CN116298910A - Battery safety control method and device - Google Patents
Battery safety control method and device Download PDFInfo
- Publication number
- CN116298910A CN116298910A CN202310217100.9A CN202310217100A CN116298910A CN 116298910 A CN116298910 A CN 116298910A CN 202310217100 A CN202310217100 A CN 202310217100A CN 116298910 A CN116298910 A CN 116298910A
- Authority
- CN
- China
- Prior art keywords
- battery
- target
- lithium
- precipitation
- state
- 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 74
- 238000001556 precipitation Methods 0.000 claims abstract description 161
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000007726 management method Methods 0.000 claims abstract description 41
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 147
- 229910052744 lithium Inorganic materials 0.000 claims description 147
- 238000012549 training Methods 0.000 claims description 64
- 230000002159 abnormal effect Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 13
- 238000002790 cross-validation Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 229910001416 lithium ion Inorganic materials 0.000 claims description 7
- 230000010261 cell growth Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 5
- 210000004027 cell Anatomy 0.000 description 42
- 238000001514 detection method Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000004804 winding Methods 0.000 description 5
- 238000007599 discharging Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007087 memory ability Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000000178 monomer Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 229910001361 White metal Inorganic materials 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910002804 graphite Inorganic materials 0.000 description 1
- 239000010439 graphite Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
- 239000010969 white metal Substances 0.000 description 1
Images
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]
- G01R31/367—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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The application discloses a battery safety control method and device. Wherein the method comprises the following steps: acquiring at least one group of target standing data of the target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state. The method and the device solve the technical problem that whether the analysis phenomenon occurs in the battery or not is difficult to accurately and rapidly find in the related technology, so that the safety of the battery is poor.
Description
Technical Field
The application relates to the technical field of battery detection, in particular to a battery safety control method and device.
Background
In the lithium ion battery, li+ is deintercalated from the positive electrode and is inserted into the negative electrode during charging, but in some abnormal situations, such as insufficient space for inserting li+ into the negative electrode, too large resistance when inserting li+ into the negative electrode, too fast li+ is deintercalated from the positive electrode but cannot be inserted into the negative electrode in an equivalent amount, etc., li+ which cannot be inserted into the negative electrode only adheres to electrons on the surface of the negative electrode, so that silvery white metallic lithium simple substance is formed, which is called lithium precipitation. The lithium precipitation not only causes a significant decrease in the performance of the lithium battery, but also limits the quick charge capacity of the lithium battery, and in addition, the lithium precipitation may cause catastrophic accidents such as combustion and explosion of the lithium battery.
Currently, the following methods are generally used to determine whether or not lithium precipitation occurs in a battery: firstly, circularly charging and discharging the lithium ion battery by adopting different charging and discharging multiplying power, and disassembling the lithium ion battery, so as to observe whether a silvery white metal lithium simple substance is formed on the surface of a negative electrode to judge whether lithium precipitation occurs in the battery, but the method needs to consume a large amount of resources and time cost; secondly, circularly charging and discharging the lithium ion battery and observing the change of coulomb efficiency, but the accuracy of the coulomb efficiency calculated by common charging and discharging is poor, so that whether lithium is separated from the battery cannot be accurately judged; and thirdly, detecting the voltage difference between the battery cathode and the battery metal shell by adopting a detection instrument so as to judge whether lithium precipitation occurs in the battery, wherein the effectiveness of the method is limited by the battery structure.
Therefore, all of the three lithium analysis detection methods cannot accurately and rapidly determine whether lithium analysis occurs in the battery.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a battery safety control method and device, which at least solve the technical problem that whether a analysis phenomenon occurs in a battery or not is difficult to accurately and rapidly find in the related technology, so that the battery safety is poor.
According to an aspect of an embodiment of the present application, there is provided a battery safety management and control method including: acquiring at least one group of target standing data of the target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state.
Optionally, the training process of the lithium analysis prediction model includes: obtaining a plurality of groups of training samples, wherein each group of training samples comprises a group of first standing data of a first battery in a first time period; determining sample labels corresponding to each group of training samples, wherein the sample labels are used for marking whether lithium precipitation occurs in the first battery in a first time period; and carrying out K-fold cross validation on the initial prediction model according to the plurality of groups of training samples and sample labels, and adjusting model parameters of the initial prediction model to obtain the lithium analysis prediction model.
Optionally, obtaining multiple sets of training samples includes: acquiring at least one group of first state parameters of the first battery in a first time period, wherein the first state parameters comprise: the method comprises the steps of (1) a state of charge of a first battery, a voltage value of an electric core in the first battery and a total current value of the first battery; preprocessing each set of first state parameters to obtain at least one set of second state parameters, wherein the preprocessing comprises the following steps: cleaning and normalizing; and for each group of second state parameters, determining whether the first battery is in a fully charged static state according to the state of charge and the total current value in the second state parameters, and if so, taking the voltage value of the battery core in the first battery in the second state parameters as a group of training samples.
Optionally, determining a sample tag corresponding to each set of training samples includes: for each group of training samples, determining whether the first battery generates a lithium precipitation phenomenon in a time period corresponding to the training samples by adopting a target method to obtain a sample label corresponding to the training samples, wherein the target method comprises at least one of the following steps: cell disassembly, cell expansion, and three electrode methods.
