CN117951629B - Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack - Google Patents
Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack Download PDFInfo
- Publication number
- CN117951629B CN117951629B CN202410346207.8A CN202410346207A CN117951629B CN 117951629 B CN117951629 B CN 117951629B CN 202410346207 A CN202410346207 A CN 202410346207A CN 117951629 B CN117951629 B CN 117951629B
- Authority
- CN
- China
- Prior art keywords
- temperature
- battery pack
- state data
- charge
- historical
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 39
- 206010000117 Abnormal behaviour Diseases 0.000 title claims description 32
- 238000001514 detection method Methods 0.000 claims abstract description 85
- 230000006399 behavior Effects 0.000 claims abstract description 58
- 230000005856 abnormality Effects 0.000 claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000007599 discharging Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 45
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000012216 screening Methods 0.000 claims description 28
- 230000035772 mutation Effects 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000009529 body temperature measurement Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 230000000379 polymerizing effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000002035 prolonged effect Effects 0.000 abstract description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 6
- 229910052744 lithium Inorganic materials 0.000 description 6
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 4
- 229910001416 lithium ion Inorganic materials 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a detection method and a detection system for abnormal charge and discharge temperature behaviors of a battery pack, wherein the detection method comprises the following steps: acquiring historical charge and discharge data and temperature monitoring data of a target battery pack to generate historical state data, removing the historical state data with abnormal temperature, and carrying out working condition division of the target battery pack by utilizing clustering; constructing a temperature normal behavior model by using a state estimation algorithm, integrating the temperature normal behavior models under different working conditions by using federal learning, and generating a temperature anomaly detection model; and taking the current state data of the target battery pack as model input to acquire residual errors between the current state and normal behaviors, analyzing whether the current state data is in a temperature abnormal state according to the residual errors, and generating alarm information. According to the invention, a global model of the battery pack charging and discharging normal temperature behaviors is established by combining multi-working condition division and federal learning, the generalization capability and the temperature abnormality detection accuracy of the model are improved, the timely operation and maintenance of abnormal conditions are ensured through real-time alarm, and the service life of the battery pack is prolonged.
Description
Technical Field
The invention relates to the technical field of battery pack safety, in particular to a method and a system for detecting abnormal charging and discharging temperature behaviors of a battery pack.
Background
As an environment-friendly clean energy source, the lithium ion battery enters a rapid development stage and is often integrated into a battery pack in a series-parallel connection mode to provide power for large-sized equipment due to the advantages of short charging time, good cycle performance, high energy density and the like. The main reason for the thermal runaway risk of the lithium battery is that the internal temperature and the external surface temperature are highly inconsistent, and as the charge and discharge continue to progress, the temperature difference is larger and larger due to accumulation, the battery pack is damaged and cannot work normally if the battery pack is light, and explosion danger can occur if the battery pack is heavy, so that a great potential safety hazard is brought to a user.
The lithium battery can generate heat during charge and discharge, and when the temperature of the battery is too high or the temperature difference between the batteries in the battery pack is too large, the service performance and the service life of the battery can be influenced, and even the risks of fire, explosion and the like can occur. Therefore, the battery pack is effectively temperature-controlled, so that the battery can normally work in a proper temperature range, and the method has important significance for the safe use of the lithium battery. However, the traditional lithium ion battery safety detection technology is difficult to meet the requirements of on-line detection and detection precision, and the realization of the lithium ion battery safety detection technology based on machine learning meets the requirements of the two aspects. Therefore, how to detect and monitor the temperature of the lithium battery in the charging and discharging process according to the state parameters of the lithium battery, and realize abnormal classification and alarm of the lithium battery are the problems which cannot be solved yet.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for detecting abnormal charge and discharge temperature behaviors of a battery pack.
The first aspect of the present invention provides a method for detecting abnormal charge-discharge temperature behavior of a battery pack, comprising:
Acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
Acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to the temperature distribution change, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, removing the historical state data, and generating an optimized historical state data set;
Carrying out working condition division on the optimized historical state data by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions;
constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
And importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
In the scheme, the temperature distribution of the battery pack is constructed to be matched with historical charge and discharge data to generate historical state data, and the method specifically comprises the following steps:
Acquiring a three-dimensional model of a target battery pack, dividing the three-dimensional model into space grid blocks, analyzing an infrared temperature measurement value of the target battery pack in a historical charge and discharge process, preprocessing the infrared temperature measurement value, and screening temperature mutation points in time sequence;
Acquiring the environmental temperature of a monitoring time stamp corresponding to the temperature mutation point, polymerizing the temperature mutation point according to the environmental temperature to generate a temperature mutation point set under different environmental temperatures, and acquiring a space grid corresponding to each temperature mutation point in each temperature mutation point set;
Counting occurrence frequencies of the space grids under different environmental temperatures, screening a preset number of space grids based on the occurrence frequencies to serve as battery pack temperature key measuring points, and coupling the battery pack temperature key measuring points and infrared temperature measuring values in a preset neighborhood range to a three-dimensional model to serve as heat sources to generate battery pack temperature distribution;
And matching the historical charge and discharge data of the target battery pack with the battery pack temperature distribution according to the time stamp to generate historical state data.
In the scheme, historical state data of temperature abnormality is screened according to an abnormality detection rule set according to influence factors to be removed, and the method specifically comprises the following steps:
Acquiring a temperature change curve of a target battery pack at different environmental temperatures according to historical state data, extracting temperature time sequence change characteristics according to the temperature change curve, and acquiring thermal characteristics of the target battery pack according to the temperature time sequence change characteristics;
Obtaining impact factors corresponding to battery temperature rise by utilizing big data retrieval, obtaining thermal characteristic analysis examples under different impact factors according to specification parameters of a target battery pack, grouping the thermal characteristic analysis examples according to different environment temperatures, and calculating similarity by utilizing the thermal characteristics of the target battery pack under different groupings;
Screening influence factors meeting a preset similarity standard, calculating weight information of each influence factor by utilizing a Relief-F algorithm, sorting by utilizing the weight information, and selecting a preset number of influence factors to obtain the influence factors of the thermal characteristics of the target battery pack;
Setting an evaluation index according to the influence factors, searching index parameters in the historical state data, clustering according to the index parameters to obtain outliers, setting an evaluation index threshold value based on the outliers, generating an abnormality detection rule, screening historical state data of temperature abnormality according to the abnormality detection rule, and eliminating.
In this scheme, utilize the cluster to carry out the operating mode division of target group battery to history state data after optimizing, specifically do:
The optimized historical state data is obtained and clustered by using a clustering algorithm, the clustering number is optimized by using a genetic algorithm, the optimal clustering number is generated, a clustering center is initialized, and membership is obtained according to Euclidean distance between a state data sample and the clustering center;
Presetting a level membership threshold, and when the membership is larger than a high level membership threshold, attributing the data sample to a nearest cluster center according to the membership to generate a cluster, and updating the cluster center through iterative clustering;
When the membership is smaller than the high-level membership threshold, screening cluster centers larger than the low-level membership threshold according to the membership, respectively attributing the data samples to the screened cluster centers to generate cluster clusters, and updating the cluster centers;
and obtaining the final clustering result to generate working condition division of the target battery pack, and obtaining a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions.
In the scheme, a temperature normal behavior model is built, and the temperature normal behavior models under different working conditions are integrated by utilizing federal learning to generate a temperature anomaly detection model, which is specifically as follows:
Respectively constructing a temperature normal behavior model according to historical state data subsets of different working conditions by using a state estimation algorithm, constructing a training set according to the historical state data subsets, and constructing a window function through a Markov distance;
traversing the training set by utilizing the window function, calculating the similarity between input data and training samples, sequencing the training samples according to the similarity, and selecting a preset number of training samples from large to small to construct a memory matrix to store the normal temperature running state of the charge and discharge of the target battery pack;
Taking the temperature normal behavior models corresponding to different working conditions as local models, adding historical state data corresponding to temperature abnormal behaviors in the training set as a verification set, training by utilizing federal learning based on the training set and the verification set, and calculating average detection errors of each local model;
Scoring the local model according to the average detection error to generate a confidence coefficient, screening the local model which is larger than the average detection error corresponding to the global temperature anomaly detection model, and setting the score of the screened local model to be zero;
Uploading and compressing the local models with scores not zero according to the confidence, aggregating each local model, updating parameters of the temperature anomaly detection model, obtaining optimal model parameters after iteration, and outputting the temperature anomaly detection model.
In this scheme, obtain the residual error between current state and the normal action, whether be the temperature abnormal condition according to residual error analysis, specifically do:
Acquiring charge and discharge data of a current time stamp of a target battery pack and battery pack temperature distribution to generate current state data, and generating an input matrix according to the current state data serving as an input data importing degree abnormality detection model;
Selecting a training sample according to the input matrix to construct a memory matrix, calculating an estimated matrix of current state data in a normal temperature running state through the memory matrix, and obtaining residual errors of the input matrix and the estimated matrix;
Acquiring the relative entropy of the residual error to judge the deviation degree of the current state data and the normal temperature running state of the target battery pack, taking the deviation degree as an abnormality judgment score, and presetting a score threshold value to judge whether the target battery pack is abnormal;
And if the temperature abnormality behavior of the target battery pack occurs, generating alarm information of different grades according to the abnormality judgment score, and transmitting and displaying in a preset mode.
