Battery drying method and device, drying equipment and storage medium

Abstract

The invention discloses a battery drying method and device, drying equipment and a storage medium. According to the battery drying method, the first detection parameters of the drying equipment at the target position are obtained in the process that the drying equipment dries the to-be-detected battery, the first detection parameters comprise the temperature and the vacuum degree, the target position is related to the to-be-detected battery, and then the first detection parameters are input into the water content model; the water content of the to-be-detected battery is output through the water content model, and then the water content of the to-be-detected battery is displayed, so that a technician can conveniently monitor the water content of the to-be-detected battery in real time, and the first detection parameter of the drying equipment at the target position is set to represent the first detection parameter of the to-be-detected battery. The manual detection process for testing the water content of the positive and negative electrodes and the diaphragm of the lithium battery can be avoided, and the battery drying efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to battery manufacturing technology, and are related to but not limited to a battery drying method, device, drying equipment and storage medium. Background Art

[0002] With the rapid development of computer technology, industrial digitalization has become a trend in today's era. In the field of new energy, lithium battery moisture drying is a special processing step. The moisture content of lithium batteries is a key factor in determining whether the battery cells are qualified. Testing the moisture content of lithium battery positive and negative electrodes and separators is the most direct characterization method for judging the quality of lithium battery cells. However, due to the cumbersome process of lithium battery moisture content testing and the current limitation of manual sampling, the material and time costs of the battery cell drying process are high, and the test results are also highly uncertain. Summary of the Invention

[0003] In view of this, the battery drying method, apparatus, drying equipment and storage medium provided in the embodiments of the present application can detect the water content of the battery in real time while the drying equipment is drying the battery, avoiding manual detection and improving the battery drying efficiency.

[0004] In a first aspect, the battery drying method provided by the embodiments of the present application includes:

[0005] During the drying process of the battery to be tested by the drying device, obtaining a first detection parameter at a target position of the drying device, the first detection parameter including temperature and vacuum degree, the target position being determined according to the battery to be tested;

[0006] Inputting the first detection parameter into a water content model, and outputting the water content of the battery to be tested through the water content model, wherein the water content model is obtained by training a preset first network model based on a first sample data set, wherein the first sample data set includes historical first detection parameters of the drying device during a process of drying a sample battery, and actual measured values of the water content of the sample battery after drying;

[0007] Output the water content of the battery to be tested.

[0008] In the above-mentioned battery drying method, the first detection parameter of the drying equipment at the target position is obtained during the process of the drying equipment drying the battery to be tested. The first detection parameter includes temperature and vacuum degree. The target position is related to the battery to be tested, and then the first detection parameter is input into the water content model. The water content of the battery to be tested is output through the water content model, and then the water content of the battery to be tested is output, so as to facilitate technicians to monitor the water content of the battery to be tested in real time, and the first detection parameter of the drying equipment at the target position is set to characterize the first detection parameter of the battery to be tested itself, which can avoid the need to conduct manual detection processes for testing the positive and negative electrodes and the water content of the diaphragm of the lithium battery respectively, thereby improving the battery drying efficiency.

[0009] In some embodiments, the water content model includes a classification submodule and a regression submodule, and outputting the water content of the battery to be tested through the water content model includes:

[0010] Inputting the first detection parameter into the classification submodule, and outputting a classification result of the first detection parameter through the classification submodule, wherein the classification result includes qualified and unqualified;

[0011] The first detection parameter with a qualified classification result is input into the regression submodule, and the water content of the battery to be tested is output through the regression submodule.

[0012] In some embodiments, the first network model includes a first sub-model and a second sub-model. Before inputting the second detection parameter into the sealing strip model, the method further includes:

[0013] Inputting the historical first detection parameter and the corresponding identification classification into the first sub-model for training to obtain the classification sub-module, wherein the identification classification includes qualified and unqualified;

[0014] The historical first detection parameter that is identified as qualified and the measured value of the water content are input into the second sub-model for training to obtain the regression sub-module.

[0015] In some embodiments, the method further comprises:

[0016] obtaining second sample data, where the second sample data includes the water content output by the water content model and a measured value of the water content of the battery to be tested;

[0017] The second sample data is input into the classification submodule and the regression submodule to iteratively update the classification submodule and the regression submodule.

[0018] In some embodiments, the method further comprises:

[0019] According to the water content of the battery to be tested, the drying parameters of the drying equipment are adjusted. The drying parameters include at least one of drying temperature, drying vacuum and drying time. The greater the water content of the battery to be tested, the greater the drying parameters.

[0020] In some embodiments, adjusting the drying parameters of the drying device according to the water content of the battery to be tested includes:

[0021] Obtaining a target difference between the water content of the battery to be tested and a preset standard water content;

[0022] According to the target difference, a drying parameter of the drying device is adjusted, and the target difference is positively correlated with the drying parameter.

[0023] In some embodiments, the number of the batteries to be tested is at least two, the target position includes at least two spatial areas of the drying equipment, different spatial areas correspond to different batteries to be tested, the first detection parameter includes the first detection parameter corresponding to each spatial area of the at least two spatial areas, and the water content of the battery to be tested output by the water content model includes the water content of each battery to be tested in the at least two batteries to be tested.

[0024] In some embodiments, the method further comprises:

[0025] During the process of drying the battery to be tested by the drying device, obtaining a second detection parameter at the target position, wherein the second detection parameter includes a vacuum degree;

[0026] Inputting the second detection parameter into a sealing strip model, and outputting the health of the sealing strip of the drying device through the sealing strip model, wherein the sealing strip model is obtained by training a preset second network model based on a second sample data set, wherein the second sample data set includes historical second detection parameters within a historical time period and the sealing degree of the drying device within the historical time period;

[0027] The health of the sealing strip is output.

[0028] In some embodiments, the sealing strip model includes an anomaly detection submodule and a health calculation submodule, and outputting the health of the sealing strip of the drying device through the sealing strip model includes:

[0029] Outputting a sealing degree set of the drying equipment through the abnormality detection submodule, the sealing degree set including changes in the sealing degree of the drying equipment within a target time period, the target time period including a current moment and at least one historical moment;

[0030] The health calculation submodule counts the target number of abnormal values in the sealing set, and when the target number reaches a preset threshold, the health of the sealing strip is obtained based on the ratio of the target number to the total number of the sealing set.

[0031] In some embodiments, the second network model includes a third sub-model and the health calculation sub-module. Before inputting the second detection parameter into the sealing strip model, the method further includes:

[0032] Inputting the historical second detection parameter and the historical sealing degree set into the third sub-model for training to obtain the anomaly detection sub-module;

[0033] The health calculation submodule is established, and the health calculation submodule is used to count the target number of abnormal values in the historical sealing set, and obtain the health of the sealing strip based on the ratio between the target number and the total number corresponding to the historical sealing set.

[0034] In some embodiments, the method further comprises:

[0035] When the health of the sealing strip is less than a preset health threshold, a prompt message is output to prompt the user to replace the sealing strip.

[0036] In a second aspect, the battery drying device provided in the embodiments of the present application is applied to a drying device, and the device includes:

[0037] A parameter acquisition module, configured to obtain a first detection parameter at a target position of the drying device during the drying process of the battery to be tested by the drying device, wherein the first detection parameter includes temperature and vacuum degree, and the target position is determined according to the battery to be tested;

[0038] a first calculation module, configured to input the first detection parameter into a water content model and output the water content of the battery to be tested using the water content model, wherein the water content model is trained based on a first sample data set, the first sample data set including historical first detection parameters of the drying device during the process of drying sample batteries and actual measured water content values of the sample batteries after drying;

[0039] The water content output module is used to output the water content of the battery to be tested.

[0040] In a third aspect, the drying device provided in the embodiment of the present application includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in the embodiment of the present application is implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method provided in the embodiment of the present application is implemented.

[0042] It should be understood that the second to fourth aspects of the embodiments of the present application are consistent with the technical solutions of the first aspect of the embodiments of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0044] Figure 1 A schematic structural diagram of the drying equipment provided in an embodiment of the present application;

[0045] Figure 2 A schematic flow chart of a battery drying method according to an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the structure of the water content model provided in the embodiment of the present application;

[0047] Figure 4 A schematic diagram of a flow chart of outputting water content using a water content model provided in an embodiment of the present application;

[0048] Figure 5 A schematic flow chart of a battery drying method according to an embodiment of the present application;

[0049] Figure 6 A schematic flow chart of a battery drying method according to an embodiment of the present application;

[0050] Figure 7 A schematic structural diagram of a sealing strip model provided in an embodiment of the present application;

[0051] Figure 8 A schematic diagram of a process for outputting the health status of a sealing strip by a sealing strip model provided in an embodiment of the present application;

[0052] Figure 9 A schematic structural diagram of a battery drying device provided in an embodiment of the present application;

[0053] Figure 10 This is a schematic diagram of the structure of the drying equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0056] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0057] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0058] For battery cells, the entire cell drying process is an extremely complex procedure. The drying equipment provides a heat source for the battery cells. During the drying process, the drying equipment performs heat conduction, heat convection and radiation on the battery to be tested, thereby achieving a drying effect. For example, during the drying process of the battery cells, the bottom surface of the battery and the bottom heating plate are contact-heated, and the vacuum pump evacuates the internal cavity of the drying equipment to provide a vacuum environment for the battery cells. Under the constant temperature vacuum environment, the boiling point of the volatile components in the positive and negative electrodes and the diaphragm of the battery cells is reduced. Volatile components such as water and solvents are heated at the same time to cause the volatile components to separate from the surface of the battery to be tested, and are taken out of the drying equipment through high vacuum or nitrogen as the medium to achieve the purpose of controlling the water content of the battery cells.

[0059] In some embodiments, the drying device may include a vacuum chamber 20, a housing 10, and an electrical control system, such as Figure 1 As shown, the vacuum chamber 20 has a battery storage space for placing the battery to be tested 30. The vacuum chamber 20 is disposed within the housing 10 and is connected to a first gas source, such as nitrogen or compressed air, via a nitrogen or compressed air pipeline. The vacuum chamber 20 is also connected to a second gas source, such as air, via an air inlet pipeline. At least one baking tray can be placed in the battery storage space, and the battery to be tested 30 can be placed on the baking tray.

[0060] In some embodiments, the housing 10 may include a heating side plate, a heating bottom plate, and a retaining frame. The heating side plate and the heating bottom plate are used to provide a heat source for the vacuum chamber 20, and the retaining frame is used to fix the vacuum chamber 20. When the interior of the oven is stabilized at the highest temperature, the temperature can rise to 105°C when unloaded and can be maintained for up to 15 minutes. The temperature can fluctuate within a range of ±3. The heating side plate or the heating bottom plate may include 6 heating plates. Each heating plate may be configured with 2 controllers, one for controlling the heating parameters of the heating plate and the other for real-time monitoring of the heating temperature of the heating plate. Each heating plate may use a PT100 temperature control probe to detect the temperature within the drying equipment, and a tray sensor may be provided to sense the presence or absence of a tray in the vacuum chamber 20 or whether the tray is in place.

[0061] In the related technology, when incoming batteries and fake batteries are input, the robot will send the batteries into the qualified fixture after completing the grabbing and scanning of the incoming batteries and fake batteries. At this time, the drying system will automatically open the cavity door of the vacuum chamber 20, and automatically close the door after the two full fixtures enter the vacuum chamber 20, and automatically dry according to the set program. After the drying is completed, the scheduling robot will take out the fixture and transfer it to the fake battery station. Then the technician will take out the fake battery for water content testing, and send the original fixture with the incoming battery back to the vacuum chamber 20; if the water content of the fake battery is qualified (OK), the incoming battery will be unloaded to the liquid injection docking line; if the water content of the fake battery is unqualified (NG), the incoming battery and the fake battery will be put back into the furnace cavity and dried again.

[0062] From the above process, it can be seen that in the related art, the water content of the battery to be tested is tested by using a fake battery. However, this will lead to insufficient detection accuracy for the following reasons:

[0063] 1. The material properties of the fake battery cells used to measure water content may not be exactly the same as those of the actual produced battery cells. Therefore, the measured water content value may not accurately represent the water content value of the actual produced battery cells.

[0064] 2. Before testing, it is necessary to sample and transport the incoming batteries and fake batteries, which will cause changes in the water content in the battery cells during the transportation process;

[0065] 3. During the testing process, since it is necessary to manually cut the sample and test it using chemical reagents on the test bench, the professional procedures of the testers will also affect the accuracy of the final water content value to some extent.

[0066] In order to solve the above problems, an embodiment of the present application provides a battery drying method, in which a first detection parameter of the drying equipment at a target position is obtained during the process of drying the battery to be tested by the drying equipment, the first detection parameter including temperature and vacuum degree, and the target position is related to the battery to be tested, and then the first detection parameter is input into a water content model, and the water content of the battery to be tested is output through the water content model, and then the water content of the battery to be tested is displayed, so as to facilitate technicians to monitor the water content of the battery to be tested in real time, and the first detection parameter of the drying equipment at the target position is set to characterize the first detection parameter of the battery to be tested itself, which can avoid the need to conduct manual detection processes for testing the positive and negative electrodes and the water content of the diaphragm of the lithium battery respectively, thereby improving the battery drying efficiency.

[0067] In some embodiments, such as Figure 2 As shown, the battery drying method may include the following steps:

[0068] Step S101, while a drying device is drying a battery to be tested, obtaining first detection parameters at a target position of the drying device, the first detection parameters including temperature and vacuum degree, and the target position is determined according to the battery to be tested;

[0069] Step S102: Inputting the first detection parameter into a water content model, and outputting the water content of the battery to be tested through the water content model. The water content model is obtained by training a preset network model based on a first sample data set. The first sample data set includes historical first detection parameters of the drying device during the process of drying the sample battery, and the measured water content value of the sample battery after drying.

[0070] Step S103: outputting the water content of the battery to be tested.

[0071] It should be understood that the means of detecting the water content of the battery in the related art is to collect the water content of the fake battery at the positive electrode, negative electrode and separator of the battery cell respectively. However, when detecting the water content at the positive electrode, negative electrode and separator of the battery cell, the battery needs to be removed from the drying equipment and then tested by technicians through chemical means. However, in the process of removing the battery, this will cause the water content of the battery to change. Therefore, in order to avoid the change in water content caused by the battery during the removal process, in this application, the first detection parameter at the target position inside the drying equipment is regarded as an influencing factor affecting the change in water content of the battery to be tested, and then the water content of the battery to be tested is obtained directly by performing data analysis on the first detection parameter, thereby improving the precision and accuracy of the water content of the battery to be tested.

[0072] It should be noted that the battery to be tested in the embodiment of the present application is the incoming battery that is actually dried by the drying equipment, rather than the dummy battery used to detect the water content in the related art. That is, in the embodiment of the present application, there is no need to introduce dummy batteries during the process of drying the incoming batteries by the drying equipment, and only the incoming batteries need to be retained.

[0073] In some embodiments, the target position may include any position on the surface that contacts the battery to be tested. For example, if the battery to be tested is contacted by a tray in a drying device, the target position may be the surface of the tray, the edge of the tray, and the gap between two adjacent trays.

[0074] In some embodiments, the first detection parameter at the target position can be obtained by setting a temperature sensor and / or a vacuum sensor at the target position, where the temperature sensor is used to collect the temperature at the target position and the vacuum sensor is used to collect the vacuum degree at the target position.

[0075] Among them, the first detection parameters at different target positions can be used to reflect the first detection parameters of the battery to be tested. For example, the temperature sensor set on the surface of the tray can reflect the temperature of the battery to be tested in direct contact with the tray, while the temperature sensor set at the edge of the tray can monitor the heat loss at the edge of the tray, thereby helping to evaluate whether the heat is effectively utilized by the battery to be tested during the drying process.

[0076] In some embodiments, the above-mentioned target position may include multiple different positions. By obtaining the first detection parameters at different positions, it can be ensured that the temperature distribution in the entire drying furnace meets the process requirements, and that the moisture inside the battery to be tested can be removed evenly and effectively, thereby meeting the temperature control required during the lithium battery drying process.

[0077] In some embodiments, the method of outputting the water content of the battery to be tested in the above-mentioned step S103 can be to display the water content of the battery to be tested on a display of the drying device, or to send a data signal including the water content of the battery to be tested to an associated device, and a communication connection is established between the associated device and the drying device. The specific setting is made by those skilled in the art according to actual conditions, and is not limited in the embodiments of the present application.

[0078] In some embodiments, the number of the above-mentioned batteries to be tested can be at least two, the target position includes at least two spatial areas of the drying equipment, different spatial areas correspond to different batteries to be tested, the first detection parameter includes the first detection parameter corresponding to each spatial area of the at least two spatial areas, and the water content of the battery to be tested output by the water content model includes the water content of each battery to be tested in the at least two batteries to be tested.

[0079] Among them, in order to distinguish the first detection parameters of the battery to be tested in different spatial areas, identification information can be added to the first detection parameter to identify the spatial area corresponding to the first detection parameter. Then, when the water content of the battery to be tested is output through the water content model, the corresponding identification information can also be output synchronously to indicate the spatial area corresponding to the water content, so that technicians can distinguish the water content of the battery to be tested in different spatial areas according to the output identification information.

[0080] It can be understood that by dividing at least two spatial regions in a single drying device and then placing at least two batteries to be tested in the at least two spatial regions, so that different spatial regions correspond to different batteries to be tested, the water content of the battery to be tested in each spatial region can be output through the water content model, thereby realizing partitioned detection of the batteries to be tested in at least two spatial regions.

[0081] In some embodiments, the above-mentioned first detection parameter may be a data set that has been preprocessed, and the preprocessing may include at least one of data cleaning, data normalization, and data redundancy deletion. That is, after the drying equipment obtains the initial detection parameters at the target position transmitted by the sensor, it may preprocess the initial detection parameters and use the preprocessed detection parameters as the first detection parameters.

[0082] In some embodiments, the water content model can be any machine learning model used to analyze regression or classification problems, such as feedforward neural networks (FNNs), models constructed using the eXtreme Gradient Boosting (XGBoost) algorithm, etc. Because the water content model in the embodiments of the present application needs to analyze and obtain the water content of the battery to be tested based on the first detection parameter, the water content model needs to train a preset first network model based on a first sample data set to obtain the relationship between the first detection parameter and the water content of the battery to be tested. The first sample data set includes the historical first detection parameter of the drying equipment during the process of drying the sample battery, as well as the measured water content value of the sample battery after drying.

[0083] It should be noted that due to the quality of the material of the battery to be tested itself, the water content of different batteries to be tested at the same time during the drying process will be quite different. The water content of the battery to be tested with higher quality is different from the water content of the battery to be tested with lower quality. In the embodiment of the present application, the first detection parameter at the target position in the drying equipment is used to characterize the water content of the battery to be tested itself, and the water content model cannot reflect the water content of batteries to be tested of different qualities through the same first detection parameter. Therefore, it is necessary to eliminate the data corresponding to the batteries to be tested with lower quality in the first detection parameter, so that the water content model can only output the water content corresponding to the batteries to be tested with better quality, thereby improving the accuracy of the water content output by the water content model.

[0084] Therefore, in the embodiment of the present application, the water content model can be divided into a classification submodule 201 and a regression submodule 202. The classification submodule 201 classifies the first detection parameters into qualified first detection parameters and unqualified first detection parameters; the regression submodule 202 analyzes the characteristics of the qualified first detection parameters to obtain the corresponding water content.

[0085] That is, in some embodiments, the water content model may include a classification submodule 201 and a regression submodule 202, such as Figure 3 As shown, the step of outputting the water content of the battery to be tested by using the water content model in the above step S102 may include:

[0086] Input the first detection parameter to the classification submodule 201, and output the classification result of the first detection parameter through the classification submodule 201, where the classification result includes qualified and unqualified;

[0087] The first detection parameter with a qualified classification result is input into the regression submodule 202 , and the water content of the battery to be tested is output through the regression submodule 202 .

[0088] Among them, after receiving the first detection parameter, the above-mentioned classification submodule 201 will evaluate the characteristics of the first detection parameter, and then classify the first detection parameter, and then eliminate the first detection parameter with an unqualified classification result, and input the first detection parameter with a qualified classification result into the regression submodule 202, so as to output the water content of the battery to be tested through the regression submodule 202.

[0089] In some embodiments, the classification submodule 201 and the regression submodule 202 may use the same type of neural network model. For example, both the classification submodule 201 and the regression submodule 202 are models built using XGBoost. XGBoost is an efficient machine learning algorithm that uses a gradient boosting decision tree as a basic learner. It iteratively trains multiple weak classifiers and combines them into a strong classifier. Each round of iteration adjusts the model based on the results of the previous round, so that the model can better fit the data.

[0090] To ensure that the prediction error of the water content model remains low, the loss function in XGBoost can use either the squared loss function or the logarithmic loss function. XGBoost can use the squared loss function as the objective function, minimizing the squared loss function to find the optimal decision tree, thereby improving the model's prediction accuracy. The logarithmic loss function can be used to evaluate the difference between the model's predicted probability and the true label. XGBoost can use the logarithmic loss function as the objective function, minimizing the logarithmic loss function to find the optimal decision tree, thereby improving the model's classification accuracy.

[0091] Therefore, in this embodiment, the classification submodule 201 may be XGBoost using the logarithmic loss function as the objective function, and the regression submodule 202 may be XGBoost using the square loss function as the objective function.

[0092] In some embodiments, the classification submodule 201 and the regression submodule 202 may use different types of neural network models. For example, the classification submodule 201 may be an XGBoost using a logarithmic loss function as an objective function, and the regression submodule 202 may be a long short-term memory network (LSTM). XGBoost classifies the first detection parameter as qualified or unqualified, removes unqualified first detection parameters, and inputs qualified first detection parameters into the LSTM model. The LSTM model analyzes the qualified first detection parameters and outputs the corresponding water content of the battery to be tested.

[0093] It should be noted that the selection of the classification submodule 201 and the regression submodule 202 can be set by those skilled in the art according to actual conditions, and the embodiments of the present application do not limit it. The above embodiments of the classification submodule 201 and the regression submodule 202 are only examples of the classification submodule 201 and the regression submodule 202 and should not be regarded as limitations on the present application.

[0094] It can be understood that after first eliminating unqualified first detection parameters through the water content model, data analysis is performed on qualified first detection parameters, so that the water content model can only output the water content corresponding to the batteries to be tested with better quality, thereby improving the accuracy of the water content output by the water content model.

[0095] Before using the classification submodule 201 and the regression submodule 202, it is necessary to train the preset first submodel and the second submodel respectively to obtain the classification submodule 201 and the regression submodule 202. Among them, since the classification submodule 201 needs to output whether the first detection parameter is qualified, when training the classification submodule 201, it is necessary to input the historical first detection parameters within the historical time period and the manually identified identification classification into the preset first submodel for training, thereby obtaining the classification submodule 201; for the regression submodule 202, since the regression submodule 202 needs to obtain the corresponding water content of the battery to be tested based on the qualified first detection parameter, when training the regression submodule 202, it is necessary to input the historical first detection parameters classified as qualified and the corresponding measured water content of the battery to be tested into the preset second submodel for training, thereby obtaining the regression submodule 202.

[0096] That is, in some embodiments, the water content model may include a classification submodule 201 and a regression submodule 202, the preset network model may include a first submodel and a second submodel, and before inputting the second detection parameter into the sealing strip model, the method may further include:

[0097] Inputting the historical first detection parameter and the corresponding identification classification into the first sub-model for training to obtain a classification sub-module 201, wherein the identification classification includes qualified and unqualified;

[0098] The historical first detection parameter identified as qualified and the measured value of the water content are input into the second sub-model for training to obtain the regression sub-module 202.

[0099] It can be understood that the first sub-model is trained based on the historical first detection parameters and the corresponding identification classification to obtain the classification sub-module 201, and the second sub-model is trained based on the historical first detection parameters that are identified as qualified and the actual measured value of the water content to obtain the regression sub-module 202, which can improve the accuracy of the water content of the battery to be tested.

[0100] Because the accuracy of the water content model is determined by the amount of data in the training sample set, the larger the data volume of the training sample set used to train the water content model, the higher the accuracy of the water content model. However, the data volume of the first sample data set is limited. Therefore, after the water content model completes training and analyzes the first detection parameter based on the training results to obtain the water content of the battery to be tested, the water content of the battery to be tested output by the water content model and the actual measured value of the water content of the battery to be tested can be input into the water content model for repeated training, thereby achieving iterative updating of the water content model.

[0101] That is, in some embodiments, the above method may further include:

[0102] obtaining second sample data, where the second sample data includes the water content of the battery to be tested output by the water content model and the actual measured value of the water content of the battery to be tested;

[0103] The second sample data is input into the classification submodule 201 and the regression submodule 202 to iteratively update the classification submodule 201 and the regression submodule 202 .

[0104] It is understandable that by repeatedly training the water content model according to the second sample data, it is possible to iteratively update the classification submodule 201 and the regression submodule 202 , thereby further improving the output accuracy of the water content model.

[0105] Figure 4 A schematic diagram of a process for processing a first detection parameter using a water content model provided in an embodiment of the present application. Figure 4 As shown, the process may include the following steps:

[0106] Step S301: after receiving the first detection parameter, the water content model first inputs the first detection parameter into the classification submodule 201;

[0107] Step S302: the classification submodule 201 classifies the first detection parameter into qualified and unqualified.

[0108] Step S303: the classification submodule 201 removes unqualified first detection parameters and inputs qualified first detection parameters into the regression submodule 202;

[0109] Step S304: The classification submodule 201 inputs the qualified first detection parameters into the regression submodule 202. At the same time, the first detection parameters manually identified as qualified can be input into the classification submodule 201 to perform iterative updates on the classification submodule 201, thereby improving the output accuracy of the classification submodule 201.

[0110] Step S305: the regression submodule 202 performs real-time prediction of the water content according to the qualified first detection parameter, and outputs the predicted water content value;

[0111] In step S306, while outputting the water content predicted by the regression submodule 202, the water content model also inputs the predicted water content and the measured value of the water content from manual sampling into the regression submodule 202 to iteratively update the regression submodule 202 and improve the output accuracy of the regression submodule 202.

[0112] Currently, drying parameters are typically preset based on process experience or laboratory data. However, in actual production, the materials and external environmental conditions of different batches of batteries under test may vary. Manual adjustments are difficult to respond to in a timely manner, which can easily lead to over-drying or under-drying, affecting battery performance and potentially wasting resources.

[0113] Therefore, in some embodiments, Figure 5 As shown, the above method also includes:

[0114] Step S104 , adjusting the drying parameters of the drying equipment according to the water content of the battery to be tested. The drying parameters include at least one of drying temperature, drying vacuum, and drying time. The greater the water content of the battery to be tested, the greater the drying parameters.

[0115] Among them, the greater the water content of the battery to be tested, the more insufficient the drying degree of the battery to be tested by the drying equipment is. It is necessary to promptly improve the drying parameters of the battery to be tested by the drying equipment, such as extending the drying time and / or increasing the drying temperature, so as to ensure that the water content of the battery to be tested can be reduced to a reasonable range in a timely manner.

[0116] It can be understood that by judging the real-time predicted water content, the drying parameters can be adjusted in real time, and the drying effect of the drying equipment on the battery to be tested can be stabilized, achieving energy-saving and high-efficiency effects.

[0117] In some embodiments, the step of adjusting the drying parameters of the drying equipment according to the water content of the battery to be tested in step S104 may include:

[0118] Obtaining a target difference between the water content of the battery to be tested and a preset standard water content;

[0119] According to the target difference, the drying parameters of the drying equipment are adjusted. The target difference is positively correlated with the drying parameters.

[0120] It should be understood that the purpose of the drying equipment for drying the battery to be tested is to adjust the water content of the battery to be tested to the level of the standard water content. Therefore, the drying equipment can adjust the drying parameters of the drying equipment according to the difference between the water content of the battery to be tested output by the water content model and the standard water content to ensure that the water content of the battery to be tested can be maintained at the numerical level of the standard water content to meet the process requirements of the battery to be tested.

[0121] The sealing strip of the drying equipment is an important component of the drying equipment. The health of the sealing strip will affect the drying parameters of the drying equipment. The higher the health of the sealing strip, the better the sealing degree of the drying equipment, and the drying parameters of the drying equipment can be maintained at the set values. The lower the health of the sealing strip, the worse the sealing degree of the drying equipment, and the internal drying parameters of the drying equipment cannot be maintained at the set values, thereby affecting the drying effect of the battery to be tested. However, the relevant technology has no corresponding monitoring means for the health status of the sealing strip during the drying process, and it can only be replaced regularly.

[0122] Therefore, in some embodiments, Figure 6 As shown, the battery drying method can also perform real-time detection of the health of the sealing strip of the drying equipment, that is, the battery drying method can also include:

[0123] Step S105, obtaining a second detection parameter at a target position during the drying process of the battery to be tested by the drying device, the second detection parameter including a vacuum degree;

[0124] Step S106: Inputting the second detection parameter into a sealing strip model, and outputting the health of the sealing strip of the drying equipment through the sealing strip model. The sealing strip model is obtained by training a preset second network model based on a second sample data set. The second sample data set includes historical second detection parameters within a historical time period, and a historical sealing degree set of the drying equipment within the historical time period. The historical sealing degree set indicates changes in the sealing degree of the drying equipment during a drying process, where the drying process includes a historical time period.

[0125] Step S107: outputting the health of the sealing strip.

[0126] In some embodiments, the above-mentioned second detection parameter may be a data set that has been preprocessed. The preprocessing may include at least one of data cleaning, data normalization, and data redundancy deletion. For example, after the drying equipment obtains the initial vacuum degree at the target position transmitted by the sensor, the initial vacuum degree may be preprocessed and the preprocessed vacuum degree may be used as the second detection parameter.

[0127] In some embodiments, because the sealing strip model primarily reflects fluctuations in the sealing condition of the drying device based on fluctuations in the second detection parameter, the sealing strip model can be any unsupervised learning model, such as a model trained using a K-Means clustering algorithm. Because the sealing strip model in the embodiments of the present application needs to reflect fluctuations in the sealing condition of the drying device based on fluctuations in the second detection parameter, the sealing strip model needs to train a preset second network model based on a second sample data set to obtain a relationship between the second detection parameter and the health of the sealing strip. The second sample data set includes historical second detection parameters within a historical time period, as well as a historical set of sealing conditions of the drying device within the historical time period.

[0128] It should be noted that steps S105 to S107 and steps S101 to S103 may be executed synchronously or in a preset order, which may be set by those skilled in the art according to actual conditions. Figure 6 The execution order in is only an example and is not limited in the embodiments of the present application.

[0129] It can be understood that according to the fluctuation of the second detection parameter during the drying process, the health of the sealing strip in the drying furnace cavity can be effectively monitored, the state of the sealing strip in the drying furnace cavity can be effectively monitored, and the effective drying can be ensured.

[0130] Because the sealing strip model reflects the fluctuation of the sealing condition in the drying equipment based on the fluctuation of the second detection parameter, thereby quantifying the health of the sealing strip, and the health of the sealing strip indicates the difference between the actual fluctuation and the standard fluctuation of the sealing condition in the drying equipment, the sealing strip model can analyze the target number of abnormal values in the sealing set in the drying equipment, and then output the health of the sealing strip of the current drying equipment based on the relationship between the size of the target number and the health of the sealing strip.

[0131] Therefore, in the embodiment of the present application, the sealing strip model can be divided into an abnormality detection submodule 401 and a health calculation submodule 402. The abnormality detection submodule 401 obtains the corresponding sealing set of the drying equipment according to the second detection parameter, and the sealing set includes the changes in the sealing of the drying equipment within the target time period; the health calculation submodule 402 further outputs the health of the sealing strip of the current drying equipment according to the target number of abnormal values in the sealing set.

[0132] That is, in some embodiments, the sealing strip model includes an abnormality detection submodule 401 and a health calculation submodule 402, such as Figure 7 As shown in the figure, the health of the sealing strip of the drying equipment is output through the sealing strip model, including:

[0133] Outputting, by the abnormality detection submodule 401, a sealing degree set of the drying equipment according to the second detection parameter, the sealing degree set including changes in the sealing degree of the drying equipment within a target time period, where the target time period includes the current moment and at least one historical moment;

[0134] The health calculation submodule 402 counts the target number of abnormal values in the sealing set, and when the target number reaches a preset threshold, the health of the sealing strip is obtained based on the ratio of the target number to the total number of the sealing set.

[0135] Among them, since the abnormality detection submodule 401 needs to output the change in the sealing degree of the drying equipment within the target time period based on the second detection parameter, the abnormality detection submodule 401 needs to analyze the second detection parameter at the current moment and the sealing degree of the drying equipment at the historical moment, and then obtain the change in the sealing degree of the drying equipment.

[0136] In some embodiments, the sealing degree of the drying equipment at a historical moment can be obtained from the second detection parameter at a historical moment, or can be obtained from a historical sealing degree set output by the abnormality detection submodule 401 at a historical moment.

[0137] In some embodiments, because anomaly detection submodule 401 needs to reflect fluctuations in the drying equipment's sealing condition based on the second detection parameter, it can be implemented as any unsupervised learning model, such as a model trained using the K-Means clustering algorithm. Health calculation submodule 402, on the other hand, only involves calculating the ratio of the number of targets to the total number of sealing sets, requiring less computational effort. This computation can be performed by control devices such as the drying equipment's controller, which lacks extensive data analysis capabilities, thereby reducing model training costs.

[0138] Before using the anomaly detection submodule 401, the preset third submodel needs to be trained separately to obtain the anomaly detection submodule 401. Since the anomaly detection submodule 401 needs to output the changes in the sealing degree of the drying equipment within the target time period, when training the anomaly detection submodule 401, the historical second detection parameters and historical sealing degree sets within the historical time period need to be input into the preset third submodel for training to obtain the anomaly detection submodule 401.

[0139] That is, in some embodiments, the second network model includes the third sub-model and the health calculation sub-module 402. Before inputting the second detection parameter into the sealing strip model, the method further includes:

[0140] Inputting the historical second detection parameter and the historical sealing degree set into the third sub-model for training to obtain the anomaly detection sub-module 401;

[0141] A health calculation submodule 402 is established, which is used to count the target number of abnormal values in the historical sealing set and obtain the health of the sealing strip based on the ratio between the target number and the total number corresponding to the historical sealing set.

[0142] In some embodiments, the health calculation submodule 402 can count the target number of abnormal values in the historical sealing set by judging whether the sealing in the sealing set is abnormal in sequence according to the time sequence of the target time period, and when an abnormal value in the sealing set is identified, the target number of abnormal values counted is increased by one.

[0143] For example, Figure 8 As shown, the process of the sealing strip model outputting the health status of the sealing strip may include the following steps:

[0144] Step S501: After receiving the second detection parameter, the sealing strip model first inputs the second detection parameter into the abnormality detection submodule 401;

[0145] Step S502: the abnormality detection submodule 401 obtains a set of sealing degrees in the drying equipment within a target time period based on the second detection parameter;

[0146] Step S503, the anomaly detection submodule 401 outputs the sealing degree set to the health degree calculation submodule 402;

[0147] In step S504, the health calculation submodule 402 receives the sealing degree set output by the anomaly detection submodule 401, sets a threshold E for triggering health degree calculation, and then sequentially determines whether the sealing degree in the sealing degree set is abnormal based on the time sequence of the target time period. When an abnormal value in the sealing degree set is identified, the target number of abnormal values counted is increased by one.

[0148] In step S505, the health calculation submodule 402 triggers a health calculation when the target number reaches E times (assuming that the total number of times the sealing is judged to be abnormal is N). That is, the calculation formula of the health HI is: HI = (N-E) / N, and the health of the sealing strip is obtained.

[0149] In some embodiments, the method of outputting the health status of the sealing strip in the above-mentioned step S107 can be to display the health status of the sealing strip through the display of the drying device, or to send a data signal including the health status of the sealing strip to an associated device, and a communication connection is established between the associated device and the drying device. The specific setting is made by those skilled in the art according to actual conditions, and is not limited in the embodiments of the present application.

[0150] In some embodiments, the above method may further include:

[0151] When the health of the sealing strip is less than a preset health threshold, a prompt message is output to prompt the user to replace the sealing strip.

[0152] Among them, the prompt information can be a text signal, an audio / visual signal, etc., whichever can alert the user, and is not limited in the embodiments of the present application.

[0153] Among them, the preset health threshold can be set by the threshold set by the drying device receiving the user, or it can be a standard value pre-set by the drying device. It is specifically set by those skilled in the art according to actual conditions, and the embodiments of this application are not limited thereto.

[0154] It is understandable that by outputting a prompt message when the health of the sealing strip is less than the preset health threshold, the user can be promptly prompted to replace the sealing strip of the drying device, further improving the drying effect of the drying device on the battery to be tested.

[0155] It should be understood that although Figure 2-Figure 8 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2-Figure 8 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0156] Based on the foregoing embodiments, an embodiment of the present application provides a battery drying device, which includes the modules included and the units included in each module, and can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

[0157] Figure 9 This is a schematic diagram of the structure of the battery drying device provided in the embodiment of the present application, as shown in FIG. Figure 9 As shown, the device may include a parameter acquisition module 901, a first calculation module 902 and a water content output module 903, wherein:

[0158] A parameter acquisition module 901 is configured to obtain a first detection parameter at a target position of the drying device during the drying process of the battery to be tested. The first detection parameter includes temperature and vacuum degree. The target position is determined based on the battery to be tested.

[0159] A first calculation module 902 is configured to input the first detection parameter into a water content model and output the water content of the battery to be tested using the water content model. The water content model is trained based on a first sample data set, wherein the first sample data set includes historical first detection parameters of the drying device during the drying process of the sample battery and actual measured water content values of the sample battery after drying.

[0160] The water content output module 903 is used to output the water content of the battery to be tested.

[0161] In some embodiments, the water content model includes a classification submodule and a regression submodule. The first calculation module 902 is specifically configured to:

[0162] Inputting the first detection parameter into the classification submodule, and outputting the classification result of the first detection parameter through the classification submodule, the classification result including qualified and unqualified;

[0163] The first detection parameter with a qualified classification result is input into the regression submodule, and the water content of the battery to be tested is output through the regression submodule.

[0164] In some embodiments, the first network model includes a first sub-model and a second sub-model, and the apparatus may further include:

[0165] A first training module is used to input the historical first detection parameter and the corresponding identification classification into the first sub-model for training before inputting the second detection parameter into the sealing strip model to obtain a classification sub-module, where the identification classification includes qualified and unqualified;

[0166] The second training module is used to input the historical first detection parameters and the measured values of water content that are marked as qualified into the second sub-model for training to obtain a regression sub-module.

[0167] In some embodiments, the above apparatus may further include:

[0168] A sample acquisition module, configured to obtain second sample data, the second sample data including the water content output by the water content model and the actual measured value of the water content of the battery to be tested;

[0169] The model updating module is used to input the second sample data into the classification submodule and the regression submodule to iteratively update the classification submodule and the regression submodule.

[0170] In some embodiments, the above apparatus may further include:

[0171] The parameter adjustment module is used to adjust the drying parameters of the drying equipment according to the water content of the battery to be tested. The drying parameters include at least one of the drying temperature, the drying vacuum degree and the drying time. The greater the water content of the battery to be tested, the greater the drying parameter.

[0172] In some embodiments, the parameter adjustment module is used to:

[0173] Obtaining a target difference between the water content of the battery to be tested and a preset standard water content;

[0174] According to the target difference, the drying parameters of the drying equipment are adjusted. The target difference is positively correlated with the drying parameters.

[0175] In some embodiments, the number of batteries to be tested is at least two, the target position includes at least two spatial regions of the drying equipment, different spatial regions correspond to different batteries to be tested, the first detection parameter includes the first detection parameter corresponding to each spatial region of the at least two spatial regions, and the water content of the battery to be tested output by the water content model includes the water content of each battery to be tested in the at least two batteries to be tested.

[0176] In some embodiments, the above apparatus may further include:

[0177] A parameter acquisition module, configured to obtain a second detection parameter at a target position during a process in which the drying device dries the battery to be tested, the second detection parameter including a vacuum degree;

[0178] a second calculation module, configured to input the second detection parameter into a sealing strip model, and output the health of the sealing strip of the drying device through the sealing strip model, the sealing strip model being obtained by training a preset second network model based on a second sample data set, the second sample data set including historical second detection parameters within a historical time period and a historical sealing degree set of the drying device within the historical time period, the historical sealing degree set indicating changes in the sealing degree of the drying device within the historical time period;

[0179] The health output module is used to output the health of the sealing strip.

[0180] In some embodiments, the sealing strip model may include an anomaly detection submodule and a health calculation submodule, wherein the second calculation submodule is configured to:

[0181] Outputting, by the anomaly detection submodule, a sealing degree set of the drying equipment according to the second detection parameter, the sealing degree set including changes in the sealing degree of the drying equipment within a target time period, the target time period including a current moment and at least one historical moment;

[0182] The health calculation submodule counts the target number of abnormal values in the sealing set, and when the target number reaches a preset threshold, the health of the sealing strip is obtained based on the ratio of the target number to the total number of the sealing set.

[0183] In some embodiments, the second network model includes a third sub-model and a health calculation sub-module, and the above apparatus may further include:

[0184] A third training module is configured to input the historical second detection parameters and the historical sealing degree set into the third sub-model for training before inputting the second detection parameters into the sealing strip model, thereby obtaining an anomaly detection sub-module;

[0185] The sub-module establishment module is used to establish a health calculation sub-module. The health calculation sub-module is used to count the target number of abnormal values in the historical sealing set, and obtain the health of the sealing strip based on the ratio between the target number and the total number corresponding to the historical sealing set.

[0186] In some embodiments, the above apparatus may further include:

[0187] The replacement prompt module is used to output a prompt message to prompt the user to replace the sealing strip when the health of the sealing strip is less than a preset health threshold.

[0188] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0189] It should be noted that in the embodiments of this application Figure 9 The module division of the battery drying device shown is schematic and represents only one logical functional division; actual implementation may employ different division methods. Furthermore, the functional units in the various embodiments of this application may be integrated into a single processing unit, exist as separate physical units, or be integrated into a single unit. These integrated units may be implemented as hardware or software functional units. Alternatively, a combination of software and hardware may be employed.

[0190] It should be noted that, in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling an electronic device to execute all or part of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0191] The embodiment of the present application provides a drying device, the internal structure of which can be shown as follows: Figure 10 As shown. The drying device includes a processor, memory, and a network interface connected via a system bus. The processor of the drying device is used to provide computing and control capabilities. The memory of the drying device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the drying device is used to store data. The network interface of the drying device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a battery drying method is implemented.

[0192] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method provided in the above embodiment are implemented.

[0193] An embodiment of the present application provides a computer program product containing instructions, which, when executed on a computer, enables the computer to execute the steps of the method provided in the above method embodiment.

[0194] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the drying equipment to which the solution of the present application is applied. The specific drying equipment may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0195] In one embodiment, the battery drying device provided by the present application can be implemented in the form of a computer program, which can be used in Figure 10The drying device is operated on the drying device shown. The memory of the drying device can store various program modules that constitute the electronic device. The computer program composed of each program module enables the processor to execute the steps of the battery drying method of each embodiment of the present application described in this specification.

[0196] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned battery drying method when executing the computer program.

[0197] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0198] It should be understood that "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, they will not be repeated here.

[0199] The term "and / or" in this article is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, object A and / or object B can mean: object A exists alone, object A and object B exist at the same time, and object B exists alone.

[0200] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0201] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms.

[0202] The modules described above as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules; they may be located in one place or distributed across multiple network units; some or all of the modules may be selected according to actual needs to achieve the purpose of this embodiment.

[0203] In addition, all functional modules in the embodiments of the present application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the above-mentioned integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0204] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and other media that can store program codes.

[0205] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling an electronic device to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0206] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0207] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0208] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0209] The above is merely an embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A battery drying method, characterized in that: Applied to drying equipment, the method comprises: During the drying process of the battery to be tested by the drying device, obtaining a first detection parameter at a target position of the drying device, the first detection parameter including temperature and vacuum degree, the target position being determined according to the battery to be tested; Inputting the first detection parameter into a water content model, and outputting the water content of the battery to be tested through the water content model, wherein the water content model is obtained by training a preset first network model based on a first sample data set, wherein the first sample data set includes historical first detection parameters of the drying device during a process of drying a sample battery, and actual measured values of the water content of the sample battery after drying; Output the water content of the battery to be tested.

2. The method according to claim 1, wherein The water content model includes a classification submodule and a regression submodule. Outputting the water content of the battery to be tested through the water content model includes: Inputting the first detection parameter into the classification submodule, and outputting a classification result of the first detection parameter through the classification submodule, wherein the classification result includes qualified and unqualified; The first detection parameter with a qualified classification result is input into the regression submodule, and the water content of the battery to be tested is output through the regression submodule.

3. The method according to claim 2, wherein The first network model includes a first sub-model and a second sub-model. Before inputting the second detection parameter into the sealing strip model, the method further includes: Inputting the historical first detection parameter and the corresponding identification classification into the first sub-model for training to obtain the classification sub-module, wherein the identification classification includes qualified and unqualified; The historical first detection parameter that is identified as qualified and the measured value of the water content are input into the second sub-model for training to obtain the regression sub-module.

4. The method according to claim 2 or 3, wherein: The method further comprises: obtaining second sample data, where the second sample data includes the water content output by the water content model and a measured value of the water content of the battery to be tested; The second sample data is input into the classification submodule and the regression submodule to iteratively update the classification submodule and the regression submodule.

5. The method according to claim 1, wherein The method further comprises: According to the water content of the battery to be tested, the drying parameters of the drying equipment are adjusted. The drying parameters include at least one of drying temperature, drying vacuum and drying time. The greater the water content of the battery to be tested, the greater the drying parameters.

6. The method according to claim 5, wherein The step of adjusting the drying parameters of the drying device according to the water content of the battery to be tested includes: Obtaining a target difference between the water content of the battery to be tested and a preset standard water content; According to the target difference, a drying parameter of the drying device is adjusted, and the target difference is positively correlated with the drying parameter.

7. The method according to claim 1, wherein The number of the batteries to be tested is at least two, the target position includes at least two spatial areas of the drying equipment, different spatial areas correspond to different batteries to be tested, the first detection parameter includes the first detection parameter corresponding to each of the at least two spatial areas, and the water content of the battery to be tested output by the water content model includes the water content of each of the at least two batteries to be tested.

8. The method according to claim 1, wherein The method further comprises: During the process of drying the battery to be tested by the drying device, obtaining a second detection parameter at the target position, wherein the second detection parameter includes a vacuum degree; Inputting the second detection parameter into a sealing strip model, and outputting the health of the sealing strip of the drying device through the sealing strip model, the sealing strip model being obtained by training a preset second network model based on a second sample data set, the second sample data set including historical second detection parameters within a historical time period and a historical sealing degree set of the drying device within the historical time period, the historical sealing degree set indicating changes in the sealing degree of the drying device within the historical time period; The health of the sealing strip is output.

9. The method according to claim 8, wherein The sealing strip model includes an abnormality detection submodule and a health calculation submodule. Outputting the health of the sealing strip of the drying device through the sealing strip model includes: Outputting, by the abnormality detection submodule, a sealing degree set of the drying device according to the second detection parameter, the sealing degree set including changes in the sealing degree of the drying device within a target time period, the target time period including a current moment and at least one historical moment; The health calculation submodule counts the target number of abnormal values in the sealing set, and when the target number reaches a preset threshold, the health of the sealing strip is obtained based on the ratio of the target number to the total number of the sealing set.

10. The method according to claim 9, wherein The second network model includes a third sub-model and the health calculation sub-module. Before inputting the second detection parameter into the sealing strip model, the method further includes: Inputting the historical second detection parameter and the historical sealing degree set into the third sub-model for training to obtain the anomaly detection sub-module; The health calculation submodule is established, and the health calculation submodule is used to count the target number of abnormal values in the historical sealing set, and obtain the health of the sealing strip based on the ratio between the target number and the total number corresponding to the historical sealing set.

11. The method according to claim 8, wherein The method further comprises: When the health of the sealing strip is less than a preset health threshold, a prompt message is output to prompt the user to replace the sealing strip.

12. A battery drying device, characterized in that: Applied to drying equipment, the device comprises: A parameter acquisition module, configured to obtain a first detection parameter at a target position of the drying device during the drying process of the battery to be tested by the drying device, wherein the first detection parameter includes temperature and vacuum degree, and the target position is determined according to the battery to be tested; a first calculation module, configured to input the first detection parameter into a water content model and output the water content of the battery to be tested using the water content model, wherein the water content model is trained based on a first sample data set, the first sample data set including historical first detection parameters of the drying device during the process of drying sample batteries and actual measured water content values of the sample batteries after drying; The water content output module is used to output the water content of the battery to be tested.

13. A drying device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images