CN116973782A - New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning - Google Patents
New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning Download PDFInfo
- Publication number
- CN116973782A CN116973782A CN202310970736.0A CN202310970736A CN116973782A CN 116973782 A CN116973782 A CN 116973782A CN 202310970736 A CN202310970736 A CN 202310970736A CN 116973782 A CN116973782 A CN 116973782A
- Authority
- CN
- China
- Prior art keywords
- battery
- vehicle
- coefficient
- new energy
- energy automobile
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012423 maintenance Methods 0.000 title claims abstract description 29
- 238000010801 machine learning Methods 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000003745 diagnosis Methods 0.000 claims abstract description 22
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims description 63
- 230000008859 change Effects 0.000 claims description 19
- 238000007599 discharging Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 14
- 230000036541 health Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000013480 data collection Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 208000032953 Device battery issue Diseases 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- 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]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Tests Of Electric Status Of Batteries (AREA)
Abstract
The application discloses a new energy automobile maintenance and fault monitoring diagnosis method based on machine learning, which relates to the technical field of new energy automobiles and comprises the following steps: the method comprises the steps of collecting information of a vehicle-mounted battery when a new energy automobile is used, including battery capacity information and vehicle-mounted BMS accuracy information, and after collection, establishing a data analysis model with the battery capacity information of the vehicle-mounted battery and the vehicle-mounted BMS accuracy information when the new energy automobile is used, so as to generate a vehicle-mounted battery information assessment index. According to the application, the battery of the new energy automobile is monitored through the BMS system, so that the abnormal condition of the new energy automobile is intelligently perceived, and a grading treatment scheme is provided for the vehicle-mounted battery of the new energy automobile. The method effectively reduces the damage failure rate of the battery of the new energy automobile, can provide data support of a battery processing scheme under related conditions when the battery needs maintenance or detection and diagnosis, and is convenient for an automobile owner to safely and efficiently use the new energy automobile.
Description
Technical Field
The application relates to the technical field of new energy automobiles, in particular to a new energy automobile maintenance and fault monitoring and diagnosis method based on machine learning.
Background
A Battery Management System (BMS) is a system specifically designed to monitor, control, and protect batteries. It is commonly used in new energy automobiles, electric vehicles, hybrid vehicles, and other applications requiring battery power. It is able to monitor and control various parameters of the battery to ensure proper operation and optimal performance of the battery. Meanwhile, the BMS also provides important data and information support for battery maintenance, fault detection and performance optimization. Plays an important role in ensuring the performance, safety and service life of the battery.
The prior art has the following defects:
although the BMS has a fault detection and diagnosis function, the BMS may not accurately detect a battery fault or provide an accurate fault code in some cases. This can lead to difficulties in quickly identifying and repairing battery failures. Meanwhile, the BMS lacks an early warning mechanism, and reminds the vehicle-mounted battery of the vehicle owner of the direction in which maintenance is needed before the occurrence of the fault, so that the occurrence frequency of the battery fault and the loss brought to the vehicle owner are reduced.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
According to the application, the battery of the new energy automobile is monitored through the BMS system, so that the abnormal condition of the new energy automobile is intelligently perceived, and a grading treatment scheme is provided for the vehicle-mounted battery of the new energy automobile. The method has the advantages that the damage failure rate of the battery of the new energy automobile is effectively reduced, the data support of a battery processing scheme under related conditions can be provided when the battery needs maintenance or detection and diagnosis, and the safe and efficient use of the new energy automobile by an automobile owner is facilitated, so that the problems in the background technology are solved.
In order to achieve the above object, the present application provides the following technical solutions: the new energy automobile maintenance and fault monitoring diagnosis method based on machine learning comprises a data acquisition module, an evaluation module, a comparison and analysis module, a processing module and an output feedback module;
the data acquisition module is used for acquiring information of the vehicle-mounted battery when the new energy automobile is used, including battery capacity information and vehicle-mounted BMS accuracy information, and transmitting the battery capacity information and the vehicle-mounted BMS accuracy information to the evaluation module after acquisition;
the evaluation module is used for establishing a data analysis model of battery capacity information of the vehicle-mounted battery and accuracy information of the vehicle-mounted BMS when the new energy automobile is used, generating a vehicle-mounted battery information evaluation index and transmitting the vehicle-mounted battery information evaluation index to the comparison analysis module;
the comparison analysis module is used for respectively comparing the vehicle-mounted battery information evaluation indexes generated in the evaluation module with the vehicle-mounted battery health threshold values to generate damage frequency signals and transmitting the damage frequency signals to the processing module;
the processing module is used for judging whether the battery of the new energy automobile needs to be detected, diagnosed or maintained according to the frequency signal after receiving the damage frequency signal in the comparison analysis module, collecting the battery data information at the moment, establishing a data analysis model, generating an abnormal evaluation index, and transmitting the abnormal evaluation index to intelligent equipment of an automobile owner through the output feedback module according to the example that the abnormal evaluation index is similar to the remote database.