Optionally, determining the lithium analysis characteristic of the cell in the target battery according to the target standing data includes: calculating a differential value of the voltage of the battery core in the target battery by using a differential voltage method in the lithium analysis prediction model; determining a lithium analysis characteristic of the battery cell in the target battery based on the differential value, wherein the lithium analysis characteristic comprises the following steps: the first voltage value at the peak position of the corresponding voltage change curve, the first differential value of the first voltage value, the first difference value of the first voltage differential value and the first differential value, the second voltage value at the trough position of the corresponding voltage change curve, the second difference value of the second voltage value and the first voltage value, and the duration of the first time when the voltage reaches the trough position and the standing start time.
Optionally, determining the safety state of the target battery based on at least one prediction result, and performing a management operation corresponding to the safety state, including: calculating a safety index of the target battery in the first time period based on at least one group of target standing data and at least one prediction result, wherein the safety index comprises: the method comprises the steps of a first time period when a target battery generates a lithium precipitation phenomenon, a first time period when the target battery generates the lithium precipitation phenomenon in a full charge of target times, a first average time period when the target battery generates the lithium precipitation phenomenon, and a difference value between a second average time period when the target battery generates the lithium precipitation phenomenon in the full charge of target times and the first average time period; when the first time length is larger than a first preset threshold value, the first time number is larger than a second preset threshold value, the first average time length is larger than a third preset threshold value and the difference value is larger than a fourth preset threshold value, determining that the target battery is in an abnormal state, and executing management and control operation corresponding to the abnormal state; otherwise, determining that the target battery is in a safe state.
Optionally, determining that the target battery is in an abnormal state, and performing a management and control operation corresponding to the abnormal state includes: when the target battery is in an abnormal state, sending out early warning prompt information, wherein the early warning prompt information is used for prompting the occurrence of lithium precipitation phenomenon in the target battery.
According to another aspect of the embodiments of the present application, there is also provided a battery safety management and control device, including: the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring at least one group of target standing data of a target battery in a standing target time period, wherein each group of target standing data is used for reflecting the voltage change state of a battery core in the target battery in the target standing time period in a first standing time period after the target battery is fully charged; the prediction module is used for sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of the battery cells in the target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and the control module is used for determining the safety state of the target battery based on at least one prediction result and executing control operation corresponding to the safety state.
According to another aspect of the embodiments of the present application, there is further provided a nonvolatile storage medium, where the nonvolatile storage medium includes a stored program, and a device where the nonvolatile storage medium is located executes the above-mentioned battery safety management method by running the program.
According to another aspect of the embodiments of the present application, there is also provided an electronic device including: the battery safety management system comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the battery safety management method through the computer program.
In the embodiment of the application, at least one group of target standing data of the target battery in a target time period is obtained, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state. Therefore, whether the lithium precipitation phenomenon occurs in the battery is accurately and rapidly predicted through the analysis prediction model, corresponding management and control measures are adopted when the lithium precipitation occurs in the battery in time, the catastrophic hazard of the battery is avoided, and the technical problem that whether the analysis phenomenon occurs in the battery is difficult to accurately and rapidly find in the related technology, so that the safety of the battery is poor is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of an alternative battery safety management method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an alternative cell in which lithium precipitation occurs according to an embodiment of the present application
Fig. 3 is a schematic structural view of an alternative battery safety management device according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and the accompanying drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For a better understanding of the embodiments of the present application, some nouns or translations of terms that appear during the description of the embodiments of the present application are explained first as follows:
k-fold cross validation: cross-validation is mainly used to prevent overfitting caused by excessive complexity of the model, and is a statistical method for evaluating the generalization capability of the data set of training data. The main idea of the K-fold cross validation is that an original data machine D is divided into K parts, each time K-1 parts are selected as training sets, the rest part is used as a test set, the cross validation is repeated K times, and finally, the average value of the K times of accuracy is taken as an evaluation index of a model, so that the occurrence of under-fitting and over-fitting states is effectively avoided, wherein the selection of the K value can be regulated according to actual conditions.
Example 1
In accordance with embodiments of the present application, a battery safety management method is provided, it being noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system, such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Fig. 1 is a flowchart of an alternative battery safety management method according to an embodiment of the present application, as shown in fig. 1, the method at least includes steps S102-S106, wherein:
Step S102, at least one group of target standing data of the target battery in a target time period is obtained, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged.
In the technical scheme provided in the step S102, the target standing data is determined by acquiring the target state parameters of the target battery from the BMS (Battery Management System ), wherein the BMS performs intelligent management and maintenance on the battery by monitoring the state of the battery, and prevents the battery from being charged and overdischarged, thereby prolonging the service life of the battery. When the target State parameter of the target battery is determined, determining that the target battery is in a fully charged standing State when the SOC (State of Charge) in the target State parameter of the target battery is greater than or equal to 98 and the total current of the battery is equal to zero, and taking the voltage of the battery cell of the target battery in the first standing time period after the full Charge as target standing data. The target time period may be determined by itself according to practical situations, and is not limited herein, and in the embodiment of the present application, 27 hours is taken as an example.
Step S104, sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of the battery cells in the target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics.
