System and method for calculating mixing conditions of a dry electrode

Abstract

The invention relates to a system and a method for calculating a mixing condition of a dry electrode. The system includes: a microscope configured to measure a dispersed image of a first dry electrode mixture for each mixing condition, where an electrode active material, a conductive material, and a binder in the first dry electrode mixture are mixed by a mixer; and a calculation device configured to machine learn the dispersion image of the first dry electrode mixture, receive a comparative dispersion image of the second dry electrode mixture, and calculate a target mixing condition of the second dry electrode mixture based on machine learning data of the dispersion images.

Description

Technical Field

[0001] The present invention relates to a dry electrode, and more particularly to a dry electrode for a secondary battery. Background Art

[0002] In recent years, the application of rechargeable secondary batteries in various fields from small electronic devices to large energy storage systems is expanding. In particular, due to the rapid growth of the electric vehicle market, research and development of secondary batteries is being actively carried out.

[0003] Electrodes for secondary batteries are usually manufactured by a wet process. In the wet process, a slurry is manufactured by dissolving an electrode active material, a binder, and a conductive material contained in the electrode with a solvent. However, recently, a dry process has received great attention, which can increase the energy density of the battery compared to the wet process without the solvent required in the wet process.

[0004] In the dry process of the electrode, the dry electrode film is prepared by preparing a mixture by mixing the electrode active material, the conductive material and the binder without any solvent, and then forming a film by pressing or calendaring. Then, the electrode can be manufactured by bonding the prepared dry electrode film to the current collector.

[0005] Compared with the wet electrode manufacturing process, the dry electrode manufacturing process can reduce the manufacturing time and cost by not using a solvent, and can control the thickness of the formed film, thereby being able to obtain a dry electrode film with a high energy density.

[0006] However, in the dry process, since only electrode materials are mixed without using a solvent, it is difficult to control the process conditions.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0008] The present invention is directed to solving the above-mentioned problems associated with the prior art, and an object of the present invention is to provide a system for calculating the mixing conditions of dry electrodes, wherein the mixing conditions can be optimized regardless of the size of the equipment used in the mixing process of the dry electrodes and the amount of dry electrodes mixed.

[0009] The objectives achieved by the present invention are not limited to the above objectives, and those skilled in the art will clearly understand other objectives not mentioned herein based on the following description.

[0010] In one aspect, the present invention provides a system for calculating the mixing conditions of a dry electrode, the system comprising: a microscope configured to measure a dispersion image of a first dry electrode mixture for each mixing condition, wherein the electrode active material, the conductive material and the binder in the first dry electrode mixture are mixed by a mixer; and a computing device configured to perform machine learning on the dispersion image of the first dry electrode mixture, the computing device being configured to receive a comparative dispersion image of a second dry electrode mixture and calculate a target mixing condition of the second dry electrode mixture based on the machine learning data of the dispersion image.

[0011] In another aspect, the present invention provides a method for calculating the mixing conditions of a dry electrode, the method comprising: measuring a dispersion image of a first dry electrode mixture under various mixing conditions by a microscope, wherein the electrode active material, the conductive material and the adhesive in the first dry electrode mixture are mixed by a mixer; performing machine learning on the dispersion image of the first dry electrode mixture by a computing device; receiving a comparative dispersion image of a second dry electrode mixture by the computing device; and calculating the target mixing conditions of the second dry electrode mixture by the computing device based on the machine learning data of the dispersion image.

[0012] Other aspects and preferred embodiments of the invention are discussed infra.

[0013] The above features and other features of the present invention are discussed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above-mentioned and other features of the present invention will now be described in detail with reference to certain exemplary embodiments shown in the accompanying drawings, which are given hereinafter by way of illustration only and are therefore non-limiting to the present invention, wherein:

[0015] Figure 1 is a schematic diagram schematically illustrating a process of manufacturing a dry electrode;

[0016] Figure 2 is a schematic diagram schematically showing a mixer used in the manufacture of a dry electrode;

[0017] Figure 3 is a schematic diagram showing a process of fibrillating a binder while applying energy to a material forming a dry electrode;

[0018] Figure 4A is a schematic diagram showing changes in the state of the dry electrode according to an increase in energy applied to a material forming the dry electrode;

[0019] Figure 4B is a schematic diagram showing changes in the state of the dry electrode according to an increase in energy applied to a material forming the dry electrode;

[0020] Figure 4C is a schematic diagram showing changes in the state of the dry electrode according to an increase in energy applied to a material forming the dry electrode;

[0021] Figure 4D is a schematic diagram showing changes in the state of the dry electrode according to an increase in energy applied to a material forming the dry electrode;

[0022] Figure 5 is a block diagram of a system for calculating a mixing condition of a dry electrode according to the present invention;

[0023] Figure 6 is a schematic diagram of a conductivity measurement device of a system according to one embodiment of the present invention;

[0024] Figure 7 is a graph representing processing of data learned by a computing device according to the present invention;

[0025] Figure 8 is a diagram illustrating a machine learning model of a computing device according to a system of the present invention; and

[0026] Fig. 9 is a graph showing the process of calculating the optimized mixing conditions by the system according to the present invention.

[0027] It should be understood that the accompanying drawings are not necessarily drawn to scale, but are appropriately simplified drawings of various preferred features presented to illustrate the basic principles of the present invention. The specific design features of the present invention disclosed herein (for example, including specific dimensions, directions, positions and shapes) will be determined in part by the specific environment to be applied and used.

[0028] In the figures, reference numbers refer to the same or equivalent parts of the present invention throughout the several figures of the drawing. DETAILED DESCRIPTION

[0029] The specific structure or functional description in the embodiment of the present invention described in the following description will be given exemplarily to describe the embodiment of the present invention, and the present invention can be implemented in many alternative forms. In addition, it will be understood that the present invention should not be construed as being limited to the embodiments described herein, and the embodiments of the present invention are provided only to fully disclose the present invention and to cover the variants, equivalents or alternatives within the scope of the present invention and the technical scope.

[0030] In the following description of the embodiments, terms such as "first" and "second" are used only to describe various elements, and these elements should not be construed as being limited by these terms. These terms are intended only to distinguish one element from other elements. For example, without departing from the scope of the present invention, a first element described below may be referred to as a second element, and similarly, a second element described below may be referred to as a first element.

[0031] When an element or layer is referred to as being “connected to” or “coupled to” another element or layer, it may be directly connected or coupled to the other element or layer, or intervening elements or layers may be present. Conversely, when an element or layer is referred to as being “directly connected to” or “directly coupled to” another element or layer, there may not be intervening elements or layers. Other words used to describe the relationship between elements should be interpreted in a similar manner, for example, “between” versus “directly between,” “adjacent” versus “directly adjacent,” etc.

[0032] As far as possible, the same reference numerals are used in all drawings to refer to the same or similar parts. The terms used herein are only used for the purpose of describing specific embodiments and are not intended to be limiting. As used herein, the singular form may be intended to also include the plural form, unless the context clearly states otherwise. The terms "comprise", "include", "contain" and "have" are inclusive, thus indicating the presence of the described features, values, operations, elements, components and / or combinations thereof, but do not exclude the presence or addition of one or more other features, values, operations, elements, components and / or combinations thereof.

[0033] Hereinafter, reference will be made in detail to various embodiments of the present invention, examples of which are illustrated in the accompanying drawings and described below.

[0034] The dry electrode can be made from a solvent-free dry electrode mixture M and a current collector. The dry electrode mixture M is a mixture containing an electrode active material, a conductive material, and a binder. In addition, the dry electrode mixture M may further contain additives.

[0035] The dry electrode may be a cathode, or may be an anode. In some embodiments, when a cathode is manufactured, the electrode active material may include a cathode active material. As a non-limiting example, the cathode active material may include LiCoO 2 (LCO), Li(Ni,Co,Mn)O 2 (NCM), Li(Ni,Co,Al)O 2 (NCA), LiMnO 4 (LMO), LiFePO 4 (LFP) or sulfur (S).

[0036] In some embodiments, when manufacturing the anode, the electrode active material may include an anode active material. As a non-limiting example, the anode active material may include natural graphite, artificial graphite, mesocarbon microbeads (MCMB) or silicon-based materials.

[0037] The conductive material may include a carbon material. For example, the conductive material may include carbon black, acetylene black, carbon fiber or carbon nanotube.

[0038] The binder may include polymer-based chemicals such as polyvinylidene fluoride (PVDF), polyvinyl alcohol (PVA), polytetrafluoroethylene (PTFE), styrene-butadiene rubber (SBR), carboxymethyl cellulose (CMC), polyacrylonitrile (PAN), and the like.

[0039] As the additive, some solid polymer electrolytes such as poly(ethylene oxide) (PEO), or oxide-based solid electrolytes and sulfide-based solid electrolytes may be used.

[0040] The dry electrode mixture M may include 70 to 99.9 wt % of an electrode active material, 0.1 to 20 wt % of a conductive material, and 0.1 to 20 wt % of a binder as a dry electrode material. Here, the additive may be added at a ratio of 0 to 20 wt %.

[0041] like Figure 1 As shown, the dry electrode mixture M can be manufactured into a dry electrode film F by a series of film-forming processes that apply heat and pressure. First, the dry electrode mixture M containing electrode active materials, conductive materials and binders is mixed by the mixer 10 at a predetermined speed for a predetermined time. As a non-limiting example, the dry electrode mixture M can be manufactured by using a rotating high shear mixer or a fluid mixer using air, and the predetermined time and speed can be adjusted by changing the rotation speed and operation time of the mixer 10. As another non-limiting example, the dry electrode mixture M can be manufactured using a compactor, a granulator or a combination thereof.

[0042] The mixed dry electrode mixture M can first be pressed into a film by an upstream press 20. The upstream roller press 20 rotates while pressing the dry electrode mixture M to form a film of the dry electrode mixture M. The dry electrode film F can be additionally pressed by the downstream roller press 30, so that the thickness of the dry electrode film can be adjusted by pressing. The obtained dry electrode film F is wound on a winder 40. Thereafter, a dry electrode can be manufactured by bonding the dry electrode film F to a current collector or laminating it on a current collector. The formation of the dry electrode film F and the lamination of the dry electrode film F on the current collector can be carried out in one device, or can be carried out in different devices respectively.

[0043] In the manufacturing process of the dry electrode, the mixing of the dry electrode mixture M can be performed by the mixer 10. In some embodiments, in such a mixing process, the dry electrode mixture M can be mixed by dispersing the electrode active material and the conductive material, and then adding the binder thereto. In some embodiments, the dry electrode mixture M can be mixed by dispersing the electrode active material, the conductive material, and the binder together.

[0044] In some embodiments, the mixer 10 may include a spiral mixer, a vertical mixer, a horizontal mixer, an oblique mixer, a planetary mixer, a paddle mixer, a screw mixer, a stand mixer, a granulator, a jet mill, a compactor, etc. In some embodiments, mixing may be performed by two or more mixers selected therefrom. However, the mixer 10 is not limited thereto.

[0045] As mixing conditions, a temperature in the range of -20°C to 200°C may be employed. In some embodiments, the mixer 10 may further include a cooler so that a low temperature may be maintained during mixing.

[0046] Figure 2 An exemplary mixer 10 is shown. The mixer 10 includes a rotatable blade 12. The blade 12 may be driven by a driving device 14 such as a motor. The mixer 10 may further include a feeding device 16. The feeding device 16 is disposed outside the blade 12 and may scrape the material that is only rotated but not mixed, so that shear force is uniformly applied to the electrode material forming the dry electrode put into the mixer 10.

[0047] The mixer 10 may further include a cooling jacket 18. Coolant circulating through the cooling jacket 18 may provide control over potential temperature changes due to heat generated during mixing.

[0048] When the materials forming the dry electrode mixture M, namely the electrode active material, the conductive material and the binder (additionally, the additive) are put into the mixer 10 and the blade 12 is rotated, energy is transferred to each particle of the material. When the binder in the material obtains appropriate energy through mixing and becomes fiberized, the mixing process can be completed when the fiberized binder connects the active material, the conductive material and the additive into a network.

[0049] like Figure 3As shown, when the electrode material is placed in the mixer 10, energy E is applied to the electrode material in various ways depending on the type of the mixer 10. Due to the energy E, the particles of the conductive material 4 gathered in the form of clusters are physically dispersed and combined with the surface of the particles of the electrode active material 2. The binder 6 can be fibrillated to form a network between the particles of the material. Here, the energy E applied to the material can be generated by various factors such as the impact applied by the blade 12, the collision between the air and the particles. When the mixer 10 is set, the amount of energy applied to the electrode material can be adjusted by the mixing time and / or mixing speed of the mixer 10.

[0050] Specifically, the mixing process of the dry electrode mixture M can be divided into four steps, such as Figure 4A , Figure 4B , Figure 4C and Figure 4D As the energy applied to the electrode material (i.e., mixing time and / or mixing speed) increases, the following sequence can be followed: Figure 4A , Figure 4B , Figure 4C and Figure 4D Steps shown.

[0051] like Figure 4A As shown, the dry electrode material is put into the mixer 10, and at the initial stage of mixing, the binder 6 is in a clumped state. The binder 6 includes primary particles and secondary particles. The primary particles refer to particles of 500 nanometers or less that form the binder 6, and particles formed by aggregating a plurality of such primary particles to a size of hundreds of micrometers can be referred to as secondary particles. Figure 4A In the state shown, due to insufficient energy applied to the electrode material, the binder 6 is not sufficiently transformed into primary particles but aggregated in the state of secondary particles. The conductive material 4 is also not sufficiently dispersed but is in an aggregated state.

[0052] Figure 4B The state where the binder 6 begins to fiberize is shown. In this state, as the energy applied to each particle of the material (i.e., mixing time and / or mixing speed) increases, the binder 6 fiberizes. Separation of the secondary particles of the binder 6 into primary particles occurs, so some particles of the binder 6 undergo fiberization (i.e., have a string shape), but other particles of the binder 6 maintain the state of secondary particles.

[0053] Figure 4C The state in which the fiberization of the binder 6 has been properly completed is shown, and the target state to be achieved by mixing the dry electrode mixture M is shown. As the binder 6 separates into primary particles, the fiberization of the binder 6 occurs. The conductive material 4 is also uniformly arranged on the surface of the particles of the electrode active material 2.

[0054] Figure 4D The particle coating state is shown in which superfibrillation of the binder 6 occurs as excessive energy is applied to the electrode material. Here, it is observed that the surface of the particles of the electrode active material 2 is coated with the binder 6. The network formed between the particles of the material by the fibrillation of the binder 6 disappears, which reduces the possibility of film formation.

[0055] like Figure 4C As shown, although the ratio of the electrode materials of the dry electrode mixture M and the operating conditions of the mixer 10 that can obtain a satisfactory fiberized state of the binder 6 are obtained, when the scale of mixing is changed or the amount of the electrode materials put into the mixer 10 is changed, the ratio of the electrode materials and the operating conditions of the mixer 10 should be changed. This is partly because the dry process involves fiberizing the binder 6 by applying appropriate energy to the binder 6 without using a solvent.

[0056] After the target mixing time and target mixing speed of the dry electrode mixture M were obtained by the mixer 10 with a small capacity (e.g., a capacity of 10 L), verification was performed on a small scale. When the verified small-scale data was modified to be suitable for large-scale mass production, it was found that the same results could not be obtained. This is because even if the mixer 10 rotates at the same linear speed, the energy of particle collision will change.

[0057] In addition, when the input amount of electrode material changes, the amount of collision of electrode material particles per hour changes. This causes the energy applied to the particles to change, so that the desired results may not be obtained by the same process as on a small scale.

[0058] Of course, the collision energy applied to the particles can be calculated by simulation. However, due to various factors in the actual system, there will be a large error between the simulation results and the results of the actual system. In this way, the dry process requires a lot of time and cost to determine the appropriate mixing conditions, so the present invention proposes a method for optimizing the mixing process of dry electrodes through machine learning.

[0059] refer to Figure 5 , a system 100 for calculating a mixing condition of a dry electrode according to the present invention includes a microscope 110 , a conductivity measuring device 120 , and a calculating device 130 .

[0060] The microscope 110 can measure the dispersion image of the dry electrode mixture M. The microscope 110 can be an optical microscope or an electron microscope. For example, the electron microscope can be a scanning electron microscope (SEM) or a transmission electron microscope (TEM), but is not limited thereto. The magnification of the microscope 110 can be adjusted. However, as described below, the microscope 110 is configured so that the dispersion image for machine learning of the computing device 130 is measured at the same magnification.

[0061] like Figure 6 As shown, the conductivity measuring device 120 can measure the conductivity of the dry electrode mixture M by applying pressure or force P1 to a specified amount of dry electrode mixture M with an area of ​​S and a height of h. Force P1 can have a value selected, for example, from 1 kilonewton (kN) to 100kN. The conductivity can be measured by a probe 200 located at the lower end of the dry electrode mixture M. Here, the probe 200 can be a 4-point probe. The conductivity (Siemens / cm, S / cm) of the dry electrode mixture M relative to the force P1 applied by the conductivity measuring device 120 can be measured. The force P1 can be changed, and the conductivity value of the dry electrode mixture M can be measured according to the size of each force P1. As described below, the computing device 130 can learn the average value of the conductivity value according to the size of each force P1, and can calculate the mixing time or mixing speed based on the learned data.

[0062] The computing device 130 can collect data and learn the collected data. In one embodiment, the computing device 130 can collect a dispersion image and conductivity data of the dry electrode mixture M. In some embodiments, by changing the mixing time of the dry electrode mixture M, a dispersion image and conductivity of the dry electrode mixture M are obtained for each mixing time. At this time, the mixing speed is fixed. In another embodiment, by changing the mixing speed of the dry electrode mixture M, a dispersion image and conductivity of the dry electrode mixture M are obtained for each mixing speed. At this time, the mixing time is fixed. In addition, for each type and proportion of each material forming the dry electrode mixture M, a dispersion image and conductivity of the dry electrode mixture M are obtained.

[0063] The computing device 130 may perform machine learning on the collected data. The computing device 130 may execute a machine learning algorithm and may use a machine learning model for training. As a non-limiting example, logistic regression, random forest, neural network, etc. may be used as a machine learning model.

[0064] The computing device 130 can obtain a low-dimensional feature vector of the dispersion image of the dry electrode mixture M by image embedding. As a non-limiting example, Inception V3 can be used as an image embedder. The machine learning model of the computing device 130 can use the feature vectors of each image as input. Here, as a dispersion image, data taken by a microscope 110 with the same conditions and at the same magnification is learned by the computing device 130. For example, the magnification can be at least 500 times.

[0065] The conductivity of the dry electrode mixture M according to the magnitude of each force P1 is measured by the conductivity measuring device 120, and its average value is learned by the calculation device 130. For example, a value that is an average value of 10 conductivities (S / cm) measured under 1 kN, 2 kN, 3 kN, 4 kN, 5 kN, 6 kN, 7 kN, 8 kN, 9 kN and 10 kN corresponds to one mixing time or mixing speed. The force when measuring the conductivity can be set to various sizes, but the average value of the conductivity measured under the same pressure or force conditions is learned by the calculation device 130.

[0066] Can be Figure 7 The conductivity according to the mixing time or mixing speed is obtained in the form of a graph shown. The conductivity of the dry electrode mixture M can be obtained according to each input energy (i.e., each mixing time or mixing speed), wherein the conductivity can be an average value within a specified range of the force applied as described above. In addition, the scattered image data at each position in the graph can be matched with the corresponding conductivity and can be used together.

[0067] In the conductivity data according to the mixing time or the mixing speed, there are parts with the same value or parts with values ​​that overlap with each other. In this regard, in order to determine whether the dry electrode mixture M has reached a satisfactory fiberization level of the binder based only on the conductivity, the entire interval should be checked. Therefore, the present invention trains the calculation device 130 with both the conductivity data and the dispersion data as feature values ​​to clearly distinguish the first point and the second point from each other.

[0068] like Figure 8 As shown, according to the present invention, the computing device 130 can receive the dispersion image and conductivity of the target dry electrode mixture (need to calculate the optimized mixing conditions) as input. Then, the computing device 130 can calculate the optimized mixing conditions (i.e., mixing time or mixing speed) as output. This will be described below by an embodiment.

[0069] refer to Fig. 9 , assuming that in the data about 10 kilograms (kg) of the mixture M learned by the computing device 130, the mixing time at the first point is 10 minutes, the mixing speed at the target point where the binder is properly fiberized is 15 minutes, and the mixing time at the second point is 25 minutes. In the following embodiment, the linear speed of the blade 12 is fixed to 30 m / s.

[0070] Prepare a first target dry electrode mixture for which the mixing conditions need to be calculated and optimized. Change the input amount of the first target dry electrode mixture to 20 kg. After mixing the first target dry electrode mixture for a preset first mixing time (e.g., 20 minutes), measure a first dispersion image and a first conductivity of the first target dry electrode mixture. When the first dispersion image and the first conductivity are input to the computing device 130, it can be determined that Fig. 9 The corresponding position of the data shown. As in the embodiment shown, it is assumed that the corresponding position is the position of the first point.

[0071] Thereafter, a second target dry electrode mixture is prepared. The components and composition ratios of the second target dry electrode mixture are the same as the components and composition ratios of the first target dry electrode mixture, but the second target dry electrode mixture is mixed for a second mixing time (e.g., 46 minutes) that is different from the first mixing time. Thereafter, a second dispersion image and a second conductivity of the second target dry electrode mixture are measured. When the second dispersion image and the second conductivity are input to the computing device 130, it can be determined Fig. 9 The corresponding position of the data shown. As in the embodiment shown, it is assumed that the corresponding position is the position of the second point.

[0072] The calculation device 130 can calculate the ratio with the target point through the results of the first target dry electrode mixture and the second target dry electrode mixture corresponding to the first point and the second point, and can calculate the optimized mixing time in the process of change. That is, the calculation device 130 can calculate the optimized mixing time of 28.67 minutes as the target object through the equation 20 minutes + (46 minutes - 20 minutes) × 5 / (25 minutes - 10 minutes).

[0073] This calculation process can be applied to the mixing speed in the same manner. When the mixing speed is calculated, the mixing time is set to be the same, and when the mixing time is calculated, the mixing speed is set to be the same. When the mixing time is the target, the mixing speed of the mixing condition is fixed based on the linear speed of the mixer 10. In addition, when the mixing speed is the target, the mixing time of the mixing condition is fixed to a certain time as long as the adhesive can be fiberized.

[0074] The computing device 130 includes a processor 132 and a memory 134. Instructions executable by the computing device 130 are stored in the memory 134. In some embodiments of the present invention, the instructions may include instructions for performing operations of the computing device 130 and / or operations of various components of the computing device 130.

[0075] The memory 134 may be a volatile memory or a non-volatile memory. As a non-limiting example, the volatile memory may be a dynamic random access memory (DRAM), a static random access memory (SRAM), etc. As another non-limiting example, the non-volatile memory may be an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic RAM (MRAM), a CD-ROM, a DVD-ROM, etc.

[0076] In addition, the memory 134 may store matrices to perform operations included in the machine learning model, and the memory 134 may store operation results generated by processing by the computing device 130 .

[0077] The processor 132 may execute instructions stored in the memory 134. The processor 132 may execute computer readable code and instructions stored in the memory 134. As non-limiting examples, the processor 132 may include a central processing unit, a graphics processing unit, a neural processing unit, a multi-core processor, a multi-processor, an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

[0078] According to some embodiments of the present invention, system 100 can be implemented in the form of a recording medium, and the recording medium includes instructions that can be executed by a computer, such as a program module executed by a computer. Computer-readable media can be any available media accessible to a computer, and include volatile media and non-volatile media and removable media and non-removable media. In addition, computer-readable media can include all computer storage media. Computer storage media include volatile media and non-volatile media and removable media and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data.

[0079] The present invention can reduce the test materials and time consumed to optimize the mixing process of dry electrodes, and can even effectively respond to situations where conditions should be changed in various ways.

[0080] As is apparent from the above description, the present invention provides a system for calculating mixing conditions of dry electrodes, wherein the mixing conditions can be optimized regardless of the size of equipment used in the mixing process of dry electrodes and the amount of dry electrodes mixed.

[0081] The effects of the present invention are not limited to the above-mentioned effects, and other effects not mentioned herein will be clearly understood by those skilled in the art from the above description.

[0082] The invention has been described in detail with reference to preferred embodiments. However, those skilled in the art will appreciate that changes may be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims

1. A system for calculating a mixing condition of a dry electrode, comprising: a microscope configured to measure a dispersion image of a first dry electrode mixture for each mixing condition, wherein an electrode active material, a conductive material, and a binder in the first dry electrode mixture are mixed by a mixer; and a computing device configured to perform machine learning on the dispersion image of the first dry electrode mixture, Wherein, the computing device is configured to receive a comparative dispersion image of the second dry electrode mixture and calculate a target mixing condition of the second dry electrode mixture based on machine learning data of the dispersion image.

2. The system for calculating the mixing condition of a dry electrode according to claim 1, wherein: The mixing condition is the mixing time or the mixing speed of the mixer.

3. The system for calculating the mixing condition of a dry electrode according to claim 2, wherein: When the mixing condition is the mixing time of the mixer, the linear speeds of the mixer for mixing the first dry electrode mixture and the second dry electrode mixture are set to be the same; or When the mixing condition is the mixing speed of the mixer, the operation time of the mixer for mixing the first dry electrode mixture and the second dry electrode mixture is set to be the same.

4. The system for calculating the mixing condition of a dry electrode according to claim 1, wherein: The target mixing condition is a mixing time or a mixing speed of a mixer when the binder included in the second dry electrode mixture satisfies a predetermined fiberizing condition.

5. The system for calculating the mixing condition of a dry electrode according to claim 1, wherein: The first dry electrode mixture and the second dry electrode mixture have the same components and composition ratio, but the amounts of the first dry electrode mixture and the second dry electrode mixture are different; or The first dry electrode mixture and the second dry electrode mixture have the same components and composition ratios, but the devices used to mix the first dry electrode mixture and the second dry electrode mixture are different.

6. The system for calculating the mixing condition of a dry electrode according to claim 1, wherein: The machine learning data includes a comparative mixing condition, wherein the comparative mixing condition is a mixing condition when the binder in the first dry electrode mixture satisfies a predetermined fiberization condition; The computing device is configured as follows: acquiring a first comparative dispersion image of a second dry electrode mixture mixed for a first comparative mixing time; acquiring a first mixing time, the first mixing time being a mixing time of the first dry electrode mixture when the first comparative dispersion image corresponds to one of the dispersion images of the first dry electrode mixture; acquiring a second comparative dispersion image of a second dry electrode mixture mixed for a second comparative mixing time; acquiring a second mixing time, the second mixing time being a mixing time of the first dry electrode mixture when the second comparative dispersion image corresponds to another one of the dispersion images of the first dry electrode mixture; A target mixing condition of the second dry electrode mixture is determined based on the ratio of the first mixing time, the second mixing time, and the comparative mixing condition.

7. The system for calculating the mixing condition of a dry electrode according to claim 1, wherein: The machine learning data includes a comparative mixing condition, wherein the comparative mixing condition is a mixing condition when the binder in the first dry electrode mixture satisfies a predetermined fiberization condition; The computing device is configured as follows: acquiring a first comparative dispersion image of a second dry electrode mixture mixed at a first comparative mixing speed; acquiring a first mixing speed, the first mixing speed being a mixing speed of the first dry electrode mixture when the first comparative dispersion image corresponds to one of the dispersion images of the first dry electrode mixture; acquiring a second comparative dispersion image of a second dry electrode mixture mixed at a second comparative mixing speed; acquiring a second mixing speed, the second mixing speed being a mixing speed of the first dry electrode mixture when the second comparative dispersion image corresponds to another one of the dispersion images of the first dry electrode mixture; A target mixing condition of the second dry electrode mixture is determined based on a ratio of the first mixing speed, the second mixing speed, and the comparative mixing condition.

8. The system for calculating the mixing condition of the dry electrode according to claim 1, further comprising a conductivity measuring device, wherein the conductivity measuring device is configured to measure the conductivity of the first dry electrode mixture under each mixing condition, in, The computing device is configured as follows: further performing machine learning on the conductivity; further receiving a comparative conductivity of a second dry electrode mixture; A target mixing condition of a second dry electrode mixture is calculated based on the dispersion image and the machine learning data of the conductivity.

9. The system for calculating the mixing condition of a dry electrode according to claim 8, wherein: The conductivity values ​​were measured when the first dry electrode mixture or the second dry electrode mixture was pressed at each pressure under each mixing condition, and each conductivity was an average value of the conductivity values ​​obtained at the respective pressures.

10. The system for calculating the mixing condition of a dry electrode according to claim 8, wherein: The machine learning data includes a comparative mixing condition, wherein the comparative mixing condition is a mixing condition when the binder in the first dry electrode mixture satisfies a predetermined fiberization condition.

11. The system for calculating the mixing condition of a dry electrode according to claim 10, wherein: The computing device is configured as follows: Acquire a first comparative dispersion image and a first comparative conductivity of a second dry electrode mixture mixed for a first comparative mixing time; acquiring a first mixing time, the first mixing time being a mixing time of the first dry electrode mixture when the first comparative dispersion image and the first comparative conductivity correspond to one of the dispersion image and one of the conductivity of the first dry electrode mixture; acquiring a second comparative dispersion image and a second comparative conductivity of a second dry electrode mixture mixed for a second comparative mixing time; acquiring a second mixing time, the second mixing time being a mixing time of the first dry electrode mixture when the second comparative dispersion image and the second comparative conductivity correspond to the other of the dispersion image and the other of the conductivity of the first dry electrode mixture; A target mixing condition of the second dry electrode mixture is determined based on the ratio of the first mixing time, the second mixing time, and the comparative mixing condition.

12. The system for calculating the mixing condition of a dry electrode according to claim 10, wherein: The computing device is configured as follows: acquiring a first comparative dispersion image and a first comparative conductivity of a second dry electrode mixture mixed at a first comparative mixing speed; acquiring a first mixing speed, the first mixing speed being a mixing speed of the first dry electrode mixture when the first comparative dispersion image and the first comparative conductivity correspond to one of the dispersion images and one of the conductivities of the first dry electrode mixture; acquiring a second comparative dispersion image and a second comparative conductivity of a second dry electrode mixture mixed at a second comparative mixing speed; acquiring a second mixing speed, the second mixing speed being a mixing speed of the first dry electrode mixture when the second comparative dispersion image and the second comparative conductivity correspond to the other of the dispersion image and the other of the conductivity of the first dry electrode mixture; A target mixing condition of the second dry electrode mixture is determined based on a ratio of the first mixing speed, the second mixing speed, and the comparative mixing condition.

13. A method for calculating a mixing condition of a dry electrode, comprising: measuring, by a microscope, a dispersion image of a first dry electrode mixture under various mixing conditions, in which an electrode active material, a conductive material, and a binder are mixed by a mixer; performing machine learning on the dispersion image of the first dry electrode mixture by a computing device; receiving, by a computing device, a comparative dispersion image of a second dry electrode mixture; A target mixing condition of the second dry electrode mixture is calculated by a computing device based on the machine learning data of the dispersion image.

14. The method according to claim 13, further comprising: measuring the conductivity of the first dry electrode mixture under various mixing conditions by a conductivity measuring device; Further performing machine learning on the conductivity by a computing device; receiving, by the computing device, a comparative conductivity of the second dry electrode mixture, Wherein, calculating the target mixing condition of the second dry electrode mixture includes calculating the target mixing condition based on the machine learning data of the conductivity.

15. The method according to claim 14, wherein: The machine learning data includes a comparative mixing condition, wherein the comparative mixing condition is a mixing condition when the binder in the first dry electrode mixture satisfies a predetermined fiberization condition, Wherein, the method further comprises: Acquiring, by a computing device, a first comparative dispersion image and a first comparative conductivity of a second dry electrode mixture mixed after a first comparative mixing time; Obtaining, by a computing device, a first mixing time, the first mixing time being a mixing time of the first dry electrode mixture when the first comparative dispersion image and the first comparative conductivity correspond to one of the dispersion image and one of the conductivity of the first dry electrode mixture; Acquiring, by a computing device, a second comparative dispersion image and a second comparative conductivity of a second dry electrode mixture mixed after a second comparative mixing time; acquiring, by the computing device, a second mixing time, the second mixing time being a mixing time of the first dry electrode mixture when the second comparative dispersion image and the second comparative conductivity correspond to the other of the dispersion image and the other of the conductivity of the first dry electrode mixture; The target mixing condition of the second dry electrode mixture is determined by the calculation device based on the ratio of the first mixing time, the second mixing time, and the comparative mixing condition.

16. The method according to claim 14, wherein: The machine learning data includes a comparative mixing condition, wherein the comparative mixing condition is a mixing condition when the binder in the first dry electrode mixture satisfies a predetermined fiberization condition, Wherein, the method further comprises: acquiring, by a computing device, a first comparative dispersion image and a first comparative conductivity of a second dry electrode mixture mixed at a first comparative mixing speed; acquiring, by a computing device, a first mixing speed, the first mixing speed being a mixing speed of the first dry electrode mixture when the first comparative dispersion image and the first comparative conductivity correspond to one of the dispersion images and one of the conductivity of the first dry electrode mixture; acquiring, by a computing device, a second comparative dispersion image and a second comparative conductivity of a second dry electrode mixture mixed at a second comparative mixing speed; acquiring, by the computing device, a second mixing speed, the second mixing speed being a mixing speed of the first dry electrode mixture when the second comparative dispersion image and the second comparative conductivity correspond to the other of the dispersion image and the other of the conductivity of the first dry electrode mixture; A target mixing condition of the second dry electrode mixture is determined by the calculation device based on the ratio of the first mixing speed, the second mixing speed, and the comparative mixing condition.

17. The method according to claim 14, wherein: The conductivity values ​​were measured when the first dry electrode mixture or the second dry electrode mixture was pressed at each pressure under each mixing condition, and each conductivity was an average value of the conductivity values ​​obtained at the respective pressures.

18. The method of claim 13, wherein: The mixing condition is the mixing time or mixing speed of the mixer; The target mixing condition is a mixing time or a mixing speed of a mixer when the binder included in the second dry electrode mixture satisfies a predetermined fiberizing condition.

19. The method of claim 13, wherein: The first dry electrode mixture and the second dry electrode mixture have the same components and composition ratios, but the first dry electrode mixture and the second dry electrode mixture have different amounts; or The first dry electrode mixture and the second dry electrode mixture have the same components and composition ratios, but the devices used to mix the first dry electrode mixture and the second dry electrode mixture are different.

20. The method of claim 13, wherein: When the mixing condition is the mixing time of the mixer, the linear speed of the mixer for mixing the first dry electrode mixture and the second dry electrode mixture is set to be the same; When the mixing condition is the mixing speed of the mixer, the operation time of the mixer for mixing the first dry electrode mixture and the second dry electrode mixture is set to be the same.

Images