Movatterモバイル変換


[0]ホーム

URL:


CN119024168A - A new energy vehicle battery fault detection method - Google Patents

A new energy vehicle battery fault detection method
Download PDF

Info

Publication number
CN119024168A
CN119024168ACN202411134434.0ACN202411134434ACN119024168ACN 119024168 ACN119024168 ACN 119024168ACN 202411134434 ACN202411134434 ACN 202411134434ACN 119024168 ACN119024168 ACN 119024168A
Authority
CN
China
Prior art keywords
battery
data
model
fault
new energy
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
CN202411134434.0A
Other languages
Chinese (zh)
Inventor
王龙杰
席林
赵陈磊
程超
张浩翔
易小兰
刘勇
金礼芬
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.)
Sichuan Geely University
Original Assignee
Sichuan Geely 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 Sichuan Geely UniversityfiledCriticalSichuan Geely University
Priority to CN202411134434.0ApriorityCriticalpatent/CN119024168A/en
Publication of CN119024168ApublicationCriticalpatent/CN119024168A/en
Pendinglegal-statusCriticalCurrent

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明公开了一种新能源汽车电池故障检测方法,属于新能源电池检测技术领域,本发明中,通过将传统的电池检测步骤与机器学习算法相结合,显著提高了故障检测的效率和准确性。在步骤S7中,利用随机森林等机器学习算法对电池充放电性能数据进行深入分析,能够快速识别出电池单体的异常行为和潜在的故障模式。与传统的仅依靠人工经验判断相比,机器学习模型能够处理大量的数据,并从中学习到复杂的模式和关系,从而更加准确地预测电池故障。这种结合方式不仅减少了人为误差,还能够在故障初期就及时发现并预警,从而避免更严重的损害和潜在的安全事故。

The present invention discloses a method for detecting battery faults in new energy vehicles, and belongs to the technical field of new energy battery detection. In the present invention, by combining the traditional battery detection steps with machine learning algorithms, the efficiency and accuracy of fault detection are significantly improved. In step S7, the battery charging and discharging performance data is deeply analyzed using machine learning algorithms such as random forests, which can quickly identify abnormal behaviors and potential failure modes of battery cells. Compared with the traditional judgment based solely on manual experience, the machine learning model can process large amounts of data and learn complex patterns and relationships from them, thereby more accurately predicting battery failures. This combination not only reduces human errors, but also can detect and warn in time at the early stages of a fault, thereby avoiding more serious damage and potential safety accidents.