The second aspect of the present invention also provides a system for detecting abnormal behavior of charge and discharge temperature of a battery pack, the system comprising: the battery pack charge-discharge temperature abnormal behavior detection method comprises a memory and a processor, wherein the memory comprises a battery pack charge-discharge temperature abnormal behavior detection method program, and when the battery pack charge-discharge temperature abnormal behavior detection method program is executed by the processor, the following steps are realized:
Acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
Acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to the temperature distribution change, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, removing the historical state data, and generating an optimized historical state data set;
Carrying out working condition division on the optimized historical state data by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions;
constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
And importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
The invention discloses a detection method and a detection system for abnormal charge and discharge temperature behaviors of a battery pack, wherein the detection method comprises the following steps: acquiring historical charge and discharge data and temperature monitoring data of a target battery pack to generate historical state data, removing the historical state data with abnormal temperature, and carrying out working condition division of the target battery pack by utilizing clustering; constructing a temperature normal behavior model by using a state estimation algorithm, integrating the temperature normal behavior models under different working conditions by using federal learning, and generating a temperature anomaly detection model; and taking the current state data of the target battery pack as model input to acquire residual errors between the current state and normal behaviors, analyzing whether the current state data is in a temperature abnormal state according to the residual errors, and generating alarm information. According to the invention, a global model of the battery pack charging and discharging normal temperature behaviors is established by combining multi-working condition division and federal learning, the generalization capability and the temperature abnormality detection accuracy of the model are improved, the timely operation and maintenance of abnormal conditions are ensured through real-time alarm, and the service life of the battery pack is prolonged.
Drawings
FIG. 1 is a flow chart showing a method for detecting abnormal charge-discharge temperature behavior of a battery pack according to the present invention;
FIG. 2 is a flow chart illustrating the filtering of historical state data for temperature anomalies in accordance with the present invention;
FIG. 3 shows a flow chart of the present invention for generating a temperature anomaly detection model;
fig. 4 is a block diagram showing a detection system of abnormal behavior of charge and discharge temperature of a battery pack according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 is a flowchart showing a method for detecting abnormal charge-discharge temperature behavior of a battery pack according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a method for detecting abnormal charge-discharge temperature behavior of a battery pack, including:
S102, acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
S104, acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to temperature distribution changes, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, eliminating the historical state data, and generating an optimized historical state data set;
S106, carrying out working condition division on the optimized historical state data by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions;
S108, constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
s110, importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
It should be noted that the characteristics of the lithium ion battery are mainly described by the characteristic parameters of the battery itself, and overcharge, overdischarge, and excessive temperature of the battery easily cause thermal runaway of the battery. The accuracy and the robustness of the battery pack state monitoring are critical, the battery management system is required to accurately acquire signals, parameters such as charge and discharge current, terminal voltage and internal resistance of the battery pack are acquired according to a preset sensor in the battery management system, the battery pack voltage and temperature information are acquired in real time through an infrared array temperature sensor and a related conversion circuit thereof, and timeliness and accuracy of information acquisition are required to be ensured.
Acquiring a three-dimensional model of a target battery pack, dividing the three-dimensional model into space grid blocks, analyzing an infrared temperature measurement value of the target battery pack in a historical charge and discharge process, preprocessing the infrared temperature measurement value, and screening temperature mutation points in time sequence; acquiring the environmental temperature of a monitoring time stamp corresponding to the temperature mutation point, polymerizing the temperature mutation point according to the environmental temperature to generate a temperature mutation point set under different environmental temperatures, and acquiring a space grid corresponding to each temperature mutation point in each temperature mutation point set; counting occurrence frequencies of the space grids under different environmental temperatures, screening a preset number of space grids based on the occurrence frequencies to serve as battery pack temperature key measuring points, and coupling the battery pack temperature key measuring points and infrared temperature measuring values in a preset neighborhood range to a three-dimensional model to serve as heat sources to generate battery pack temperature distribution; and matching the historical charge and discharge data of the target battery pack with the battery pack temperature distribution according to the time stamp to generate historical state data.
Because the effective SOC and the cycle life of the battery pack can be attenuated in the use process to change battery characteristic parameters, external environment and working conditions can influence the battery characteristic parameters, temperature low-frequency monitoring is constructed on the space grids except the space grids corresponding to the temperature mutation points, k neighbor sampling is conducted on the low-frequency temperature monitoring value set by using a KNN algorithm based on temperature measurement values of the temperature mutation points, a target temperature mutation point is selected, the distance between each temperature measurement value data in the low-frequency temperature monitoring value set and the temperature measurement value of the target temperature mutation point is calculated according to a distance measurement function, a distance vector is obtained, and when the distance vector is smaller than a preset distance threshold, the space grid corresponding to the temperature measurement value data is used as a new temperature mutation point.
FIG. 2 shows a flow chart of the present invention for filtering historical state data for temperature anomalies.
According to the embodiment of the invention, historical state data of temperature abnormality is screened out according to an abnormality detection rule set according to influence factors, and the method specifically comprises the following steps:
s202, acquiring a temperature change curve of a target battery pack at different environmental temperatures according to historical state data, extracting temperature time sequence change characteristics according to the temperature change curve, and acquiring thermal characteristics of the target battery pack through the temperature time sequence change characteristics;
S204, acquiring impact factors corresponding to battery temperature rise by utilizing big data retrieval, acquiring thermal characteristic analysis examples under different impact factors according to specification parameters of a target battery pack, grouping the thermal characteristic analysis examples according to different environment temperatures, and calculating similarity by utilizing the thermal characteristics of the target battery pack under different groupings;
S206, screening influence factors meeting preset similarity standards, calculating weight information of each influence factor by utilizing a Relief-F algorithm, sorting by utilizing the weight information, and selecting a preset number of influence factors to obtain influence factors of the thermal characteristics of the target battery pack;
And S208, setting an evaluation index according to the influence factors, searching index parameters in the historical state data, clustering according to the index parameters to obtain outliers, setting an evaluation index threshold value based on the outliers, generating an abnormality detection rule, and screening historical state data of temperature abnormality according to the abnormality detection rule to eliminate.
It should be noted that, the thermal characteristics of the battery pack may include charge-discharge rate, ambient temperature, state of charge, and heat exchange coefficient, for example, the higher the battery discharge rate, the larger the heat exchange coefficient, and the larger the battery temperature and temperature difference. According to example comparison and similarity calculation, obtaining an influence factor with high response degree to the thermal characteristics of a target battery pack, determining battery performance parameters and environment parameters as preliminary screening indexes by using the influence factor, calculating weight information of the preliminary screening indexes by using a Relief-F algorithm to realize final selection of evaluation indexes, selecting characteristics by using the Relief-F algorithm based on distinguishing capability of the characteristics to close range samples, firstly selecting samples from a training set, then searching for n nearest similar samples and n nearest different types of samples from samples similar to the samples, and when the distance between the selected similar samples and the selected different types of samples on a certain characteristic is smaller than the distance between the similar samples and the selected different types of samples, proving that the characteristics are beneficial to distinguishing nearest neighbors of the similar samples and the different types, increasing weights of the characteristics, and obtaining average weights of the characteristics by repeated iteration.
The method comprises the steps of obtaining optimized historical state data, clustering by using a clustering algorithm, optimizing the clustering cluster number by using a genetic algorithm, initializing a population, taking a profile coefficient as a fitness function, generating the optimal clustering cluster number by selecting, crossing and mutating, initializing a clustering center, and obtaining membership according to Euclidean distance between a state data sample and the clustering center; the factors such as the charging parameters of the battery pack are closely related, and the related operating parameters are mostly continuous along with time, if the state data are divided into different working conditions, the transition data between the different working conditions cannot be classified, so that the hierarchical membership threshold is set, the transition data between the different working conditions are distributed to the adjacent working conditions, the actual condition of the battery pack is met, and the classification accuracy is improved. Presetting a level membership threshold, and when the membership is larger than a high level membership threshold, attributing the data sample to a nearest cluster center according to the membership to generate a cluster, and updating the cluster center through iterative clustering; when the membership is smaller than the high-level membership threshold, screening cluster centers larger than the low-level membership threshold according to the membership, respectively attributing the data samples to the screened cluster centers to generate cluster clusters, and updating the cluster centers; and obtaining the final clustering result to generate working condition division of the target battery pack, and obtaining a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions.
FIG. 3 shows a flow chart of the present invention for generating a temperature anomaly detection model.
According to the embodiment of the invention, a temperature normal behavior model is constructed, and the temperature normal behavior models under different working conditions are integrated by utilizing federal learning to generate a temperature anomaly detection model, which is specifically as follows:
S302, respectively constructing a normal temperature behavior model according to historical state data subsets of different working conditions by using a state estimation algorithm, constructing a training set according to the historical state data subsets, and constructing a window function through a Markov distance;
S304, traversing the training set by utilizing the window function, calculating the similarity between input data and training samples, sequencing the training samples according to the similarity, and selecting a preset number of training samples from large to small to construct a memory matrix to store the normal running state of the temperature of the charge and discharge of the target battery pack;
S306, taking the temperature normal behavior models corresponding to different working conditions as local models, adding historical state data corresponding to temperature abnormal behaviors in the training set as a verification set, training by utilizing federal learning based on the training set and the verification set, and calculating average detection errors of each local model;
S308, scoring the local model according to the average detection error to generate a confidence coefficient, screening the local model which is larger than the average detection error corresponding to the global temperature anomaly detection model, and setting the score of the screened local model to be zero;
And S310, uploading and compressing the local models with scores which are not zero according to the confidence, aggregating each local model, updating parameters of the temperature anomaly detection model, obtaining optimal model parameters after iteration, and outputting the temperature anomaly detection model.