In the technical scheme provided in the above step S104, the lithium analysis prediction model uses the plurality of groups of target standing data obtained in the step S102 to determine the lithium analysis characteristics of the battery cells in the target battery as characteristic input, and obtains at least one prediction result corresponding to output, wherein the prediction results are all values within 0-1, namely prediction probability values, so that the prediction probability values can be converted into classification labels for identifying whether the lithium analysis phenomenon occurs in the target battery, for example, if the prediction result is less than or equal to 0.5, the lithium analysis phenomenon does not occur in the target battery, and the labels 0 are marked on the lithium analysis phenomenon; if the predicted result is more than 0.5, the lithium precipitation phenomenon in the target battery is indicated, and the target battery is marked with a label 1. According to the method, whether the lithium precipitation phenomenon occurs in the target battery can be accurately and rapidly judged, and the problems that a large amount of manpower and material resources are consumed in the traditional lithium precipitation detection method and the obtained lithium precipitation detection result is inaccurate are avoided.
And step S106, determining the safety state of the target battery based on at least one prediction result, and executing the control operation corresponding to the safety state.
In the technical scheme provided in the step S106 of the present invention, the safety state of the target battery can be determined according to at least one prediction result output by the lithium analysis prediction model, so as to prevent the target battery from greatly reducing the performance and the service life of the battery due to the lithium analysis phenomenon, and possibly causing combustion, explosion, etc.
In the embodiment of the application, at least one group of target standing data of the target battery in a target time period is obtained, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state. Therefore, whether the lithium precipitation phenomenon occurs in the battery is accurately and rapidly predicted through the analysis prediction model, corresponding management and control measures are adopted when the lithium precipitation occurs in the battery in time, the catastrophic hazard of the battery is avoided, and the technical problem that whether the analysis phenomenon occurs in the battery is difficult to accurately and rapidly find in the related technology, so that the safety of the battery is poor is solved.
The above-described method in this embodiment will be further described below.
As an optional implementation manner, in the technical solution provided in step S104 of the present invention, the training process of the lithium analysis prediction model includes: obtaining a plurality of groups of training samples, wherein each group of training samples comprises a group of first standing data of a first battery in a first time period; determining sample labels corresponding to each group of training samples, wherein the sample labels are used for marking whether lithium precipitation occurs in the first battery in a first time period; and carrying out K-fold cross validation on the initial prediction model according to the plurality of groups of training samples and sample labels, and adjusting model parameters of the initial prediction model to obtain the lithium analysis prediction model.
In this embodiment, since the artificial neural network (Artificial Netural Network, ANN) has advantages of self-learning ability, associative memory ability, high-speed optimizing ability, and the like, the initial prediction model in the present application may be an artificial neural network model, and it should be noted that the selection of the initial prediction model is not specifically limited in the present application.
In addition, as the prediction model is divided into the training set and the test set to have an important influence on the final effect of the model during training, the method for dividing the optimal training set and the test set can be adopted in the application, namely, K-fold cross validation is adopted to adjust model parameters of the initial prediction model, so that each training sample is ensured to participate in training of the model and is tested, generalization errors are reduced, and meanwhile, the model effect is improved, wherein the value of K can be selected according to actual conditions.
Specifically, the relevant parameters of the artificial neural network model may be set according to table 1 to ensure that the output result accuracy of the established lithium analysis prediction model is maximized, as shown in table 1.
TABLE 1
Optionally, at least one set of first state parameters of the first battery in the first period of time is acquired, wherein the first state parameters include: the method comprises the steps of (1) a state of charge of a first battery, a voltage value of an electric core in the first battery and a total current value of the first battery; preprocessing each set of first state parameters to obtain at least one set of second state parameters, wherein the preprocessing comprises the following steps: cleaning and normalizing; and for each group of second state parameters, determining whether the first battery is in a fully charged static state according to the state of charge and the total current value in the second state parameters, and if so, taking the voltage value of the battery core in the first battery in the second state parameters as a group of training samples.
For example, at least one set of first state parameters of the first battery in a first period of time is first obtained, wherein each set of first state parameters includes: timestamp information, cell voltage (i.e., the voltage of each cell in the battery), total battery current, and battery SOC.
Then, since each item of data in the first state parameter obtained from the voltage management system is chaotic and not comprehensive enough, information cannot be effectively identified and extracted from the first state parameter during model training, so that the effectiveness, repeatability and generalization capability of model prediction are affected, and the quality of the pre-trained lithium-ion prediction model is affected, therefore, the model can be further preprocessed, wherein preprocessing operations include, but are not limited to, clearing error values and abnormal values in the first state parameter, normalizing the first state parameter and the like. Thus, at least one set of second state parameters after the pretreatment is represented by table 2.
TABLE 2
| Time stamp information | Monomer voltage | Total current | SOC |
| 2022-02-28 00:05:07 | [4.1,4.1,4.0,...] | -7 | 68 |
| 2022-03-01 00:05:07 | [4.0,4.0,4.0,...] | 0 | 99 |
| 2022-03-01 06:12:05 | [4.0,4.0,4.0,...] | 8 | 72 |
| …… | …… | …… | …… |
| 2022-03-02 03:10:16 | [3.8,3.7,4.0,...] | 0 | 98 |
As can be seen from table 2, for each row of data (i.e., each set of second state parameters), when the SOC is greater than 98 and the total current value is equal to 0, the first battery is determined to be in a fully charged rest state, and the voltage value of the battery cell in the first rest period after the first battery is fully charged is taken as a set of training samples, so that multiple sets of training samples in the training process of the lithium analysis prediction model can be obtained.
Optionally, for each set of training samples, determining whether the first battery generates a lithium precipitation phenomenon in a time period corresponding to the training samples by using a target method, so as to obtain a sample label corresponding to the training samples, wherein the target method comprises at least one of the following steps: cell disassembly, cell expansion, and three electrode methods.
Specifically, for each set of training samples, a cell disassembly method is adopted to determine whether a lithium precipitation phenomenon occurs in a time period corresponding to the training samples in the first battery, fig. 2 is a schematic diagram of an optional cell according to an embodiment of the present application, as can be seen from fig. 2, if a local lithium precipitation exists at a winding position of the cell, a sample label corresponding to the set of training samples is marked as 1; otherwise, it is marked as 0.
For example, the sample labels of the cells in table 2 were determined as described above, so that it was visually seen from table 3 whether or not lithium precipitation occurred in the cells in the battery, as shown in table 3.
TABLE 3 Table 3
| Time stamp information | Monomer voltage | Total current | SOC | Status of | Lithium precipitation |
| 2022-02-28 00:05:07 | [4.1,4.1,4.0,...] | -7 | 68 | 1 | [1,0,0,…,1] |
| 2022-03-01 00:05:07 | [4.0,4.0,4.0,...] | 0 | 99 | 0 | [1,0,0,...1,] |
| 2022-03-01 06:12:05 | [4.0,4.0,4.0,...] | 8 | 72 | 2 | [0,...,1,0,...] |
| …… | …… | …… | …… | …… | …… |
| 2022-03-02 03:10:16 | [3.8,3.7,4.0,...] | 0 | 98 | 0 | [0,...,1,0,...] |
Optionally, after obtaining the prediction result through the lithium analysis prediction model, verifying the prediction result through a cell disassembly method.
For example, a plurality of electric cores with predicted lithium precipitation and longer lithium precipitation time are selected as the disassembly objects, and whether the selected electric cores are subjected to lithium precipitation is verified by a disassembly method, as shown in table 4, 6 electric cores are randomly selected as the disassembly objects, and the disassembly results shown in table 4 are respectively obtained.
TABLE 4 Table 4
| Battery cell serial number (virtual) | Accumulating lithium-separating time | Disassembly results |
| 1 | 1117 | Local lithium evolution at 70 large faces or windings |
| 2 | 958 | Local lithium evolution at 57 large faces or windings |
| 3 | 885 | The tiny local lithium precipitation exists at 20 large surfaces |
| 4 | 824 | Local lithium evolution at 25 large faces or windings |
| 5 | 677 | Local lithium evolution at 41 large faces or windings |
| 6 | 375 | The existence of tiny local lithium precipitation at 14 large faces |
As an optional implementation manner, in the technical solution provided in step S104 of the present invention, the method further includes: calculating a differential value of the voltage of the battery core in the target battery by using a differential voltage method in the lithium analysis prediction model; determining a lithium analysis characteristic of the battery cell in the target battery based on the differential value, wherein the lithium analysis characteristic comprises the following steps: the first voltage value at the peak position of the corresponding voltage change curve, the first differential value of the first voltage value, the first difference value of the first voltage differential value and the first differential value, the second voltage value at the trough position of the corresponding voltage change curve, the second difference value of the second voltage value and the first voltage value, and the duration of the first time when the voltage reaches the trough position and the standing start time.
In the embodiment, the lithium analysis prediction model calculates a first-order differential value, a second-order differential value and a third-order differential value of the voltage of the battery cell in the target battery by using a differential voltage method, and determines the lithium analysis characteristic of the battery cell in the target battery based on the first-order differential value, the second-order differential value and the third-order differential value. In general, if a lithium precipitation phenomenon does not occur in a battery, the open circuit voltage of the battery tends to decay exponentially just after the end of charging. The dynamic voltage curve can be analyzed by an equivalent circuit. If the battery is lithium-precipitating, lithium precipitated during the relaxation time is continuously intercalated into the graphite layer, thereby increasing LiC 6 Is a concentration of (3). Therefore, a differential voltage method is adopted in the relaxation process, so that the analysis of the voltage change condition of the battery in a standing state is facilitated.
For example, the lithium analysis prediction model calculates a first-order differential value, a second-order differential value and a third-order differential value of the voltage of the battery cell in the target battery by using a differential voltage method, determines the trough position and the peak position of the dynamic voltage curve according to the first-order differential value, the second-order differential value and the third-order differential value, and calculates relevant lithium analysis characteristics according to each data in table 1 to obtain the lithium analysis characteristics shown in table 5.
TABLE 5
As an optional implementation manner, in the technical solution provided in step S106 of the present invention, the method includes: calculating a safety index of the target battery in the first time period based on at least one group of target standing data and at least one prediction result, wherein the safety index comprises: the method comprises the steps of a first time period when a target battery generates a lithium precipitation phenomenon, a first time period when the target battery generates the lithium precipitation phenomenon in a full charge of target times, a first average time period when the target battery generates the lithium precipitation phenomenon, and a difference value between a second average time period when the target battery generates the lithium precipitation phenomenon in the full charge of target times and the first average time period; when the first time length is larger than a first preset threshold value, the first time number is larger than a second preset threshold value, the first average time length is larger than a third preset threshold value and the difference value is larger than a fourth preset threshold value, determining that the target battery is in an abnormal state, and executing management and control operation corresponding to the abnormal state; otherwise, determining that the target battery is in a safe state.
Optionally, when the target battery is in an abnormal state, sending out early warning prompt information, wherein the early warning prompt information is used for prompting the occurrence of lithium precipitation phenomenon in the target battery.
In this embodiment, after determining whether lithium precipitation occurs in the target battery according to the plurality of prediction results, a safety index for safety warning may be calculated according to a plurality of sets of target rest data, where, by counting a duration from a time when the target battery is in a state of lithium precipitation, after a single charge is completed to a position of a trough in a first rest period as a single lithium precipitation duration, the accumulated lithium precipitation duration (i.e., a first duration) of the target battery in a target time is counted; counting the first times of the lithium precipitation phenomenon of the target battery in the target times of charging, for example, counting the times of the lithium precipitation phenomenon of the target battery in the last ten times of charging; counting the number of times of lithium precipitation of the target battery in the target time, and calculating the accumulated average lithium precipitation amount (namely the first average time length) according to the first time length and the lithium precipitation number; and counting the accumulated lithium precipitation amount of the lithium precipitation phenomenon of the target battery in the target times of charging, calculating the average lithium precipitation amount (namely the second average time length) according to the accumulated lithium precipitation amount and the first time number, and then calculating the difference value between the second average time length and the first average time length. By using the indexes as the safety indexes and comparing the safety indexes with a preset threshold value of the system, the safety state of the target battery can be judged, and the management and control operation corresponding to the safety state is selected, so that the safety of the target battery is ensured. In addition, when the target battery is in an abnormal state, the safety early warning information related to the target battery can be stored, so that related technicians can conveniently carry out safety control on the target battery according to the historical safety early warning information of the target battery.
It should be noted that, the above-determined safety index is updated continuously according to the obtained target standing data, and is not accumulated. In addition, the setting of each preset threshold is not particularly limited herein.
For example, when the first time length in the safety index of a certain battery is greater than 4000min, the first time number is greater than 6 times, the first average time length is greater than 60min and the difference is greater than 5min, determining that the battery is in an abnormal state, and outputting corresponding safety early warning prompt information to prompt a relevant technician that the battery may have lithium precipitation; otherwise, the battery is in a normal state, and no management and control measures are temporarily taken for the battery. In addition, the safety early warning prompt information of the battery is stored, the stored historical safety early warning information corresponding to the battery is read, and if the time that the accumulation of the battery cells in the battery does not exceed the preset threshold value exceeds 90 days, the battery does not send relevant safety early warning information about the battery cells any more, and the early warning battery cell serial number in the past early warning information is modified; if the accumulation of all the battery cells in the battery is no longer more than 90 days, the battery does not send out safety early warning information any more, and the early warning ending time in the history early warning information is modified to be 90 days before.
In the steps, the lithium analysis characteristics of the battery after being charged are scientifically, accurately and in detail described by detecting the voltage change of the battery after being charged based on the lithium analysis principle and adopting a differential voltage method; the target standing data is obtained based on big data analysis, and whether the lithium precipitation phenomenon occurs in the battery is predicted and predicted efficiently by establishing a lithium precipitation prediction model, so that the problems of high energy consumption, poor effectiveness and the like caused by traditional lithium precipitation detection can be solved effectively; the safety index for safety early warning is determined through a plurality of prediction results and target standing data output by the lithium analysis prediction model, so that relevant technicians can rapidly conduct safety control on the battery according to the safety index data, and the safety and the service life of the battery are effectively improved.
Example 2
According to an embodiment of the present application, there is further provided a battery safety control device for implementing the above battery safety control method, and fig. 3 is a schematic structural diagram of an alternative battery safety control device according to an embodiment of the present application, as shown in fig. 3, where the battery safety control device at least includes an obtaining module 31, a predicting module 32, and a control module 33, where:
the obtaining module 31 is configured to obtain at least one set of target rest data of the target battery in a target period, where each set of target rest data is configured to reflect a voltage state of a battery cell in the target battery in a first rest period after the target battery is fully charged.
The target standing data is determined by acquiring target state parameters of a target battery from a BMS (Battery Management System ), wherein the BMS is used for intelligently managing and maintaining the battery by monitoring the state of the battery, and preventing the battery from being charged and discharged, so that the service life of the battery is prolonged. When the target State parameter of the target battery is determined, determining that the target battery is in a fully charged standing State when the SOC (State of Charge) in the target State parameter of the target battery is greater than or equal to 98 and the total current of the battery is equal to zero, and taking the voltage of the battery cell of the target battery in the first standing time period after the full Charge as target standing data. The target time period may be determined by itself according to practical situations, and is not limited herein, and in the embodiment of the present application, 27 hours is taken as an example.
The prediction module 32 is configured to sequentially input at least one set of target rest data into a pre-trained lithium-precipitation prediction model, so as to obtain at least one prediction result output by the lithium-precipitation prediction model, where the lithium-precipitation prediction model is configured to determine a lithium-precipitation characteristic of an electrical core in the target battery according to the target rest data, and predict whether the target battery generates a lithium-precipitation phenomenon according to the lithium-precipitation characteristic.
The lithium analysis prediction model takes the lithium analysis characteristics of the battery cells in the target battery determined by the multiple groups of target standing data acquired by the acquisition module 31 as characteristic input, and obtains at least one prediction result corresponding to output, wherein the prediction results are all values within 0-1, namely prediction probability values, so that the prediction probability values can be converted into classification labels for identifying whether lithium analysis occurs in the target battery, for example, if the prediction result is less than or equal to 0.5, the lithium analysis does not occur in the target battery, and the labels are marked with labels 0; if the predicted result is more than 0.5, the lithium precipitation phenomenon in the target battery is indicated, and the target battery is marked with a label 1. According to the method, whether the target battery generates the lithium precipitation phenomenon can be accurately and rapidly judged, and the problems that a large amount of manpower and material resources are consumed, and the obtained lithium precipitation detection result is inaccurate in the traditional lithium precipitation detection method are avoided
As an alternative embodiment, the training process of the lithium analysis prediction model includes: obtaining a plurality of groups of training samples, wherein each group of training samples comprises a group of first standing data of a first battery in a first time period; determining sample labels corresponding to each group of training samples, wherein the sample labels are used for marking whether lithium precipitation occurs in the first battery in a first time period; and carrying out K-fold cross validation on the initial prediction model according to the plurality of groups of training samples and sample labels, and adjusting model parameters of the initial prediction model to obtain the lithium analysis prediction model.
In this embodiment, since the artificial neural network (Artificial Netural Network, ANN) has advantages of self-learning ability, associative memory ability, high-speed optimizing ability, and the like, the initial prediction model in the present application may be an artificial neural network model, and it should be noted that the selection of the initial prediction model is not specifically limited in the present application.
In addition, as the prediction model is divided into the training set and the test set to have an important influence on the final effect of the model during training, the method for dividing the optimal training set and the test set can be adopted in the application, namely, K-fold cross validation is adopted to adjust model parameters of the initial prediction model, so that each training sample is ensured to participate in training of the model and is tested, generalization errors are reduced, and meanwhile, the model effect is improved, wherein the value of K can be selected according to actual conditions.
Specifically, the parameters related to the manual application network model may be set as follows: the number of Hidden layers (Hidden layers) is set as one; the number of the neurons is 30, wherein each neuron is a multiple-input single-output unit; 900 data are processed in each batch; the K value of the K-fold cross validation parameter is 10; the iteration times are 200, so that the accuracy of the output result of the lithium-ion prediction model established by the artificial neural network model can be ensured to be up to 99.1%.
Optionally, at least one set of first state parameters of the first battery in the first period of time is acquired, wherein the first state parameters include: the method comprises the steps of (1) a state of charge of a first battery, a voltage value of an electric core in the first battery and a total current value of the first battery; preprocessing each set of first state parameters to obtain at least one set of second state parameters, wherein the preprocessing comprises the following steps: cleaning and normalizing; and for each group of second state parameters, determining whether the first battery is in a fully charged static state according to the state of charge and the total current value in the second state parameters, and if so, taking the voltage value of the battery core in the first battery in the second state parameters as a group of training samples.
Optionally, for each set of training samples, determining whether the first battery generates a lithium precipitation phenomenon in a time period corresponding to the training samples by using a target method, so as to obtain a sample label corresponding to the training samples, wherein the target method comprises at least one of the following steps: cell disassembly, cell expansion, and three electrode methods.
Specifically, for each group of training samples, a battery cell disassembly method is adopted to judge whether the lithium precipitation phenomenon occurs in the first battery in a time period corresponding to the training samples.
Optionally, for each set of training samples, determining whether the first battery generates a lithium precipitation phenomenon in a time period corresponding to the training samples by using a target method, so as to obtain a sample label corresponding to the training samples, wherein the target method comprises at least one of the following steps: cell disassembly, cell expansion, and three electrode methods.
As another alternative embodiment, the lithium separation characteristic of the cell in the target battery may be obtained by: calculating a differential value of the voltage of the battery core in the target battery by using a differential voltage method in the lithium analysis prediction model; determining a lithium analysis characteristic of the battery cell in the target battery based on the differential value, wherein the lithium analysis characteristic comprises the following steps: the first voltage value at the peak position of the corresponding voltage change curve, the first differential value of the first voltage value, the first difference value of the first voltage differential value and the first differential value, the second voltage value at the trough position of the corresponding voltage change curve, the second difference value of the second voltage value and the first voltage value, and the duration of the first time when the voltage reaches the trough position and the standing start time.
In addition, after the prediction result is obtained through the lithium analysis prediction model, the prediction result can be verified through a cell disassembly method.
And a management and control module 33 for determining a safety state of the target battery based on at least one prediction result and performing a management and control operation corresponding to the safety state.
As an alternative embodiment, the control module 33 may control the target battery according to the following rules: calculating a safety index of the target battery in the first time period based on at least one group of target standing data and at least one prediction result, wherein the safety index comprises: the method comprises the steps of a first time period when a target battery generates a lithium precipitation phenomenon, a first time period when the target battery generates the lithium precipitation phenomenon in a full charge of target times, a first average time period when the target battery generates the lithium precipitation phenomenon, and a difference value between a second average time period when the target battery generates the lithium precipitation phenomenon in the full charge of target times and the first average time period; when the first time length is larger than a first preset threshold value, the first time number is larger than a second preset threshold value, the first average time length is larger than a third preset threshold value and the difference value is larger than a fourth preset threshold value, determining that the target battery is in an abnormal state, and executing management and control operation corresponding to the abnormal state; otherwise, determining that the target battery is in a safe state.
Optionally, when the target battery is in an abnormal state, sending out early warning prompt information, wherein the early warning prompt information is used for prompting the occurrence of lithium precipitation phenomenon in the target battery.
In this embodiment, after determining whether lithium precipitation occurs in the target battery according to the plurality of prediction results, a safety index for safety warning may be calculated according to a plurality of sets of target rest data, where, by counting a duration from a time when the target battery is in a state of lithium precipitation, after a single charge is completed to a position of a trough in a first rest period as a single lithium precipitation duration, the accumulated lithium precipitation duration (i.e., a first duration) of the target battery in a target time is counted; counting the first times of the lithium precipitation phenomenon of the target battery in the target times of charging, for example, counting the times of the lithium precipitation phenomenon of the target battery in the last ten times of charging; counting the number of times of lithium precipitation of the target battery in the target time, and calculating the accumulated average lithium precipitation amount (namely the first average time length) according to the first time length and the lithium precipitation number; and counting the accumulated lithium precipitation amount of the lithium precipitation phenomenon of the target battery in the target times of charging, calculating the average lithium precipitation amount (namely the second average time length) according to the accumulated lithium precipitation amount and the first time number, and then calculating the difference value between the second average time length and the first average time length. By using the indexes as the safety indexes and comparing the safety indexes with a preset threshold value of the system, the safety state of the target battery can be judged, and the management and control operation corresponding to the safety state is selected, so that the safety of the target battery is ensured. In addition, when the target battery is in an abnormal state, the safety early warning information related to the target battery can be stored, so that related technicians can conveniently carry out safety control on the target battery according to the historical safety early warning information of the target battery.
In addition, the determined safety index is updated continuously according to the obtained target standing data without accumulation, and the setting of each preset threshold is not particularly limited in the embodiment of the present application.
It should be noted that, each module in the battery safety control device in the embodiment of the present application corresponds to each implementation step of the battery safety control method in embodiment 1 one by one, and since the embodiment 1 has been described in detail, some details not shown in the embodiment may refer to embodiment 1, and will not be described in detail here.
Example 3
According to an embodiment of the present application, there is further provided a nonvolatile storage medium including a stored program, where a device in which the nonvolatile storage medium is located executes the battery safety management method in embodiment 1 by running the program.
Optionally, the device where the nonvolatile storage medium is located performs the following steps by running the program: acquiring at least one group of target standing data of the target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state.
According to an embodiment of the present application, there is also provided a processor for running a program, wherein the program executes the battery safety management method in embodiment 1.
Optionally, the program execution realizes the following steps: acquiring at least one group of target standing data of the target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state.
According to an embodiment of the present application, there is also provided an electronic device including: a memory and a processor, wherein the memory stores a computer program, the processor is configured to execute the battery safety management method in embodiment 1 by the computer program.
Optionally, the processor is configured to implement the following steps by computer program execution: acquiring at least one group of target standing data of the target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged; sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of a battery cell in a target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics; and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of units may be a logic function division, and there may be another division manner in actual implementation, for example, multiple units 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 through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present 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 integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution, in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (10)
1. A battery safety control method, comprising:
acquiring at least one group of target standing data of a target battery in a target time period, wherein each group of target standing data is used for reflecting the voltage state of a battery core in the target battery in a first standing time period after the target battery is fully charged;
sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining lithium-precipitation characteristics of an electric core in the target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon of the target battery occurs according to the lithium-precipitation characteristics;
and determining the safety state of the target battery based on at least one prediction result, and executing a management and control operation corresponding to the safety state.
2. The method of claim 1, wherein the training process of the lithium analysis prediction model comprises:
obtaining a plurality of groups of training samples, wherein each group of training samples comprises a group of first standing data of a first battery in a first time period;
determining sample labels corresponding to each group of training samples, wherein the sample labels are used for marking whether the lithium precipitation phenomenon of the first battery occurs in the first time period;
and carrying out K-fold cross validation on an initial prediction model according to a plurality of groups of training samples and sample labels, and adjusting model parameters of the initial prediction model to obtain the lithium-ion analysis prediction model.
3. The method of claim 2, wherein obtaining a plurality of sets of training samples comprises:
acquiring at least one group of first state parameters of the first battery in the first time period, wherein the first state parameters comprise: the state of charge of the first battery, the voltage value of the battery core in the first battery and the total current value of the first battery;
preprocessing each set of the first state parameters to obtain at least one set of second state parameters, wherein the preprocessing comprises the following steps: cleaning and normalizing;
And for each group of the second state parameters, determining whether the first battery is in a fully charged standing state according to the charge state and the total current value in the second state parameters, and if so, taking the voltage value of the battery core in the first battery in the second state parameters as a group of the training samples.
4. The method of claim 2, wherein determining a sample tag corresponding to each set of the training samples comprises:
for each group of training samples, determining whether the first battery generates a lithium precipitation phenomenon in a time period corresponding to the training samples by adopting a target method to obtain the sample label corresponding to the training samples, wherein the target method comprises at least one of the following steps: cell disassembly, cell expansion, and three electrode methods.
5. The method of claim 1, wherein determining the lithium evolution characteristics of the cells within the target cell based on the target rest data comprises:
the lithium analysis prediction model calculates a differential value of the voltage of the battery core in the target battery by adopting a differential voltage method;
determining a lithium analysis characteristic of the battery cell in the target battery based on the differential value, wherein the lithium analysis characteristic comprises the following steps: the voltage measuring device comprises a first voltage value at a peak position corresponding to a voltage change curve, a first-order differential value of the first voltage value, a first difference value of the first voltage differential value and the first-order differential value, a second voltage value at a trough position corresponding to the voltage change curve, a second difference value of the second voltage value and the first voltage value, and a duration of a first time and a standing start time when the voltage reaches the trough position.
6. The method of claim 1, wherein determining a safety state of the target battery based on at least one of the prediction results and performing a management operation corresponding to the safety state, comprises:
calculating a safety index of the target battery in the target time period based on the at least one group of target standing data and the at least one prediction result, wherein the safety index comprises the following components: the method comprises the steps of generating a first time length of a lithium precipitation phenomenon of a target battery, generating a first time number of the lithium precipitation phenomenon of the target battery in a target time number full charge, generating a first average time length of the lithium precipitation phenomenon of the target battery, generating a difference value between a second average time length of the lithium precipitation phenomenon of the target battery in the target time number full charge and the first average time length;
when the first time length is larger than a first preset threshold value, the first times are larger than a second preset threshold value, the first average time length is larger than a third preset threshold value and the difference value is larger than a fourth preset threshold value, determining that the target battery is in an abnormal state, and executing a management and control operation corresponding to the abnormal state;
otherwise, determining that the target battery is in a safe state.
7. The method of claim 6, wherein determining that the target battery is in the abnormal state and performing a management operation corresponding to the abnormal state comprises:
and when the target battery is in the abnormal state, sending out early warning prompt information, wherein the early warning prompt information is used for prompting the occurrence of the lithium precipitation phenomenon in the target battery.
8. A battery safety control device, comprising:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring at least one group of target standing data of a target battery in a standing target time period, wherein each group of target standing data is used for reflecting the voltage change state of a battery cell in the target battery in the target standing time period in a first standing time period after the target battery is fully charged;
the prediction module is used for sequentially inputting at least one group of target standing data into a pre-trained lithium-precipitation prediction model to obtain at least one prediction result output by the lithium-precipitation prediction model, wherein the lithium-precipitation prediction model is used for determining the lithium-precipitation characteristics of the battery cells in the target battery according to the target standing data and predicting whether the lithium-precipitation phenomenon occurs in the target battery according to the lithium-precipitation characteristics;
And the control module is used for determining the safety state of the target battery based on at least one prediction result and executing control operation corresponding to the safety state.
9. A nonvolatile storage medium, characterized in that the nonvolatile storage medium includes a stored program, wherein a device in which the nonvolatile storage medium is located executes the battery safety management method according to any one of claims 1 to 7 by running the program.
10. An electronic device, comprising: a memory and a processor, wherein the memory has stored therein a computer program configured to execute the battery safety management method of any one of claims 1 to 7 by the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310217100.9A CN116298910A (en) | 2023-03-07 | 2023-03-07 | Battery safety control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310217100.9A CN116298910A (en) | 2023-03-07 | 2023-03-07 | Battery safety control method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116298910A true CN116298910A (en) | 2023-06-23 |
Family
ID=86835537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310217100.9A Pending CN116298910A (en) | 2023-03-07 | 2023-03-07 | Battery safety control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116298910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521857A (en) * | 2024-01-05 | 2024-02-06 | 宁德时代新能源科技股份有限公司 | Battery cell lithium analysis method and device, readable storage medium and electronic equipment |
-
2023
- 2023-03-07 CN CN202310217100.9A patent/CN116298910A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117521857A (en) * | 2024-01-05 | 2024-02-06 | 宁德时代新能源科技股份有限公司 | Battery cell lithium analysis method and device, readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN110224192B (en) | Method for predicting service life of power battery by gradient utilization | |
| CN109655754B (en) | Battery performance evaluation method based on multi-dimensional grading of charging process | |
| CN112092675A (en) | Battery thermal runaway early warning method, system and server | |
| CN103954913B (en) | Electric automobile power battery life-span prediction method | |
| CN111584952A (en) | Method and system for online evaluation of electrochemical cells of energy storage power station | |
| CN111257775A (en) | Method, system and device for monitoring battery impedance abnormity based on charging process | |
| CN109604186A (en) | Power battery performance flexibility assesses method for separating | |
| CN112946483B (en) | Comprehensive evaluation method for battery health of electric vehicle and storage medium | |
| CN108732510A (en) | Lithium ion battery conformity classification group technology based on internal feature | |
| CN114818831B (en) | Bidirectional lithium ion battery fault detection method and system based on multi-source perception | |
| CN116401585B (en) | Energy storage battery failure risk assessment method based on big data | |
| CN116298910A (en) | Battery safety control method and device | |
| CN113657360A (en) | Lithium battery health state estimation method, device, equipment and readable storage medium | |
| CN111983474A (en) | Lithium ion battery life prediction method and system based on capacity decline model | |
| CN114720899A (en) | Retired battery echelon utilization and sorting method and system, electronic equipment and storage medium | |
| CN116381541A (en) | Health assessment method and system for energy storage lithium battery system | |
| CN114578251A (en) | Battery module safety state evaluation method and device based on convolutional neural network | |
| Sohn et al. | CNN-based Online Diagnosis of Knee-point in Li-ion Battery Capacity Fade Curve | |
| CN116956639B (en) | High-heat-dissipation storage battery assessment method and system based on data analysis | |
| KR102159817B1 (en) | Energy storage device through deep learning operation method and recording medium storing program for executing the same, and computer program stored in recording medium for executing the same | |
| CN113702844B (en) | Method for evaluating influence of feedback overcharge behavior of whole vehicle on service life of battery | |
| CN116819328A (en) | Electric automobile power battery fault diagnosis method, system, equipment and medium | |
| CN115128468A (en) | Chemical energy storage battery PHM undervoltage fault prediction method | |
| CN112485694B (en) | Battery pack detection method and device |
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 |