermal runaway risk assessment method based on big data
CN114565008A (en) Lithium battery abnormity detection method based on long-time and short-time memory self-encoder
CN114580496A (en) Self-detection method for single fault of lithium ion battery
CN113884884B (en) Power battery pack fault diagnosis method and system based on correlation
Xu et al. Safety warning analysis for power battery packs in electric vehicles with running data
CN114545275A (en) Indirect prediction method for remaining service life of lithium ion battery
CN114646888A (en) Assessment method and system for capacity attenuation of power battery
CN114036647A (en) Power battery safety risk assessment method based on real vehicle data
CN114460481A (en) Energy storage battery thermal runaway early warning method based on Bi-LSTM and attention mechanism
CN114509678A (en) Power battery thermal runaway prediction method based on big data
CN111859710A (en) Quantitative and safe cumulative risk model modeling method
CN116973763A (en) Method and device for early warning out of control of lithium battery Bao Re
CN116796285A (en) Power battery thermal runaway advanced early warning method and system based on multi-source information fusion
CN115958957A (en) Method and system for predicting charging overheating fault of power battery of electric automobile
CN115494399A (en) Intelligent identification method for individual difference risks of new energy automobile battery system
CN113935423A (en) Power battery fault early warning method and system for coupling fuzzy control rule with Elman neural network
CN115469226A (en) Real-time safety early warning method for electric vehicle power battery based on operation big data

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