It should be noted that, the core of the state estimation algorithm is a memory matrix composed of normal operation data, for example, a nonlinear state estimation technique, etc. In the embodiment, a window function is constructed through a mahalanobis distance; and utilizing the window function to carry out sliding window traversal training set, calculating the similarity between input data and training samples, realizing dynamic selection of the training samples, and preferably, setting sampling intervals to ensure the uniformity of data sampling and accord with actual distribution when the training samples are selected based on similarity sorting. The dynamic selection and construction of the memory matrix improves the utilization rate of training samples, avoids the construction of the memory matrix by using all training samples or single-working-condition similar samples, reduces estimation errors and calculated amount, and improves the detection precision of temperature abnormal behaviors. The integrated learning of the local model is realized through federal learning, the superior precision and generalization capability are obtained, the local model is dynamically selected and uploaded in federal learning, the unsatisfactory local model with zero score is restrained, the aggregation speed of the model is optimized, the parameter updating of the global temperature anomaly detection model is distributed to the unsatisfactory local model again for iterative training, and after the multi-round uploading and the issuing are completed, the model convergence is trained, and the construction of the temperature anomaly detection model is completed.
Judging whether similar samples with the similarity larger than a preset threshold exist in the training set and the verification set according to the detection result of the temperature anomaly detection model, when the similar samples do not exist, performing parameter increment and updating according to the anomaly grade degree, deleting redundant data which are repeated with new data, adjusting and updating parameters of the model by using the new data, discarding or backing up the new data, and not occupying extra storage space.
The charge and discharge data of the current time stamp of the target battery pack and the battery pack temperature distribution are acquired to generate current state data, and an input matrix is generated according to the current state data serving as an input data importation degree abnormality detection model，/>，/>The state data at the current t moment; training samples are selected according to the input matrix to construct a memory matrix/>，/> ，/>The temperature normal operation state data are obtained, and m is the total number of samples; calculating an estimated matrix/>, under the normal temperature running state, of the current state data through the memory matrixThe calculation of the estimation matrix is as follows: /(I)，/>Is a nonlinear operator; acquiring relative entropy of residual errors of the input matrix and the estimation matrix to judge the deviation degree of the current state data and the normal temperature running state of the target battery pack, taking the deviation degree as an abnormality judgment score, and presetting a score threshold value to judge whether the target battery pack is abnormal; and if the temperature abnormality behavior of the target battery pack occurs, generating alarm information of different grades according to the abnormality judgment score, and transmitting and displaying in a preset mode.
Fig. 4 is a block diagram showing a detection system of abnormal behavior of charge and discharge temperature of a battery pack according to the present invention.
The second aspect of the present invention also provides a detection system 4 for abnormal behavior of charge and discharge temperature of a battery pack, the system comprising: the memory 41 and the processor 42, the memory includes a method program for detecting abnormal behavior of the charge and discharge temperature of the battery, and the method program for detecting abnormal behavior of the charge and discharge temperature of the battery realizes the following steps when executed by the processor:
Acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
Acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to the temperature distribution change, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, removing the historical state data, and generating an optimized historical state data set;
Carrying out working condition division on the optimized historical state data by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions;
constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
And importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
The third aspect of the present invention also provides a computer-readable storage medium, in which a method program for detecting abnormal behavior of charge and discharge temperatures of a battery pack is included, which when executed by a processor, implements the steps of the method for detecting abnormal behavior of charge and discharge temperatures of a battery pack as described in any one of the above.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The method for detecting the abnormal behavior of the charge and discharge temperature of the battery pack is characterized by comprising the following steps of:
Acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
Acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to the temperature distribution change, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, removing the historical state data, and generating an optimized historical state data set;
Carrying out working condition division on the optimized historical state data set by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery set under different working conditions;
constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
And importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
2. The method for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 1, wherein the step of constructing a battery pack temperature distribution to match with historical charge and discharge data to generate historical state data comprises the following steps:
Acquiring a three-dimensional model of a target battery pack, dividing the three-dimensional model into space grid blocks, analyzing an infrared temperature measurement value of the target battery pack in a historical charge and discharge process, preprocessing the infrared temperature measurement value, and screening temperature mutation points in time sequence;
Acquiring the environmental temperature of a monitoring time stamp corresponding to the temperature mutation point, polymerizing the temperature mutation point according to the environmental temperature to generate a temperature mutation point set under different environmental temperatures, and acquiring a space grid corresponding to each temperature mutation point in each temperature mutation point set;
Counting occurrence frequencies of the space grids under different environmental temperatures, screening a preset number of space grids based on the occurrence frequencies to serve as battery pack temperature key measuring points, and coupling the battery pack temperature key measuring points and infrared temperature measuring values in a preset neighborhood range to a three-dimensional model to serve as heat sources to generate battery pack temperature distribution;
And matching the historical charge and discharge data of the target battery pack with the battery pack temperature distribution according to the time stamp to generate historical state data.