Description

New energy automobile battery fault detection method
Technical Field
The invention belongs to the technical field of new energy battery detection, and particularly relates to a new energy automobile battery fault detection method.
Background
The new energy automobile battery is a core component of the new energy automobile, and the performance of the new energy automobile battery is directly related to the endurance mileage, the safety and the service life of the automobile. The new energy automobile battery mainly adopts the lithium ion battery technology and has the following characteristics: high energy density: the energy stored in the unit volume or the weight of the battery is higher, and longer-range cruising ability is provided for new energy automobiles. Long cycle life: the charge and discharge cycle times of the lithium ion battery can reach thousands of times, and the service life of the battery is ensured. The charging efficiency is high: the battery charging speed is high, and part of vehicle types can be charged to more than 80% of electric quantity in half an hour. Environmental protection and energy saving: the new energy automobile battery has no pollution and accords with the green trip concept. The new energy automobile battery fault detection is an important means for guaranteeing battery performance and safety, and mainly comprises the following contents: and (3) voltage detection: and judging whether the battery has faults such as overcharge, overdischarge and the like by detecting the voltage of the battery monomer. And (3) temperature detection: the temperature of the battery is monitored in real time, prevent the battery from overheating and ensure the use safety. Internal resistance detection: the aging degree and performance state of the battery are evaluated by measuring the internal resistance of the battery. Insulation detection: and detecting the insulating property of the battery and preventing electric leakage accidents. Fault diagnosis and analysis: and an advanced diagnosis algorithm is adopted to rapidly locate and classify the battery faults.
However, the conventional method often depends on experience and expertise of technicians, and may have subjectivity in judging battery faults, and cannot process a large amount of data for analysis, and meanwhile, maintenance may be performed after the faults occur, which results in higher maintenance cost and may cause rapid degradation of battery performance.
Disclosure of Invention
The invention aims at: in order to solve the problems, a new energy automobile battery fault detection method is provided.
The technical scheme adopted by the invention is as follows: the new energy automobile battery fault detection method comprises the following steps:
s1: firstly, preparing a battery detection, namely preparing a universal meter, a battery internal resistance tester, a thermal infrared imager, an insulation resistance tester, a battery charge-discharge tester, a BMS diagnostic instrument tool and equipment;
S2: performing appearance inspection of the battery to ensure that the battery is free from damage, deformation and corrosion;
s3: after the connection between the battery pack and the vehicle is disconnected, detecting the voltage of the battery cell;
s4: detecting the internal resistance of the battery by a battery internal resistance tester;
S5: detecting the temperature of the battery by using a thermal infrared imager;
S6: detecting insulation resistance by using an insulation resistance tester;
S7: detecting the charge and discharge performance of the battery, combining the battery charge and discharge performance with a random forest machine learning algorithm, analyzing a model prediction result, determining whether the battery has faults and the type of the faults, and performing corresponding maintenance or replacement treatment according to the fault type indicated by the model;
S8: battery management system data is read using a BMS diagnostic instrument. And checking the working state of the BMS system to ensure that all parameters are normal. Analyzing a BMS system fault code and searching potential fault reasons;
S9: and (3) carrying out equalizing charge, maintenance or replacement on the faulty battery unit according to the detection result, checking and maintaining a battery pack cooling system and an insulating material, replacing damaged connectors and plug-in components, re-detecting the performance of the battery pack, confirming the fault elimination, and ending the whole new energy automobile battery fault detection flow.
In a preferred embodiment, in the step S1, the detection environment must ensure that the detection site is well ventilated, so as to avoid fire sources and high-temperature safety hazards and prevent accidents in the detection process;
In the step S2, it is also necessary to check whether the connector and the plug-in component of the battery pack are firm, loose, falling off or damaged. The stability of the fixing bracket is also important to ensure that there is no loosening or deformation, as these problems can lead to displacement of the battery during operation of the vehicle, which in turn can lead to more serious malfunctions.
In a preferred embodiment, in step S3, the voltages of the battery cells are measured one by one using a multimeter, and the data are recorded and compared with a standard voltage range (typically 2.8V-4.2V). If the voltage is abnormal, the fault monomer number should be recorded immediately. Meanwhile, the voltages of the single cells are compared, if the voltage difference exceeds 0.3V, the voltage of the single cells is unbalanced, and balanced charge is needed to restore the performance of the battery.
In a preferred embodiment, in the step S4, the internal resistance of each battery cell is ensured to be within a normal range during measurement. If the internal resistance is detected to be abnormal, the fault monomer number should be recorded. In addition, comparing internal resistances among the single cells, if the internal resistance difference exceeds 10mΩ, the internal resistances among the single cells are unbalanced, and balanced charging treatment is needed.
