CN117007999A - Battery pack fault diagnosis method, device and system - Google Patents
Battery pack fault diagnosis method, device and system Download PDFInfo
- Publication number
- CN117007999A CN117007999A CN202310991865.8A CN202310991865A CN117007999A CN 117007999 A CN117007999 A CN 117007999A CN 202310991865 A CN202310991865 A CN 202310991865A CN 117007999 A CN117007999 A CN 117007999A
- Authority
- CN
- China
- Prior art keywords
- battery pack
- battery
- tested
- temperature
- condition
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 238000012549 training Methods 0.000 claims description 48
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 description 8
- 208000032953 Device battery issue Diseases 0.000 description 5
- 238000007599 discharging Methods 0.000 description 3
- 238000004880 explosion Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 206010000369 Accident Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
-
- 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]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
Abstract
The application is suitable for the technical field of battery fault diagnosis, and provides a battery fault diagnosis method, device and system.
Description
Technical Field
The application belongs to the technical field of battery fault diagnosis, and particularly relates to a method, a device and a system for diagnosing battery faults.
Background
Under the dual pressures of environmental pollution and energy crisis, electric automobiles have become the focus of future development trend and competition. The battery system is used as a core component of the battery system, and the comprehensive performance of the electric automobile is directly affected to a great extent. However, as automobile batteries fail under extreme working conditions and severe environments in recent years to cause the continuous occurrence of fire accidents of electric automobiles, the safety performance of the batteries is receiving more and more attention.
At present, fault diagnosis of a battery mostly stays in a laboratory stage, and the fault type is determined mainly by monitoring the battery in the use process and by values of parameters such as voltage, current or resistance. When the battery fails, the voltage, current or resistance of the battery is not the same as the value of the normal use condition. But can only be determined at the moment of the battery failure by the method, and can not be found in time in advance to avoid the battery failure from being burnt. Before a plurality of batteries are in failure, the battery parameter values at certain time are greatly different from those in a normal state, so that the temperature change of the battery pack is caused, and if the batteries which are about to be in failure can be found out in advance for early warning, the damage of a vehicle can be avoided, and the occurrence of accidents is reduced.
Disclosure of Invention
Therefore, the application provides a battery pack fault diagnosis method, device and system, which are used for solving the problem that a battery which is about to be subjected to fault cannot be early-warned in advance.
The application is realized in the following way:
the application provides a battery pack fault diagnosis method, which is characterized by comprising the following steps:
acquiring a corresponding relation between discharge time of each battery pack under a preset operation condition and cell temperature in the battery pack, wherein the preset operation condition at least comprises a first condition and a second condition, the first condition is determined by running equipment for measuring the battery pack, and the second condition is determined by the current environment temperature;
deep learning is carried out through the corresponding relation of each battery pack, and a battery pack fault model with complete training is obtained;
diagnosing the battery pack to be tested through the battery fault model with complete training, and determining that the battery pack to be tested has faults when the difference value between the temperature of the battery core in the battery pack to be tested and the temperature of the battery core in the battery pack fault model with complete training under the same condition exceeds a threshold value; or alternatively, the first and second heat exchangers may be,
and when the difference value of the temperature variation amplitude of the battery cell in the battery pack to be tested in the first time and the temperature variation amplitude of the battery cell under the same condition in the well-trained battery fault model exceeds a threshold value, determining that the battery pack to be tested breaks down.
Optionally, the method further comprises:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
Optionally, the method further comprises:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
Optionally, the performing deep learning through the corresponding relation of each battery pack, and obtaining the battery pack fault model with complete training includes:
dividing the corresponding relation of each battery pack into a training set and a testing set;
and training the fault model of the battery pack according to the training set and the testing set to obtain a fully trained deep segmentation model.
Optionally, the method further comprises:
if the running conditions of the battery pack to be tested are different from the running conditions in the battery pack fault model with complete training, respectively calculating the difference value between the temperature variation amplitude of each battery cell in the first time period of the battery pack to be tested and the temperature variation amplitude of each battery cell in all the first time periods in the battery pack fault model with complete training, and determining that the battery pack to be tested fails when the difference value exceeds a threshold value.
Another object of the present application is to provide a battery pack failure diagnosis apparatus, comprising:
the battery pack management device comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring the corresponding relation between the discharge time of each battery pack under the preset operation condition and the temperature of an electric core in the battery pack, the preset operation condition at least comprises a first condition and a second condition, the first condition is determined by the driving distance and the service life of an automobile, and the second condition is determined by the current environment temperature;
the training unit is used for performing deep learning through the corresponding relation of each battery pack to obtain a battery pack fault model with complete training;
the diagnosis unit is used for diagnosing the battery pack to be tested through the training complete battery fault model, and determining that the battery pack to be tested breaks down when the difference value between the temperature of the battery core in the battery pack to be tested and the temperature of the battery core in the training complete battery pack fault model under the same condition exceeds a threshold value; or alternatively, the first and second heat exchangers may be,
and when the difference value of the temperature variation amplitude of the battery core in the battery pack to be tested in the first time and the temperature variation amplitude of the battery core under the same condition in the training complete battery fault model exceeds a threshold value, determining that the battery pack to be tested breaks down.
Optionally, the diagnostic unit is further configured to:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
Optionally, the diagnostic unit is further configured to:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
Another object of the present application is to provide a battery pack failure diagnosis system, comprising: terminal equipment, transmission equipment and server equipment; the terminal equipment is connected with the server equipment through the transmission equipment;
the terminal equipment is used for obtaining a diagnosis result of the battery pack to be tested;
the transmission equipment is used for transmitting the diagnosis result of the battery pack to be tested;
the server apparatus is for performing the battery pack failure diagnosis method of any one of the above.
By implementing the technical scheme disclosed by the application, the following beneficial technical effects can be achieved:
1. the temperature of the battery cell in the battery pack to be tested is monitored, the temperature change amplitude of the battery cell in time is monitored, and then whether the battery pack fails or not can be judged through a battery failure model, so that the method for detecting the temperature is simpler and more convenient than the method for detecting the voltage, the current and the like of the battery pack.
2. Through obtaining the corresponding relation between the discharging time of a plurality of battery packs under the preset running condition and the temperature of the battery cells in the battery packs, training the battery packs, a battery pack fault model records the scene of the impending faults of the plurality of battery packs, and when the battery packs to be tested accord with the scene of the impending faults, early warning can be carried out in advance so as to avoid the damage of vehicles caused by the faults of the battery packs.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure;
FIG. 1 is a flow chart of a method according to an embodiment of the present application;
FIG. 2 is a block diagram of a device according to an embodiment of the present application;
fig. 3 is a system module structure diagram according to an embodiment of the present application.
Detailed Description
The present application 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 application more apparent. It should be understood that the detailed description and specific examples, while indicating the application, are intended for purposes of illustration only and are not intended to limit the application,
in addition, embodiments of the present disclosure and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Specific implementations of the application are described in detail below in connection with specific embodiments.
As shown in fig. 1, a flowchart of a battery fault diagnosis method according to an embodiment of the present application may include the following steps:
step S101, obtaining the corresponding relation between the discharge time of each battery pack under the preset operation condition and the cell temperature in the battery pack.
In this embodiment, there are many methods for determining the temperature of the battery cells in the battery pack, for example, a temperature sensor may be installed in the battery pack to measure the temperature of the battery cells, and the temperature sensor may be a thermistor, a thermocouple, or an infrared sensor, etc., to convert the temperature into an electrical signal for measurement. Thermal imagers can also be used to measure the temperature of the cells in the battery pack without contact. The thermal imager can detect infrared radiation on the surface of the object, convert the infrared radiation into a temperature image, and obtain the temperature distribution of the battery cell by analyzing the image.
In this embodiment, the discharge time of the battery pack may be determined by the capacity of the battery pack and the remaining capacity estimation of the battery pack, and in fact, the remaining capacity of the battery may be determined by a Battery Management System (BMS) which may monitor the state and performance of the battery. By means of the BMS you can obtain the remaining capacity of the battery. The remaining power of the battery can also be determined by the remaining power and the remaining driving mileage of the current battery pack displayed on a dashboard of the vehicle or an on-board computer system. There are many specific methods for determining the remaining capacity of the battery pack, and the present application is not limited thereto. In this embodiment, the preset operating conditions include at least a first condition and a second condition, the first condition is determined by a running device for measuring the battery pack, for example, the running distance may be 5W-10W kilometers, and the cars with the service lives of 5-8 years may be classified into the same class, and recorded as a first condition a, the cars with the running distance within 5W kilometers and the service lives of less than 3 years may be classified into the same class, and recorded as a first condition B.
The second condition may be determined by the current ambient temperature, and for example, the current ambient temperature may be classified into a second condition a, a second condition B, and a second condition C at intervals of several degrees such as 0 to 5,5 to 10, and 10 to 15. It will be appreciated that the degree of spacing between each class may be reduced if increased accuracy is required. Since the temperature of the current environment is also affected by the humidity value and the amount of water in the vehicle radiator, the preset operating conditions may also include the humidity value of the current environment, the amount of water in the vehicle radiator, and other parameters, which the present application is not limited to.
The preset operation conditions may further include a third condition, which may be determined by a running speed of the vehicle, and may divide the running speed into a plurality of sections, and divide the vehicles running in the same section into the same class.
And then, by collecting a large amount of existing data, determining the corresponding relation between the discharge time and the temperature of the battery pack under each preset operation condition.
Step S102, deep learning is carried out through the corresponding relation of each battery pack, and a battery pack fault model with complete training is obtained.
In this embodiment, performing deep learning through the correspondence of each battery pack, and obtaining a trained complete battery pack fault model includes:
dividing the corresponding relation of each battery pack into a training set and a testing set;
and training the battery fault model according to the training set and the testing set to obtain a battery fault model with complete training.
In this embodiment, the corresponding relationship of each battery pack may be preprocessed, including data cleaning, missing value processing, outlier processing, and the like. The quality and accuracy of the data are ensured to facilitate subsequent model training and analysis.
A suitable deep learning model is selected to train the battery fault model. Common deep learning models include Convolutional Neural Networks (CNNs), recurrent Neural Networks (RNNs), long-term short-term memory networks (LSTM), and the like.
And dividing the corresponding relation of each battery pack after pretreatment into a training set and a testing set, wherein the training set carries out manual fault calibration, and the corresponding relation when faults occur and the corresponding relation when no faults occur are calibrated. And marking to obtain a batch of corresponding relations marked with fault types. The manufactured training set is led into a battery fault model to be trained for training, and the result is enabled to be more and more close to a correct result after multiple training. After training, the test set is used for testing, so that the corresponding relation of faults and the corresponding relation of non-faults can be correctly identified.
And step S103, diagnosing the battery pack to be tested through the training complete battery fault model.
In this embodiment, different operation conditions may be set, a corresponding relationship between the discharge time of the battery to be tested and the temperature of the battery cell in the battery pack under the above operation conditions is determined by training a complete battery pack fault model, and whether the battery pack to be tested has a fault is determined by the corresponding relationship between the discharge time and the temperature under the same operation conditions as in the trained complete battery pack fault model.
Step S104A, when the difference between the temperature of the battery cell in the battery pack to be tested and the temperature of the battery cell under the same condition in the trained complete battery pack fault model exceeds a threshold value, determining that the battery pack to be tested has a fault.
In this embodiment, the maximum value of the temperature of the battery cells in the battery pack under each operating condition and discharge time when no failure occurs may be determined first. When the temperature of the battery pack to be tested exceeds the maximum value, it can be determined that it is malfunctioning.
A threshold value, for example 5 or 8, may also be preset, and the difference between the temperature of the battery to be tested and the temperature in the battery fault model exceeds the threshold value under the same operating conditions and discharge time, so that the battery fault is determined to occur. For example, the driving distance of the battery pack to be tested is 12 ten thousand kilometers, the service life is 8 years, the current environment temperature is 25 degrees, the driving speed is 70km/h, and then the corresponding relation between the driving time and the temperature in the running environment is found from the battery pack fault model. And determining the temperature of the battery pack to be tested under the driving time, and determining that the battery pack fails when the temperature difference between the battery pack and the battery pack exceeds the threshold value at a certain time. At this time, the battery pack to be tested does not reach the temperature at which the battery pack is damaged or explosion is guaranteed, so that damage to the vehicle is avoided.
And step S104B, when the difference value of the temperature variation amplitude of the battery core in the battery pack to be tested in the first time and the temperature variation amplitude of the battery core under the same condition in the battery fault model with complete training exceeds a threshold value, determining that the battery pack to be tested breaks down.
In this embodiment, the temperature of the battery pack may be affected by other factors, so that the method of directly comparing the temperatures in step S104A is prone to false alarm. Therefore, in this step, the judgment can be made by comparing the temperature change magnitudes of both. By way of example, also under the same operating conditions, the temperature of the battery pack to be tested during the discharge time of 15-20 minutes increases from 35 ° to 41 °, the temperature change amplitude of the battery pack to be tested in the above period is 6, and in the correspondence of the operating conditions in the battery pack fault model, the temperature of the battery pack increases from 30 to 35.3 ° and the temperature change amplitude is 5.3, then if the threshold value of the temperature change amplitude is set to 1, then the battery pack to be tested is not judged to be faulty.
As a preferred embodiment of the present application, the method further comprises:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
In this embodiment, since one battery pack includes a plurality of batteries, the temperatures of the batteries do not greatly differ during use, and thus, by this method, it is also easy to determine whether or not a failure has occurred in the battery pack to be tested.
As a preferred embodiment of the present application, the method further comprises:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
In this embodiment, the battery fault model may first determine the maximum and minimum values of the voltage and current of the battery that is not faulty from the respective correspondence relations. And comparing the voltage and the current of the failed battery pack with the voltage and the current of the failed battery pack, and determining the reason of the failure. For example, when the voltage of the failed battery pack is greater than the maximum voltage of the non-failed battery pack, then determining that the battery pack is overcharged; when the voltage of the battery pack with faults is smaller than the maximum voltage of the battery pack without faults, the overdischarge of the battery pack is determined; when the current of the failed battery pack is larger than the maximum value of the current of the non-failed battery pack, determining that the battery pack is short-circuited; and when the current of the failed battery pack is smaller than the maximum current of the non-failed battery pack, determining that the battery pack is disconnected.
Furthermore, the fault cause can also be determined by measuring the resistance of the battery pack, and the specific method is similar to the above, and will not be described here again.
As a preferred embodiment of the present application, the method further comprises:
if the running conditions of the battery pack to be tested are different from the running conditions in the battery pack fault model with complete training, respectively calculating the difference value between the temperature variation amplitude of each battery cell in the first time period of the battery pack to be tested and the temperature variation amplitude of each battery cell in all the first time periods in the battery pack fault model with complete training, and determining that the battery pack to be tested fails when the difference value exceeds a threshold value.
In this embodiment, due to the large number of parameters in the operating conditions of the battery pack, when the collected historical data is insufficient, the battery pack failure model may not find the same correspondence relationship with the operating conditions of the battery pack to be tested. At this time, the temperature variation amplitude of the battery pack to be tested in the discharging time period can be compared with the temperature variation amplitude of the battery pack under all other operating conditions in the discharging time period, and the failure probability of the battery pack is reduced, so that when the difference value between the temperature variation amplitude of the battery pack to be tested and a certain temperature variation amplitude exceeds a threshold value, the battery pack is determined to be failed, if false judgment is afraid, the battery pack can be further detected to determine whether the battery pack is failed.
It should be noted that, the above-mentioned multiple fault detection methods may be implemented separately or simultaneously, so as to further reduce the probability of damage to the vehicle caused by the failure of the battery pack. For example, a first threshold value of the battery pack temperature, which is the maximum value of the battery pack temperature at which no failure occurs, may be set, while a second threshold value is set for determining whether the difference between the temperature at a certain discharge time of the battery pack to be tested and the temperature at a certain discharge time in the battery failure model is excessive, and a third threshold value is set for determining whether the difference between the temperature variation amplitude of a certain discharge time period of the battery pack to be tested and the temperature variation amplitude in the battery failure model is excessive. The application is not limited in this regard.
Thus, the flow shown in fig. 1 is completed.
In the embodiment of the application, the corresponding relation between the discharge time and the temperature of a plurality of battery packs under the preset operation condition is obtained and trained, so that a battery pack fault model records the scene that a plurality of battery packs are about to be broken down, when the difference value between the temperature of a certain discharge time of the battery pack to be tested under the operation condition and the temperature value under the same condition in the battery pack fault model is overlarge, or when the difference value between the temperature change amplitude of a certain discharge time period and the temperature change amplitude of the battery pack under the same condition in the battery pack fault model is overlarge, the battery pack to be tested can be determined to break down, and the battery pack to be tested does not reach the temperature of damage or explosion guarantee at the moment through early warning, so that the damage of a vehicle is avoided.
As shown in fig. 2, the embodiment of the present application further provides a battery fault diagnosis device, which includes:
an obtaining unit 201, configured to obtain a correspondence between a discharge time of each battery pack under a preset operation condition and a cell temperature in the battery pack, where the preset operation condition includes at least a first condition and a second condition, the first condition is determined by a driving device for measuring the battery pack, and the second condition is determined by a current ambient temperature;
the training unit 202 is configured to perform deep learning according to the correspondence of each battery pack, so as to obtain a battery pack fault model with complete training;
the diagnosing unit 203 is configured to diagnose, through the trained complete battery fault model, a battery pack to be tested, and determine that the battery pack to be tested has a fault when a difference between a temperature of a battery cell in the battery pack to be tested and a temperature of the battery cell under the same condition in the trained complete battery fault model exceeds a threshold value; or alternatively, the first and second heat exchangers may be,
and when the difference value of the temperature variation amplitude of the battery core in the battery pack to be tested in the first time and the temperature variation amplitude of the battery core under the same condition in the training complete battery fault model exceeds a threshold value, determining that the battery pack to be tested breaks down.
Optionally, the diagnostic unit 203 is further configured to:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
Optionally, the diagnostic unit 203 is further configured to:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
Based on the method and the device, the application also provides a battery fault diagnosis system, as shown in fig. 3, comprising: terminal equipment, transmission equipment and server equipment; the terminal equipment is connected with the server equipment through the transmission equipment;
the terminal equipment is used for obtaining a diagnosis result of the battery pack to be tested;
the transmission equipment is used for transmitting the diagnosis result of the battery pack to be tested;
the server apparatus is for performing the battery pack failure diagnosis method of any one of the above.
According to the battery pack fault diagnosis method, the battery pack fault diagnosis device and the battery pack fault diagnosis system are provided, and when the battery pack to be tested is in fault, the battery pack to be tested does not reach the temperature of damage or explosion guarantee at the moment through early warning, so that the damage of a vehicle is avoided.
The embodiment also discloses a computer device, which comprises a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to realize the battery pack fault diagnosis method.
In addition, in the embodiment of the battery pack fault diagnosis apparatus of the above example, the logic division of each program module is merely illustrative, and in practical application, the above function allocation may be performed by different program modules, for example, in view of the configuration requirement of corresponding hardware or the convenience of implementation of software, that is, the internal structure of the apparatus for optimizing the face picture quality evaluation model is divided into different program modules, so as to perform all or part of the functions described above.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "a particular example," "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the application. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
It will be appreciated by those skilled in the art that the above embodiments are merely for clarity of illustration of the present disclosure, and are not intended to limit the scope of the present disclosure. Other variations or modifications will be apparent to persons skilled in the art from the foregoing disclosure, and such variations or modifications are intended to be within the scope of the present disclosure.
Claims (9)
1. A battery pack failure diagnosis method, characterized by comprising:
acquiring a corresponding relation between discharge time of each battery pack under a preset operation condition and cell temperature in the battery pack, wherein the preset operation condition at least comprises a first condition and a second condition, the first condition is determined by running equipment for measuring the battery pack, and the second condition is determined by the current environment temperature;
deep learning is carried out through the corresponding relation of each battery pack, and a battery pack fault model with complete training is obtained;
diagnosing the battery pack to be tested through the battery fault model with complete training, and determining that the battery pack to be tested has faults when the difference value between the temperature of the battery core in the battery pack to be tested and the temperature of the battery core in the battery pack fault model with complete training under the same condition exceeds a threshold value; or alternatively, the first and second heat exchangers may be,
and when the difference value of the temperature variation amplitude of the battery cell in the battery pack to be tested in the first time and the temperature variation amplitude of the battery cell under the same condition in the well-trained battery fault model exceeds a threshold value, determining that the battery pack to be tested breaks down.
2. The method according to claim 1, wherein the method further comprises:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
3. The method according to claim 1, wherein the method further comprises:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
4. The method of claim 1, wherein the deep learning through the correspondence of each battery pack to obtain a trained battery pack fault model comprises:
dividing the corresponding relation of each battery pack into a training set and a testing set;
and training the fault model of the battery pack according to the training set and the testing set to obtain a fully trained deep segmentation model.
5. The method according to claim 1, wherein the method further comprises:
if the running conditions of the battery pack to be tested are different from the running conditions in the battery pack fault model with complete training, respectively calculating the difference value between the temperature variation amplitude of each battery cell in the first time period of the battery pack to be tested and the temperature variation amplitude of each battery cell in all the first time periods in the battery pack fault model with complete training, and determining that the battery pack to be tested fails when the difference value exceeds a threshold value.
6. A battery pack failure diagnosis apparatus, characterized by comprising:
an obtaining unit, configured to obtain a corresponding relationship between a discharge time of each battery pack under a preset operation condition and a cell temperature in the battery pack, where the preset operation condition includes at least a first condition and a second condition, the first condition is determined by a driving device for measuring the battery pack, and the second condition is determined by a current ambient temperature;
the training unit is used for performing deep learning through the corresponding relation of each battery pack to obtain a battery pack fault model with complete training;
the diagnosis unit is used for diagnosing the battery pack to be tested through the training complete battery fault model, and determining that the battery pack to be tested breaks down when the difference value between the temperature of the battery core in the battery pack to be tested and the temperature of the battery core in the training complete battery pack fault model under the same condition exceeds a threshold value; or alternatively, the first and second heat exchangers may be,
and when the difference value of the temperature variation amplitude of the battery core in the battery pack to be tested in the first time and the temperature variation amplitude of the battery core under the same condition in the training complete battery fault model exceeds a threshold value, determining that the battery pack to be tested breaks down.
7. The apparatus of claim 6, wherein the diagnostic unit is further configured to:
and detecting the temperature of the battery cells in the same battery pack to be tested, and determining that the battery pack to be tested fails when the temperature difference between the battery cells exceeds a preset threshold value.
8. The apparatus of claim 6, wherein the diagnostic unit is further configured to:
and detecting the voltage and the current of the battery pack with faults, and determining the fault reason of the battery pack according to the maximum value and the minimum value of the voltage and the current of the battery pack without faults.
9. A battery pack failure diagnosis system, comprising: terminal equipment, transmission equipment and server equipment; the terminal equipment is connected with the server equipment through the transmission equipment;
the terminal equipment is used for obtaining a diagnosis result of the battery pack to be tested;
the transmission equipment is used for transmitting the diagnosis result of the battery pack to be tested;
the server apparatus is for performing the battery pack failure diagnosis method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310991865.8A CN117007999A (en) | 2023-08-08 | 2023-08-08 | Battery pack fault diagnosis method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310991865.8A CN117007999A (en) | 2023-08-08 | 2023-08-08 | Battery pack fault diagnosis method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117007999A true CN117007999A (en) | 2023-11-07 |
Family
ID=88568793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310991865.8A Pending CN117007999A (en) | 2023-08-08 | 2023-08-08 | Battery pack fault diagnosis method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117007999A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101192758A (en) * | 2006-11-27 | 2008-06-04 | 松下电工株式会社 | Charger |
| CN103078150A (en) * | 2012-12-31 | 2013-05-01 | 普天新能源有限责任公司 | Safe prewarning method and device for power batteries |
| CN107478999A (en) * | 2017-08-10 | 2017-12-15 | 中国科学院宁波材料技术与工程研究所 | A kind of Forecasting Methodology and device of remaining battery useful life |
| CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
| CN113687255A (en) * | 2020-05-19 | 2021-11-23 | 国家能源投资集团有限责任公司 | Method and device for diagnosing state of battery cell and storage medium |
| CN113820604A (en) * | 2021-08-30 | 2021-12-21 | 昆明理工大学 | Lithium battery SOH estimation method based on temperature prediction |
| CN114792851A (en) * | 2022-04-24 | 2022-07-26 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for determining temperature difference threshold of battery module |
| CN114924193A (en) * | 2022-05-27 | 2022-08-19 | 徐州市恒源电器有限公司 | Battery safety assessment method |
| WO2022180639A1 (en) * | 2021-02-23 | 2022-09-01 | Tvs Motor Company Limited | A battery pack |
| CN115704719A (en) * | 2021-08-10 | 2023-02-17 | 北京车和家信息技术有限公司 | Method and device for detecting temperature abnormality of battery pack, storage medium and electronic equipment |
| CN115723631A (en) * | 2021-08-25 | 2023-03-03 | 北京车和家信息技术有限公司 | Battery thermal management method and device, storage medium and electronic equipment |
-
2023
- 2023-08-08 CN CN202310991865.8A patent/CN117007999A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101192758A (en) * | 2006-11-27 | 2008-06-04 | 松下电工株式会社 | Charger |
| CN103078150A (en) * | 2012-12-31 | 2013-05-01 | 普天新能源有限责任公司 | Safe prewarning method and device for power batteries |
| CN107478999A (en) * | 2017-08-10 | 2017-12-15 | 中国科学院宁波材料技术与工程研究所 | A kind of Forecasting Methodology and device of remaining battery useful life |
| CN113687255A (en) * | 2020-05-19 | 2021-11-23 | 国家能源投资集团有限责任公司 | Method and device for diagnosing state of battery cell and storage medium |
| WO2022180639A1 (en) * | 2021-02-23 | 2022-09-01 | Tvs Motor Company Limited | A battery pack |
| CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
| CN115704719A (en) * | 2021-08-10 | 2023-02-17 | 北京车和家信息技术有限公司 | Method and device for detecting temperature abnormality of battery pack, storage medium and electronic equipment |
| CN115723631A (en) * | 2021-08-25 | 2023-03-03 | 北京车和家信息技术有限公司 | Battery thermal management method and device, storage medium and electronic equipment |
| CN113820604A (en) * | 2021-08-30 | 2021-12-21 | 昆明理工大学 | Lithium battery SOH estimation method based on temperature prediction |
| CN114792851A (en) * | 2022-04-24 | 2022-07-26 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for determining temperature difference threshold of battery module |
| CN114924193A (en) * | 2022-05-27 | 2022-08-19 | 徐州市恒源电器有限公司 | Battery safety assessment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102854473B (en) | Automatic test and diagnosis system and method of power batteries of electric automobile | |
| CN111823952B (en) | Battery cell temperature diagnosis method, storage medium and electronic equipment | |
| CN107478946B (en) | Diagnosis method and system for single voltage acquisition wiring harness of power battery and vehicle | |
| CN110970679B (en) | Battery pack temperature sensor rationality diagnosis method based on thermal symmetry | |
| US20120081076A1 (en) | Secondary Battery System for Detecting Distribution of Heat Generation | |
| CN202770974U (en) | Electric vehicle power battery automatic test and diagnosis system | |
| CN111579121B (en) | Method for diagnosing faults of temperature sensor in new energy automobile battery pack on line | |
| CN112924887A (en) | Battery pack health detection method and device, readable storage medium and electronic equipment | |
| CN113791364A (en) | Lithium ion battery internal short circuit diagnosis method and system driven by model fusion signal | |
| CN115327386A (en) | Battery pack multi-fault diagnosis method based on electric-thermal coupling model | |
| CN113030619A (en) | Fault detection method and fault detection system of temperature sensor and vehicle | |
| CN117002309B (en) | Intelligent fault early warning method and system for charging pile | |
| CN116736156A (en) | SOC calibration method, SOH judgment method, detection device, system and energy storage device | |
| CN117284151A (en) | Method and system for monitoring battery power of self-adaptive new energy vehicle | |
| CN117007999A (en) | Battery pack fault diagnosis method, device and system | |
| CN115684976A (en) | Online fault diagnosis and positioning method for energy storage battery, electronic equipment and medium | |
| CN116736123A (en) | Power battery signal acquisition fault diagnosis method and device, medium and electronic equipment | |
| CN115219903A (en) | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis | |
| CN113391214A (en) | Battery micro-fault diagnosis method based on battery charging voltage ranking change | |
| CN112540301A (en) | Battery detection method, device and storage medium | |
| CN110673042B (en) | Data-based battery PACK thermal field change evaluation method | |
| Ren et al. | Multi-fault diagnosis strategy based on a non-redundant interleaved measurement circuit and improved fuzzy entropy for the battery system | |
| US11718200B2 (en) | Facilitating battery maintenance | |
| CN113296011B (en) | Circuit conducted signal active detection analysis system | |
| CN113567874B (en) | Monitoring and detecting method and device for safety state of power battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |