Automatic rubber coating and lug folding device for small polymer square lithium battery and control method of automatic rubber coating and lug folding device

Abstract

The invention relates to an automatic rubber coating and lug folding device for a small polymer square lithium battery and a control method of the automatic rubber coating and lug folding device. The automatic rubber coating and lug folding device comprises a battery cell feeding assembly, a top rubber coating assembly, a top rubber coating pressing and shaping assembly, a lug folding assembly, a lug folding and shaping assembly, a surrounding rubber assembly and a rotary discharging assembly, the battery cell feeding assembly, the top rubber coating assembly, the top rubber coating pressing and shaping assembly, the tab folding assembly, the tab folding and shaping assembly, the surrounding rubber assembly and the rotary discharging assembly are sequentially and annularly arranged in the anticlockwise direction, and a hollow rotary platform assembly is arranged at the center of the battery cell feeding assembly, the top rubber coating assembly, the top rubber coating pressing and shaping assembly, the tab folding assembly, the tab folding and shaping assembly, the surrounding rubber assembly and the rotary discharging assembly. A plurality of jigs for clamping battery cells are uniformly arranged at the edge of the rotary table, and a rotary table is arranged at the center of the bottom of the rotary table. The production efficiency can be remarkably improved, the labor cost is reduced, the consistency and quality of products are ensured, real-time monitoring and dynamic adjustment are achieved through a sensor and a control system, and the production efficiency and the product quality are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic taping and ear folding processing for lithium batteries, and particularly to an automatic taping and ear folding device for small polymer square lithium batteries and its control method. Background Art

[0002] The importance of ear bending and taping for lithium batteries. The ear is an important component of a lithium battery, used to connect the internal electrode of the battery to the external circuit. The ear bending and taping processes directly affect the performance and safety of the battery; the bending operation needs to ensure the accurate shape and position of the ear to avoid short circuits or poor contact; taping is used to fix the ear and prevent it from loosening or falling off during battery use; in traditional processes, ear bending and taping mostly rely on manual operations, which have problems such as low efficiency, poor accuracy, and high labor intensity, and are difficult to meet the requirements of large-scale production.

[0003] In the prior art, manual operation has low efficiency: the traditional manual bending and taping methods are slow and difficult to meet the high-efficiency requirements of modern lithium battery production; the accuracy and consistency are poor: manual operation easily leads to inconsistent ear bending angles and inaccurate taping positions, affecting battery performance and yield; tape handling problems: during the taping process, tape cutting and fitting often require multiple processes, and the tape is easily stretched due to excessive tension during cutting, resulting in poor fitting effects. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the present invention provides an automatic taping and ear folding device for small polymer square lithium batteries and its control method, which can not only significantly improve production efficiency, reduce labor costs, and ensure product consistency and quality, but also achieve real-time monitoring and dynamic adjustment through sensors and control systems, further improving production efficiency and product quality.

[0005] To achieve the above object and other related objects, the technical solutions provided by the present invention are as follows:

[0006] An automatic taping and ear folding device for small polymer square lithium batteries, comprising a battery core loading component, a top glue wrapping component, a top glue pressing and shaping component, an ear folding component, an ear shaping component, a surrounding glue component, and a rotating unloading component. The battery core loading component, the top glue wrapping component, the top glue pressing and shaping component, the ear folding component, the ear shaping component, the surrounding glue component, and the rotating unloading component are arranged in a ring in a counterclockwise direction in sequence, and a hollow rotating platform component is provided at the center. The central control rotating platform component includes a turntable and a fixture. A plurality of fixtures clamping battery cores are evenly arranged at the edge of the turntable. A rotating table is provided at the center of the bottom of the turntable, and the rotating table is connected to the output shaft of a servo motor.

[0007] Further, a belt conveying component is provided on the side of the rotating unloading component.

[0008] Further, a support base is provided at the bottom of the servo motor.

[0009] To achieve the above and other related purposes, the present invention provides a control method applied to the automatic rubber coating and ear folding device for small polymer square lithium batteries described in any one of the above, and the control method includes:

[0010] U1. During the process of folding the pole ears of the battery cell, based on the cameras at the battery cell loading station, top rubber coating station, top rubber coating pressing and shaping station, pole ear folding station, ear folding shaping station, surrounding rubber coating station and rotary unloading station, the data information of the images of the battery cell processing status at each station is obtained in real time, and a pixel point matrix of the image of the battery cell processing status is constructed to obtain the data information of the pixel point matrix of the image of the battery cell processing status;

[0011] U2. Based on the data information of the pixel point matrix of the image of the battery cell processing status, and collecting the historical data information of the pixel point matrix of the image after the battery cell processing is completed at each station, the completion degree of the battery cell processing at each station is predicted by using the elman neural network prediction algorithm based on seagull optimization to obtain the data information of the completion degree of the battery cell processing at each station after prediction;

[0012] U3. Based on the data information of the completion degree of the battery cell processing at each station after prediction, the improved Archimedes optimization algorithm based on the adaptive feedback adjustment factor is used to optimize the data of the completion degree of the battery cell processing at each station to obtain the data information of the completion degree of the battery cell processing at each station after optimization;

[0013] U4. Based on the data information of the completion degree of the battery cell processing at each station after optimization, a dynamic adjustment value function W of the central control rotary platform assembly is constructed, and the dynamic adjustment value of the central control rotary platform assembly is calculated to obtain the data information of the dynamic adjustment value of the central control rotary platform assembly.

[0014] Further, the method further includes:

[0015] U5. Based on the data information of the dynamic adjustment value of the central control rotary platform assembly, a preset threshold is set. If the dynamic adjustment value of the central control rotary platform assembly is less than the preset threshold, the rotation frequency of the central control rotary platform assembly meets the requirements and no adjustment is required. If the dynamic adjustment value of the central control rotary platform assembly is greater than the preset threshold, the rotation frequency of the central control rotary platform assembly does not meet the requirements and adjustment is required.

[0016] Further, the dynamic adjustment value function W of the central control rotary platform assembly is

[0017]

[0018] Among them, x i is the data information of the completion degree of the battery cell processing at the i-th optimized station, α i , β i and δ i are weight coefficients, and n is the total number of stations.

[0019] Furthermore, in step U2, the prediction of the completion degree of the battery cell processing at each station by using the elman neural network prediction algorithm based on seagull optimization includes:

[0020] U21. Input the data information of the pixel point matrix of the image of the battery cell processing state and the historical data information of the pixel point matrix of the image after the battery cell processing at each station into the elman neural network prediction model for training and learning, initialize the parameters of the elman neural network prediction model, and obtain the data information of the parameters of the new elman neural network prediction model;

[0021] U22. Based on the data information of the parameters of the new elman neural network prediction model, initialize the seagull population, determine the population parameters and the maximum number of iterations, and obtain the data information of the initialized seagull population;

[0022] U23. Based on the data information of the initialized seagull population, establish the fitness value function Q of the population individuals,

[0023]

[0024] where y is the data information of the initialized seagull population, and γ1, γ2, and γ3 are any constant parameters between 0 and 1, and calculate the fitness values of the seagull population individuals to obtain the data information of the fitness values of the seagull population individuals;

[0025] U24. Based on the data information of the fitness values of the seagull population individuals, establish the target optimization function R,

[0026]

[0027] where z is the data information of the fitness values of the seagull population individuals, optimize the parameters of the new elman neural network prediction model, and obtain the optimized elman neural network prediction model.

[0028] Furthermore, the prediction of the completion degree of the battery cell processing at each station by using the elman neural network prediction algorithm based on seagull optimization further includes:

[0029] U25. Based on the optimized Elman neural network prediction model, input the data information of the pixel point matrix of the image of the cell processing state and the historical data information of the pixel point matrix of the image after the cell processing is completed at each station, and predict the completion degree of the cell processing at each station to obtain the data information of the completion degree of the cell processing at each predicted station.

[0030] Further, in step U3, the optimization of the data of the completion degree of the cell processing at each station by using the improved Archimedes optimization algorithm based on the adaptive feedback adjustment factor includes:

[0031] U31. Based on the data information of the completion degree of the cell processing at each predicted station, initialize the Archimedes population, determine the population parameters, and obtain the data information of the initialized Archimedes population;

[0032] U32. Based on the data information of the initialized Archimedes population, establish a fitness value function G of the population individuals based on the adaptive feedback adjustment factor,

[0033]

[0034] where r is the data information of the initialized Archimedes population, f is the Levy rotation transformation function of the Archimedes population, and ω1, ω2, and ω3 are adaptive feedback adjustment factors, and calculate the fitness value of the population individuals to obtain the data information of the fitness value of the Archimedes population individuals;

[0035] U33. Based on the data information of the fitness value of the Archimedes population individuals, establish an update function H of the population,

[0036]

[0037] where h is the fitness of the Archimedes population individuals, and optimize the data of the completion degree of the cell processing at each station to obtain the data information of the optimized completion degree of the cell processing at each station.

[0038] Further, the Levy rotation transformation function f of the Archimedes population is

[0039]

[0040] where r is the data information of the initialized Archimedes population.

[0041] The present invention has the following positive effects:

[0042] 1. The present invention integrates processes such as ear bending, winding with glue, and cutting into one device, reducing the conversion time between processes and improving the overall production efficiency. Meanwhile, the demand for automation and intelligence in lithium battery manufacturing equipment is increasing day by day. Automated equipment can significantly improve production efficiency, reduce labor costs, and ensure product consistency and quality.

[0043] 2. The present invention predicts the completion degree of cell processing at each station by using an Elman neural network prediction algorithm based on seagull optimization and optimizes the data of the completion degree of cell processing at each station by using an improved Archimedes optimization algorithm based on an adaptive feedback adjustment factor. Combining with the dynamic adjustment value function W of the central control rotating platform component, the dynamic adjustment value of the central control rotating platform component is calculated. It can not only dynamically and accurately adjust the cell processing process, improve production efficiency and product quality, but also the whole process does not require manual participation, solving the problems that manual operation is prone to cause inconsistent ear bending angles and inaccurate winding positions, affecting battery performance and yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a schematic structural diagram of the present invention;

[0045] Figure 2 is a schematic structural diagram (I) of the central control rotating platform component of the present invention;

[0046] Figure 3 is a schematic structural diagram (II) of the central control rotating platform component of the present invention;

[0047] Figure 4 is a schematic flow diagram of the method of the present invention;

[0048] Figure 5 is a schematic flow diagram of the Elman neural network prediction algorithm based on seagull optimization of the present invention;

[0049] Figure 6 is a schematic flow diagram of the improved Archimedes optimization algorithm based on an adaptive feedback adjustment factor of the present invention.

[0050] Explanation of the reference numerals in the drawings: 1 - cell loading component, 2 - top glue wrapping component, 3 - top glue pressing and shaping component, 4 - ear folding component, 5 - ear shaping component, 6 - surrounding glue component, 7 - rotating unloading component, 8 - central control rotating platform component, 81 - turntable, 82 - fixture, 83 - cell, 84 - rotating table, 85 - servo motor, 86 - support seat, 9 - belt conveying component. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The following describes exemplary embodiments of the present disclosure in conjunction with the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0052] Embodiment 1: As Figure 1 or Figure 2 or Figure 3 shown, an automatic glue wrapping and ear folding device for small polymer square lithium batteries includes a battery cell loading component 1, a top glue wrapping component 2, a top glue pressing and shaping component 3, a pole ear folding component 4, an ear folding shaping component 5, a surrounding glue component 6, and a rotary unloading component 7. The battery cell loading component 1, the top glue wrapping component 2, the top glue pressing and shaping component 3, the pole ear folding component 4, the ear folding shaping component 5, the surrounding glue component 6, and the rotary unloading component 7 are arranged in a ring in a counterclockwise direction in sequence, and a hollow rotary platform component 8 is provided at the center. The central control rotary platform component 8 includes a turntable 81 and a jig 82. A plurality of jigs 82 clamping battery cells 83 are evenly provided at the edge of the turntable 81. A turntable 84 is provided at the center of the bottom of the turntable 81, and the turntable 84 is connected to the output shaft of a servo motor 85.

[0053] In this embodiment, a belt conveying component 9 is provided on the side of the rotary unloading component 7.

[0054] In this embodiment, a support seat 86 is provided at the bottom of the servo motor 85.

[0055] In this embodiment, the hollow rotary platform component provides power to rotate each station of the turntable by a fixed angle. There are key components such as a hollow rotary platform, a servo motor, a turntable, and a jig; the battery cell loading component assists manual loading, and through a cylinder fixture, it conveys to a fixed position on the turntable to achieve the displacement and clamping of the battery cell; the top glue wrapping component realizes the top glue wrapping action of the small polymer square lithium battery. This station is a specific mechanism developed specifically for this station and can realize the function of wrapping the top glue of the battery; the pole ear folding component realizes the pole ear folding function of the small polymer square lithium battery. This station is a specific mechanism designed specifically for this station and can realize the pole ear folding function of the battery; the surrounding glue component is an automatic surrounding glue mechanism after the ear folding of the small polymer square lithium battery, and the automatic surrounding glue function of the battery can be realized through this mechanism; the unloading component consists of two parts. One is a pneumatic clamping and rotating 90° mechanism, which can realize the feeding function of a 90° square battery cell, and the other is a conveying line, which conveys the manufactured lithium battery for unloading through the conveying line.

[0056] Working principle of the present invention: This encapsulation machine completes the process of folding and encapsulating the tabs of small polymer square lithium battery cells. It realizes the entire process from manual cell loading, top glue encapsulation, top glue encapsulation shaping, tab folding, tab folding shaping, loop glue encapsulation to unloading on a rotary table station through a central control rotating hollow platform component.

[0057] In this embodiment, the work process is as follows: Manual cell loading - top glue encapsulation - top glue encapsulation shaping - tab folding - tab folding shaping - loop glue encapsulation - unloading.

[0058] Embodiment 2: On the basis of the automatic tab encapsulation and folding device for small polymer square lithium batteries in Embodiment 1, the present invention will be further described and explained below.

[0059] As Figure 4 shown, a control method applied to the automatic tab encapsulation and folding device for small polymer square lithium batteries described in any one of the above, the control method includes:

[0060] U1. During the process of tab folding of the cell, based on the data information of the images of the cell processing status obtained in real time by the cameras at the cell loading station, top glue encapsulation station, top glue pressing and shaping station, tab folding station, tab folding shaping station, surrounding glue station and rotary unloading station, and constructing a pixel point matrix of the image of the cell processing status, the data information of the pixel point matrix of the image of the cell processing status is obtained;

[0061] U2. Based on the data information of the pixel point matrix of the image of the cell processing status, and collecting the historical data information of the pixel point matrix of the images after the cell processing is completed at each station, using the elman neural network prediction algorithm based on seagull optimization to predict the completion degree of the cell processing at each station, and obtaining the data information of the completion degree of the cell processing at each station after prediction;

[0062] U3. Based on the data information of the completion degree of the cell processing at each station after prediction, using the improved Archimedes optimization algorithm based on the adaptive feedback adjustment factor to optimize the data of the completion degree of the cell processing at each station, and obtaining the data information of the completion degree of the cell processing at each station after optimization;

[0063] U4. Based on the data information of the completion degree of the cell processing at each station after optimization, constructing a dynamic adjustment value function W of the central control rotating platform component, calculating the dynamic adjustment value of the central control rotating platform component, and obtaining the data information of the dynamic adjustment value of the central control rotating platform component.

[0064] In this embodiment, the method further includes:

[0065] U5. Based on the data information of the dynamic adjustment value of the central control rotating platform component, set a preset threshold. If the dynamic adjustment value of the central control rotating platform component is less than the preset threshold, the rotation frequency of the central control rotating platform component meets the requirements and no adjustment is needed. If the dynamic adjustment value of the central control rotating platform component is greater than the preset threshold, the rotation frequency of the central control rotating platform component does not meet the requirements and adjustment is needed.

[0066] Specifically, when the completion degree of the battery cell processing at a certain station is relatively low and the central control rotating platform component rotates at the specified time, it will cause the battery cells with low completion degree to enter the next process for further processing. Eventually, the obtained battery cells may be defective products. If the rotation frequency of the central control rotating platform component can be dynamically adjusted according to the state of the completion degree of the battery cell processing at each station, while preventing the generation of defective battery cell processing, it will also speed up or slow down the processing frequency of the battery cells according to the situation of the completion degree of the battery cell processing, improving the efficiency and quality of the battery cell processing.

[0067] In this embodiment, the dynamic adjustment value function W of the central control rotating platform component is

[0068] where x i is the data information of the completion degree of the battery cell processing at the i-th station after optimization, and α i , β i and δ i are weight coefficients, and n is the total number of stations.

[0069] In this embodiment, as Figure 5 shown, in step U2, the prediction of the completion degree of the battery cell processing at each station by using the elman neural network prediction algorithm based on the seagull optimization includes:

[0070] U21. Input the data information of the pixel point matrix of the image of the battery cell processing state and the historical data information of the pixel point matrix of the image after the battery cell processing at each station into the elman neural network prediction model for training and learning, and initialize the parameters of the elman neural network prediction model to obtain the data information of the parameters of the new elman neural network prediction model;

[0071] U22. Based on the data information of the parameters of the new elman neural network prediction model, initialize the seagull population, determine the population parameters and the maximum number of iterations, and obtain the data information of the initialized seagull population;

[0072] U23. Based on the data information of the initialized seagull population, establish the fitness value function Q of the population individuals,

[0073]

[0074] Among them, y is the data information of the initialized seagull population. γ1, γ2, and γ3 are any constant parameters between 0 and 1. The fitness values of the seagull population individuals are calculated to obtain the data information of the fitness values of the seagull population individuals.

[0075] U24. Based on the data information of the fitness values of the seagull population individuals, a target optimization function R is established.

[0076]

[0077] Among them, z is the data information of the fitness values of the seagull population individuals. The parameters of the new elman neural network prediction model are optimized to obtain the optimized elman neural network prediction model.

[0078] In this embodiment, the step of predicting the completion degree of the battery cell processing at each station by using the seagull optimization-based elman neural network prediction algorithm further includes:

[0079] U25. Based on the optimized elman neural network prediction model, the data information of the pixel point matrix of the image of the battery cell processing state and the historical data information of the pixel point matrix of the image after the battery cell processing is completed at each station are input, and the completion degree of the battery cell processing at each station is predicted to obtain the data information of the predicted completion degree of the battery cell processing at each station.

[0080] In this embodiment, as Figure 6 shown, in step U3, the step of optimizing the data of the completion degree of the battery cell processing at each station by using the improved Archimedes optimization algorithm based on the adaptive feedback adjustment factor includes:

[0081] U31. Based on the data information of the predicted completion degree of the battery cell processing at each station, the Archimedes population is initialized, the population parameters are determined, and the data information of the initialized Archimedes population is obtained.

[0082] U32. Based on the data information of the initialized Archimedes population, a fitness value function G of the population individuals based on the adaptive feedback adjustment factor is established.

[0083]

[0084] Among them, r is the data information of the initialized Archimedes population, f is the Levy rotation transformation function of the Archimedes population, ω1, ω2, and ω3 are the adaptive feedback adjustment factors, and the fitness values of the population individuals are calculated to obtain the data information of the fitness values of the Archimedes population individuals.

[0085] U33. Based on the data information of the fitness values of the individuals in the Archimedes population, establish the population update function H,

[0086]

[0087] where h is the fitness data of the individuals in the Archimedes population, and the data of the completion degree of the battery cell processing at each station is optimized to obtain the optimized data information of the completion degree of the battery cell processing at each station.

[0088] In this embodiment, the Lévy rotation transformation function f of the Archimedes population is

[0089]

[0090] where r is the data information of the initialized Archimedes population.

[0091] In summary, the present invention can not only significantly improve production efficiency, reduce labor costs, and ensure product consistency and quality, but also achieve real-time monitoring and dynamic adjustment through sensors and control systems, further improving production efficiency and product quality.

[0092] The above specific embodiments do not constitute a limitation to the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. An automatic glue wrapping and ear folding device for a small polymer square lithium battery, comprising a battery cell feeding assembly (1), a top glue wrapping assembly (2), a top glue pressing and shaping assembly (3), a pole ear folding assembly (4), an ear folding shaping assembly (5), a surrounding glue assembly (6) and a rotating blanking assembly (7), characterized in that: The battery cell loading component (1), the top glue wrapping component (2), the top glue pressing and shaping component (3), the pole ear folding component (4), the ear folding and shaping component (5), the surrounding glue component (6), and the rotating unloading component (7) are arranged in a ring in the counterclockwise direction in sequence, and a hollow rotating platform component (8) is provided at the center. The central control rotating platform component (8) includes a turntable (81) and a fixture (82). A plurality of fixtures (82) clamping battery cells (83) are evenly provided at the edge of the turntable (81). A turntable (84) is provided at the center of the bottom of the turntable (81), and the turntable (84) is connected to the output shaft of a servo motor (85).

2. The automatic glue-wrapping and ear-folding device for small polymer square lithium batteries according to claim 1, wherein: A belt conveying component (9) is provided on the side of the rotating unloading component (7).

3. The automatic rubber coating and ear folding device for small polymer square lithium batteries according to claim 1, wherein: A support base (86) is provided at the bottom of the servo motor (85).

4. A control method for an automatic encapsulation and ear folding device of a small polymer square lithium battery according to any one of claims 1-3, characterized in that, The control method includes: U1. During the process of folding the pole ears of the battery cell, based on the data information of the images of the battery cell processing states obtained in real time by the cameras at the battery cell loading station, the top glue wrapping station, the top glue pressing and shaping station, the pole ear folding station, the ear folding and shaping station, the surrounding glue station, and the rotating unloading station, a pixel point matrix of the image of the battery cell processing state is constructed, and the data information of the pixel point matrix of the image of the battery cell processing state is obtained; U2. Based on the data information of the pixel point matrix of the image of the battery cell processing state, and collecting the historical data information of the pixel point matrix of the image after the battery cell processing is completed at each station, a prediction algorithm of the elman neural network based on seagull optimization is used to predict the completion degree of the battery cell processing at each station, and the data information of the completion degree of the battery cell processing at each station after prediction is obtained; U3. Based on the data information of the completion degree of the battery cell processing at each station after prediction, an improved Archimedes optimization algorithm based on an adaptive feedback adjustment factor is used to optimize the data of the completion degree of the battery cell processing at each station, and the data information of the completion degree of the battery cell processing at each station after optimization is obtained; U4. Based on the data information of the completion degree of the battery cell processing at each station after optimization, a dynamic adjustment value function W of the central control rotating platform component is constructed, and the dynamic adjustment value of the central control rotating platform component is calculated to obtain the data information of the dynamic adjustment value of the central control rotating platform component.

5. The control method according to claim 4, wherein The method further includes: U5. Based on the data information of the dynamic adjustment value of the central control rotating platform component, a preset threshold is set. If the dynamic adjustment value of the central control rotating platform component is less than the preset threshold, the rotation frequency of the central control rotating platform component meets the requirements and no adjustment is required. If the dynamic adjustment value of the central control rotating platform component is greater than the preset threshold, the rotation frequency of the central control rotating platform component does not meet the requirements and adjustment is required.

6. The control method according to claim 4, characterized in that: The dynamic adjustment value function W of the central control rotating platform component is Among them, x i is the data information of the completion degree of the battery cell processing at the i-th optimized station, α i , β i and δ i are weight coefficients, and n is the total number of stations.

7. The control method according to claim 4, characterized in that In step U2, the prediction of the completion degree of the battery cell processing at each station by using the prediction algorithm of the elman neural network based on seagull optimization includes: U21. Input the data information of the pixel point matrix of the image of the battery cell processing state and the historical data information of the pixel point matrix of the image after the battery cell processing at each station into the Elman neural network prediction model for training and learning, initialize the parameters of the Elman neural network prediction model, and obtain the data information of the parameters of the new Elman neural network prediction model; U22. Based on the data information of the parameters of the new Elman neural network prediction model, initialize the seagull population, determine the population parameters and the maximum number of iterations, and obtain the data information of the initialized seagull population; U23. Based on the data information of the initialized seagull population, establish the fitness value function Q of the population individuals, where y is the data information of the initialized seagull population, and γ1, γ2, and γ3 are any constant parameters between 0 and 1, and calculate the fitness values of the seagull population individuals to obtain the data information of the fitness values of the seagull population individuals; U24. Based on the data information of the fitness values of the seagull population individuals, establish the objective optimization function R, where z is the data information of the fitness values of the seagull population individuals, and optimize the parameters of the new Elman neural network prediction model to obtain the optimized Elman neural network prediction model.

8. The control method according to claim 7, wherein The prediction of the completion degree of the battery cell processing at each station by using the Elman neural network prediction algorithm based on seagull optimization further includes: U25. Based on the optimized Elman neural network prediction model, input the data information of the pixel point matrix of the image of the battery cell processing state and the historical data information of the pixel point matrix of the image after the battery cell processing at each station, and predict the completion degree of the battery cell processing at each station to obtain the data information of the predicted completion degree of the battery cell processing at each station.

9. The control method according to claim 4, wherein In step U3, the optimization of the data of the completion degree of the battery cell processing at each station by using the improved Archimedes optimization algorithm based on the adaptive feedback adjustment factor includes: U31. Based on the data information of the predicted completion degree of the battery cell processing at each station, initialize the Archimedes population, determine the population parameters, and obtain the data information of the initialized Archimedes population; U32. Based on the data information of the initialized Archimedes population, establish the fitness value function G of the population individuals based on the adaptive feedback adjustment factor, where r is the data information of the initialized Archimedes population, f is the Levy rotation transformation function of the Archimedes population, and ω1, ω2, and ω3 are the adaptive feedback adjustment factors, and calculate the fitness values of the population individuals to obtain the data information of the fitness values of the Archimedes population individuals; U33. Based on the data information of the fitness values of the Archimedes population individuals, establish the population update function H, where h is the fitness of the Archimedes population individuals, and optimize the data of the completion degree of the battery cell processing at each station to obtain the data information of the optimized completion degree of the battery cell processing at each station.

10. The control method according to claim 9, wherein: The Levy rotation transformation function f of the Archimedes population is Among them, r is the data information of the initialized Archimedes population.

Images