Preferably, the battery capacity information includes a battery capacity duty ratio coefficient, a battery pack electric quantity balance coefficient and a battery charge-discharge cycle coefficient, and after the acquisition, the data acquisition module respectively calibrates the battery capacity duty ratio coefficient, the battery pack electric quantity balance coefficient and the battery charge-discharge cycle coefficient to R δ 、J δ and Cδ On-vehicle BMS accuracy information includes on-vehicle BMS accuracy coefficient, gathers the back, and data acquisition module marks on-vehicle BMS accuracy coefficient as Z δ ；
The logic for obtaining the battery capacity size ratio coefficient is as follows:
the capacity of the battery is measured when the battery is currently full, and the battery capacity is calculated as a ratio of = (current full/rated power) ×100%.
Preferably, the logic for obtaining the battery pack electric quantity balance coefficient is as follows:
s1, acquiring voltage change conditions of each unit cell in the charging and discharging process of the battery pack during normal use of the automobile, and changing the voltageThe rate of conversion is calibrated to U e x In the process of collecting data, ensuring that all batteries are in a stable and continuous charge and discharge state, wherein x represents the number of each unit battery of the battery pack, and x=1, 2, 3, 4, … … and u are positive integers;
s2, obtaining the change rate U of each unit voltage of the battery pack e x And calibrating the standard deviation as z, wherein the calculation formula of the standard deviation z is as follows:
，
wherein ,voltage change rate U of each unit cell of standard battery pack with same model b x Is obtained as: />
S3, through the voltage change rate U of each unit cell of the battery pack e x The standard deviation z of the battery pack electric quantity balance coefficient is obtained, and the obtained expression is: j (J) δ ＝z。
Preferably, the logic for obtaining the battery charge-discharge cycle coefficient is as follows:
s1, collecting the times of charging and discharging the vehicle-mounted battery of the standard quality battery pack when the standard quality battery pack runs for thousands of kilometers through a database, taking a data average value, and setting the data average value as a reference value K i ；
S2, acquiring the times of charging and discharging of the vehicle-mounted battery when the vehicle runs for thousands of kilometers in the normal use process of the vehicle, and calibrating the times of charging and discharging of the battery to be K r ；
S3, calculating a battery charge-discharge cycle coefficient, wherein a calculation formula is as follows:
preferably, the logic for acquiring the accuracy coefficients of the onboard BMS is as follows:
s1, collecting the error reporting times of a standard quality BMS system in thousands of kilometers of normal use of an automobile through a database, taking a data average value, and setting the data average value as a normal rated value E i ；
S2, acquiring the number of times of error reporting of the BMS system every thousand kilometers when the automobile is normally used, and calibrating the number of times of error reporting as E r ；
S3, calculating an accuracy coefficient of the vehicle BMS, wherein the calculation formula is as follows: z is Z δ ＝E r -E i ；
When on-vehicle BMS degree of accuracy coefficient Z δ When the frequency is larger than 0, transmitting error frequency signals to an output feedback module, and performing no subsequent evaluation;
when on-vehicle BMS degree of accuracy coefficient Z δ And when the frequency is less than or equal to 0, not transmitting an error frequency signal to the output feedback module, and continuing to carry out subsequent evaluation.
Preferably, the evaluation module obtains the battery capacity size ratio R δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ Establishing a data analysis model to generate a vehicle-mounted battery information evaluation index PG z The formula according to is:
wherein e1, e2 and e3 are the ratio R of the capacity of the battery δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ E1, e2, e3 are all greater than 0;
the comparison and analysis module compares the vehicle-mounted battery information evaluation index generated by the evaluation module with the vehicle-mounted battery health threshold value, and the comparison and analysis module is divided into the following cases:
if the vehicle-mounted battery information evaluation index is greater than or equal to the vehicle-mounted battery health threshold, generating a low-damage frequency signal, transmitting the low-damage frequency signal to an output feedback module through a processing module, and prompting the vehicle owner that the damage degree of the vehicle-mounted battery is currently controllable and only needs to be maintained;
if the vehicle-mounted battery information evaluation index is smaller than the vehicle-mounted battery health threshold, generating a high-damage frequency signal, and transmitting the high-damage frequency signal to an output feedback module through a processing module to prompt a vehicle owner that the vehicle-mounted battery is high in damage degree and needs to be subjected to fault maintenance work.
Preferably, after the processing module receives the damage frequency signal, the battery environment data and the battery characteristic data are collected through the BMS system, wherein the battery environment data comprise a temperature coefficient and a humidity coefficient, and are respectively calibrated to be W d and Sd The battery characteristic data includes a battery age coefficient and a battery internal resistance coefficient, and is calibrated to N x and Rz ；
The logic for temperature coefficient acquisition is as follows:
the data acquisition module acquires the information of the environmental temperature of the vehicle-mounted battery in a certain period through the BMS system, and sets the information as T c C=1, 2, 3, 4, … …, j is a positive integer, combined with the standard temperature T of the battery i Temperature coefficient
Preferably, the humidity coefficient acquisition logic is as follows:
the data acquisition module acquires the environmental humidity information of the vehicle-mounted battery in a certain period through the BMS system, and sets the environmental humidity information as H w W=1, 2, 3, 4, … …, u being a positive integer, combined with the standard humidity H of the battery i Coefficient of humidity
Preferably, the logic for battery age factor acquisition is as follows:
the service life of the vehicle-mounted battery is set as X nx Then the battery age factor N x ＝e Xnx 。
The logic for obtaining the internal resistance coefficient of the battery is as follows:
by measuring the charging state of the vehicle-mounted battery during normal operation of the automobileThe voltage change rate and the current value in the discharging process are calculated to obtain the actual internal resistance value of the battery, and the actual internal resistance value is set as Z sj The standard value of the resistance obtained by database feedback is Z bz Then the internal resistance coefficient R of the battery z ＝(Z bz -Z sj ) 2 。
Preferably, the processing module obtains the temperature coefficient W d Coefficient of humidity S d Battery life factor N x Internal resistance coefficient R of battery z Establishing a single data analysis model to generate a single evaluation value, PG z1 ＝e1*W d ，PG z2 ＝e2*S d ，PG z3 ＝e3*N x ，PG z4 ＝e4*R z Dividing the theoretical maximum performance score to the theoretical failure performance score in each direction of the battery into 9 parts, respectively corresponding to serial numbers 1-9, accessing the single evaluation value evaluated by the processing module into a database to correspond to the single evaluation value, and respectively obtaining X 1 、X 2 、X 3 、X 4 ，X 1 、X 2 、X 3 、X 4 The value of (1) is the corresponding serial number of each evaluation value in the database, and finally an abnormality evaluation index PG is generated yc The formula according to is:
PG yc ＝1000X 1 +100X 2 +10X 3 +X 4
wherein e1, e2, e3, e4 are temperature coefficients W respectively d Coefficient of humidity S d Battery life factor N x Internal resistance coefficient R of battery z E1, e2, e3, e4 are all greater than 0;
the processing module transmits the damage frequency signal and the abnormality evaluation coefficient to the output feedback module, the output feedback module compares the damage frequency signal and the abnormality evaluation coefficient in the database, gives out the same damage frequency signal, the same abnormality scoring data case and solving method, and feeds back the data collection work to the database again after the vehicle owner improves the battery condition.
In the technical scheme, the application has the technical effects and advantages that:
according to the application, the battery of the new energy automobile is monitored through the BMS system, so that the abnormal condition of the new energy automobile is intelligently perceived, and a grading treatment scheme is provided for the vehicle-mounted battery of the new energy automobile. The damage failure rate of the battery of the new energy automobile is effectively reduced, and the data support of a battery processing scheme in related conditions can be provided when the battery needs maintenance or detection and diagnosis, so that the new energy automobile can be safely and efficiently used by an automobile owner;
according to the application, the battery improving direction is judged through detecting and feeding back the working condition of the vehicle-mounted battery when the new energy automobile runs, meanwhile, the internal and external influence factors of the battery are collected for comprehensive analysis, the analysis result is compared with the database, a subsequent scheme is provided, the accuracy of judging the condition of the vehicle-mounted battery by the BMS of the new energy automobile is improved, the trust degree of the vehicle owner to the BMS is further improved, and the long-term and effective play of the vehicle-mounted battery is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.
Fig. 1 is a schematic block diagram of a new energy automobile maintenance and fault monitoring and diagnosis method based on machine learning.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
The application provides a new energy automobile maintenance and fault monitoring diagnosis method based on machine learning as shown in figure 1, which comprises a data acquisition module, an evaluation module, a comparison analysis module, a processing module and an output feedback module;
the data acquisition module is used for acquiring information of the vehicle-mounted battery when the new energy automobile runs, including battery capacity information and vehicle-mounted BMS accuracy information, and transmitting the battery capacity information and the vehicle-mounted BMS accuracy information to the evaluation module after acquisition;
preferably, the battery capacity information includes a battery capacity duty ratio coefficient, a battery pack electric quantity balance coefficient and a battery charge-discharge cycle coefficient, and after the acquisition, the data acquisition module respectively calibrates the battery capacity duty ratio coefficient, the battery pack electric quantity balance coefficient and the battery charge-discharge cycle coefficient to R δ 、J δ and Cδ On-vehicle BMS accuracy information includes on-vehicle BMS accuracy coefficient, gathers the back, and data acquisition module marks on-vehicle BMS accuracy coefficient as Z δ 。
Example 1
When the vehicle-mounted battery in the new energy automobile maintenance and fault monitoring diagnosis method based on machine learning has a product quality problem, the vehicle-mounted battery condition of the new energy automobile can be estimated and described by the following quantized values, wherein the vehicle-mounted battery can cause a vehicle owner to bear a huge threat in terms of personal safety and property loss:
capacity fade: as the battery usage and the number of charge and discharge cycles increase, the capacity of the battery gradually decreases. The original cruising ability of the battery is deteriorated, the service time is shortened, and frequent charging is required.
Imbalance and capacity variance: in the battery pack, there may be an imbalance between different unit cells. Even if the equalization operation is performed, the capacity difference between the batteries may gradually increase as the use time increases. This may result in the BMS not accurately evaluating the overall capacity and health of the battery pack.
Charging problem: the battery may not be fully charged or the charging speed is abnormally slow. Even if connected to a power source, the battery charge may not increase or increase at a slow rate, which may be due to charger failure, internal battery damage, or connection problems.
The quality of the vehicle-mounted battery is evaluated mainly from the capacity of the battery, the capacity difference between battery packs and the rate period of the battery charging and discharging process, in order to ensure the normal use of the vehicle-mounted battery, the BMS system collects the data of the battery for several rounds of cyclic charging and discharging after the vehicle stably works, and then the classification evaluation suggestion is carried out, so that possible errors are eliminated, and the accuracy and the tightness of the data are ensured.
Therefore, the logic for obtaining the battery capacity size duty cycle is as follows:
the capacity of the battery is measured when the battery is currently full, and the battery capacity is calculated as a ratio of = (current full/rated power) ×100%.
The logic for obtaining the battery pack electric quantity balance coefficient is as follows:
when the capacitance of a battery is large, meaning that it is capable of storing more charge, its charge and discharge rate are slow and the voltage change is relatively slow under the same load conditions. In contrast, under the same load condition, the battery with smaller capacity has faster charge and discharge speed and quicker voltage change;
s1, acquiring voltage change conditions of each unit cell in the charging and discharging process of a battery pack when an automobile is normally used, and calibrating the voltage change rate as U e x In the process of collecting data, ensuring that all batteries are in a stable and continuous charge and discharge state, wherein x represents the number of each unit battery of the battery pack, and x=1, 2, 3, 4, … … and u are positive integers;
s2, obtaining the change rate U of each unit voltage of the battery pack e x And calibrating the standard deviation as z, wherein the calculation formula of the standard deviation z is as follows:
，
wherein ,voltage change rate U of each unit cell of standard battery pack with same model b x Is obtained as: />
S3, through the voltage change rate U of each unit cell of the battery pack e x The standard deviation z of the battery pack electric quantity balance coefficient is obtained, and the obtained expression is: j (J) δ ＝z。
The logic for obtaining the battery charge-discharge cycle coefficient is as follows:
s1, collecting the times of charging and discharging the vehicle-mounted battery of the standard quality battery pack when the standard quality battery pack runs for thousands of kilometers through a database, taking a data average value, and setting the data average value as a reference value K i ；
S2, acquiring the times of charging and discharging of the vehicle-mounted battery when the vehicle runs for thousands of kilometers in the normal use process of the vehicle, and calibrating the times of charging and discharging of the battery to be K r ；
S3, calculating a battery charge-discharge cycle coefficient, wherein a calculation formula is as follows:
the logic for acquiring the accuracy coefficient of the vehicle-mounted BMS is as follows:
s1, collecting the error reporting times of a standard quality BMS system in thousands of kilometers of normal use of an automobile through a database, taking a data average value, and setting the data average value as a normal rated value E i ；
S2, acquiring the number of times of error reporting of the BMS system every thousand kilometers when the automobile is normally used, and calibrating the number of times of error reporting as E r ；
S3, calculating an accuracy coefficient of the vehicle BMS, wherein the calculation formula is as follows: z is Z δ ＝E r -E i ；
When on-vehicle BMS degree of accuracy coefficient Z δ When the error frequency signal is larger than 0, the data obtained by the vehicle-mounted BMS system is possibly inaccurate, the vehicle-mounted BMS system needs to be overhauled, and the error frequency signal is transmitted to the output feedback module without subsequent evaluation;
when on-vehicle BMS degree of accuracy coefficient Z δ When the value is smaller than or equal to 0, the value obtained by the BMS system is within a preset range, and an error frequency signal is not transmitted to the output feedback module, so that the operation is continuedAnd (5) subsequent evaluation.
The evaluation module obtains the duty ratio R of the battery capacity δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ Establishing a data analysis model to generate a vehicle-mounted battery information evaluation index PG z The formula according to is:
wherein e1, e2 and e3 are the ratio R of the capacity of the battery δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ E1, e2, e3 are all greater than 0;
the calculated expression shows that the larger the expression value of the evaluation index is, the higher the quality of the vehicle-mounted battery is, and the lower the quality of the vehicle-mounted battery is;
the comparison and analysis module compares the vehicle-mounted battery information evaluation index generated by the evaluation module with the vehicle-mounted battery health threshold value, and the comparison and analysis module is divided into the following cases:
if the vehicle-mounted battery information evaluation index is greater than or equal to the vehicle-mounted battery health threshold, generating a low-damage frequency signal, transmitting the low-damage frequency signal to an output feedback module through a processing module, and prompting the vehicle owner that the damage degree of the vehicle-mounted battery is currently controllable and only needs to be maintained;
if the vehicle-mounted battery information evaluation index is smaller than the vehicle-mounted battery health threshold, generating a high-damage frequency signal, and transmitting the high-damage frequency signal to an output feedback module through a processing module to prompt a vehicle owner that the vehicle-mounted battery is high in damage degree and needs to be subjected to fault maintenance work.
Example 2
After the processing module receives the damage frequency signal transmitted by the comparison and analysis module, battery environment data and battery characteristic data are collected through the BMS system, and the battery environment data comprise a temperature coefficient and a humidity coefficient and are respectively calibrated to be W d and Sd The battery characteristic data includes a battery age coefficient and electricityChi Nazu coefficient, designated N x and Rz ；
The logic for temperature coefficient acquisition is as follows:
the data acquisition module acquires the information of the environmental temperature of the vehicle-mounted battery in a certain period through the BMS system, and sets the information as T c C=1, 2, 3, 4, … …, j is a positive integer, combined with the standard temperature T of the battery i Temperature coefficient
The humidity coefficient acquisition logic is as follows:
the data acquisition module acquires the environmental humidity information of the vehicle-mounted battery in a certain period through the BMS system, and sets the environmental humidity information as H w W=1, 2, 3, 4, … …, u being a positive integer, combined with the standard humidity H of the battery i Coefficient of humidity
The logic for battery age factor acquisition is as follows:
the service life of the vehicle-mounted battery is set as X nx Then the battery age factor N x ＝e Xnx 。
The logic for obtaining the internal resistance coefficient of the battery is as follows:
the actual internal resistance value of the battery is calculated by measuring the voltage change rate and the current value of the vehicle-mounted battery in the charging and discharging processes when the vehicle normally runs, and the value is set as Z sj The standard value of the resistance obtained by database feedback is Z bz Then the internal resistance coefficient R of the battery z ＝(Z bz -Z sj ) 2 。
The processing module obtains the temperature coefficient W d Coefficient of humidity S d Battery life factor N x Internal resistance coefficient R of battery z Establishing a single data analysis model to generate a single evaluation value, PG z1 ＝e1*W d ，PG z2 ＝e2*S d ，PG z3 ＝e3*N x ，PG z4 ＝e4*R z A battery is providedDividing the theoretical maximum performance score to the theoretical failure performance score in each direction into 9 parts, respectively corresponding to serial numbers 1-9, accessing the single evaluation value evaluated by the processing module into a database to correspond to the single evaluation value, and respectively obtaining X 1 、X 2 、X 3 、X 4 ，X 1 、X 2 、X 3 、X 4 The value of (1) is the corresponding serial number of each evaluation value in the database, and finally an abnormality evaluation index PG is generated yc The formula according to is:
PG yc ＝1000X 1 +100X 2 +10X 3 +X 4
wherein e1, e2, e3, e4 are temperature coefficients W respectively d Coefficient of humidity S d Battery life factor N x Internal resistance coefficient R of battery z E1, e2, e3, e4 are all greater than 0;
according to the calculated expression, thousands, hundreds and tens of four digits of the evaluation index respectively represent different problem directions, the directions of the vehicle-mounted battery needing maintenance or maintenance can be indicated through the four digits in a brief way, meanwhile, the reasons of vehicle damage are various, sometimes the problem time can even affect each other, the improvement scheme of the vehicle condition which is the most similar can be found out through the four digits representation method, the greater the number corresponding to the four digits respectively is, the higher the abnormality degree of the vehicle-mounted battery is, and otherwise, the lower the abnormality degree of the vehicle-mounted battery is;
the processing module transmits the damage frequency signal and the abnormality evaluation coefficient to the output feedback module, the output feedback module compares the damage frequency signal and the abnormality evaluation coefficient in the database, gives out the same damage frequency signal, the same abnormality scoring data case and solving method, and feeds back the data collection work to the database again after the vehicle owner improves the battery condition.
According to the application, the battery of the new energy automobile is monitored through the BMS system, so that the abnormal condition of the new energy automobile is intelligently perceived, and a grading treatment scheme is provided for the vehicle-mounted battery of the new energy automobile. The damage failure rate of the battery of the new energy automobile is effectively reduced, and the data support of a battery processing scheme in related conditions can be provided when the battery needs maintenance or detection and diagnosis, so that the new energy automobile can be safely and efficiently used by an automobile owner;
according to the application, the battery improving direction is judged through detecting and feeding back the working condition of the vehicle-mounted battery when the new energy automobile runs, meanwhile, the internal and external influence factors of the battery are collected for comprehensive analysis, the analysis result is compared with the database, a subsequent scheme is provided, the accuracy of judging the condition of the vehicle-mounted battery by the BMS of the new energy automobile is improved, the trust degree of the vehicle owner to the BMS is further improved, and the long-term and effective play of the vehicle-mounted battery is ensured.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided by the present application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on 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 the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application 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 application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The new energy automobile maintenance and fault monitoring and diagnosis method based on machine learning is characterized by comprising the following steps of:
step one, acquiring information of a vehicle-mounted battery when a new energy automobile is used, wherein the information comprises battery capacity information and vehicle-mounted BMS accuracy information;
step two, establishing a data analysis model from battery capacity information of the vehicle-mounted battery and accuracy information of the vehicle-mounted BMS when the new energy automobile is used, and generating a vehicle-mounted battery information evaluation index;
step three, the vehicle-mounted battery information evaluation indexes generated in the step two are respectively compared with the vehicle-mounted battery health threshold values to generate damage frequency signals;
and step four, after receiving the damage frequency signal in the step three, judging whether the battery of the new energy automobile needs detection diagnosis or maintenance according to the frequency signal, collecting battery data information at the moment, establishing a data analysis model, generating an abnormal evaluation index, and then transmitting output feedback to intelligent equipment of an automobile owner according to the abnormal evaluation index and matching a similar example in a remote database.
2. The machine learning-based new energy automobile maintenance and fault monitoring diagnosis method according to claim 1, wherein the battery capacity information includes a battery capacity duty ratio coefficient, a battery pack electric quantity balance coefficient and a battery charge-discharge cycle coefficient, and the data acquisition module respectively calibrates the battery capacity duty ratio coefficient, the battery pack electric quantity balance coefficient and the battery charge-discharge cycle coefficient to R after acquisition δ 、J δ and Cδ On-vehicle BMS accuracy information includes on-vehicle BMS accuracy coefficient, gathers the back, and data acquisition module marks on-vehicle BMS accuracy coefficient as Z δ ；
The logic for obtaining the battery capacity size ratio coefficient is as follows:
the capacity of the battery is measured when the battery is currently full, and the battery capacity is calculated as a ratio of = (current full/rated power) ×100%.
3. The machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 2, wherein the logic for obtaining the battery pack electric quantity balance coefficient is as follows:
s1, acquiring voltage change conditions of each unit cell in the charging and discharging process of a battery pack when an automobile is normally used, and calibrating the voltage change rate as U e x In the process of collecting data, ensuring that all batteries are in a stable and continuous charge and discharge state, wherein x represents the number of each unit battery of the battery pack, and x=1, 2, 3, 4, … … and u are positive integers;
s2, obtaining the change rate U of each unit voltage of the battery pack e x Is the standard of (2)The standard deviation is calibrated as z, and the calculation formula of the standard deviation z is as follows:
，
wherein ,voltage change rate U of each unit cell of standard battery pack with same model b x Is obtained as: />
S3, through the voltage change rate U of each unit cell of the battery pack e x The standard deviation z of the battery pack electric quantity balance coefficient is obtained, and the obtained expression is: j (J) δ ＝z。
4. The machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 3, wherein the logic for acquiring the battery charge-discharge cycle coefficient is as follows:
s1, collecting the times of charging and discharging the vehicle-mounted battery of the standard quality battery pack when the standard quality battery pack runs for thousands of kilometers through a database, taking a data average value, and setting the data average value as a reference value K i ；
S2, acquiring the times of charging and discharging of the vehicle-mounted battery when the vehicle runs for thousands of kilometers in the normal use process of the vehicle, and calibrating the times of charging and discharging of the battery to be K r ；
S3, calculating a battery charge-discharge cycle coefficient, wherein a calculation formula is as follows:
5. the machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 4, wherein the logic for acquiring the accuracy coefficient of the vehicle-mounted BMS is as follows:
s1, collecting the error reporting times of a standard quality BMS system in thousands of kilometers of normal use of an automobile through a database, taking a data average value, and setting the data average value as a normal rated value E i ；
S2, acquiring the number of times of error reporting of the BMS system every thousand kilometers when the automobile is normally used, and calibrating the number of times of error reporting as E r ；
S3, calculating an accuracy coefficient of the vehicle BMS, wherein the calculation formula is as follows: z is Z δ ＝E r -E i ；
When on-vehicle BMS degree of accuracy coefficient Z δ When the frequency is larger than 0, transmitting error frequency signals to an output feedback module, and performing no subsequent evaluation;
when on-vehicle BMS degree of accuracy coefficient Z δ And when the frequency is less than or equal to 0, not transmitting an error frequency signal to the output feedback module, and continuing to carry out subsequent evaluation.
6. The new energy automobile maintenance and fault monitoring and diagnosis method based on machine learning as set forth in claim 5, wherein the step two is to obtain the battery capacity size duty ratio coefficient R δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ Establishing a data analysis model to generate a vehicle-mounted battery information evaluation index PG z The formula according to is:
，
wherein e1, e2 and e3 are the ratio R of the capacity of the battery δ Battery pack electric quantity equalization coefficient J δ Cycle coefficient C of battery charge and discharge δ E1, e2, e3 are all greater than 0;
step three, comparing the vehicle-mounted battery information evaluation index generated in the step two with a vehicle-mounted battery health threshold value, and dividing the vehicle-mounted battery information evaluation index into the following cases:
if the vehicle-mounted battery information evaluation index is greater than or equal to the vehicle-mounted battery health threshold, generating a low-damage frequency signal, and carrying out output feedback on the low-damage frequency signal through a processing module;
if the vehicle-mounted battery information evaluation index is smaller than the vehicle-mounted battery health threshold, generating a high-damage frequency signal, and carrying out output feedback on the high-damage frequency signal through the processing module.
7. The machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 6, wherein the processing module collects battery environment data and battery characteristic data through the BMS system after receiving the damage frequency signal, the battery environment data including a temperature coefficient and a humidity coefficient, and respectively calibrated as W d and Sd The battery characteristic data includes a battery age coefficient and a battery internal resistance coefficient, and is calibrated to N x and Rz ；
The logic for temperature coefficient acquisition is as follows:
the data acquisition module acquires the environmental temperature information of the vehicle-mounted battery in the service period through the BMS system, and sets the environmental temperature information as T c C=1, 2, 3, 4, … …, j is a positive integer, combined with the standard temperature T of the battery i Temperature coefficient
8. The machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 7, wherein the logic for acquiring the humidity coefficient is as follows:
step one, acquiring information of environmental humidity in a service period of a vehicle-mounted battery through a BMS system, and setting the information as H w W=1, 2, 3, 4, … …, u being a positive integer, combined with the standard humidity H of the battery i Coefficient of humidity
9. The machine learning-based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 8, wherein the logic for obtaining the battery age coefficient is as follows:
the service life of the vehicle-mounted battery is set as X nx Then the battery age factor N x ＝e Xnx 。
The logic for obtaining the internal resistance coefficient of the battery is as follows:
the actual internal resistance value of the battery is calculated by measuring the voltage change rate and the current value of the vehicle-mounted battery in the charging and discharging processes when the vehicle normally runs, and the actual internal resistance value is set as Z sj The standard value of the resistance obtained by database feedback is Z bz Then the internal resistance coefficient R of the battery z ＝(Z bz -Z sj ) 2 。
10. The machine learning based new energy automobile maintenance and fault monitoring and diagnosis method according to claim 9, wherein the processing module obtains the temperature coefficient W d Coefficient of humidity S d Battery life factor N x Internal resistance coefficient R of battery z Establishing a single data analysis model to generate a single evaluation value, PG z1 ＝e1*W d ，PG z2 ＝e2*S d ，PG z3 ＝e3*N x ，PG z4 ＝e4*R z Dividing the theoretical maximum performance score to the theoretical failure performance score in each direction of the battery into 9 parts, respectively corresponding to serial numbers 1-9, and accessing the single evaluation value evaluated in the fourth step into a database to correspond to the single evaluation value, so as to respectively obtain X 1 、X 2 、X 3 、X 4 ，X 1 、X 2 、X 3 、X 4 The value of (1) is the corresponding serial number of each evaluation value in the database, and finally an abnormality evaluation index PG is generated yc The formula according to is:
PG yc ＝1000X 1 +100X 2 +10X 3 +X 4
wherein e1, e2, e3, e4 are temperature coefficients W respectively d Coefficient of humidity S d Battery life factor N x In-batteryResistance coefficient R z E1, e2, e3, e4 are all greater than 0;
and step four, transmitting the damage frequency signal and the abnormality evaluation coefficient to a database, comparing the damage frequency signal and the abnormality evaluation coefficient in the database, giving out data cases and solutions with identical abnormality scores of the same damage frequency signal, and feeding back the data collection work to the database again after the vehicle owner improves the battery condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310970736.0A CN116973782B (en) | 2023-08-03 | 2023-08-03 | New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310970736.0A CN116973782B (en) | 2023-08-03 | 2023-08-03 | New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116973782A true CN116973782A (en) | 2023-10-31 |
| CN116973782B CN116973782B (en) | 2024-05-24 |
Family
ID=88472915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310970736.0A Active CN116973782B (en) | 2023-08-03 | 2023-08-03 | New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116973782B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117594860A (en) * | 2024-01-19 | 2024-02-23 | 新立讯科技股份有限公司 | New energy automobile process guidance method and system based on DLP |
| CN117936949A (en) * | 2024-03-22 | 2024-04-26 | 深圳玖逸行新能源汽车技术有限公司 | Rapid intelligent detection maintenance system for new energy automobile battery pack |
| CN117991108A (en) * | 2024-04-07 | 2024-05-07 | 邦邦汽车销售服务(北京)有限公司 | Data-based power battery damage detection method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105904986A (en) * | 2016-04-26 | 2016-08-31 | 深圳市德传技术有限公司 | Remote battery management and detection method and system for new-energy vehicle |
| CN109143072A (en) * | 2017-06-28 | 2019-01-04 | 东软集团股份有限公司 | A kind of test method of battery management system, device and equipment |
| CN109683096A (en) * | 2018-12-17 | 2019-04-26 | 珠海格力电器股份有限公司 | Battery management system function test system and test method |
| US20200269722A1 (en) * | 2019-02-25 | 2020-08-27 | Toyota Research Institute, Inc. | Systems, methods, and storage media for adapting machine learning models for optimizing performance of a battery pack |
| US20210005027A1 (en) * | 2019-07-04 | 2021-01-07 | QodeLogix Systems Inc. | System and method for battery maintenance management |
| CN113022374A (en) * | 2021-02-04 | 2021-06-25 | 东风汽车集团股份有限公司 | Passive equalization control method and system for battery management system of electric vehicle |
| CN113043912A (en) * | 2021-04-06 | 2021-06-29 | 广州汽车集团股份有限公司 | Full-time battery detection device and system and automobile |
| CN114529067A (en) * | 2022-01-30 | 2022-05-24 | 常伟 | Method for performing predictive maintenance on electric vehicle battery based on big data machine learning |
| CN115366683A (en) * | 2022-08-09 | 2022-11-22 | 北京理工大学 | Fault diagnosis strategy for new energy automobile power battery multi-dimensional model fusion |
-
2023
- 2023-08-03 CN CN202310970736.0A patent/CN116973782B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105904986A (en) * | 2016-04-26 | 2016-08-31 | 深圳市德传技术有限公司 | Remote battery management and detection method and system for new-energy vehicle |
| CN109143072A (en) * | 2017-06-28 | 2019-01-04 | 东软集团股份有限公司 | A kind of test method of battery management system, device and equipment |
| CN109683096A (en) * | 2018-12-17 | 2019-04-26 | 珠海格力电器股份有限公司 | Battery management system function test system and test method |
| US20200269722A1 (en) * | 2019-02-25 | 2020-08-27 | Toyota Research Institute, Inc. | Systems, methods, and storage media for adapting machine learning models for optimizing performance of a battery pack |
| US20210005027A1 (en) * | 2019-07-04 | 2021-01-07 | QodeLogix Systems Inc. | System and method for battery maintenance management |
| CN113022374A (en) * | 2021-02-04 | 2021-06-25 | 东风汽车集团股份有限公司 | Passive equalization control method and system for battery management system of electric vehicle |
| CN113043912A (en) * | 2021-04-06 | 2021-06-29 | 广州汽车集团股份有限公司 | Full-time battery detection device and system and automobile |
| CN114529067A (en) * | 2022-01-30 | 2022-05-24 | 常伟 | Method for performing predictive maintenance on electric vehicle battery based on big data machine learning |
| CN115366683A (en) * | 2022-08-09 | 2022-11-22 | 北京理工大学 | Fault diagnosis strategy for new energy automobile power battery multi-dimensional model fusion |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117594860A (en) * | 2024-01-19 | 2024-02-23 | 新立讯科技股份有限公司 | New energy automobile process guidance method and system based on DLP |
| CN117594860B (en) * | 2024-01-19 | 2024-04-05 | 新立讯科技股份有限公司 | New energy automobile process guidance method and system based on DLP |
| CN117936949A (en) * | 2024-03-22 | 2024-04-26 | 深圳玖逸行新能源汽车技术有限公司 | Rapid intelligent detection maintenance system for new energy automobile battery pack |
| CN117936949B (en) * | 2024-03-22 | 2024-06-07 | 深圳玖逸行新能源汽车技术有限公司 | Rapid intelligent detection maintenance system for new energy automobile battery pack |
| CN117991108A (en) * | 2024-04-07 | 2024-05-07 | 邦邦汽车销售服务(北京)有限公司 | Data-based power battery damage detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116973782B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108254696B (en) | Battery health state evaluation method and system | |
| CN116973782B (en) | New energy automobile maintenance and fault monitoring and diagnosing method based on machine learning | |
| CN114430080B (en) | Power battery cell abnormal self-discharge identification method based on operation data | |
| CN102854473B (en) | Automatic test and diagnosis system and method of power batteries of electric automobile | |
| CN112098850B (en) | Lithium ion battery voltage fault diagnosis method and system based on SDO algorithm | |
| CN104813182B (en) | The steady state detection of abnormal charge event in the cell device being connected in series | |
| KR20230129953A (en) | Method, device, apparatus, and storage medium for evaluating consistency of vehicle battery cell | |
| CN110045291B (en) | Lithium battery capacity estimation method | |
| CN111257753B (en) | Battery system fault diagnosis method | |
| US11959969B2 (en) | Apparatus and method for diagnosing battery | |
| CN110920400B (en) | Battery system consistency fault diagnosis and whole vehicle processing method for pure electric vehicle | |
| CN114329760A (en) | Vehicle-mounted lithium ion battery modeling and fault diagnosis method based on digital twinning | |
| CN113253138A (en) | Method for classifying battery, battery recycling system and motor vehicle | |
| CN116819332A (en) | Battery fault diagnosis method, device, medium and BMS system | |
| CN116224075A (en) | Power battery monomer abnormality early warning method and device, electronic equipment and storage medium | |
| CN115248379A (en) | Power battery micro-short-circuit diagnosis method and system based on multi-scene fusion | |
| CN113866641A (en) | Fault detection method and device for lithium ion battery | |
| CN113687251B (en) | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| Kaypmaz et al. | An advanced cell model for diagnosing faults in operation of Li-ion Polymer batteries | |
| Tang et al. | An aging-and load-insensitive method for quantitatively detecting the battery internal-short-circuit resistance | |
| CN116930764A (en) | Power-electron-fused fault diagnosis and danger prediction method for lithium battery energy storage system | |
| JP2022034380A (en) | Manufacturing method of rechargeable secondary battery | |
| CN116840702A (en) | Method and device for detecting abnormality of storage battery in running state | |
| CN113420494B (en) | Super-capacitor Bayes probability fusion modeling method |
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 |