3. The method for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 1, wherein the method for detecting abnormal behavior of charge and discharge temperature of a battery pack is characterized in that historical state data of abnormal temperature is filtered according to an influence factor setting abnormality detection rule to be removed, specifically:
Acquiring a temperature change curve of a target battery pack at different environmental temperatures according to historical state data, extracting temperature time sequence change characteristics according to the temperature change curve, and acquiring thermal characteristics of the target battery pack according to the temperature time sequence change characteristics;
Obtaining impact factors corresponding to battery temperature rise by utilizing big data retrieval, obtaining thermal characteristic analysis examples under different impact factors according to specification parameters of a target battery pack, grouping the thermal characteristic analysis examples according to different environment temperatures, and calculating similarity by utilizing the thermal characteristics of the target battery pack under different groupings;
Screening influence factors meeting a preset similarity standard, calculating weight information of each influence factor by utilizing a Relief-F algorithm, sorting by utilizing the weight information, and selecting a preset number of influence factors to obtain the influence factors of the thermal characteristics of the target battery pack;
Setting an evaluation index according to the influence factors, searching index parameters in the historical state data, clustering according to the index parameters to obtain outliers, setting an evaluation index threshold value based on the outliers, generating an abnormality detection rule, screening historical state data of temperature abnormality according to the abnormality detection rule, and eliminating.
4. The method for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 1, wherein the working condition of the target battery pack is divided by clustering the optimized historical state data set, specifically:
The method comprises the steps of obtaining an optimized historical state data set, carrying out clustering by using a clustering algorithm, optimizing the clustering cluster number by using a genetic algorithm, generating an optimal clustering cluster number, initializing a clustering center, and obtaining membership according to Euclidean distance between a state data sample and the clustering center;
Presetting a level membership threshold, and when the membership is larger than a high level membership threshold, attributing the data sample to a nearest cluster center according to the membership to generate a cluster, and updating the cluster center through iterative clustering;
When the membership is smaller than the high-level membership threshold, screening cluster centers larger than the low-level membership threshold according to the membership, respectively attributing the data samples to the screened cluster centers to generate cluster clusters, and updating the cluster centers;
and obtaining the final clustering result to generate working condition division of the target battery pack, and obtaining a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions.
5. The method for detecting abnormal charge and discharge temperature behavior of a battery pack according to claim 1, wherein a normal temperature behavior model is constructed, and the normal temperature behavior models under different working conditions are integrated by federal learning to generate a abnormal temperature detection model, specifically:
Respectively constructing a temperature normal behavior model according to historical state data subsets of different working conditions by using a state estimation algorithm, constructing a training set according to the historical state data subsets, and constructing a window function through a Markov distance;
traversing the training set by utilizing the window function, calculating the similarity between input data and training samples, sequencing the training samples according to the similarity, and selecting a preset number of training samples from large to small to construct a memory matrix to store the normal temperature running state of the charge and discharge of the target battery pack;
Taking the temperature normal behavior models corresponding to different working conditions as local models, adding historical state data corresponding to temperature abnormal behaviors in the training set as a verification set, training by utilizing federal learning based on the training set and the verification set, and calculating average detection errors of each local model;
Scoring the local model according to the average detection error to generate a confidence coefficient, screening the local model which is larger than the average detection error corresponding to the global temperature anomaly detection model, and setting the score of the screened local model to be zero;
Uploading and compressing the local models with scores not zero according to the confidence, aggregating each local model, updating parameters of the temperature anomaly detection model, obtaining optimal model parameters after iteration, and outputting the temperature anomaly detection model.
6. The method for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 1, wherein a residual error between a current state and normal behavior is obtained, and whether the abnormal behavior is a temperature abnormal state is analyzed according to the residual error, specifically:
Acquiring charge and discharge data of a current time stamp of a target battery pack and battery pack temperature distribution to generate current state data, and importing the current state data serving as input data into a temperature anomaly detection model to generate an input matrix;
Selecting a training sample according to the input matrix to construct a memory matrix, calculating an estimated matrix of current state data in a normal temperature running state through the memory matrix, and obtaining residual errors of the input matrix and the estimated matrix;
Acquiring the relative entropy of the residual error to judge the deviation degree of the current state data and the normal temperature running state of the target battery pack, taking the deviation degree as an abnormality judgment score, and presetting a score threshold value to judge whether the target battery pack is abnormal;
And if the temperature abnormality behavior of the target battery pack occurs, generating alarm information of different grades according to the abnormality judgment score, and transmitting and displaying in a preset mode.
7. A system for detecting abnormal charge-discharge temperature behavior of a battery pack, the system comprising: the battery pack charge-discharge temperature abnormal behavior detection method comprises a memory and a processor, wherein the memory comprises a battery pack charge-discharge temperature abnormal behavior detection method program, and when the battery pack charge-discharge temperature abnormal behavior detection method program is executed by the processor, the following steps are realized:
Acquiring historical charge and discharge data and temperature monitoring data of a target battery pack, and constructing battery pack temperature distribution and historical charge and discharge data matching to generate historical state data;
Acquiring thermal characteristics of the target battery pack in the charging and discharging processes according to the temperature distribution change, analyzing influence factors, setting abnormality detection rules according to the influence factors, screening historical state data of temperature abnormality, removing the historical state data, and generating an optimized historical state data set;
Carrying out working condition division on the optimized historical state data set by utilizing clustering to obtain a historical state data subset which normally corresponds to the temperature of the target battery set under different working conditions;
constructing a temperature normal behavior model by using a state estimation algorithm according to the historical state data subsets corresponding to different working conditions, integrating the temperature normal behavior models of different working conditions by using federal learning, and generating a temperature anomaly detection model;
And importing the current state data of the target battery pack into the temperature anomaly detection model, acquiring residual errors between the current state and normal behaviors, analyzing whether the residual errors are temperature anomaly conditions according to the residual errors, and judging whether to generate alarm information based on analysis results.
8. The system for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 7, wherein the working condition of the target battery pack is divided by clustering the optimized historical state data set, specifically:
The method comprises the steps of obtaining an optimized historical state data set, carrying out clustering by using a clustering algorithm, optimizing the clustering cluster number by using a genetic algorithm, generating an optimal clustering cluster number, initializing a clustering center, and obtaining membership according to Euclidean distance between a state data sample and the clustering center;
Presetting a level membership threshold, and when the membership is larger than a high level membership threshold, attributing the data sample to a nearest cluster center according to the membership to generate a cluster, and updating the cluster center through iterative clustering;
When the membership is smaller than the high-level membership threshold, screening cluster centers larger than the low-level membership threshold according to the membership, respectively attributing the data samples to the screened cluster centers to generate cluster clusters, and updating the cluster centers;
and obtaining the final clustering result to generate working condition division of the target battery pack, and obtaining a historical state data subset which normally corresponds to the temperature of the target battery pack under different working conditions.
9. The system for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 7, wherein a normal behavior model of temperature is constructed, and the normal behavior models of temperature under different working conditions are integrated by federal learning to generate a abnormal temperature detection model, specifically:
Respectively constructing a temperature normal behavior model according to historical state data subsets of different working conditions by using a state estimation algorithm, constructing a training set according to the historical state data subsets, and constructing a window function through a Markov distance;
traversing the training set by utilizing the window function, calculating the similarity between input data and training samples, sequencing the training samples according to the similarity, and selecting a preset number of training samples from large to small to construct a memory matrix to store the normal temperature running state of the charge and discharge of the target battery pack;
Taking the temperature normal behavior models corresponding to different working conditions as local models, adding historical state data corresponding to temperature abnormal behaviors in the training set as a verification set, training by utilizing federal learning based on the training set and the verification set, and calculating average detection errors of each local model;
Scoring the local model according to the average detection error to generate a confidence coefficient, screening the local model which is larger than the average detection error corresponding to the global temperature anomaly detection model, and setting the score of the screened local model to be zero;
Uploading and compressing the local models with scores not zero according to the confidence, aggregating each local model, updating parameters of the temperature anomaly detection model, obtaining optimal model parameters after iteration, and outputting the temperature anomaly detection model.
10. The system for detecting abnormal behavior of charge and discharge temperature of a battery pack according to claim 7, wherein a residual error between a current state and normal behavior is obtained, and whether the abnormal behavior is a temperature abnormal state is analyzed according to the residual error, specifically:
Acquiring charge and discharge data of a current time stamp of a target battery pack and battery pack temperature distribution to generate current state data, and importing the current state data serving as input data into a temperature anomaly detection model to generate an input matrix;
Selecting a training sample according to the input matrix to construct a memory matrix, calculating an estimated matrix of current state data in a normal temperature running state through the memory matrix, and obtaining residual errors of the input matrix and the estimated matrix;
Acquiring the relative entropy of the residual error to judge the deviation degree of the current state data and the normal temperature running state of the target battery pack, taking the deviation degree as an abnormality judgment score, and presetting a score threshold value to judge whether the target battery pack is abnormal;
And if the temperature abnormality behavior of the target battery pack occurs, generating alarm information of different grades according to the abnormality judgment score, and transmitting and displaying in a preset mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410346207.8A CN117951629B (en) | 2024-03-26 | 2024-03-26 | Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410346207.8A CN117951629B (en) | 2024-03-26 | 2024-03-26 | Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117951629A CN117951629A (en) | 2024-04-30 |
| CN117951629B true CN117951629B (en) | 2024-06-11 |
Family
ID=90803282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410346207.8A Active CN117951629B (en) | 2024-03-26 | 2024-03-26 | Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117951629B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118551325B (en) * | 2024-07-19 | 2024-10-01 | 烟台海博电气设备有限公司 | Battery pack consistency anomaly detection method and system based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002021662A2 (en) * | 2000-09-04 | 2002-03-14 | Invensys Energy Systems (Nz) Limited | Battery monitoring network |
| CN111483343A (en) * | 2020-05-11 | 2020-08-04 | 王永宽 | Intelligent and safe charging system for new energy automobile |
| CN116804706A (en) * | 2023-06-06 | 2023-09-26 | 淮阴工学院 | Temperature prediction method and device for lithium battery of electric automobile |
| CN117235655A (en) * | 2023-11-15 | 2023-12-15 | 北明天时能源科技(北京)有限公司 | Intelligent heat supply abnormal condition identification method and system based on federal learning |
| CN117607691A (en) * | 2023-10-09 | 2024-02-27 | 广东恒翼能科技股份有限公司 | Tracking detection method and device for charging working temperature of lithium ion battery |
-
2024
- 2024-03-26 CN CN202410346207.8A patent/CN117951629B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002021662A2 (en) * | 2000-09-04 | 2002-03-14 | Invensys Energy Systems (Nz) Limited | Battery monitoring network |
| CN111483343A (en) * | 2020-05-11 | 2020-08-04 | 王永宽 | Intelligent and safe charging system for new energy automobile |
| CN116804706A (en) * | 2023-06-06 | 2023-09-26 | 淮阴工学院 | Temperature prediction method and device for lithium battery of electric automobile |
| CN117607691A (en) * | 2023-10-09 | 2024-02-27 | 广东恒翼能科技股份有限公司 | Tracking detection method and device for charging working temperature of lithium ion battery |
| CN117235655A (en) * | 2023-11-15 | 2023-12-15 | 北明天时能源科技(北京)有限公司 | Intelligent heat supply abnormal condition identification method and system based on federal learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117951629A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116775408B (en) | Intelligent monitoring method for operation state of energy storage equipment | |
| CN117951629B (en) | Method and system for detecting abnormal behavior of charge and discharge temperature of battery pack | |
| CN111614491B (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
| CN109375116B (en) | Battery system abnormal battery identification method based on self-encoder | |
| CN113343633A (en) | Thermal runaway fault classification and risk prediction method and system for power lithium battery | |
| CN109604186A (en) | Power battery performance flexibility assesses method for separating | |
| CN116990692B (en) | Lithium battery health condition assessment and residual life prediction method and system | |
| CN107330474A (en) | A kind of lithium battery cascade utilization screening method | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| CN116933666B (en) | Thermal management optimization method, system and medium for container energy storage system | |
| CN116956639B (en) | High-heat-dissipation storage battery assessment method and system based on data analysis | |
| CN117494072B (en) | Method and system for monitoring operation state of battery-changing cabinet based on data fusion | |
| CN115366683A (en) | Fault diagnosis strategy for new energy automobile power battery multi-dimensional model fusion | |
| CN108960321A (en) | A kind of large size lithium battery energy storage battery power station battery failures prediction technique | |
| WO2023124220A1 (en) | Vehicle detection method and device | |
| CN114487856A (en) | Thermal runaway early warning method and system for battery replacement station | |
| CN114578251A (en) | Battery module safety state evaluation method and device based on convolutional neural network | |
| CN116737510A (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN116061690A (en) | Safety early warning method and device in electric automobile charging process | |
| Zhu et al. | A novel fast estimation and regroup method of retired lithium‐ion battery cells | |
| CN114460481A (en) | Energy storage battery thermal runaway early warning method based on Bi-LSTM and attention mechanism | |
| Ma et al. | A novel health index for battery RUL degradation modeling and prognostics | |
| CN113253125A (en) | Information fusion-based lithium iron phosphate battery thermal runaway monitoring method and system | |
| CN116901707A (en) | Power battery pack fault early warning method, system and vehicle | |
| CN116720650A (en) | Battery life cycle management method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |