Method of controlling electrode coating face density and related products

Abstract

The embodiment of the present application provides a kind of electrode coating surface density control method and related product, the method is by obtaining first surface density and first parameter set, the first surface density is the surface density of user's expected coating, the first parameter set includes the parameter with the correlation degree of coating surface density greater than first threshold value;And based on the first surface density, the first parameter set and target model, target pump revolution is obtained, and then the density of coating is accurately adjusted, can greatly improve the charge-discharge performance of battery.

Description

Technical Field

[0001] This application relates to the field of battery manufacturing technology, and in particular to a method for controlling the surface density of electrode coating and related products. Background Technology

[0002] As a crucial component of electric vehicles, the performance of the power battery directly impacts the overall performance of the vehicle. Battery performance is closely related to the areal density of the coating on the electrodes. During the production process, the ability to accurately and quickly adjust the areal density of the coating is a critical factor determining the battery's charge and discharge performance.

[0003] To accurately and quickly adjust the areal density of the coating, it is necessary to strictly control the pump speed of the coating machine for the coating slurry. In today's battery production process, the pump speed of the coating slurry mainly relies on the subjective experience of the operators for control.

[0004] However, relying solely on the prior knowledge of the staff makes it impossible to accurately adjust the pump speed, which in turn makes it impossible to accurately control the surface density of the coating, severely affecting the charging and discharging performance of the battery. Summary of the Invention

[0005] This application discloses a method for controlling electrode coating surface density and related products. The method uses coating parameters to establish a statistical prediction model, and calculates the target pump speed of the slurry pump based on the trained model and the set value of coating surface density, thereby accurately adjusting the coating surface density and greatly improving the charging and discharging performance of the battery.

[0006] In a first aspect, this application provides a method for controlling the surface density of an electrode coating, comprising: obtaining a first surface density and a first parameter set, wherein the first surface density is the surface density of a coating desired by a user, and the first parameter set includes parameters whose correlation with the coating surface density is greater than a first threshold; obtaining a target pump speed based on the first surface density, the first parameter set, and a target model, wherein the target model characterizes the relationship between the pump speed of the slurry and the surface density of the coating; and controlling the input amount of the slurry in the coating machine according to the target pump speed to obtain a target coating, wherein the surface density of the target coating is a second surface density, and the difference between the second surface density and the first surface density is less than a second threshold.

[0007] This method uses coating parameters to establish a statistical prediction model. Based on the trained model and the coating surface density setting value, the target speed of the slurry pump is calculated, thereby achieving rapid software closed-loop adjustment. This allows for accurate adjustment of the coating surface density and greatly improves the charging and discharging performance of the battery.

[0008] In an optional implementation of the first aspect, after obtaining the target pump revolutions based on the first areal density, the first parameter set, and the target model, the method further includes: updating the target model using the second areal density and the first parameter set.

[0009] In this embodiment, the target model can be continuously learned and updated based on the actual measured areal density and the first parameter, thereby continuously improving the performance of the target model and enabling more accurate adjustment of the coating areal density.

[0010] In an optional implementation of the first aspect, obtaining the target pump revolutions based on the first areal density, the first parameter set, and the target model includes: obtaining a first pump revolution, wherein the first pump revolution is an estimate that makes the coating areal density equal to the first areal density; generating a pump revolution set based on the first pump revolution, wherein the minimum pump revolution in the pump revolution set is less than the first pump revolution, and the maximum pump revolution in the pump revolution set is greater than the first pump revolution; sequentially using each pump revolution in the first parameter set and the pump revolution set as input to the target model to obtain an areal density set; obtaining a third areal density from the areal density set, wherein the difference between the third areal density and the first areal density is less than a second threshold; and determining the pump revolution in the pump revolution set corresponding to the third areal density as the target pump revolution.

[0011] In this embodiment, the operator can determine the pump revolutions (PCRs) that will result in a coating density approximately equal to the first areal density, based on the first areal density and their prior knowledge. Then, based on the first PCR, several pump revolutions close to the first PCR are selected as the pump revolution set. Each PCR in the pump revolution set and the first parameter set are then used as inputs to the target model to obtain several corresponding areal densities. It is understood that among these areal densities, there exists an areal density that is relatively close to the first areal density (i.e., the third areal density), and the pump revolutions corresponding to the third areal density can be used as the target pump revolutions.

[0012] In this embodiment, the approximate value of the pump speed is determined by the first areal density, and a large number of samples are selected based on this value. The target model is used to predict these samples, which can obtain the target pump speed more accurately, so that the final areal density of the coating is closer to the first areal density.

[0013] In an optional implementation of the first aspect, before obtaining the first areal density and the first parameter set, the method further includes: determining a second parameter set, the second parameter set including parameters characterizing the properties of the slurry and parameters characterizing the performance of the coating machine, the first parameter set being a subset of the second parameter set; and determining the parameters in the second parameter set whose correlation with the coating areal density is greater than a first threshold as the first parameter set.

[0014] Correlation is a measure of the degree of linear correlation between variables. Due to the different research subjects, correlation can be defined in various ways. Correlation is a statistical indicator used to reflect the closeness of the relationship between variables. It can be calculated using the product-moment method, which is based on the deviations of two variables from their respective means, and the degree of correlation between the two variables is reflected by multiplying the two deviations.

[0015] Generally, the correlation between two variables is an objectively existing coefficient. To calculate this coefficient, a large amount of sample data is usually used. In this sample data, the values ​​of the two variables are fixed in each data point. For example, assuming that there is a parameter X in the first parameter set mentioned above, and the coating surface density is represented by Y, the correlation between these two parameters can be calculated based on the sample data shown in Table 1 below:

[0016] Table 1

[0017] Sample number 1 2 …… N-1 N (X, Y) <![CDATA[(X1,Y1)]]> <![CDATA[(X2,Y2)]]> …… <![CDATA[(X N-1 ,AND N-1 )]]> <![CDATA[(X1,Y1)]]>

[0018] (X1, Y1) represents the area density of the coating obtained when the value of parameter X is X1, where X1 and Y1 are both fixed values; (X2, Y2) represents the area density of the coating obtained when the value of parameter X is X2, where X2 and Y2 are both fixed values, and so on.

[0019] Based on the above sample data, correlation analysis can be used to obtain the correlation between these two coefficients. Generally speaking, the larger the sample data, i.e., the larger the value of N, the more accurate the calculated correlation will be.

[0020] Understandably, during the coating process of a battery, the characteristics of the coating slurry (e.g., slurry pump count, slurry pump pressure, slurry temperature, slurry density, etc.) and the performance of the coating machine (e.g., die head operating clearance, die head drive clearance viscosity η, coating speed, etc.) can all significantly affect the coating areal density. In this embodiment, to determine these parameters strongly correlated with coating areal density and exclude other parameters unrelated to it, correlation analysis or analysis of variance can be used to identify the influencing factors strongly correlated with coating areal density from a large number of coating parameters. This reduces the predictive burden on the model and allows for more accurate determination of the target pump speed, enabling more precise control over the coating areal density.

[0021] In one alternative embodiment of the first aspect, the first set of parameters includes one or more of the following: number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter differential pressure of the coating machine, die cavity pressure, die head operating clearance, die head drive clearance, viscosity, and coating speed.

[0022] In an optional implementation of the first aspect, before obtaining the first areal density and the first parameter set, the method further includes: training multiple sample data to obtain multiple weak learners, wherein any sample data in the multiple sample data represents the correspondence between the first parameter set, the pump speed and the coating areal density; and weightedly fusing the multiple weak learners to obtain the target model.

[0023] The sample data can be obtained by recording the previous coating process, and may include the specific values ​​of each parameter in the first parameter set, the pump revolutions, and the areal density of the coating at that pump revolution. In this embodiment, the training samples are distributed according to different weights to obtain the multiple sample data. Each sample data can be trained by selecting a corresponding basis function as a weak learner for the decision tree. The distribution of the training data is updated iteratively until the number of iterations is reached or the loss function is less than a certain threshold. Then, these multiple weak learners are weighted and fused to produce a final stronger learner (i.e., the target model). In this way, the obtained target model can accurately predict the areal density of the coating by the pump revolution, so that the workers can more accurately obtain the pump revolutions corresponding to the desired areal density (i.e., the first areal density).

[0024] In one alternative embodiment of the first aspect, the third areal density is the areal density in the set of areal densities that has the smallest difference from the first areal density.

[0025] In this embodiment, by obtaining the areal density with the smallest difference from the first areal density in the areal density set as the third areal density, the difference between the coated areal density and the desired areal density (and the first areal density) can be minimized to the greatest extent possible during the subsequent coating process.

[0026] In an optional implementation of the first aspect, generating a set of pump revolutions based on the first pump revolutions includes: generating a first pump revolution sequence based on the first pump revolutions, wherein the first pump revolution sequence is an arithmetic progression and any pump revolution in the first pump revolution sequence is greater than the first pump revolution; generating a second pump revolution sequence based on the first pump revolutions, wherein the second pump revolution sequence is an arithmetic progression and any pump revolution in the second pump revolution sequence is less than the first pump revolution; and combining the first pump revolutions, the first pump revolution sequence, and the second pump revolution sequence to obtain the set of pump revolutions.

[0027] In this embodiment, after determining the first pump revolutions, the first pump revolutions can be used as a base point. The first pump revolutions are gradually increased, with each increase being the same value, and the revolutions after each increase are obtained, resulting in an arithmetic sequence, i.e., the first pump revolutions sequence. Then, the first pump revolutions are gradually decreased, with each decrease being the same value, and the revolutions after each decrease are obtained, resulting in another arithmetic sequence, i.e., the second pump revolutions sequence. Combining these two sequences with the first pump revolutions yields the aforementioned set of pump revolutions. Thus, when subsequently predicting the coating surface density corresponding to each pump revolution in the set of pump revolutions using the target model, the surface density values ​​in the resulting set of surface densities are evenly distributed, thereby minimizing the difference between the final coating surface density and the first surface density.

[0028] Secondly, this application provides a device for controlling the surface density of an electrode coating, comprising: an acquisition unit for acquiring a first surface density and a first parameter set, wherein the first surface density is the surface density of a coating desired by a user, and the first parameter set includes parameters whose correlation with the coating surface density is greater than a first threshold; a prediction unit for obtaining a target pump speed based on the first surface density, the first parameter set, and a target model, wherein the target model characterizes the relationship between the pump speed of the slurry and the surface density of the coating; and a control unit for controlling the input amount of slurry in the coating machine according to the target pump speed to obtain a target coating, wherein the surface density of the target coating is a second surface density, and the difference between the second surface density and the first surface density is less than a second threshold.

[0029] In an alternative embodiment of the second aspect, the apparatus further includes an update unit for updating the target model using the second surface density and the first parameter set.

[0030] In an optional implementation of the second aspect, the prediction unit is specifically configured to: acquire a first pump revolution, the first pump revolution being an estimated value that makes the coating areal density equal to the first areal density; generate a set of pump revolutions based on the first pump revolution, wherein the minimum pump revolution in the set is less than the first pump revolution, and the maximum pump revolution in the set is greater than the first pump revolution; sequentially use each pump revolution in the first parameter set and the set of pump revolutions as input to the target model to obtain a set of areal densities; acquire a third areal density from the set of areal densities, wherein the difference between the third areal density and the first areal density is less than a second threshold; and determine the pump revolution in the set of pump revolutions corresponding to the third areal density as the target pump revolution.

[0031] In an optional embodiment of the second aspect, the apparatus further includes: a determining unit, configured to determine a second parameter set, the second parameter set including parameters characterizing the properties of the slurry and parameters characterizing the performance of the coating machine, wherein the first parameter set is a subset of the second parameter set; and an analysis unit, configured to determine the parameters in the second parameter set whose correlation with the coating surface density is greater than a first threshold as the first parameter set.

[0032] In an optional embodiment of the second aspect, the first set of parameters includes one or more of the following: number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter differential pressure of the coating machine, die cavity pressure, die head operating clearance, die head drive clearance, viscosity, and coating speed.

[0033] In an optional embodiment of the second aspect, the apparatus further includes: a training unit for training multiple sample data to obtain multiple weak learners, wherein any sample data in the multiple sample data represents the correspondence between the first parameter set, the pump speed and the coating surface density; and a fusion unit for weighted fusion of the multiple weak learners to obtain the target model.

[0034] In an optional implementation of the second aspect, the third areal density is the areal density in the set of areal densities that has the smallest difference from the first areal density.

[0035] In an optional implementation of the second aspect, the prediction unit is specifically configured to: generate a first pump rotation number sequence based on the first pump rotation number, wherein the first pump rotation number sequence is an arithmetic progression sequence and any pump rotation number in the first pump rotation number sequence is greater than the first pump rotation number; generate a second pump rotation number sequence based on the first pump rotation number, wherein the second pump rotation number sequence is an arithmetic progression sequence and any pump rotation number in the second pump rotation number sequence is less than the first pump rotation number; and combine the first pump rotation number, the first pump rotation number sequence, and the second pump rotation number sequence to obtain the pump rotation number set.

[0036] Thirdly, this application provides an electronic device comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, and the one or more processors invoking the computer instructions to cause the electronic device to perform the methods described in the first aspect and any possible method described in the first aspect.

[0037] Fourthly, this application provides a computer-readable storage medium including instructions, characterized in that, when the instructions are executed on an electronic device, the electronic device performs the methods described in the first aspect and any possible method described in the first aspect. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments or background art of this application, the accompanying drawings used in the embodiments or background art of this application will be briefly introduced below.

[0039] Figure 1 A flowchart illustrating a method for controlling electrode coating surface density provided in this application embodiment;

[0040] Figure 2 A flowchart illustrating a method for controlling electrode coating surface density provided in this application embodiment;

[0041] Figure 3 A flowchart illustrating a method for controlling electrode coating surface density provided in this application embodiment;

[0042] Figure 4 A flowchart illustrating a model training method provided in this application embodiment;

[0043] Figure 5 A flowchart illustrating a method for obtaining a target pump speed provided in an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of the structure of an electrode coating surface density control device provided in an embodiment of this application;

[0045] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described below in conjunction with the accompanying drawings.

[0047] The terms "first" and "second," etc., used in the specification, claims, and drawings of this application are used only to distinguish different objects and not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0048] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0049] In this application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the relationship between related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items. For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c".

[0050] This invention provides methods and related products for controlling the areal density of electrode coatings. To more clearly describe the solutions of this invention, the following section introduces some knowledge related to the electrode coating areal density control methods and related products provided in this application.

[0051] (1) Pump speed

[0052] Pump speed refers to the number of rotations of the pump shaft (centrifugal pump, rotary pump, etc.) that drives the impeller or rotor in a coating machine. The number of rotations is positively correlated with the coating surface density. By adjusting the pump speed in the coating machine, the input amount of coating slurry can be adjusted accordingly, thereby adjusting the coating surface density.

[0053] (2) Bootstrap aggregating (Bagging) algorithm

[0054] Bagging, also known as the bagging algorithm, is an important ensemble learning method. This algorithm extracts a training set from the original sample set. In each round, n training samples are extracted from the original sample set (some samples may be extracted multiple times, while others may not be extracted at all); this process is repeated k times, resulting in k independent training sets. Each time, one training set is used to obtain a model. The k training sets yield k models with relatively weak learning abilities. Finally, these k models are weighted and fused to obtain a model with stronger learning abilities.

[0055] (3) Analysis of variance

[0056] Analysis of variance (ANOVA) is a statistical method used to analyze the differences in means among multiple groups of data. It can be used to test whether the means of multiple populations are equal and to study the influence of one or more categorical independent variables on a numerical dependent variable.

[0057] (4) Correlation coefficient method

[0058] The correlation coefficient is a statistic calculated from sample data to measure the strength of the linear relationship between two variables. The correlation coefficient method involves performing a significance test on the correlation coefficient to determine whether the relationship reflected in the sample is representative of the relationship between the two variables in the population.

[0059] With the urgent need for energy conservation and emission reduction across society, developing new energy vehicles with environmental protection and energy-saving advantages has become a consensus in the automotive industry. Electric vehicles, as the main direction of new energy vehicle development, face many challenges and pressures. As an important component of electric vehicles, the performance of power batteries directly affects the overall performance of electric vehicles. Battery performance is directly related to electrode parameters. As one of the main parameters of electrodes, the coating density of electrode materials is crucial. If the coating density is too small, the battery capacity may not reach the nominal capacity. If the coating density is too large, it will easily lead to material waste, affecting the charging and discharging performance and service life of the battery. In severe cases, it may even cause safety hazards.

[0060] To accurately and quickly adjust the areal density of the coating, it is necessary to strictly control the pump speed of the coating machine on the coating slurry. For example... Figure 1As shown, in current battery production processes, controlling the coating slurry pump speed primarily relies on the measuring device at the tail of the coating machine. After online measurement of the coating surface density, operators can adjust the pump speed based on their subjective experience to control the coating surface density. However, relying solely on the operator's prior knowledge makes it impossible to accurately adjust the pump speed, thus hindering precise control of the coating surface density and severely impacting the battery's charge and discharge performance. Furthermore, the significant distance between the tail-end measuring device and the feed adjustment equipment at the head of the machine results in a lag in adjustment, preventing accurate and rapid online adjustment.

[0061] To address the above problems, embodiments of this application provide a method for controlling electrode coating surface density, such as... Figure 2 As shown, this method can establish a statistical prediction model using coating parameters, and calculate the target pump speed of the slurry pump based on the trained model and the set value of the coating surface density, thereby accurately adjusting the coating surface density and greatly improving the charging and discharging performance of the battery.

[0062] Next Figure 2 The method for controlling the electrode coating surface density involved in the process will be further explained in detail; please refer to [link / reference needed]. Figure 3 .

[0063] Figure 3 This is a flowchart illustrating a method for controlling the surface density of an electrode coating, as provided in an embodiment of this application. Figure 3 As shown, the method may include the following steps:

[0064] 301. The electronic device acquires the first surface density and the first set of parameters.

[0065] The aforementioned electronic device can be a mobile phone, tablet computer, computer with data transceiver capabilities (such as a laptop computer, PDA, etc.), mobile internet device, terminal in industrial control, or wearable device. Optionally, when the electronic device is a terminal in industrial control, it can be an electronic coating machine with data processing capabilities. It is understood that this application does not limit the specific form of the terminal device.

[0066] The aforementioned first areal density is the areal density of the coating desired by the user. During battery production, different battery models may have different requirements for coating areal density. In this embodiment, the operator can determine the appropriate coating areal density (i.e., the aforementioned first areal density) based on the battery model and input it into the electronic device.

[0067] The aforementioned first parameter set includes parameters whose correlation with coating surface density is greater than a first threshold. This first parameter set may include, but is not limited to, parameters such as the number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter differential pressure, die cavity pressure, die head operating clearance, die head drive clearance, viscosity, and coating speed. It should be understood that these parameters are all strongly correlated with coating surface density, and their specific values ​​can be measured. In practice, in this application, the electronic device will acquire these parameters and their specific values.

[0068] Understandably, during the coating process of a battery, the characteristics of the coating slurry (e.g., slurry pump count, slurry pump pressure, slurry temperature, slurry density, etc.) and the performance of the coating machine (e.g., die head operating clearance, die head drive clearance viscosity η, coating speed, etc.) can both significantly affect the coating surface density. Assuming all parameters potentially strongly correlated with coating surface density are referred to as the second parameter set, which includes parameters characterizing the slurry characteristics and parameters characterizing the coating machine performance; to determine the truly strongly correlated parameters (i.e., the aforementioned first parameter set) from this second parameter set and exclude other parameters unrelated to coating surface density, in an optional implementation, before performing step 301, correlation analysis or variance analysis can be used to identify the influencing factors strongly correlated with coating surface density from a large number of coating parameters. This reduces the predictive burden on the model and allows for more accurate determination of the target pump speed, enabling more precise control over the coating surface density.

[0069] Specifically, to determine these parameters strongly correlated with coating surface density and exclude other parameters unrelated to it, correlation analysis or analysis of variance can be used to identify the influencing factors strongly correlated with coating surface density from a large number of coating parameters. For example, to calculate the correlation between slurry temperature and coating surface density, after obtaining a certain amount of data on slurry temperature and coating surface density, the following formula can be used to calculate the correlation coefficient between slurry temperature and coating surface density:

[0070]

[0071] Where X represents the slurry temperature, Y represents the coating areal density, and cov(X,Y) represents the covariance of these two parameters calculated based on the above data. This represents the variance of the slurry temperature calculated based on the above data. This represents the variance of the coating surface density calculated based on the above data. ρ xyThis refers to the correlation coefficient between slurry temperature and coating surface density. A value close to 1 or -1 is considered to indicate a strong correlation. In the embodiments of this application, parameters strongly correlated with coating surface density may include the number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter pressure difference, mold cavity pressure, mold head operating clearance, mold head drive clearance, viscosity, and coating speed.

[0072] Understandably, the correlation between other parameters and coating surface density can be calculated using the above formulas, which will not be listed here. In addition, besides the methods mentioned above, other correlation analysis methods (such as chart analysis, information entropy and mutual information analysis, etc.) can also be used to calculate the correlation between each parameter and coating surface density, which is not limited in this application.

[0073] 302. The electronic device obtains the target pump speed based on the first surface density, the first parameter set, and the target model.

[0074] The target model described above characterizes the relationship between the pump speed of the slurry and the areal density of the coating.

[0075] In an optional implementation, to reduce the difference between the first surface density and the second surface density, after obtaining the target revolutions and the second surface density, the electronic device will update the target model using the target revolutions and the second surface density. That is, after obtaining the target revolutions and the second surface density, the electronic device can use the second surface density, the second revolutions, and the first parameter set as new sample data, and then use this new sample data as the input for model training to obtain a model with better predictive performance, thereby achieving adaptation to long-term fluctuations and measurement deviations in the production line.

[0076] Optionally, before implementing this method, the aforementioned electronic device can train the target model on the sample data based on the bagging algorithm. Figure 4 This is a flowchart illustrating a model training method provided in an embodiment of this application. The target model described above can be obtained based on the process illustrated in the flowchart. Figure 4 As shown, any sample data in the total training sample includes the aforementioned first parameter set, the pump speed of the coating slurry (the values ​​of each parameter in the first parameter set and the value of the pump speed are already determined), and the areal density of the coating machine under the first parameter set and the pump speed. In the actual training process, the above total training sample can be first divided into different weights (i.e., Figure 4 As shown in the diagram, W1, W2, ..., Wn) are assigned to obtain n sub-training samples. Then, weak learners with corresponding basis functions (decision trees) are selected for each of these n sub-training samples for training, resulting in n weak learners with relatively weak learning abilities (i.e.,...). Figure 4The weak learners shown (1, 2, ..., n) are trained and then assigned weights according to the weight allocation strategy (i.e. Figure 4 The n weak learners (W1', W2', ..., Wn') shown in the figure are weighted and fused to obtain a strong learner with stronger learning ability, which can be used as the target model mentioned above.

[0077] Specifically, to obtain the target pump revolutions, after the electronic device acquires the first areal density and the first parameter set, it will also acquire a first pump revolution, which is the pump revolution that makes the coating density approximately equal to the first areal density. This pump revolution can be derived by the operator based on their prior knowledge and then input into the electronic device. Afterward, the electronic device can select several pump revolutions that are close in magnitude to the first pump revolution as the pump revolution set, and sequentially use each pump revolution in the pump revolution set and the first parameter set as input to the target model to obtain several corresponding areal densities. It is understood that among these areal densities, there exists an areal density that is relatively close to the first areal density (hereinafter referred to as the third areal density), and the pump revolution corresponding to this third areal density can be used as the target pump revolution.

[0078] Furthermore, in an optional implementation, the aforementioned set of pump revolutions can be obtained as follows: After determining the first pump revolution, using the first pump revolution as a base, the first pump revolution is gradually increased, with each increase being the same value, and the revolution value after each increase is obtained, resulting in an arithmetic sequence, i.e., the first pump revolution sequence; then, the first pump revolution is gradually decreased, with each decrease being the same value, and the revolution value after each decrease is obtained, resulting in another arithmetic sequence, i.e., the second pump revolution sequence; finally, these two sequences are combined with the first pump revolution to obtain the aforementioned set of pump revolutions. In this way, when subsequently predicting the coating surface density corresponding to each pump revolution in the aforementioned set of pump revolutions using the aforementioned target model, the surface density values ​​in the obtained surface density set are evenly distributed, thereby minimizing the difference between the final coating surface density and the first surface density. Furthermore, the difference in the aforementioned arithmetic sequence can be set according to actual needs, and this application does not limit this.

[0079] In an optional implementation, in order to ensure that the difference between the actual areal density of the coating and the desired areal density (and the first areal density) is minimized during the subsequent coating process, the electronic device may select the areal density with the smallest difference from the first areal density from the set of areal densities as the third areal density.

[0080] To provide a more detailed explanation of the aforementioned set of pump reference numbers and the process for obtaining the target pump speed, please refer to the following text. Figure 5. Figure 5 This is a flowchart illustrating a method for obtaining a target pump speed according to an embodiment of this application. Figure 5 As shown, Figure 5 In this context, 'r' represents the first pump revolutions. The electronic device can use this pump revolutions 'r' as a base point, with a difference of 0.001r, to gradually increase the first pump revolutions, obtaining the revolution value after each increase, resulting in an arithmetic sequence 502. This arithmetic sequence 502 is the first pump revolution sequence. Similarly, using this pump revolutions 'r' as a base point, with a difference of 0.001r, the first pump revolutions can be gradually decreased, with each decrease being the same value, obtaining the revolution value after each decrease, resulting in another arithmetic sequence 501. This arithmetic sequence 501 is the second pump revolution sequence. It should be understood that... Figure 5 Only some values ​​in sequence 501 and sequence 502 are shown symbolically, and each number in sequence 501 and sequence 502 is not shown.

[0081] After obtaining sequences 501 and 502, the aforementioned electronic device can sequentially use each revolution in sequences 501 and 502, along with parameter set 503, as input to the target model, and obtain several predicted values ​​of surface density (ρ(0.5r)……ρ(0.75r)……ρ(r)……ρ(1.25r)……ρ(1.5r)), which serve as the aforementioned surface density set, i.e. Figure 5 The areal density set 504 is shown in the diagram. The parameter set 503 is the aforementioned first parameter set, which may include multiple parameters such as X1r, X2r, ..., Xnr. These parameters can be parameters strongly related to the coating areal density, such as the number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter pressure difference, mold cavity pressure, mold head operating clearance, mold head drive clearance, viscosity, and coating speed. It should be noted that in this method, the values ​​of these parameters can be measured and are uniquely determined.

[0082] After obtaining the predicted values ​​of the above-mentioned areal densities, the electronic device will select the predicted value ρ that meets the requirements. s , the ρ s That is, it can be used as the third surface density mentioned above, ρ s It must satisfy the condition |ρ s -ρ t |<=D, where ρ t Where ρ is the first surface density mentioned above, D is the second threshold mentioned above. Afterwards, the electronic device can then... s The corresponding revolutions r s The target pump speed is as described above.

[0083] Understandably, there may be multiple areal densities that meet the requirements within the aforementioned areal density set. For example, when the value of the first areal density is 100 and the second threshold is 0.1, there exists an areal density ρ1 with a value of 9.96, corresponding to a pump speed r1; furthermore, there exists an areal density ρ2 with a value of 9.92, corresponding to a pump speed r2. In this case, the difference between areal density ρ1 and the first areal density is 0.04, and the difference between areal density ρ2 and the first areal density is 0.08. The electronic device can use the pump speed (i.e., r2) corresponding to the areal density with the smaller difference as the target pump speed.

[0084] 303. The electronic equipment controls the input amount of slurry in the coating machine according to the target pump speed mentioned above, so as to obtain the target coating.

[0085] The aforementioned target pump speed is used to control the input amount of slurry in the coating machine to obtain the aforementioned target coating. The areal density of this target coating is a second areal density, and the difference between this second areal density and the aforementioned first areal density is less than a second threshold. It is understood that the aforementioned target pump speed is merely the pump speed calculated by the aforementioned target model based on the aforementioned first parameter set and the aforementioned first areal density. That is, for the aforementioned target model, the target pump speed is the ideal pump speed that makes the coating areal density of the coating machine equal to the aforementioned first areal density under the aforementioned first parameter set. However, in reality, when the coating machine uses the first pump speed to coat the battery, the actual areal density of the resulting coating (i.e., the aforementioned second areal density) will still have a certain difference from the aforementioned first areal density. When this difference is less than the aforementioned second threshold, the target pump speed can be used as the final pump speed.

[0086] After obtaining the target pump speed, the electronic device can adjust the pump speed of the coating slurry in the coating machine, thereby controlling the input amount of the coating slurry in the coating machine to obtain the target coating with an areal density close to the first areal density.

[0087] The following is a schematic diagram of the structure of an electrode coating surface density control device provided in an embodiment of this application. Please refer to... Figure 6 .like Figure 6 As shown, Figure 6 The areal density control device in the middle can perform Figure 3 A process flow for controlling the surface density of the coating on the intermediate electrode, the apparatus comprising:

[0088] The acquisition unit 601 is used to acquire a first areal density and a first parameter set, wherein the first areal density is the areal density of the coating expected by the user, and the first parameter set includes parameters whose correlation with the coating areal density is greater than a first threshold.

[0089] The prediction unit 602 is used to obtain a target pump speed based on the first areal density, the first parameter set and the target model. The target model characterizes the relationship between the pump speed of the slurry and the areal density of the coating. The target pump speed is used to control the input amount of slurry in the coating machine.

[0090] Control unit 603 is used to control the input amount of slurry in the coating machine according to the target pump speed to obtain the target coating, wherein the areal density of the target coating is a second areal density, and the difference between the second areal density and the first areal density is less than a second threshold.

[0091] In an optional embodiment, the above-described apparatus further includes an update unit 604, configured to update the target model using the second surface density and the first parameter set.

[0092] In an optional implementation, the prediction unit is specifically configured to: obtain a first pump revolution, which is an estimate of the areal density of the coating; generate a set of pump revolutions based on the first pump revolution, wherein the minimum pump revolution in the set is less than the first pump revolution, and the maximum pump revolution in the set is greater than the first pump revolution; sequentially use each pump revolution in the first parameter set and the pump revolution set as input to the target model to obtain an areal density set; obtain a third areal density from the areal density set, wherein the difference between the third areal density and the first areal density is less than the second threshold; and determine the pump revolution corresponding to the third areal density in the pump revolution set as the target pump revolution.

[0093] In an optional embodiment, the above-mentioned apparatus further includes: a determining unit 605, configured to determine a second parameter set, the second parameter set including parameters characterizing the properties of the slurry and parameters characterizing the performance of the coating machine, wherein the first parameter set is a subset of the second parameter set; and an analysis unit 606, configured to determine the parameters in the second parameter set whose correlation with the coating surface density is greater than a first threshold as the first parameter set.

[0094] In one optional implementation, the first set of parameters includes one or more of the following: number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter differential pressure of the coating machine, die cavity pressure, die head operating clearance, die head drive clearance, viscosity, and coating speed.

[0095] In an optional embodiment, the above apparatus further includes: a training unit 607, used to train multiple sample data to obtain multiple weak learners; each of the multiple sample data represents the correspondence between the first parameter set, the pump speed and the coating surface density; and a fusion unit 608, used to perform weighted fusion of the multiple weak learners to obtain the target model.

[0096] In an optional implementation, the third areal density is the areal density in the set of areal densities that has the smallest difference from the first areal density.

[0097] In an optional implementation, the prediction unit is specifically used to: generate a first pump revolution sequence based on the first pump revolution, wherein the first pump revolution sequence is an arithmetic progression sequence and any pump revolution in the first pump revolution sequence is greater than the first pump revolution; generate a second pump revolution sequence based on the first pump revolution, wherein the second pump revolution sequence is an arithmetic progression sequence and any pump revolution in the second pump revolution sequence is less than the first pump revolution; and combine the first pump revolution, the first pump revolution sequence, and the second pump revolution sequence to obtain the pump revolution set.

[0098] It should be understood that the division of the control device into units with the above density is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. For example, each of the above units can be a separately established processing element, or they can be integrated into the same chip. Alternatively, they can be stored as program code in the controller's storage element, and called and executed by a processing element of the processor. Furthermore, the units can be integrated together or implemented independently. The processing element here can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the method or each of the above units can be completed through integrated logic circuits in the hardware of the processor element or through software instructions. The processing element can be a general-purpose processor, such as a CPU, or one or more integrated circuits configured to implement the above method, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), etc.

[0099] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7As shown, the electronic device 70 includes a processor 701, a memory 702, and a communication interface 703; the processor 701, memory 702, and communication interface 703 are interconnected via a bus 704. Specifically, the electronic device 70 can be the electronic device described above.

[0100] The memory 702 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CDROM). The memory 702 is used for related instructions and data. The communication interface 704 is used for receiving and sending data. Specifically, the communication interface 704 can implement... Figure 6 The function of the acquisition unit 601 in the middle.

[0101] Processor 701 can be one or more central processing units (CPUs). When processor 701 is a CPU, the CPU can be a single-core CPU or a multi-core CPU. Specifically, processor 701 can implement... Figure 5 The functions of the control unit 603, determination unit 605, analysis unit 606, training unit 607, fusion unit 608, and update unit 604 are described.

[0102] In embodiments of this application, another computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, performs the following: obtaining a first areal density and a first parameter set, wherein the first areal density is the areal density of a coating desired by a user, and the first parameter set includes parameters whose correlation with the coating areal density is greater than a first threshold; obtaining a target pump speed based on the first areal density, the first parameter set, and a target model, wherein the target model characterizes the relationship between the pump speed of the slurry and the areal density of the coating; and obtaining a target coating based on the input amount of slurry in the coating machine, wherein the areal density of the target coating is a second areal density, and the difference between the second areal density and the first areal density is less than a second threshold.

[0103] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the electrode coating surface density control method provided in the foregoing embodiments.

[0104] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] This invention is described in terms of flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowcharts and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0108] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling the surface density of an electrode coating, characterized in that, include: Obtain a first areal density and a first parameter set, wherein the first areal density is the areal density of the coating expected by the user, and the first parameter set includes parameters whose correlation with the coating areal density is greater than a first threshold. Obtain the first pump speed, which is an estimated value of the pump speed when the coating surface density is the first surface density, and the first pump speed is input by the user; Based on the first pump speed, a first pump speed sequence is generated. The first pump speed sequence is an arithmetic sequence, and any pump speed in the first pump speed sequence is greater than the first pump speed. Based on the first pump revolution, a second pump revolution sequence is generated. The second pump revolution sequence is an arithmetic sequence, and any pump revolution in the second pump revolution sequence is less than the first pump revolution. By combining the first pump revolution count, the first pump revolution count sequence, and the second pump revolution count sequence, a pump revolution count set is obtained; Each pump revolution in the first parameter set and the pump revolution set is used as the input to the target model to obtain the areal density set; the target model characterizes the relationship between the pump revolution of the slurry and the areal density of the coating. A third surface density is obtained from the set of surface densities, wherein the difference between the third surface density and the first surface density is less than a second threshold. The pump revolutions corresponding to the third surface density in the set of pump revolutions are determined as the target pump revolutions; Based on the target pump speed, the input amount of slurry in the coating machine is controlled to obtain the target coating. The areal density of the target coating is the second areal density, and the difference between the second areal density and the first areal density is less than the second threshold. The first parameter set includes a first parameter, and the correlation between the first parameter and the coating surface density is determined based on the following formula: Where X represents the first parameter, Y represents the coating surface density, and cov(X,Y) represents the calculated covariance between the first parameter and the coating surface density. This represents the variance of the calculated first parameter. This represents the variance of the calculated coating surface density. This indicates the correlation between the first parameter and the coating surface density.

2. The method according to claim 1, characterized in that, After obtaining the target pump speed based on the first areal density, the first parameter set, and the target model, the method further includes: The target model is updated using the second surface density and the first parameter set.

3. The method according to claim 1 or 2, characterized in that, Before obtaining the first areal density and the first set of parameters, the method further includes: A second parameter set is determined, which includes parameters characterizing the properties of the slurry and parameters characterizing the performance of the coating machine, wherein the first parameter set is a subset of the second parameter set; The parameters in the second parameter set whose correlation with the coating surface density is greater than the first threshold are determined as the first parameter set.

4. The method according to claim 1 or 2, characterized in that, The first set of parameters includes one or more of the following: number of slurry pumps, slurry pump pressure, slurry temperature, slurry density, filter pressure difference of the coating machine, die cavity pressure, die head operating clearance, die head driving clearance, viscosity, and coating speed.

5. The method according to claim 1 or 2, characterized in that, Before obtaining the first areal density and the first set of parameters, the method further includes: Multiple weak learners are obtained by training on multiple sample data, wherein any sample data in the multiple sample data represents the correspondence between the first parameter set, the pump speed and the coating surface density; The target model is obtained by weighted fusion of the multiple weak learners.

6. The method according to claim 1 or 2, characterized in that, The third areal density is the areal density in the set of areal densities that has the smallest difference from the first areal density.

7. A device for controlling areal density, characterized in that, include: The acquisition unit is used to acquire a first areal density and a first parameter set, wherein the first areal density is the areal density of the coating expected by the user, and the first parameter set includes parameters whose correlation with the coating areal density is greater than a first threshold. A prediction unit is used to obtain a first pump revolution count, which is an estimated value of the pump revolution count when the areal density of the coating is equal to the first areal density, and the first pump revolution count is input by the user; based on the first pump revolution count, a first pump revolution count sequence is generated, which is an arithmetic progression sequence, and any pump revolution count in the first pump revolution count sequence is greater than the first pump revolution count; based on the first pump revolution count, a second pump revolution count sequence is generated, which is an arithmetic progression sequence, and any pump revolution count in the second pump revolution count sequence is less than the first pump revolution count; combining the first pump revolution count, the first pump revolution count sequence, and the second pump revolution count sequence, a pump revolution count set is obtained; each pump revolution count in the first parameter set and the pump revolution count set is used as the input of the target model in sequence to obtain an areal density set; the target model represents the relationship between the pump revolution count of the slurry and the areal density of the coating; a third areal density is obtained from the areal density set, and the difference between the third areal density and the first areal density is less than a second threshold; the pump revolution count in the pump revolution count set corresponding to the third areal density is determined as the target pump revolution count; The control unit is used to control the input amount of slurry in the coating machine according to the target pump speed to obtain the target coating. The areal density of the target coating is a second areal density, and the difference between the second areal density and the first areal density is less than a second threshold. The first parameter set includes a first parameter, and the correlation between the first parameter and the coating surface density is determined based on the following formula: Where X represents the first parameter, Y represents the coating surface density, and cov(X,Y) represents the calculated covariance between the first parameter and the coating surface density. This represents the variance of the calculated first parameter. This represents the variance of the calculated coating surface density. This indicates the correlation between the first parameter and the coating surface density.

8. An electronic device, characterized in that, The electronic device includes: one or more processors and a memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1 to 6.

Images