In a preferred embodiment, in the step S5, if there is a local overheating phenomenon, the fault location should be recorded. Analyzing the reasons of abnormal temperature, which may include poor heat dissipation, aging of battery cells or internal short circuit, wherein the factors may lead to the degradation of battery performance or potential safety hazard;
In the step S6, an insulation resistance tester is used to measure the insulation resistance of the battery pack, so as to ensure that the battery pack meets the national standard. If the insulation resistance is detected to be low, the fault position is recorded and the reason is analyzed.
In a preferred embodiment, the step S7 specifically includes the following steps:
Step 1, data collection: during the battery charge and discharge test, a large amount of battery performance data including voltage, current, temperature, internal resistance, charge/discharge time, capacity, power is collected. For known faulty batteries, their performance data is collected and labeled as faulty data.
Step 2, data preprocessing: data cleaning: outliers, missing values, and extraneous data are removed. Characteristic engineering: features related to battery performance are extracted.
And 3, model training, namely selecting a random forest machine learning algorithm to divide the preprocessed data into a training set and a verification set, and training a machine learning model by using the training set data.
And 4, model verification and optimization, namely evaluating model performance by using verification set data, and adjusting model parameters. Cross-validation is performed to ensure generalization capability of the model. And optimizing the model structure and parameters according to the verification result.
And 5, fault detection, namely inputting the battery performance data collected in real time into a trained machine learning model. And outputting a predicted result of whether the battery is normal or not through the model.
Threshold setting: and setting a threshold according to the probability or decision score output by the model so as to judge whether the battery has faults or not.
And 6, analyzing the model prediction result to determine whether the battery has faults and the type of the faults. And carrying out corresponding maintenance or replacement treatment according to the fault type indicated by the model.
In a preferred embodiment, the data cleaning: the cleaning was performed using the z-score method, and the calculation formula was:
z= (X- μ)/σ, where X is the observed value, μ is the mean, σ is the standard deviation, and the data of |z| >3 is removed.
In a preferred embodiment, the model training selects a random forest whose decision function is:
where wi is the weight of the ith tree and hi (x) is the prediction of the ith tree.
Partitioning training set Dtrain = { (Xi, yi) }, where Xi is a feature vector and Yi is a label;
in the model training process, a mean square error optimization algorithm is used for minimizing a loss function, and a calculation formula is as follows:
where Y i is the model predictor.
In a preferred embodiment, the model validation uses validation set Dval = { (Xi, yi) }, to calculate the loss or accuracy on the validation set; cross-validation of the model the k-fold cross-validation was used to evaluate model stability: dividing the data set into k subsets, training with k-1 subsets each time, and verifying the remaining subset;
The fault detection real-time data Xreal-time is input into a model, and a model output prediction formula is as follows: then, a threshold value θ is set, and if Y^real-time > θ, a failure is determined.
In a preferred embodiment, in the step S8, the following steps are generally followed using the BMS diagnostic apparatus:
and (3) connection: the BMS diagnostic instrument is connected to an OBD port or BMS communication interface of the vehicle.
Starting and initializing: the diagnostic device is turned on, and a communication connection with the BMS is established after it is initialized.
Reading data: and selecting a corresponding function, and reading real-time data or historical fault codes of the BMS.
Analysis data: the status and potential problems of the battery system are analyzed based on the read data.
The operation is performed: and performing necessary operations according to the diagnosis result.
Recording and reporting: the diagnostic process and results are recorded and reports are generated for subsequent analysis and archiving.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. In the invention, the efficiency and accuracy of fault detection are obviously improved by combining the traditional battery detection step with the machine learning algorithm. In step S7, the battery charge and discharge performance data is further analyzed by using a machine learning algorithm such as random forest, so that abnormal behaviors and potential failure modes of the battery can be rapidly identified. Compared with the traditional judgment which only depends on manual experience, the machine learning model can process a large amount of data and learn complex modes and relations from the data, so that battery faults can be predicted more accurately. The combination mode not only reduces human errors, but also can discover and early warn in time at the initial stage of the fault, thereby avoiding more serious damage and potential safety accidents.
2. In the invention, through the data preprocessing step, the data is cleaned by a z-score method and key indexes are extracted by characteristic engineering, so that the quality of the data input into a machine learning model is ensured. High-quality data input is a key for ensuring model prediction accuracy, and the method is effectively processed in the link, so that the detection accuracy is further improved. The cross verification and parameter optimization in the model training and verification process ensure that the model has good generalization capability and robustness, so that the model can keep higher detection accuracy under different working conditions.
