CN116794533A

CN116794533A - Battery cell capacity grading method and related products

Info

Publication number: CN116794533A
Application number: CN202311048823.7A
Authority: CN
Inventors: 蔡翔; 吴长风
Original assignee: Shenzhen Haichen Energy Storage Control Technology Co ltd; Xiamen Hithium Energy Storage Technology Co Ltd
Current assignee: Shenzhen Haichen Energy Storage Control Technology Co ltd; Xiamen Hithium Energy Storage Technology Co Ltd
Priority date: 2023-08-21
Filing date: 2023-08-21
Publication date: 2023-09-22
Anticipated expiration: 2043-08-21
Also published as: CN116794533B

Abstract

The application relates to a battery cell capacity grading method and a related product. The method comprises the following steps: acquiring a target cell; performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, and the second voltage is larger than a preset voltage value; and inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell. By adopting the method, the formation data and the partial capacity data can be obtained by only carrying out formation operation and partial capacity division operation on the target battery core, the capacity shift of the target battery core can be obtained through the battery core capacity shift model, the battery core capacity can be shifted without completely discharging the battery core, the time and the electric quantity consumption of the capacity shift process are obviously shortened, and the improvement of the production efficiency of the battery core is facilitated.

Description

Battery cell capacity grading method and related products

Technical Field

The application relates to the technical field of data processing, in particular to a battery cell capacity grading method and a related product.

Background

With the rapid development of electronic industry technology and the rapid improvement of the living standard of people, more and more electronic products are emerging on the market. Accordingly, the demand of rechargeable batteries is also increasing, which is a great challenge for the cell manufacturers.

In the process of producing the battery cells, the step-by-step according to the capacity of the battery cells is an important production link. At present, when a battery cell manufacturer grades battery cells according to capacity, the battery cells are graded in a full capacity mode, namely, the battery cells are fully charged and then fully discharged to count the fully discharged capacity, the battery cells are graded according to the fully discharged capacity, and finally, the battery cells are charged to finish battery cell shipment. Obviously, the current battery cell capacity grading process is long in time consumption, and is unfavorable for improving the production efficiency of the battery cells.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a battery cell capacity grading method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the battery cell production efficiency.

In a first aspect, the present application provides a method for battery cell capacity grading. The method comprises the following steps:

Acquiring a target cell;

performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, and the second voltage is larger than a preset voltage value;

and inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell.

In a second aspect, the application further provides a battery cell capacity grading device. The device comprises:

the acquisition module is used for acquiring the target battery cell;

the execution module is used for executing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, and the second voltage is larger than a preset voltage value;

and the input module is used for inputting the formation data and partial capacity-dividing data of the target battery cell into the battery cell capacity grading model to obtain the capacity gear of the target battery cell.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

acquiring a target cell;

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

acquiring a target cell;

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

acquiring a target cell;

The battery cell capacity grading method, the battery cell capacity grading device, the computer equipment, the storage medium and the computer program product acquire a target battery cell; performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, and the second voltage is larger than a preset voltage value; and inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell. By adopting the method provided by the embodiment of the application, the formation operation is carried out on the target battery cell, and only partial capacity division operation is carried out, so that the capacity shift of the target battery cell can be obtained by inputting the formation data and the partial capacity division data of the target battery cell into the battery cell capacity shift model, the capacity of the battery cell can be shifted without completely discharging the battery cell, the time and the electric quantity consumption of the capacity shift process are obviously shortened, and the improvement of the production efficiency of the battery cell is facilitated.

Drawings

FIG. 1 is an application environment diagram of a battery cell capacity grading method in one embodiment;

FIG. 2 is a flow chart of a method of battery capacity staging in one embodiment;

FIG. 3 is a flow chart of a method for battery capacity grading in another embodiment;

FIG. 4 is a block diagram of a battery cell capacity stepper in one embodiment;

FIG. 5 is a block diagram of a battery cell capacity step device according to another embodiment;

FIG. 6 is an internal block diagram of a computer device in one embodiment;

fig. 7 is an internal structural view of a computer device in another embodiment.

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 specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

It should be noted that in the following description, the terms "first, second and third" are used merely to distinguish similar objects and do not represent a specific order for the objects, it being understood that the "first, second and third" may be interchanged with a specific order or sequence, if allowed, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.

The battery cell capacity grading method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server.

The terminal 102 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, an internet of things device, and a portable wearable device, and the internet of things device may be a smart speaker, a smart television, a smart air conditioner, and a smart vehicle device. The portable wearable device may be a smart watch, smart bracelet, headset, or the like.

The server 104 may be a separate physical server or may be a service node in a blockchain system, where a Peer-To-Peer (P2P) network is formed between service nodes, and the P2P protocol is an application layer protocol that runs on top of a transmission control protocol (TCP, transmission Control Protocol) protocol.

The server 104 may be a server cluster formed by a plurality of physical servers, and may be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

The terminal 102 and the server 104 may be connected by a communication connection manner such as bluetooth, USB (Universal Serial Bus ) or a network, which is not limited herein.

In one embodiment, as shown in fig. 2, there is provided a method for battery capacity grading, which may be performed by a server or a terminal in fig. 1, or by a server and a terminal in cooperation, and which is illustrated by way of example by the terminal in fig. 1, including the steps of:

s202, acquiring a target battery cell.

The battery cell is a component part of a lithium battery, and the lithium battery comprises the battery cell, a protection circuit board and a shell package.

The embodiment of the application can be applied to a control terminal for grading the capacity of the battery cell, and the control terminal is also used for executing formation operation and partial capacity grading operation on the battery cell, so that the target battery cell is the battery cell to be graded, the capacity grade of which is not yet determined.

S204, performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, and the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, wherein the second voltage is larger than a preset voltage value.

The formation operation is an initialization operation of the lithium battery, so that the active substances of the battery core are activated, and the comprehensive performances of the battery core, such as charge and discharge performance, self-discharge, storage and the like, are improved, and the formation operation is an energy conversion process.

And the capacity-dividing operation is to perform charge and discharge operation on the battery core, so that the capacity of the battery is determined by detecting the discharge capacity of the battery when the capacity is divided and fully charged. The partial capacity division operation refers to a part of the complete capacity division operation, that is, the partial capacity division operation does not execute complete full charge and discharge, and finally, the voltage of the battery core is not reduced to the minimum value.

The formation data may include voltage data and temperature data obtained after the formation operation of the target cell.

The partial capacity data can comprise voltage data and temperature data obtained after the target battery cell is subjected to partial capacity operation.

Specifically, the voltage of the target battery cell is reduced from the first voltage to the second voltage which is larger than the preset voltage value, so that only partial capacity division operation is needed to be performed on the target battery cell, and complete capacity division operation is not needed to be performed on the target battery cell to reduce the voltage of the target battery cell to zero, that is, the capacity of the battery cell can be stepped without completely discharging the battery cell, and the time and the electric consumption of the capacity step process are obviously shortened.

S206, inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell.

The battery cell capacity grading model can comprise at least one grading model, so that the battery cell capacity grading model can predict the capacity gear of the target battery cell in a mode that a plurality of grading models are cascaded. The battery cell capacity grading model comprises a main grading model and at least one auxiliary grading model, and the prediction reliability of the main grading model on the capacity gear of the battery cell is higher than that of the auxiliary grading model.

Each capacity shift corresponds to a different cell capacity range, specifically, the cell capacity ranges corresponding to adjacent capacity shifts may be separated by a fixed interval.

For example, if the battery cell capacity ranges from 298 to 308Ah, and the battery cell capacity is graded according to one grade of every 2Ah, the battery cell with the battery cell capacity between 298 to 308Ah can be graded into 5 capacity grades of 0 to 4, the battery cell capacity between 298 to 300Ah is graded into 0, the battery cell capacity between 300 to 302Ah is graded into 1, the battery cell capacity between 302 to 304Ah is graded into 2, the battery cell capacity between 304 to 306Ah is graded into 3, and the battery cell capacity between 306 to 308Ah is graded into 4. Therefore, the battery cell capacity grading model is used for determining the battery cell capacity of the target battery cell according to the formation data and the partial capacity grading data of the target battery cell and then determining the capacity gear of the target battery cell according to the battery cell capacity. It should be noted that, the correspondence between the battery cell capacity range and the capacity shift of the battery cell in the above example is only an example, and is not limited to the correspondence between the battery cell capacity range and the capacity shift of the battery cell.

Further, when the target battery cell is obtained, the target battery cell specification corresponding to the target battery cell and the historical capacity gear corresponding to the historical battery cell with the battery cell specification as the target battery cell specification can be obtained, so that after the capacity gear of the target battery cell is obtained, the capacity gear of the target battery cell is matched with the historical capacity gear to obtain a gear matching result, if the dislocation rate of the gear matching result is greater than or equal to the preset dislocation rate, the terminal can generate a prompting message of the capacity gear of the target battery cell, the prompting message can be used for prompting an operator to carry out the gear grading of the battery cell capacity again on the target battery cell, and the terminal can also automatically execute the steps S202-S206 again to obtain a new capacity gear of the target battery cell and then match the new capacity gear with the historical capacity gear again. The dislocation rate of the matching result= |capacity gear of the target battery cell-history capacity gear|/capacity gear number.

Further, before the target battery cell is obtained, an estimated battery cell capacity range and a target battery cell specification of the target battery cell can be obtained, an estimated capacity gear range of the target battery cell is determined according to the estimated battery cell capacity range and the target battery cell specification, and an output capacity gear of the battery cell capacity grading model is determined as the estimated capacity gear range, so that the battery cell capacity grading model obtains the capacity gear of the target battery cell in the estimated capacity gear range according to formation data and partial capacity data of the target battery cell.

In the battery cell capacity grading method, a target battery cell is obtained; performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, and the second voltage is larger than a preset voltage value; and inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell. By adopting the method provided by the embodiment of the application, the formation operation is carried out on the target battery cell, and only partial capacity division operation is carried out, so that the capacity shift of the target battery cell can be obtained by inputting the formation data and the partial capacity division data of the target battery cell into the battery cell capacity shift model, the capacity of the battery cell can be shifted without completely discharging the battery cell, the time and the electric quantity consumption of the capacity shift process are obviously shortened, and the improvement of the production efficiency of the battery cell is facilitated.

In one embodiment, before the target cell is obtained, the method further includes:

determining at least one classification model;

inputting formation data and partial capacity data of the training battery core into each of at least one grading model to obtain a training capacity gear output by each grading model;

Matching the training capacity gear output by each grading model with the actual capacity gear of the training battery core to obtain a prediction result of each grading model;

and determining a battery cell capacity grading model according to the prediction result of each grading model.

The grading model may include a model for data grading such as lightGBM, XGboost, random Forest, and the like.

In this embodiment, when determining the battery cell capacity grading model, formation data and partial capacity grading data of the training battery cell are input into each grading model in at least one grading model, and the obtained training capacity gear output by each grading model is matched with the actual capacity gear of the training battery cell to obtain a prediction result of each grading model, and finally, the battery cell capacity grading model is determined according to the prediction result of each grading model. The battery cell capacity grading model determined by the embodiment of the application comprises at least one grading model, and the prediction of the capacity gear of the battery cell is determined based on the prediction results of different grading models, so that the accuracy of the battery cell capacity grading model in predicting the capacity gear of the battery cell is improved.

In one embodiment, determining the battery capacity grading model according to the prediction result of each grading model includes:

According to the prediction result of each grading model, determining the probability corresponding to the first prediction correct rate and different dislocation gear numbers of each grading model, the second prediction correct rate corresponding to the multiple confidence intervals and the third prediction correct rate corresponding to different data volume proportions sequenced by the highest confidence interval;

and determining a battery cell capacity grading model according to the first prediction accuracy, the probability, the second prediction accuracy and the third prediction accuracy.

The first prediction accuracy refers to the proportion of the number of the matched training capacity gears which are consistent with the actual capacity gears in the training capacity gears output by the corresponding grading model in the total number of the training capacity gears, that is, the prediction accuracy of the corresponding grading model on the capacity gear grading result of the training battery cell.

The dislocation gear number refers to the phase difference gear number between the training capacity gear number and the actual capacity gear number output by the gear classification model, and the dislocation gear number is = |training capacity gear number-actual capacity gear number|. For example, assuming that the capacity shift is 0 to 4, if the training capacity shift output by the shift model is 1 and the actual capacity shift is 3, the dislocation shift number= |training capacity shift-actual capacity shift|= |1 to 3|=2 at this time.

The probability corresponding to different dislocation gear numbers refers to the proportion of a certain dislocation gear number output by the corresponding gear model in the total number of training capacity gear numbers.

For example, a certain gear-shifting model predicts the capacity gear of 100 training electric cores, the predicted result of 85 training electric cores in the 100 training electric cores is correct, namely, the training capacity gear of 85 training electric cores in 100 training capacity gears output by the gear-shifting model is consistent with the actual capacity gear corresponding to the 85 training electric cores, and the first prediction accuracy of the gear-shifting model is 85%; the predicted result of 10 training cells in 100 training cells is that the dislocation gear number is 1, and the probability corresponding to the stepping model when the dislocation gear number is 1 is 10%.

Confidence, which refers to the prediction reliability of the grading model for a certain capacity gear of the battery cell. Accordingly, the second prediction accuracy rate corresponding to the grading model in the confidence intervals is the second prediction accuracy rate corresponding to the confidence intervals with different sizes in the confidence intervals. For example, in a capacity shift of 100 cells predicted by a certain classification model, the confidence coefficient of 50 cells is greater than 0.8, and 45 cells matched with the actual capacity shift in the 50 cells are provided, then the second prediction accuracy rate=45/50=0.9, that is, the second prediction accuracy rate of the classification model for the confidence coefficient interval with the confidence coefficient of greater than 0.8 is 0.9.

The different data volume ratios of the highest confidence intervals are the data volume ratios corresponding to the highest-ranking confidence intervals in all confidence intervals of the grading model. For example, if the first 60% of data quantity of a certain grading model ordered according to the highest confidence interval is the capacity gear of the predicted 60 electric cores, 50 electric cores matched with the actual capacity gear are included in the 60 electric cores, the third prediction accuracy=50/60≡0.83, that is, the third prediction accuracy corresponding to the first 60% of data quantity proportion of the grading model ordered in the highest confidence interval is 0.83.

Specifically, the battery cell capacity grading model comprises at least one grading model, the first prediction accuracy of each grading model in the at least one grading model is higher than a first preset value, the probability corresponding to the dislocation gear number is lower than a second preset value, the second prediction accuracy is higher than a third preset value, the third prediction accuracy is higher than a fourth preset value, and the first preset value, the third preset value and the fourth preset value are all higher than the second preset value; further, in the probabilities corresponding to different dislocation gear numbers, each of the gear models included in the battery capacity gear model has a negative correlation with the corresponding probability, and for a certain gear model, the probability of the dislocation gear number being 2 is smaller than the probability of the dislocation gear number being 1.

For example, in order to determine to obtain a battery cell capacity grading model, assuming that the battery cell is divided into 5 capacity steps of 0-4, selecting a grading model suitable for smaller training data amount, such as selecting lightGBM, XGboost, logistic Regression and Random Forest, and inputting formation data and partial capacity grading data of the training battery cell into the four grading models respectively to obtain training capacity steps of each grading model in the four grading models; matching the training capacity gear output by each grading model with the actual capacity gear of the training battery core to obtain a prediction result of each grading model; according to the prediction result of each grading model, determining to obtain probabilities respectively corresponding to the first prediction accuracy and the dislocation gear number of each grading model shown in table 1 being 1-4, wherein each grading model shown in table 2 has a second prediction accuracy corresponding to a plurality of confidence intervals of more than 0.6, more than 0.7, more than 0.8, more than 0.9 and more than 0.95, and has a third prediction accuracy respectively corresponding to the data volume proportions of the first 60%, the first 70%, the first 80%, the first 90% and the first 95% of the highest confidence intervals corresponding to each grading model shown in table 3;

Firstly, as can be seen from table 1, the four gear models all show the highest first prediction accuracy, and the probabilities corresponding to different dislocation gear numbers and the dislocation gear number size show negative correlation, so that at this time, the gear prediction of the battery cell capacity by the four gear models can be confirmed to accord with logic, meanwhile, the lightGBM has the highest first prediction accuracy corresponding to the first prediction accuracy, and the probabilities when the dislocation gear number is 1 and 2 are the lowest, and the gear prediction accuracy of the lightGBM can be primarily considered to be the highest;

secondly, if the confidence level of the grading model is considered, the confidence level and the prediction accuracy should show a positive correlation, and as can be seen from table 3, while the confidence level interval increases, only the second prediction accuracy of Logistic Regression is decreasing, that is, the Logistic Regression gear prediction of the battery cell capacity does not accord with the logic level under the condition of considering the confidence level, so that it is determined Logistic Regression is not suitable for predicting the battery cell capacity gear, logistic Regression is removed from the four grading models, and the other three grading models are left;

again, in the data sorted by the highest confidence interval, the prediction accuracy corresponding to the data sorted by the more forward should be higher, that is, the data amount ratio and the third prediction accuracy should show a negative correlation, as can be seen from table 3, as the data amount ratio decreases, the third prediction accuracy of lightGBM, XGboost and Random Forest gradually increases, so far, it can be determined that all three classification models are suitable for performing classification prediction on the battery core capacity, and, by integrating the prediction performance data of tables 1-3, the prediction performance data of lightGBM is optimal, so that the lightGBM is determined as a first classification model, and the XGboost and Random Forest are determined as a second classification model or a third classification model, respectively, and the obtained battery core capacity classification model includes the lightGBM as the first classification model, the XGboost as the second classification model, and the Random Forest as the third classification model, wherein the second classification model and the third classification model can be interchanged;

That is, among the plurality of shift models, after the shift model whose shift prediction for the battery cell capacity does not meet the logic is eliminated, the shift model whose first prediction accuracy is the largest, whose probability corresponding to the different shift numbers is the smallest, whose second prediction accuracy is the largest, and whose third prediction accuracy is the largest is determined as the first shift model, that is, the main shift model of the battery cell capacity shift model, and the other shift models whose remaining shift predictions for the battery cell capacity meet the logic but whose prediction performance data is inferior to the first shift model are determined as the second shift model or the third shift model as the auxiliary shift model.

In this embodiment, the battery cell capacity grading model is not simply provided with the first grading model, because the situation that the value of the prediction accuracy of the battery cell capacity is higher due to the nature of the model is prevented from being caused by the first grading model, so that the second grading model and the third grading model are introduced to play an auxiliary supporting role in battery cell grading prediction, so that the accuracy and the reliability of the battery cell capacity grading model are ensured.

TABLE 1

TABLE 2

TABLE 3 Table 3

In this embodiment, when determining the battery cell capacity grading model according to the prediction result of each grading model, determining the first prediction accuracy of each grading model, the probability corresponding to different dislocation gear numbers, the second prediction accuracy corresponding to the confidence intervals, and the third prediction accuracy corresponding to the different data amount ratios ordered by the highest confidence interval according to the prediction result of each grading model, and finally determining the battery cell capacity grading model with higher prediction accuracy for the capacity gear of the battery cell according to the first prediction accuracy, the probability, the second prediction accuracy and the third prediction accuracy.

In one embodiment, the battery cell capacity grading model includes a first grading model and at least one second grading model.

In one embodiment, the battery capacity grading model includes a first grading model, a second grading model and a third grading model; the step of inputting the formation data and the partial capacity data of the target battery cell into the battery cell capacity grading model to obtain the capacity gear of the target battery cell comprises the following steps:

the formation data and partial capacity division data of the target battery core are respectively input into a first grading model, a second grading model and a third grading model to obtain a first capacity gear corresponding to the first grading model, a second capacity gear corresponding to the second grading model and a third capacity gear corresponding to the third grading model;

if the confidence coefficient of the first capacity gear is larger than or equal to the first preset confidence coefficient, determining that the capacity gear of the target battery cell is the first capacity gear;

if the confidence coefficient of the first capacity gear is smaller than the first preset confidence coefficient, determining the capacity gear of the target battery cell according to the second capacity gear and the third capacity gear.

The first grading model is a main grading model in the battery cell capacity grading model, and the second grading model and the third grading model are auxiliary grading models in the battery cell capacity grading model. Specifically, the prediction accuracy of the first grading model, the probability corresponding to different dislocation gear numbers, the second prediction accuracy corresponding to the multiple confidence intervals and the third prediction accuracy corresponding to different data volume proportions sequenced by the highest confidence intervals are better than the second grading model and the third grading model, that is, the prediction reliability of the first grading model to the capacity gear of the battery core is higher than the second grading model and the third grading model.

For example, the first hierarchical model may be a lightGBM model, and the second and third hierarchical models may be XGboost and Random Forest models.

Exemplarily, assume that the first capacity shift is 1 and the confidence is 0.9; the magnitude of the first preset confidence coefficient can be determined according to the actual battery cell capacity grading requirement condition, so that if the first preset confidence coefficient set by the terminal is 0.8, the confidence coefficient of the first capacity gear is larger than the first preset confidence coefficient at the moment, and the capacity gear of the target battery cell is determined to be the first capacity gear, namely 1; if the first preset confidence coefficient set by the terminal is 0.95, the confidence coefficient of the first capacity gear is smaller than the first preset confidence coefficient, and the capacity gear of the target battery cell is determined to be one gear of the second capacity gear or the third capacity gear.

In this embodiment, since the first gear model serving as the main gear model has a relatively critical prediction decision function, when the confidence coefficient of the first capacity gear corresponding to the first gear model is greater than or equal to a first preset confidence coefficient, the capacity gear of the target battery cell is determined to be the first capacity gear; when the confidence coefficient of the first capacity gear is smaller than the first preset confidence coefficient, the first gear model serving as the main gear model is difficult to ensure the accuracy of the prediction result at the moment, so that the capacity gear of the target battery cell needs to be determined according to the second capacity gear and the third capacity gear at the moment. Therefore, the battery cell capacity grading model has reliability for capacity grading of the target battery cell, and accuracy and reliability of the obtained capacity grade of the target battery cell are improved.

In one embodiment, the determining the capacity shift of the target cell according to the second capacity shift and the third capacity shift includes:

if the second capacity gear is consistent with the third capacity gear, determining that the capacity gear of the target battery cell is the second capacity gear or the third capacity gear;

and if the second capacity gear is inconsistent with the third capacity gear, determining the capacity gear of the target battery cell according to the confidence degree of the second capacity gear and the confidence degree of the third capacity gear.

For example, if the second capacity gear and the third capacity gear are both 2, that is, the second capacity gear is consistent with the third capacity gear, the capacity gear of the target battery cell is determined to be 2; if the second capacity gear is 2 and the third capacity gear is 3, that is, the second capacity gear is inconsistent with the third capacity gear, the capacity gear of the target battery cell is determined according to the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear, and the capacity gear of the target battery cell is determined to be 2 or 3.

In this embodiment, when determining the capacity shift position of the target battery cell according to the second capacity shift position and the third capacity shift position, whether the second capacity shift position is consistent with the third capacity shift position or not is performed, specifically, when the second capacity shift position is consistent with the third capacity shift position, the capacity shift position of the target battery cell is determined to be the second capacity shift position or the third capacity shift position; and when the second capacity gear is inconsistent with the third capacity gear, determining the capacity gear of the target battery cell according to the confidence degree of the second capacity gear and the confidence degree of the third capacity gear. Therefore, the battery cell capacity grading model has reliability for capacity grading of the target battery cell, and accuracy and reliability of the obtained capacity grade of the target battery cell are improved.

In one embodiment, determining the capacity shift of the target cell according to the confidence of the second capacity shift and the confidence of the third capacity shift includes:

if the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both larger than the second preset confidence coefficient, determining whether the second capacity gear and the third capacity gear have the same capacity gear as the first capacity gear or not;

if the capacity gear which is the same as the first capacity gear exists in the second capacity gear and the third capacity gear, determining that the capacity gear of the target battery cell is the first capacity gear;

if the second capacity gear and the third capacity gear do not have the same capacity gear as the first capacity gear, respectively determining products between confidence degrees and prediction accuracy rates of the first gear classification model, the second gear classification model and the third gear classification model, and respectively correspondingly obtaining a first calculation result, a second calculation result and a third calculation result;

and determining the capacity gear predicted by the maximum calculation model corresponding to the maximum calculation result in the first calculation result, the second calculation result and the third calculation result as the capacity gear of the target battery cell.

The second preset confidence level may be smaller than the first preset confidence level.

Specifically, when the same capacity gear as the first capacity gear exists in the second capacity gear and the third capacity gear, it is indicated that the same capacity gear as the first capacity gear exists in the second capacity gear and the third capacity gear, and therefore, the capacity gear of the target battery cell is determined to be the first capacity gear, or the capacity gear of the target battery cell is determined to be the same capacity gear as the first capacity gear in the second capacity gear and the third capacity gear.

Specifically, the product between the confidence degrees and the prediction accuracy rates of the first grading model, the second grading model and the third grading model refers to the product between different confidence degrees and the prediction accuracy rates respectively corresponding to different grading models.

For example, assuming that the first capacity gear is 1 and the confidence coefficient is 0.9, if the confidence coefficient of the second capacity gear is 0.85, the confidence coefficient of the third capacity gear is 0.8, and the second preset confidence coefficient set by the terminal is 0.75, the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both greater than the second preset confidence coefficient, and if the second capacity gear is 1 and the third capacity gear is 3 at this time, the second capacity gear is the same as the first capacity gear at this time, so the capacity gear of the target battery is determined to be 1; if the second capacity gear is 2 and the third capacity gear is 3 at this time, there is no capacity gear identical to the first capacity gear in the second capacity gear and the third capacity gear, then the products between the confidence levels and the prediction accuracy of the first, second and third capacity gears are determined respectively, specifically, assuming that the prediction accuracy of the first capacity gear model is 0.9, the prediction accuracy of the second capacity gear model is 0.85, the prediction accuracy of the third capacity gear model is 0.8, then the prediction accuracy of the first calculation result=0.9×0.81 of the first capacity gear, the prediction accuracy of the second calculation result=0.85×0.85× 0.7225 of the second capacity gear, and the prediction accuracy of the third capacity gear=0.8×0.64 of the third capacity gear, namely, the first calculation result=0.8×0.64 of the third capacity gear, the first calculation result is the maximum calculation result, namely, the first calculation result is the maximum calculation result, and the first calculation result is obviously greater than 1.

In this embodiment, when the confidence coefficient of the first capacity gear is smaller, the second capacity gear is inconsistent with the third capacity gear, and the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both greater than the second preset confidence coefficient, then when the same capacity gear as the first capacity gear exists in the second capacity gear and the third capacity gear, the capacity gear of the target battery is determined to be the first capacity gear, so that even when the confidence coefficient of the first capacity gear is smaller, other capacity gears with higher confidence coefficient and consistent with the first capacity gear can be output as the capacity gear of the target battery; and when the same capacity gear as the first capacity gear does not exist in the second capacity gear and the third capacity gear, respectively determining products among the confidence coefficient and the prediction accuracy of the first gear model, the second gear model and the third gear model, and determining the capacity gear predicted by the maximum calculation model corresponding to the maximum calculation result of the products as the capacity gear of the target battery core, wherein the confidence coefficient of the first capacity gear is smaller, the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are not both larger than the second preset confidence coefficient, and when the same capacity gear as the first capacity gear does not exist in the second capacity gear and the third capacity gear, the confidence coefficient and the prediction accuracy of each gear model can be comprehensively considered, so that the capacity gear of the determined target battery core has higher accuracy and reliability.

if the confidence coefficient of the second capacity gear or the confidence coefficient of the third capacity gear is larger than or equal to the second preset confidence coefficient, determining that the capacity gear of the target battery cell is the corresponding capacity gear with the confidence coefficient in the second capacity gear and the third capacity gear being larger than or equal to the second preset confidence coefficient.

Exemplarily, assuming that the second capacity shift is 2 and the confidence is 0.85, the third capacity shift is 3 and the confidence is 0.8, the second preset confidence set by the terminal is 0.83; at this time, only the confidence coefficient of the second capacity gear is larger than the second preset confidence coefficient in the confidence coefficient of the second capacity gear or the confidence coefficient of the third capacity gear, and then the capacity gear of the target battery cell is determined to be the second capacity gear with the confidence coefficient larger than the second preset confidence coefficient, namely 2.

In this embodiment, when the confidence coefficient of the first capacity gear is smaller, the second capacity gear is inconsistent with the third capacity gear, and the confidence coefficient of the second capacity gear or the confidence coefficient of the third capacity gear is greater than or equal to the second preset confidence coefficient, that is, when the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are not both higher than the second preset confidence coefficient, the corresponding capacity gear with the higher confidence coefficient is determined as the capacity gear of the target battery cell. And when the confidence coefficient of the first capacity gear is smaller, determining the capacity gear with larger confidence coefficient in the second capacity gear and the third capacity gear as the capacity gear of the target battery cell, so that the determined capacity gear of the target battery cell has higher accuracy and reliability.

if the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are smaller than the second preset confidence coefficient, determining whether at least two identical capacity gears exist in the first capacity gear, the second capacity gear and the third capacity gear;

if at least two identical capacity gears exist, determining that the capacity gear of the target battery cell is any one of the at least two identical capacity gears;

and if at least two identical capacity gears do not exist, determining that the capacity gear of the target battery cell is the first capacity gear.

Specifically, in the first capacity shift, the second capacity shift, and the third capacity shift, if there are two capacity shifts that are the same, at least two identical capacity shifts exist at this time. Illustratively, the first capacity shift is 1, the second capacity shift is 2, and the third capacity shift is 1, and it can be seen that at this time, the first capacity shift is the same as the third capacity shift, and then the same capacity shift is 1.

Illustratively, assuming that the confidence level of the second capacity shift is 0.85, the confidence level of the third capacity shift is 0.8, and the second preset confidence level set by the terminal is 0.9; the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are smaller than the second preset confidence coefficient, so that the capacity gear of the target battery cell is determined through majority voting, whether at least two identical capacity gears exist in the first capacity gear, the second capacity gear and the third capacity gear or not is determined, and if the first capacity gear is 1 and the second capacity gear and the third capacity gear are both 2, two identical capacity gears 2 exist at the moment, and therefore the capacity gear of the target battery cell is determined to be 2; if the first capacity gear is 1, the second capacity gear is 2, and the third capacity gear is 3, then each capacity gear is different, that is, at least two identical capacity gears do not exist, so that the capacity gear of the target battery cell is the first capacity gear, that is, 1.

In the embodiment, when the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are smaller than the second preset confidence coefficient, if at least two identical capacity gears exist, the capacity gear of the target battery cell is determined to be any one of the at least two identical capacity gears, so that the obtained capacity gear of the target battery cell is ensured to have higher accuracy and reliability through a majority voting function; and when at least two identical capacity gears do not exist, the first capacity gear output by the first gear-dividing model serving as the main gear-dividing model is determined as the capacity gear of the target battery cell, and the reliability of the prediction of the capacity gear of the battery cell by the main gear-dividing model is higher than that of the auxiliary gear-dividing model, so that the obtained capacity gear of the target battery cell is ensured to have higher accuracy and reliability.

In one embodiment, the formation data is voltage data and temperature data obtained after the formation operation of the target battery cell, and the partial capacity data is voltage data and temperature data obtained after the partial capacity operation of the target battery cell.

The following describes the application process of the battery capacity grading method in combination with a detailed embodiment, specifically as follows: as shown in fig. 3, the battery cell capacity grading method provided by the application is applied to a terminal, and the terminal acquires a target battery cell; performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; inputting formation data and partial capacity grading data of a target battery cell into a battery cell capacity grading model, wherein the battery cell capacity grading model comprises a first grading model, a second grading model and a third grading model, the first grading model is a main grading model, and the second grading model and the third grading model are auxiliary grading models;

Specifically, the formation data and partial capacity division data of the target battery core are respectively input into a first grading model, a second grading model and a third grading model in the battery core capacity grading model to obtain a first capacity gear corresponding to the first grading model, a second capacity gear corresponding to the second grading model and a third capacity gear corresponding to the third grading model; accordingly, whether the confidence coefficient of the first capacity gear is larger than or equal to a first preset confidence coefficient is determined, if yes, the capacity gear of the target battery cell is determined to be the first capacity gear, and if not, whether the second capacity gear is consistent with the third capacity gear is determined;

when determining whether the second capacity gear is consistent with the third capacity gear, if yes, determining that the capacity gear of the target battery cell is the second capacity gear or the third capacity gear, and if no, determining whether the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both larger than a second preset confidence coefficient; when determining whether the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both larger than the second preset confidence coefficient, if yes, determining whether the second capacity gear and the third capacity gear have the same capacity gear as the first capacity gear; when determining whether the second capacity gear and the third capacity gear have the same capacity gear as the first capacity gear, if yes, determining that the capacity gear of the target battery cell is the first capacity gear or the capacity gear which is the same as the first capacity gear in the second capacity gear and the third capacity gear, otherwise, determining products between confidence degrees and prediction accuracy of the first grading model, the second grading model and the third grading model respectively, correspondingly obtaining a first calculation result, a second calculation result and a third calculation result respectively, and determining that the maximum calculation model corresponding to the maximum calculation result in the first calculation result, the second calculation result and the third calculation result predicts the capacity gear which is the capacity gear of the target battery cell;

When determining whether the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both larger than the second preset confidence coefficient, if not, further determining whether the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both smaller than the second preset confidence coefficient;

if the confidence level is not determined, that is, the confidence level of the second capacity gear or the confidence level of the third capacity gear is determined to be greater than or equal to the second preset confidence level, that is, at the moment, the confidence level of the second capacity gear and the confidence level of the third capacity gear are not both greater than or equal to the second preset confidence level and are not both less than the second preset confidence level, determining that the capacity gear of the target battery core is the corresponding capacity gear with the confidence level in the second capacity gear and the third capacity gear being greater than or equal to the second preset confidence level;

if yes, namely, the confidence degree of the second capacity gear and the confidence degree of the third capacity gear are smaller than the second preset confidence degree, whether at least two identical capacity gears exist in the first capacity gear, the second capacity gear and the third capacity gear is further determined;

if yes, namely determining that at least two identical capacity gears exist in the first capacity gear, the second capacity gear and the third capacity gear, determining that the capacity gear of the target battery cell is any one of the at least two identical capacity gears; and if not, determining that at least two identical capacity gears do not exist in the first capacity gear, the second capacity gear and the third capacity gear, and determining that the capacity gear of the target battery cell is the first capacity gear. So far, the capacity gear of the target battery cell is obtained.

In this embodiment, the battery cell capacity grading model includes a first grading model, a second grading model and a third grading model, which correspond to the first capacity gear, the second capacity gear and the third capacity gear respectively, so that in the process of obtaining the capacity gear of the target battery cell, the determination is performed according to the first capacity gear, the second capacity gear and the third capacity gear and the confidence degrees corresponding to the first capacity gear, the second capacity gear and the third capacity gear respectively. Thereby having higher prediction accuracy for the capacity gear of the target battery cell.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a battery cell capacity grading device for realizing the above-mentioned related battery cell capacity grading method. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of the embodiment of the device for grading the battery cell capacity provided below may be referred to the limitation of the method for grading the battery cell capacity hereinabove, and will not be repeated here.

In one embodiment, as shown in fig. 4, there is provided a battery cell capacity grading device, comprising: an acquisition module 1002, an execution module 1004, and an input module 1006, wherein:

the obtaining module 1002 is configured to obtain a target cell.

An execution module 1004, configured to execute formation operation and partial capacity division operation on the target battery cell, so as to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, and the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, wherein the second voltage is larger than a preset voltage value.

And an input module 1006, configured to input the formation data and the partial capacity data of the target battery cell into the battery cell capacity grading model, so as to obtain a capacity grade of the target battery cell.

In one embodiment, as shown in fig. 5, the apparatus further includes a determining module 1008, where, before the obtaining module 1002 performs obtaining the target cell, the determining module 1008 is configured to:

determining at least one classification model;

In one embodiment, the determining module 1008 is further configured to, in determining the cell capacity grading model based on the prediction of each grading model:

In one embodiment, the battery capacity grading model includes a first grading model, a second grading model and a third grading model; in terms of inputting the formation data and the partial capacity data of the target battery cell into the battery cell capacity grading model to obtain the capacity gear of the target battery cell, the input module 1006 is further configured to:

In one embodiment, in determining the capacity shift of the target cell according to the second capacity shift and the third capacity shift, the input module 1006 is further configured to:

In one embodiment, the input module 1006 is further configured to, in determining the capacity shift of the target cell according to the confidence level of the second capacity shift and the confidence level of the third capacity shift:

The above-mentioned various modules in the battery capacity grading device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the cell data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of battery capacity profiling.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a method of battery capacity profiling. The display unit of the computer equipment is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device, wherein the display screen can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on a shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A method for battery capacity grading, the method comprising:

acquiring a target cell;

performing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, and the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, wherein the second voltage is larger than a preset voltage value;

2. The method of claim 1, wherein prior to the acquiring the target cell, the method further comprises:

determining at least one classification model;

inputting formation data and partial capacity data of the training battery core into each of the at least one grading model to obtain training capacity gears output by each grading model;

and determining the battery cell capacity grading model according to the prediction result of each grading model.

3. The method of claim 2, wherein said determining said cell capacity grading model based on said predictions for each grading model comprises:

determining the first prediction correct rate of each grading model, the probability corresponding to different dislocation gear numbers, the second prediction correct rate corresponding to a plurality of confidence intervals and the third prediction correct rate corresponding to different data volume proportions sequenced by the highest confidence interval according to the prediction result of each grading model;

And determining the battery cell capacity grading model according to the first prediction accuracy, the probability, the second prediction accuracy and the third prediction accuracy.

4. The method of claim 1, wherein the cell capacity grading model comprises a first grading model, a second grading model, and a third grading model; the step of inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity grade of the target battery cell comprises the following steps:

the formation data and partial capacity data of the target battery core are respectively input into the first grading model, the second grading model and the third grading model to obtain a first capacity gear corresponding to the first grading model, a second capacity gear corresponding to the second grading model and a third capacity gear corresponding to the third grading model;

if the confidence coefficient of the first capacity gear is larger than or equal to a first preset confidence coefficient, determining that the capacity gear of the target battery cell is the first capacity gear;

and if the confidence coefficient of the first capacity gear is smaller than the first preset confidence coefficient, determining the capacity gear of the target battery cell according to the second capacity gear and the third capacity gear.

5. The method of claim 4, wherein the determining the capacity shift of the target cell from the second capacity shift and the third capacity shift comprises:

and if the second capacity gear is inconsistent with the third capacity gear, determining the capacity gear of the target battery cell according to the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear.

6. The method of claim 5, wherein the determining the capacity shift of the target cell based on the confidence level of the second capacity shift and the confidence level of the third capacity shift comprises:

if the confidence coefficient of the second capacity gear and the confidence coefficient of the third capacity gear are both larger than a second preset confidence coefficient, determining whether the second capacity gear and the third capacity gear have the same capacity gear as the first capacity gear or not;

if the second capacity gear and the third capacity gear have the same capacity gear as the first capacity gear, determining that the capacity gear of the target battery cell is the first capacity gear;

and determining the capacity gear predicted by a maximum calculation model corresponding to the maximum calculation result in the first calculation result, the second calculation result and the third calculation result as the capacity gear of the target battery cell.

7. The method of claim 5, wherein the determining the capacity shift of the target cell based on the confidence level of the second capacity shift and the confidence level of the third capacity shift comprises:

8. The method of claim 5, wherein the determining the capacity shift of the target cell based on the confidence level of the second capacity shift and the confidence level of the third capacity shift comprises:

if the at least two identical capacity gears exist, determining that the capacity gear of the target battery cell is any one of the at least two identical capacity gears;

and if the at least two identical capacity gears do not exist, determining that the capacity gear of the target battery cell is the first capacity gear.

9. The method according to any one of claims 1 to 8, wherein the formation data is voltage data and temperature data obtained after the formation operation of the target cell, and the partial capacity data is voltage data and temperature data obtained after the partial capacity operation of the target cell.

10. A battery cell capacity grading device, the device comprising:

the acquisition module is used for acquiring the target battery cell;

the execution module is used for executing formation operation and partial capacity division operation on the target battery cell to obtain formation data and partial capacity division data of the target battery cell; the formation operation is used for increasing the voltage of the target battery cell to a first voltage, and the partial capacity division operation is used for reducing the voltage of the target battery cell from the first voltage to a second voltage, wherein the second voltage is larger than a preset voltage value;

and the input module is used for inputting the formation data and partial capacity-dividing data of the target battery cell into a battery cell capacity grading model to obtain the capacity gear of the target battery cell.

11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 9 when the computer program is executed.

12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 9.

13. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 9.