3. In the invention, the use of the BMS diagnostic apparatus provides comprehensive monitoring and diagnosis for the battery management system, and ensures that the battery operates in an optimal state. Through firmware updating and system calibration, the BMS diagnostic apparatus can further improve the performance of the battery management system, optimize the battery charging and discharging strategy, and further prolong the service life of the battery. Such preventive maintenance measures are more effective in reducing long-term maintenance costs than post-repair. In conclusion, the method not only improves the detection efficiency and accuracy, but also reduces the maintenance cost, prolongs the service life of the battery, and has important significance for the reliability and economy of the new energy automobile. The method provides an efficient and intelligent solution for the battery maintenance of the new energy automobile, and is helpful for promoting the healthy development of the new energy automobile industry.
Drawings
Fig. 1 is a schematic flow diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
With reference to figure 1 of the drawings,
A new energy automobile battery fault detection method comprises the following steps:
s1: firstly, preparing a battery detection, namely preparing a universal meter, a battery internal resistance tester, a thermal infrared imager, an insulation resistance tester, a battery charge-discharge tester, a BMS diagnostic instrument tool and equipment;
S2: performing appearance inspection of the battery to ensure that the battery is free from damage, deformation and corrosion;
s3: after the connection between the battery pack and the vehicle is disconnected, detecting the voltage of the battery cell;
s4: detecting the internal resistance of the battery through a battery internal resistance tester;
S5: detecting the temperature of the battery by using a thermal infrared imager;
S6: detecting insulation resistance by using an insulation resistance tester;
S7: detecting the charge and discharge performance of the battery, combining the battery charge and discharge performance with a random forest machine learning algorithm, analyzing a model prediction result, determining whether the battery has faults and the type of the faults, and performing corresponding maintenance or replacement treatment according to the fault type indicated by the model;
S8: battery management system data is read using a BMS diagnostic instrument. And checking the working state of the BMS system to ensure that all parameters are normal. Analyzing a BMS system fault code and searching potential fault reasons;
S9: and (3) carrying out equalizing charge, maintenance or replacement on the faulty battery unit according to the detection result, checking and maintaining a battery pack cooling system, insulating materials and the like, replacing damaged connectors, plug-ins and other components, re-detecting the performance of the battery pack, confirming the fault elimination, and ending the whole new energy automobile battery fault detection flow.
In the step S1, the detection environment must ensure that the ventilation of the detection site is good, and potential safety hazards such as fire sources, high temperature and the like are avoided so as to prevent accidents in the detection process;
In step S2, it is also necessary to check whether components such as the connector and the plug-in of the battery pack are firm, loose, falling off or damaged. The stability of the fixing bracket is also important to ensure that there is no loosening or deformation, as these problems can lead to displacement of the battery during operation of the vehicle, which can lead to more serious malfunctions
In step S3, the voltages of the battery cells are measured one by one using a multimeter, and the data are recorded and compared with a standard voltage range (typically 2.8V-. 4.2V). If the voltage is abnormal, the fault monomer number should be recorded immediately. Meanwhile, comparing the voltages of all the cells, if the voltage difference exceeds 0.3V, indicating that the voltages of the cells are unbalanced, and carrying out equalizing charge to restore the performance of the cells;
In step S4, it is necessary to ensure that the internal resistance of each battery cell is within a normal range (typically 20mΩ -80mΩ) during measurement. If the internal resistance is detected to be abnormal, the fault monomer number should be recorded. In addition, comparing internal resistances among the single cells, if the internal resistance difference exceeds 10mΩ, the internal resistances among the single cells are unbalanced, and balanced charging treatment is needed.
In step S5, if there is a local overheating phenomenon, the fault location should be recorded. Analyzing the reasons of abnormal temperature, which may include poor heat dissipation, aging of battery cells, internal short circuit and the like, wherein the factors may lead to the reduction of battery performance or potential safety hazard;
in step S6, an insulation resistance tester is used to measure the insulation resistance of the battery pack, so as to ensure that the battery pack meets the national standard (generally more than 500 ohm/V). If a low insulation resistance is detected, the fault location should be recorded and the cause should be analyzed, such as water intake of the battery pack, aging or damage of the insulation material, etc., which may cause leakage or short circuit of the battery.
In step S7, the method specifically includes the following steps:
step 1, data collection: during battery charge and discharge testing, a large amount of battery performance data is collected, including voltage, current, temperature, internal resistance, charge/discharge time, capacity, power, etc. For known faulty batteries, their performance data is collected and labeled as faulty data.
Step 2, data preprocessing: data cleaning: outliers, missing values, and extraneous data are removed. Characteristic engineering: features related to battery performance, such as time series features, statistical features, etc., are extracted.
And 3, model training, namely selecting a random forest machine learning algorithm to divide the preprocessed data into a training set and a verification set, and training a machine learning model by using the training set data.
And 4, model verification and optimization, namely evaluating model performance by using verification set data, and adjusting model parameters. Cross-validation is performed to ensure generalization capability of the model. And optimizing the model structure and parameters according to the verification result.
And 5, fault detection, namely inputting the battery performance data collected in real time into a trained machine learning model. And outputting a predicted result of whether the battery is normal or not through the model.
Threshold setting: and setting a threshold according to the probability or decision score output by the model so as to judge whether the battery has faults or not.
And 6, analyzing the model prediction result to determine whether the battery has faults and the type of the faults. And carrying out corresponding maintenance or replacement treatment according to the fault type indicated by the model.
Data cleaning: the cleaning was performed using the z-score method, and the calculation formula was:
z= (X- μ)/σ, where X is the observed value, μ is the mean, σ is the standard deviation, and the data of |z| >3 is removed.
The model training selects a random forest, and the decision function is as follows:
where wi is the weight of the ith tree and hi (x) is the prediction of the ith tree.
Partitioning training set Dtrain = { (Xi, yi) }, where Xi is a feature vector and Yi is a label;
in the model training process, a mean square error optimization algorithm is used for minimizing a loss function, and a calculation formula is as follows:
wherein Y i is the model predictor
Model validation using validation set Dval = { (Xi, yi) }, calculate the loss or accuracy on the validation set; cross-validation of the model the k-fold cross-validation was used to evaluate model stability: dividing the data set into k subsets, training with k-1 subsets each time, and verifying the remaining subset;
The fault detection real-time data Xreal-time is input into a model, and the model output prediction formula is as follows: then, a threshold value θ is set, and if Y^real-time > θ, a failure is determined.
In step S8, the following steps are followed using the BMS diagnostic instrument:
and (3) connection: the BMS diagnostic instrument is connected to an OBD port or BMS communication interface of the vehicle.
Starting and initializing: the diagnostic device is turned on, waits for its initialization and establishes a communication connection with the BMS.
Reading data: and selecting a corresponding function, and reading real-time data or historical fault codes of the BMS.
Analysis data: the status and potential problems of the battery system are analyzed based on the read data.
The operation is performed: and performing necessary operations such as equalizing charge, system calibration, or firmware update according to the diagnosis result.
Recording and reporting: the diagnostic process and results are recorded and reports are generated for subsequent analysis and archiving.
In the invention, the efficiency and accuracy of fault detection are obviously improved by combining the traditional battery detection step with the machine learning algorithm. In step S7, the battery charge and discharge performance data is further analyzed by using a machine learning algorithm such as random forest, so that abnormal behaviors and potential failure modes of the battery can be rapidly identified. Compared with the traditional judgment which only depends on manual experience, the machine learning model can process a large amount of data and learn complex modes and relations from the data, so that battery faults can be predicted more accurately. The combination mode not only reduces human errors, but also can discover and early warn in time at the initial stage of the fault, thereby avoiding more serious damage and potential safety accidents.
In the invention, the data preprocessing step, such as a z-score method, is used for cleaning the data and extracting key indexes from the feature engineering, so that the quality of the data input into the machine learning model is ensured. High-quality data input is a key for ensuring model prediction accuracy, and the method is effectively processed in the link, so that the detection accuracy is further improved. The cross verification and parameter optimization in the model training and verification process ensure that the model has good generalization capability and robustness, so that the model can keep higher detection accuracy under different working conditions.
In the invention, the use of the BMS diagnostic apparatus provides comprehensive monitoring and diagnosis for the battery management system, and ensures that the battery operates in an optimal state. Through firmware updating and system calibration, the BMS diagnostic apparatus can further improve the performance of the battery management system, optimize the battery charging and discharging strategy, and further prolong the service life of the battery. Such preventive maintenance measures are more effective in reducing long-term maintenance costs than post-repair. In conclusion, the method not only improves the detection efficiency and accuracy, but also reduces the maintenance cost, prolongs the service life of the battery, and has important significance for the reliability and economy of the new energy automobile. The method provides an efficient and intelligent solution for the battery maintenance of the new energy automobile, and is helpful for promoting the healthy development of the new energy automobile industry.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The previous description is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

CN202411134434.0A2024-08-192024-08-19 A new energy vehicle battery fault detection methodPendingCN119024168A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202411134434.0ACN119024168A (en)2024-08-192024-08-19 A new energy vehicle battery fault detection method

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202411134434.0ACN119024168A (en)2024-08-192024-08-19 A new energy vehicle battery fault detection method

Publications (1)

Publication NumberPublication Date
CN119024168Atrue CN119024168A (en)2024-11-26

Family

ID=93538799

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202411134434.0APendingCN119024168A (en)2024-08-192024-08-19 A new energy vehicle battery fault detection method

Country Status (1)

CountryLink
CN (1)CN119024168A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN119619868A (en)*2025-02-112025-03-14四川吉利学院 A method for detecting power failure of new energy vehicles

Cited By (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN119619868A (en)*2025-02-112025-03-14四川吉利学院 A method for detecting power failure of new energy vehicles

Similar Documents

PublicationPublication DateTitle
Yang et al.A fractional-order model-based battery external short circuit fault diagnosis approach for all-climate electric vehicles application
CN112092675B (en)Battery thermal runaway early warning method, system and server
CN113933732B (en)New energy automobile power battery health state analysis method, system and storage medium
CN112098850B (en)Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm
CN112147512B (en)Diagnosis and separation method for short-circuit and abuse faults of lithium ion battery
Wu et al.A fault detection method of electric vehicle battery through Hausdorff distance and modified Z-score for real-world data
CN113687251B (en)Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method
Sun et al.A multi-fault advanced diagnosis method based on sparse data observers for lithium-ion batteries
CN111579121B (en)Method for diagnosing faults of temperature sensor in new energy automobile battery pack on line
CN115469226B (en)Real-time safety early warning method for power battery of electric automobile based on operation big data
CN118457303A (en)Intelligent charging pile system with fault judgment function
CN118528791B (en) Fault handling method and system for automobile motor drive system
CN119024168A (en) A new energy vehicle battery fault detection method
CN116150572A (en)Automobile battery monomer consistency defect evaluation method based on cluster analysis
CN117783890A (en)New energy automobile battery voltage fault diagnosis method based on operation data
CN118425818A (en) A power battery risk assessment method integrating health decline and consistency
CN119355533A (en) A battery fault diagnosis method based on multi-dimensional feature fusion
CN118980934A (en) A method and system for rapid evaluation and detection of electrochemical batteries
CN114037098A (en)Intelligent management system for operation safety and maintenance of electric vehicle
CN116953534A (en)Vehicle-mounted storage battery failure judging method and device
CN119224592A (en) New energy battery health status monitoring method and system based on big data analysis
CN118777886A (en) A method for detecting battery charge state
CN118688671A (en) Early internal short circuit fault diagnosis method for lithium-ion battery pack
CN118759370A (en) A method and system for evaluating accident battery damage based on Internet of Vehicles big data
CN117783872A (en) Data anomaly detection method, device, server and storage medium for power battery

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp