Electronic device and control method of electronic device

Abstract

According to embodiments disclosed herein, an electronic device includes a communication circuitry in communication with a drying apparatus including a plurality of drying areas for drying an introduced electrode, and a plurality of heating apparatuses respectively provided in correspondence with the plurality of drying areas to provide heat to the electrode; a memory for storing one or more instructions; and a processor. The one or more instructions, when executed, can be configured to cause the processor to, upon a shutdown of the drying apparatus, acquire operation state information of the drying apparatus, acquire state information of at least one electrode introduced into the drying apparatus, determine an output of each of the plurality of heating apparatuses based on the operation state information of the drying apparatus and the state information of the at least one electrode, and control the plurality of heating apparatuses based on the determined output of each of the plurality of heating apparatuses.

Description

Technical Field

[0001] This application claims the benefit of Korean Patent Application No. 10-2024-0104157 filed on August 5, 2024, and Korean Patent Application No. 10-2024-0127271 filed on September 20, 2024, the disclosures of which are incorporated herein by reference in their entirety.

[0002] Example embodiments of this disclosure relate to an electronic device and a method for controlling the electronic device. Background Technology

[0003] Recently, research and development of rechargeable batteries have been actively underway. Here, rechargeable batteries refer to batteries that can be recharged and discharged, meaning this includes all conventional nickel-cadmium (Ni / Cd) batteries, nickel-metal hydride (Ni / MH) batteries, and the newest lithium-ion batteries. Among rechargeable batteries, lithium-ion batteries have a higher energy density compared to conventional Ni / Cd and Ni / MH batteries. Furthermore, lithium-ion batteries can be manufactured in small sizes and are lightweight, thus being used as power sources for mobile devices. Recently, with their applications expanding to power electric vehicles, lithium-ion batteries have attracted considerable attention as a next-generation energy storage medium.

[0004] A secondary battery includes a negative electrode and a positive electrode, and can be manufactured through manufacturing processes of electrodes corresponding to the negative and positive electrodes. The manufacturing process of a secondary battery can include various steps, and a drying process for removing moisture from the electrodes can be performed within this process. In this drying process, the surface of the electrodes must be properly dried. Inadequate drying conditions can lead to defects in the electrodes. Summary of the Invention

[0005] Technical issues

[0006] The purpose of this disclosure is to provide an electronic device and a method for controlling the electronic device to stably manage the surface of an electrode during a drying process by optimally controlling the state of the drying apparatus.

[0007] However, the problems to be solved by the exemplary embodiments of this disclosure are not limited to those described above, and those skilled in the art can clearly understand other problems from the following exemplary embodiments.

[0008] Technical solution

[0009] According to an example embodiment of this disclosure, an electronic device is provided, comprising: a communication circuit configured to communicate with a drying apparatus, the drying apparatus including a plurality of drying regions for drying introduced electrodes, and a plurality of heating devices respectively disposed corresponding to the plurality of drying regions and configured to provide heat to the electrodes; a memory configured to store one or more instructions; and a processor, which, when the one or more instructions are executed, is configured to: acquire operating status information of the drying apparatus after the drying apparatus has been shut down; acquire status information of at least one electrode introduced into the drying apparatus; determine the output of each of the plurality of heating devices based on the operating status information of the drying apparatus and the status information of the at least one electrode; and control the plurality of heating devices based on the determined output of each of the plurality of heating devices.

[0010] The operating status information of the drying device may include: the shutdown time and previous operating time of the drying device, and the initial temperature of the heating device corresponding to the drying area where the electrode is discharged, and the status information of the electrode may include: the initial temperature of the surface of the electrode located in each of the plurality of drying areas, and the target temperature of the surface of the electrode at the target time point.

[0011] The target time point may include: the time point from the time the electrode is introduced into the drying device, after which the time required for the introduced electrode to reach the drying area where the electrode in the plurality of drying areas is discharged.

[0012] The processor can be configured to input the operating status information of the drying device and the status information of the at least one electrode into a trained deep learning model, and to confirm the output of each of the plurality of heating devices output from the deep learning model.

[0013] The deep learning model can be a learning model that uses multiple state information of multiple electrodes and multiple operating state information of the drying device corresponding to multiple operations of the drying device as input datasets for learning; uses the output of each of the multiple heating devices corresponding to the multiple operations of the drying device as output datasets for learning; and models the correlation between the input datasets for learning and the output datasets for learning.

[0014] The trained deep learning model may include an LSTM model.

[0015] The processor can be configured to select multiple variables related to at least one of the operating state of the drying device and the state of the electrode, and to determine the input variables of the deep learning model by performing a correlation analysis between the multiple variables and the target temperature of the electrode surface based on the travel speed of the electrode.

[0016] The processor can be configured to control the output of all heating devices when the electrode is negative, and to control the output of the heating device among the plurality of heating devices corresponding to the drying area where the electrode is discharged when the electrode is positive.

[0017] The plurality of drying zones may include a first drying zone, a second drying zone, and a third drying zone disposed along the travel path of the electrode.

[0018] According to another exemplary embodiment of this disclosure, a method for controlling an electronic device is also provided. The electronic device includes a plurality of drying regions for drying introduced electrodes, and is configured to control a plurality of heating devices respectively disposed corresponding to the plurality of drying regions and configured to provide heat to the electrodes. The method includes: acquiring operating status information of the drying device when it is running after the drying device has been shut down; acquiring status information of at least one electrode introduced into the drying device; determining the output of each of the plurality of heating devices based on the operating status information of the drying device and the status information of the at least one electrode; and controlling the plurality of heating devices based on the determined output of each of the plurality of heating devices.

[0019] Beneficial effects

[0020] The electronic device and its control method according to the exemplary embodiments of this disclosure can stably manage the surface of the electrode during the drying process. Therefore, electrode defects can be prevented.

[0021] The electronic device and control method of the electronic device according to the exemplary embodiments of this disclosure can effectively determine the optimal conditions by using a trained deep learning model, even when the drying device has various states such as operation after shutdown.

[0022] Various other effects may be provided, either directly or indirectly, through this disclosure. Attached Figure Description

[0023] Figure 1 This is a block diagram illustrating the configuration of a system according to an example embodiment of the present disclosure.

[0024] Figure 2 This is a diagram showing the configuration of a drying apparatus 200 according to an exemplary embodiment of the present disclosure.

[0025] Figure 3 This is a diagram illustrating an example of the structure of a deep learning model according to an exemplary implementation of this disclosure.

[0026] Figure 4 This is a diagram illustrating an example of the results of applying a deep learning model according to an exemplary implementation of this disclosure.

[0027] Figure 5 to Figure 8 This is a diagram illustrating an example of correlation analysis used to determine the input variables of a deep learning model.

[0028] Figure 9 This is a flowchart used to describe an example implementation of a control method according to the present disclosure.

[0029] Figure 10 This is a flowchart describing a detailed control method for an electronic device according to an exemplary embodiment of the present disclosure.

[0030] Figure 11 This is a flowchart describing a method for obtaining a trained deep learning model according to an exemplary implementation of the present disclosure. Detailed Implementation

[0031] In the following description, various exemplary embodiments of the present disclosure will be illustrated with reference to the accompanying drawings. However, it should be understood that this is not intended to limit the present disclosure to the specific exemplary embodiments, but rather to include various modifications, equivalents, and / or alternatives to the exemplary embodiments of the present disclosure.

[0032] In this disclosure, the singular form of nouns corresponding to an item may include one or more items unless the context clearly indicates otherwise. In this disclosure, expressions such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B, or C,” “at least one of A, B, and C,” and “at least one of A, B, or C” may each include one of the items listed together with the corresponding phrases in these expressions, or all possible combinations thereof. Terms such as “first,” “second,” or “first” or “second” may be used only to distinguish the corresponding component from other components and do not limit the corresponding component in other respects (e.g., importance or order). Where a component (e.g., first) is described as “functionally” or “communically” “combined” or “connected” to another component (e.g., second), with or without the use of the terms “functionally” or “communically”, “integrated”, or “connected”, it should be understood that the component may be connected to the other component directly (e.g., wired), wirelessly, or via a third component.

[0033] Each component (e.g., a module or program) described in this disclosure may include a single object or multiple objects. According to various example implementations, one or more components or operations in a given component may be omitted, or one or more additional components or operations may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as the respective components among the multiple components performed their functions prior to integration. According to various example implementations, operations performed by a module, program, or other component may be performed sequentially, in parallel, repeatedly, or heuristically. Alternatively, one or more operations may be performed in a different order or omitted, or one or more additional operations may be added to them.

[0034] The terms "module" or "unit" as used in this disclosure can include units implemented in hardware, software, or firmware, and can be replaced by terms such as logic, logic block, component, or circuit. A module can be a monolithically formed component or the smallest unit or part of a component that performs one or more functions. For example, according to an example implementation, a module can be implemented as an application-specific integrated circuit (ASIC).

[0035] Various example implementations can be implemented as software (e.g., a program or application) that includes one or more instructions stored in a machine-readable storage medium (e.g., memory). For example, a machine's processor can invoke at least one of the one or more instructions stored in the storage medium and execute that at least one instruction. This enables the machine to operate to perform at least one function according to at least one invoked instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory" simply means that the storage medium is tangible and does not include signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is stored semi-permanently in the storage medium and cases where data is stored temporarily in the storage medium.

[0036] Figure 1 This is a block diagram illustrating the configuration of system 10 according to an example embodiment of this disclosure. (Refer to...) Figure 1The system 10 may include a drying device 200 for drying electrodes and an electronic device 100 that communicates with and controls the drying device 200.

[0037] Electrode manufacturing processes can include various types of processes, and as an example, may include a drying process for drying the electrode surface. For instance, the electrode drying process may be performed after a slitting process and a notching process. Here, the slitting process may refer to the process of cutting the electrode to match the battery specifications, and the notching process may refer to the process of removing portions other than those used to form electrode tabs from the uncoated portions where no active material has been applied. In the drying process, the surface of the electrode after the notching process can be heated to remove moisture from the electrode.

[0038] In the electrode drying process, insufficient or excessive drying can affect the quality of the electrode and may lead to defects. For example, when the electrode is not sufficiently dried, defects may occur due to moisture in the electrode. In addition, when the electrode is over-dried or dried at excessively high temperatures, surface defects such as thermal wrinkles may occur.

[0039] In particular, during the drying process, when the drying device 200 used to dry the electrodes is shut down and then restarted, the state of the drying device 200 and the electrodes can change each time the drying device 200 is shut down and then restarted, making it difficult to perform drying suitable for each state.

[0040] Therefore, the electronic device 100 can determine and control the state of the drying device 200 during the electrode drying process. In this way, the surface of the electrode can be stably managed during the electrode drying process, and defects can be prevented. In particular, even when the drying device 200 is running after being shut down, the electronic device 100 can take into account various initial states to control the drying device 200 to an optimal state.

[0041] The drying apparatus 200 may include a plurality of drying zones 210 and a plurality of heating devices 220. According to an example embodiment, the plurality of drying zones may include a first drying zone, a second drying zone, and a third drying zone disposed along the travel path of the electrode. For example, the first drying zone may be an introduction zone through which the electrode is introduced into the drying apparatus 200, the third drying zone may be an discharge zone through which the electrode is discharged to the outside of the drying apparatus 200, and the second drying zone may be an intermediate zone.

[0042] Electrodes can be introduced into the drying apparatus 200. The drying apparatus 200 can dry the surface of the electrodes by providing heat to the electrodes introduced therein. The electrodes can be conveyed in a direction defined by a conveying path, and the surface can be dried while the electrodes are conveyed in the defined direction within the drying apparatus 200.

[0043] For this purpose, the drying apparatus 200 may include a plurality of heating devices 220. The plurality of heating devices 220 may be respectively disposed corresponding to a plurality of drying zones 210 and may provide heat to the electrodes. For example, the heating device may be a mid-infrared (MIR) lamp that emits infrared light to the electrodes. However, this is only an example, and the type of heating device is not limited to this.

[0044] The electronic device 100 can manage the electrodes during the drying process, determine the state of the drying device 200 for drying under optimal conditions, and control the drying device 200. For example, when the drying device 200 is running after being shut down, the electronic device 100 can determine the output of each of the plurality of heating devices 220 and control the plurality of heating devices 220 based on the determined output.

[0045] According to an example implementation, electronic device 100 may include communication circuitry 110, memory 120, and processor 130. At least one of the components included in electronic device 10 may be omitted, or other components may be added to electronic device 10. Alternatively or additionally, some components may be implemented integratedly, or may be implemented as a single entity or multiple entities. At least some components in electronic device 10 may be implemented integratedly, or may be implemented as a single entity or multiple entities. At least some components in electronic device 10 may be interconnected via a bus, general purpose input / output (GPIO), serial peripheral interface (SPI), mobile industry processor interface (MIPI), etc., and may send and receive data and / or signals to each other.

[0046] The communication circuit 110 can establish a wired or wireless communication channel with an external device (e.g., the drying device 100) and send and receive various data from the external device. The communication circuit 110 may include at least one port for connecting to the external device via a wired cable for wired communication. The communication circuit 110 may include a cellular communication module and may be configured to connect to a cellular network (e.g., 3G, LTE, 5G, Wibro, or WiMAX). According to an example embodiment, the communication circuit 110 may include a near-field communication module to send and receive data from the external device using near-field communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), or UWB), but is not limited thereto. For example, the communication circuit 110 of the electronic device 100 can communicate with the drying device 200 and can send and receive various data and / or signals via communication.

[0047] Memory 120 may store various data used by at least one component (e.g., processor 130). Memory 120 stores instructions for the operation of processor 130. Programs may be stored in memory 120 as software, including, for example, operating systems, middleware, or application programs. In this disclosure, memory 120 may refer to a collection of one or more memories 120 unless otherwise stated. For example, memory 120 may store a trained deep learning model.

[0048] Processor 130 may be an element for performing computational or data processing to perform communication and / or control of each element, and may be operatively connected to the elements of electronic device 10. Processor 130 may load instructions or data received from other elements of electronic device 10 into memory 120, may process instructions or data stored in memory 120, and may store result data. The processor 130 mentioned in this disclosure may refer to a collection of one or more processors 130, unless otherwise stated.

[0049] According to an example implementation, the processor 130 can acquire the operating status information of the drying apparatus 200 when it is running after the drying apparatus 200 has been shut down. When the drying apparatus 200 is running after being shut down, it may have various operating states, and the processor 130 can acquire the operating status information of the drying apparatus 200 to optimally manage the drying of the electrodes based on the operating state of the drying apparatus 200. For example, the processor 130 can acquire the operating status information of the drying apparatus 200 by communicating with the drying apparatus 200 via the communication circuit 110.

[0050] According to an example embodiment, the operating status information of the drying apparatus 200 may include at least a portion of the drying apparatus 200's shutdown time and previous operating time, the initial state of each of the plurality of drying zones 210, and the initial state of each of the plurality of heating devices 220. Here, the shutdown time of the drying apparatus 200 may refer to the time between the end of the previous operation and the start of the current operation, and the previous operating time of the drying apparatus 200 may refer to the duration of the previous operation. The initial state of each of the plurality of drying zones 210 may, for example, include the internal temperature of each drying zone. The initial state of each of the plurality of heating devices 220 may, for example, include the initial temperature of each heating device. Furthermore, the initial state described herein may refer to the state of the drying apparatus 200 at a point in time after shutdown.

[0051] Specifically, the operating status information of the drying device 200 may include the stop time and previous operating time of the drying device, as well as the initial temperature of the heating device corresponding to the drying area where the electrodes are discharged.

[0052] According to an example implementation, the processor 130 can acquire state information of at least one electrode introduced into the drying apparatus 200. Since the state of the electrode can change at any point in time after the drying apparatus 200 has been shut down, the processor 130 can acquire the state information of the electrode.

[0053] According to an example implementation, the state information of the electrode may include the initial temperature of the surface of the electrode located in each of the plurality of drying zones 220, and the target temperature of the surface of the electrode at a target time point.

[0054] The processor 130 is designed to stably manage the surface of the electrode during the drying process, and for this purpose, it is designed to control the surface temperature of the electrode within a target temperature range. Therefore, the processor 130 can acquire the initial temperature of the electrode surface and the target temperature of the electrode surface at a target time point as state information of the electrode to control the drying process of the electrode when the drying apparatus 200 is running after shutdown.

[0055] According to an example implementation, the target time point may include the time elapsed from the time the electrode is introduced into the drying apparatus 200 until the electrode is discharged from one of the plurality of drying regions 210. In other words, the target time point may include the time elapsed from the time the electrode is introduced into the drying apparatus 200 until the electrode reaches the final drying region. For example, when the plurality of drying regions 220 include a first drying region, a second drying region, and a third drying region, the target time point may be the time elapsed from the time the electrode is introduced into the drying apparatus 200 until the electrode reaches the third drying region. As an example, when the electrode reaches the third drying region 9 seconds after being introduced into the first drying region, the target time point may be the time elapsed 9 seconds after the time the electrode is introduced into the first drying region.

[0056] Since the goal is to ensure that the surface temperature of the electrode meets the target temperature when the electrode drying process is performed, the processor 130 can set the target time point as the time required from the time the electrode is introduced into the drying apparatus 200 to the time required for the introduced electrode to reach the drying zone in one of the multiple drying zones 210 where the electrode is discharged.

[0057] Furthermore, a target time point can be set for each of the multiple drying zones 220. That is, different target time points can be set for each drying zone. For example, when the multiple drying zones 220 include a first drying zone, a second drying zone, and a third drying zone, and when the time required for the electrode introduced into the drying apparatus 200 to reach the first drying zone is 7 seconds, the time required to reach the second drying zone is 8 seconds, and the time required to reach the third drying zone is 9 seconds, the target time point for the first drying zone can be set to 7 seconds after the electrode is introduced, the target time point for the second drying zone can be set to 8 seconds after the electrode is introduced, and the target time point for the third drying zone can be set to 9 seconds after the electrode is introduced. Therefore, the processor 130 can set a target time point in each drying zone to finely manage the drying conditions during the process of the electrode passing through each drying zone.

[0058] According to the example implementation, when the time point from the moment the electrode is introduced into the drying apparatus 200 until the time required for the electrode to reach the final drying area is referred to as the first target time point, the target time point may further include a second target time point from the first target time point after a second time has elapsed. The second time can be preset. For example, the second time can be set based on the electrode's moving speed, similar to the first time.

[0059] The output of the heating device in the final drying zone can be set higher than the output of the heating devices in other drying zones, and the surface of the electrode may be over-dried due to the heat supplied while the electrode is passing through the final drying zone or due to the residual heat after the electrode has passed through the final drying zone. Therefore, the processor 130 can set a second target time point after a predetermined time has elapsed since the electrode arrived at the final drying zone, and can manage the target temperature of the electrode surface at the second target time point. For example, the second target time point could be a time point 6 seconds after the first target time point.

[0060] For example, when the drying apparatus 200 operates at a low initial electrode temperature, and without considering the target temperature at the second target time point, the outputs of the multiple heating devices 220 may be set higher to reach the target temperature of the electrode surface at the first target time point. In this case, the outputs of the heating devices in the final drying region may become higher, and the slope of the temperature increase on the electrode surface may become larger. Therefore, the temperature of the electrode surface may exceed the target temperature range after the first target time point.

[0061] Therefore, according to the example implementation, the processor 130 may further consider the target temperature of the electrode surface at a second target time point after a predetermined time has elapsed since the first target time point. In this case, the target temperature of the electrode surface at the second target time point can be used as an input variable for the deep learning model described later (i.e., the target temperature of the electrode surface at the target time point).

[0062] According to an example implementation, processor 130 can determine the output of each of the plurality of heating devices 220 based on the operating status information of the drying apparatus and the status information of at least one electrode. Processor 130 can determine the output of each of the plurality of heating devices 220 to manage the drying of the electrodes when the drying apparatus 200 is shut down.

[0063] According to an example implementation, processor 130 can determine the output of each of the plurality of heating devices 220 by using a trained deep learning model. To this end, processor 130 can obtain a trained deep learning model by generating and training the deep learning model. In some cases, the generation and training of the deep learning model can be performed in a separate device (e.g., an external server for training) rather than in electronic device 100. In this case, processor 130 can obtain the trained deep learning model from the external server.

[0064] Training deep learning models

[0065] The following description will be provided under the assumption that the deep learning model is generated and trained by the electronic device 100.

[0066] First, the processor 130 can generate a deep learning model. Generating a deep learning model can refer to setting the structure of the neural network that constitutes the deep learning model, as well as the initial values ​​of the parameters assigned to the neural network.

[0067] Furthermore, the processor 130 can ultimately generate a trained deep learning model by training the generated deep learning model. Here, generating a trained deep learning model through training can refer to training an initially generated deep learning model using multiple training data according to a training method, thereby creating a trained deep learning model configured to perform desired characteristics (or objectives). As mentioned above, such training can be performed within the electronic device 100 itself, or via a separate server and / or a separate system. Examples of training methods for deep learning models include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0068] The neural network structure that constitutes a deep learning model can be formed by multiple neural network layers. Each of these layers can have multiple weight values, and neural network operations can be performed by calculating the results of previous layers and these weight values. The weight values ​​of multiple neural network layers can be optimized using the training results of the deep learning model. For example, a loss function or cost function can be set for the deep learning model to achieve optimal learning, and the weight values ​​can be updated to reduce or minimize the loss or cost values ​​obtained by the deep learning model in each training process.

[0069] Artificial neural networks that make up deep learning models can include, but are not limited to, deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory (LSTM), restricted Boltzmann machines (RBM), deep belief networks, bidirectional recurrent deep neural networks (BRDNN), and deep Q-networks.

[0070] The processor 130 can acquire a dataset for training a deep learning model. The dataset for training may consist of multiple pre-acquired data or multiple data generated based on them, and can be configured to be suitable according to the training method of the deep learning model, the purpose of the deep learning model, the type of neural network, etc.

[0071] According to an example implementation, a deep learning model can learn the correlation between input and output data by using an input dataset and an output dataset for learning. The deep learning model can be trained to predict the output given the input data and to predict the output data for learning from the input data. In this way, the deep learning model can model the correlation between the output data and the input data during the learning process. This can be understood as performing supervised learning of the deep learning model, and the deep learning model can be trained using the output dataset for learning as a label. For example, the deep learning model can generate predictions from the input dataset for learning and can be trained by comparing these predictions with the output dataset.

[0072] According to the example implementation, the deep learning model can have multiple operating state information of the drying device 200 corresponding to multiple operations of the drying device 200 and multiple state information of multiple electrodes as input datasets for learning, and can have the output of each of the multiple heating devices 220 corresponding to multiple operations of the drying device 200 as output datasets for learning.

[0073] For example, processor 130 can acquire operating status information of drying device 200 from each of a plurality of previous runs of drying device 200, and thereby form an input dataset for learning. Furthermore, processor 130 can acquire the output of each of a plurality of heating devices 220 from each of a plurality of previous runs of drying device 200, and thereby form an output dataset for learning.

[0074] Since the processor 130 obtains the optimal output of the plurality of heating devices 220 for drying electrodes by using a deep learning model, the output of each of the plurality of heating devices corresponding to the plurality of operations of the drying device 200 can form an output dataset for learning the deep learning model.

[0075] In addition, to improve the performance of the deep learning model, the processor 130 can select variables related to the output of the multiple heating devices 220 or the target temperature of the electrode surface, and form multiple data corresponding to the selected variables into an input dataset for learning.

[0076] For deep learning models, since the learning performance and result prediction performance decrease when the input and output have little or no relationship, the processor 130 can select variables associated with the target output characteristics and form an input dataset for learning.

[0077] According to an example implementation, processor 130 can select multiple variables associated with at least one of the operating state of drying device 200 and the state of the electrodes. To select input variables for training a deep learning model, processor 130 can select and analyze multiple variables. For example, processor 130 can select variables such as the initial state of drying device 200 or the initial temperature of the electrode surface as multiple variables.

[0078] According to an example implementation, the processor 130 can determine the input variables for training a deep learning model by analyzing the correlation between multiple variables and the target temperature of the electrode surface based on the travel speed of the electrode.

[0079] Electrodes can be conveyed in a defined direction within the drying apparatus 200, and the travel speed of the electrodes can be set differently depending on the circumstances. In order to optimally control the drying process of the electrodes even in environments with varying electrode speeds, the electronic device 100 can identify variables that are correlated even at different speeds as input variables for a deep learning model.

[0080] To this end, the processor 130 can analyze the correlation and interaction between input variables and output characteristics based on the electrode's travel speed. For example, in the electrode drying process, the electrode's travel speed can be set to 1000 mm / s or 300 mm / s, and the processor 130 can select the input variable that has a correlation and interaction with the target temperature of the electrode surface as the output characteristic in both cases where the electrode's travel speed is 1000 mm / s and 300 mm / s.

[0081] However, this is just an example. The training of the deep learning model and the determination of the input variables used for that training can be performed in an external device (e.g., an external server for training), rather than in the processor 130. In this case, the processor 130 can obtain the trained deep learning model and its input variable information from the external server via communication circuitry 110.

[0082] According to an example implementation, the input variables that form the input data for learning a deep learning model may include: 1) the downtime of the drying device; 2) the previous operating time of the drying device; 3) the initial temperature of the surface of the electrode located in each of the plurality of drying zones; 4) the initial temperature of the heating device corresponding to the drying zone where the electrode is discharged; and 5) the target temperature of the surface of the electrode at the target time point.

[0083] The input variables can be determined through the correlation analysis and interaction analysis described above. (Refer to Figure 5 below.) Figure 8 Provide a supplementary description of the basis for calculating the input variables.

[0084] For example, since the output of each of the multiple heating devices is used to learn a deep learning model in order to manage the drying state of the electrode surface in the process of drying the electrode through the drying device 200 and to control the temperature of the electrode surface to a target temperature for this purpose, the processor 130 may include the target temperature of the electrode surface at a target time point as an input variable as input data for learning the deep learning model.

[0085] In this context, the deep learning model can receive input data for learning, which consists of the following input variables: 1) the downtime of the drying device; 2) the previous running time of the drying device; 3) the initial temperature of the surface of the electrode in each of the multiple drying zones; 4) the initial temperature of the heating device corresponding to the drying zone of the discharge electrode; and 5) the target temperature of the surface of the electrode at the target time point, and can be trained using this input data.

[0086] Therefore, the processor 130 can generate an input dataset and an output dataset for learning, use them to repeatedly train a deep learning model, and thereby obtain a trained deep learning model that optimizes the prediction of the output of each of the plurality of heating devices 220.

[0087] According to an example implementation, the trained deep learning model may include a Long Short-Term Memory (LSTM) model. LSTM models are high-performance models in time series or signal data analysis, and also high-performance models in discovering complex patterns. Therefore, electronic device 100 can use an LSTM model to learn the complex relationships between various variables related to the state of drying device 200 and electrodes and the output values ​​of each of the plurality of heating devices 220.

[0088] Use of trained deep learning models

[0089] According to the example implementation, the processor 130 can input the operating status information of the drying device 200 and the status information of at least one electrode into a trained deep learning model. Furthermore, the processor 130 can confirm the output of each of the plurality of heating devices 220 output from the deep learning model. That is, the processor 130 can determine the optimal output of the plurality of heating devices 220 by using the trained deep learning model when the drying device 200 is running after shutdown.

[0090] As described above, the processor 130 can confirm the output of each of the plurality of heating devices 220 by using the output from the deep learning model. The processor 130 can obtain the output of each of the plurality of heating devices 220 by feeding information of the input variables that form the input data for learning into the trained deep learning model.

[0091] According to the example implementation, the processor 130 can input the following information obtained at the time point after the drying device 200 is shut down: 1) the shutdown time of the drying device; 2) the previous operating time of the drying device; 3) the initial temperature of the surface of the electrode in each of the plurality of drying areas; 4) the initial temperature of the heating device corresponding to the drying area of ​​the discharged electrode; and 5) the target temperature of the surface of the electrode at the target time point into a trained deep learning model, and confirm the output of each of the plurality of heating devices 220 output from the trained deep learning model.

[0092] According to an example implementation, processor 130 can control multiple heating devices based on the output of each of the multiple heating devices. This can be understood as processor 130 controlling multiple heating devices 220 in their initial operating state when the drying device 200 is running after shutdown.

[0093] Therefore, the processor 130 can control the output of each of the plurality of heating devices 220 while the drying device 200 is running after shutdown. In other words, the processor 130 can set the output value obtained from the trained deep learning model as the initial output of each of the plurality of heating devices 220.

[0094] Furthermore, the processor 130 can monitor the surface temperature of the electrodes during operation of the drying apparatus 200. According to an example embodiment, the processor 130 can correct the output of at least one of the plurality of heating devices 220 based on the surface temperature of the electrodes. For example, when the rate of temperature rise of the electrode surface in the final drying region exceeds a threshold, the processor 130 can reduce the output power of the heating devices disposed in the final drying region.

[0095] According to an example implementation, the processor 130 can control the drying apparatus 200 differently depending on the type of electrode.

[0096] According to the example implementation, when the electrode is negative, the processor 130 can control the output of all heating devices. Furthermore, when the electrode is positive, the processor 130 can control the output of the heating device among the plurality of heating devices corresponding to the drying area where the electrode is discharged. In other words, the output of the heating devices located in the final drying area can be controlled. As an example, when the electrode is positive, the processor 130 can set the output of the heating device corresponding to the drying area other than the final drying area to 0.

[0097] For example, processor 130 can obtain the outputs of multiple heating devices 220 from the same deep learning model and selectively apply at least a portion of the outputs of the multiple heating devices 220 according to the type of electrode.

[0098] As another example, processor 130 can generate different deep learning models that apply different input variables for learning based on the type of electrode, and can apply the output of the heating device from the corresponding deep learning model according to the type of electrode. For example, when the electrode is positive, input variables corresponding to the final drying area can be applied, and input variables corresponding to other drying areas can be excluded, so that a deep learning model can be generated and trained.

[0099] Figure 2 This is a diagram showing the configuration of a drying apparatus 200 according to an exemplary embodiment of the present disclosure.

[0100] Reference Figure 2 The drying apparatus 200 may include multiple drying zones 211, 213, and 215. The electrodes may move within the drying apparatus 200 along a defined direction D.

[0101] Furthermore, the drying apparatus 200 may include a plurality of heating devices 221, 223, and 225 configured to correspond to each drying zone. For example, the first heating device 221 may be configured in the first drying zone 211, the second heating device 223 may be configured in the second drying zone 213, and the third heating device 225 may be configured in the third drying zone 215.

[0102] Each of the plurality of heating devices 221, 223 and 225 may be disposed above and below the conveying path 20. For example, the heating device 221 disposed in the first drying zone 211 may be formed by a pair of heating devices disposed above the conveying path 20 and a pair of heating devices disposed below the conveying path 20.

[0103] The electrode can be moved in a defined direction D within the drying apparatus 200, and the plurality of heating elements 221, 223, and 225 of the drying apparatus 200 can dry the electrode by emitting heat. For example, in order to remove moisture from the electrode after the cutting process, the drying apparatus 200 can dry the electrode by heating the surface of the electrode.

[0104] Figure 3 This is a diagram illustrating an example of the structure of a deep learning model according to an exemplary implementation of this disclosure.

[0105] Reference Figure 3 This illustrates an example of the structure of a neural network when the deep learning model is an LSTM model. The LSTM model according to the example implementation may include an input layer 310, a splicing layer 320, and a hidden layer 330.

[0106] The sequence length parameter for the input data can be defined in the LSTM model. Here, the sequence length can be a parameter representing elements of data such as the length of the input data fed into the LSTM model. Depending on the implementation, the sequence length in the LSTM model can be set to the number of input variables. For example, when six different input variables are fed into the LSTM model, the sequence length can be set to 6.

[0107] According to the example implementation, the processor 130 can apply different deep learning models based on the electrode type, and can generate different deep learning models for this purpose. In this case, the number of input variables used to train the deep learning model can vary depending on the electrode type, and therefore the sequence length can be set to vary.

[0108] According to the example implementation, among the input variables of the deep learning model, the target temperature of the electrode surface at the target time point can be input to the hidden layer 330. In this case, the sequence length in the deep learning model can be set to a value obtained by subtracting the number of input variables corresponding to the target temperature of the electrode surface at the target time point from the number of input variables.

[0109] Figure 3 The example shown is for a sequence of length 4. The circular dots represent individual nodes. Figure 3 The example shown is for a sequence length of 4, but it is not limited to this.

[0110] Input data corresponding to the sequence length of the LSTM model can be fed into the input layer 310. The input data fed into the input layer 310 can pass through multiple corresponding sequence nodes according to the input position. For example, it can include multiple sub-neural networks 311, 313, 315, and 317, each containing multiple sequence nodes for each input position. The multiple sub-neural networks 311, 313, 315, and 317 can learn the relationships between the nodes.

[0111] The output of each input data point at the final node 319 can pass through the concatenation layer 320. The concatenation layer 320 can concatenate the results of each input data point passing through the input layer 310.

[0112] The output from the splicing layer 320 can pass through the hidden layer 330. In this case, the hidden layer 330 can include nodes whose number corresponds to the number of drying areas. For example, when the drying device 200 includes a first drying area, a second drying area, and a third drying area, such as... Figure 3 As shown, hidden layer 330 may include three nodes.

[0113] Data on the target temperature of the electrode surface at the target time point in each dry region can be input to each node of the hidden layer 330. For example, as described in the example above, data on tout(9) as the target temperature of the electrode surface at the first target time point and data on tout(15) as the target temperature of the electrode surface at the second target time point can be input.

[0114] That is, the output of the splicing layer 320 and the target temperature data of the electrode surface at the target time point in each drying region can be input into the hidden layer 330, and the hidden layer 330 can ultimately export the respective outputs of multiple drying regions 220 as output values ​​(i.e., yin, ymid, yout).

[0115] Figure 4 This is a diagram illustrating an example of the results of applying a deep learning model according to an exemplary implementation of this disclosure. Figure 4 The results of achieving the target temperature of the electrode during the drying process via the drying apparatus 200 are shown. As the rate of achieving the target temperature of the electrode increases, the defect rate in the electrode drying process can be reduced, and it can be indicated that the performance of the trained deep learning model is relatively high. Here, the target temperature of the electrode can refer to the target temperature at the aforementioned target time point.

[0116] For example, refer to Figure 4 When the electrode moving speed is 1000 mm / s, as a result of controlling the output of multiple heating devices 220 by using a trained deep learning model, it can be confirmed that the target temperature achievement rate is 98.8% in the case of negative electrode and 92.8% in the case of positive electrode.

[0117] The target temperature achievement rate of the electrode can be calculated by the ratio of the number of times the electrode temperature reaches the target temperature to the number of times the drying device 200 is repeatedly run after shutdown. For example, in the case of the negative electrode, since the target temperature is reached 238 times out of a total of 241 runs, the target temperature achievement rate can be calculated to be 98.8%. In the case of the positive electrode, since the target temperature is reached 90 times out of a total of 97 runs, the target temperature achievement rate can be calculated to be 92.8%.

[0118] Therefore, when the drying device 200 is running after it has stopped, the electronic device 100 can use a trained deep learning model to control the output of multiple heating devices 220. In this way, the drying performance of the electrodes can be improved and the defect rate of the electrodes can be reduced.

[0119] Figure 5 to Figure 8 This is a diagram illustrating an example of correlation analysis used to determine the input variables of a deep learning model.

[0120] First, refer to Figure 5a and Figure 5b For electrodes with a speed of 1000 mm / s ( Figure 5a ) and 300 mm / s ( Figure 5b The graph shows the one-to-one correlation between various variables and the target temperature of the electrode surface in the discharge region, considering the different travel speeds of the electrodes.

[0121] Figure 5aFigures 511 to 517 respectively illustrate the relationship between the target temperature of the electrode surface in the discharge zone and log_stop time, log_previous running time, the initial temperature of the electrode surface in the introduction zone, the initial temperature of the electrode surface in the discharge zone, the temperature of the electrode surface in the introduction zone at the target time point, the output of the heating device in the introduction zone, and the output of the heating device in the discharge zone when the electrode travel speed is 1000 mm / s. Similarly, Figure 5b Figures 521 to 527 show the results when the electrode moving speed is 300 mm / s.

[0122] Reference Figure 5a and Figure 5b It can be confirmed that the target temperature of the electrode surface in the discharge region is similar to that of the various input variables at different travel speeds (1000 mm / s and 300 mm / s). For example, when comparing Graph 513 and Graph 523, it can be confirmed that the scatter plots have similar trends.

[0123] In other words, it can be inferred that Figure 5a and Figure 5b The input variables shown are related to the target temperature of the electrode surface in the discharge region, even at different travel speeds.

[0124] Specifically, in order to analyze the relationship, it can be confirmed that... Figure 5a and Figure 5b The values ​​showing the correlation between the input variables and the output characteristics are as follows, and Figure 6 The results of the correlation analysis of the input variables are shown in the figure.

[0125] Table 610 shows the results of the correlation analysis between the input variables and the target temperature of the electrode surface in the discharge zone. Table 620 shows the results of the correlation analysis between the input variables and the output of the heating device in the introduction zone. Table 630 shows the results of the correlation analysis between the input variables and the output of the heating device in the discharge zone.

[0126] Reference Figure 6 Tables 610 to 630 confirm that the correlation between the Y value and each input variable is similar at different linear velocities, and the correlation values ​​are statistically significant.

[0127] However, it was derived that, among multiple input variables, at a speed of 1000 mm / s, the variables of log_previous running time and the surface temperature of the electrode in the introduction region at the target time point are not correlated with the output of the heating device in the introduction region, and at a speed of 1000 mm / s, log_previous running time is not correlated with the output of the heating device in the discharge region.

[0128] However, although there is no one-to-one correlation between the predetermined input variables and the predetermined output characteristics, the interaction between the input variables needs to be considered in the correlation analysis.

[0129] to this end, Figure 7 The results of the correlation analysis, which takes into account the interactions between the input variables, are shown.

[0130] Reference Figure 7 The table shown illustrates the results of a correlation analysis between two selected input variables and the output characteristic, presented as components of a matrix. Specifically, the value of each component represents the frequency with which the two selected variables show a high correlation with the output characteristic. For example, since a correlation value considering the interaction indicates a strong correlation when it is greater than or equal to 0.7, the number of times a correlation value greater than or equal to 0.7 can be counted.

[0131] exist Figure 7 In the study, it was confirmed that, for all cases with line speeds of 1000 mm / s and 300 mm / s, the important variables showing a correlation with the output characteristics were similar. That is, when the frequency of use of the variable corresponding to each component was confirmed, the higher the frequency of use of the variable, the stronger its correlation with the output characteristics was likely to be. Furthermore, it was confirmed that the frequency distributions of the input variables were similar for both line speeds of 1000 mm / s and 300 mm / s.

[0132] In correlation analysis that considers the interactions between input variables, while these interactions can be taken into account, it is difficult to analyze the simultaneous effects on multiple output characteristics. Therefore, a multivariate analysis of variance (MANOVA) can be performed to examine the interactions between input variables and output characteristics. Furthermore, Figure 8 The results of the multivariate analysis of variance are shown in the figure.

[0133] Reference Figure 8 This allows us to confirm the impact of input variables on output characteristics at different travel speeds. Figure 8 This illustrates the effect of input variables on the output characteristics of the input zone heating device SCR_IN and the output of the output zone heating device SCR_OUT. Specifically, in Figure 8 The results from various calculation methods are derived in the form of a Pr>F term. Here, the Pr>F term can represent the value of a correlation factor. When the value is less than 0.05, a correlation can be assessed.

[0134] That is to say, refer to Figure 8 Figure 5 to be evaluated Figure 8The input variables analyzed are correlated with the output characteristics of the heating device; therefore, these input variables can be used to train a deep learning model.

[0135] Figure 9 This is a flowchart illustrating a control method for an electronic device according to an exemplary embodiment of the present disclosure.

[0136] Reference Figure 9 In step S910, the processor 130 can acquire the operating status information of the drying device after the drying device 200 has been shut down and is running again. The operating status information of the drying device 200 may include, for example, the shutdown time and previous operating time of the drying device, and the initial temperature of the heating device corresponding to the drying area where the electrodes are discharged. For example, the processor 130 can acquire this information from the drying device 200 via the communication circuit 110.

[0137] In step S920, the processor 130 may acquire state information of at least one electrode introduced into the drying apparatus 200. The electrode state information may include, for example, the initial temperature of the surface of the electrode located in each of the plurality of drying zones, and the target temperature of the electrode surface at a target time point. For example, the processor 130 may acquire this information from the drying apparatus 200 via the communication circuit 110.

[0138] In step S930, the processor 130 can determine the output of each of the plurality of heating devices 220. For example, the processor 130 can determine the output of each of the plurality of heating devices 220 by inputting the operating status information of the drying device and the status information of at least one electrode into a trained deep learning model.

[0139] In step S940, the processor 130 can control a plurality of heating devices 220. For example, the processor 130 can control the output of each of the determined plurality of heating devices 220 to the initial output of each of the plurality of heating devices 220 when the drying device 200 is shut down.

[0140] Figure 10 This is a flowchart describing a detailed control method for an electronic device according to an exemplary embodiment of the present disclosure. (The following will be omitted.) Figure 10 Zhongyu Figure 9 Similar redundant descriptions.

[0141] Reference Figure 10In step S1030, the processor 130 can input the operating status information of the drying device 200 and the status information of at least one electrode into the trained deep learning model. For example, the processor 130 can input data such as the downtime and previous operating time of the drying device as operating status information, and data such as the initial temperature of the surface of the electrode located in each of the multiple drying areas as electrode status information into the trained deep learning model.

[0142] In step S1040, the processor 130 can determine the output of each of the plurality of heating devices 220. The processor 130 can confirm the output of each of the plurality of heating devices 220 output from the deep learning model and determine the output of each of the plurality of heating devices 220 in the case of operation after the drying device 220 has been shut down.

[0143] The processor 130 can control multiple heating devices 220 according to the type of electrode. When the electrode is negative, the processor 130 can execute step S1050; when the electrode is positive, the processor 130 can execute step S1060.

[0144] In step S1050, when the electrode is negative, the processor 130 can control the output of all heating devices. The processor 130 can control the output confirmed by the deep learning model as the initial output of each of all heating devices.

[0145] In step S1060, when the electrode is positive, the processor 130 can control the output of the heating device corresponding to the drying area where the electrode is discharged. That is, the processor 130 can control the output of the heating device in the discharge area. For example, the processor 130 can set the output of heating devices located in other drying areas besides the discharge area to 0.

[0146] Figure 11 This is a flowchart illustrating a method for obtaining a trained deep learning model according to an exemplary embodiment of the present disclosure. The following description is based on the assumption that training of the deep learning model is performed in the electronic device 100. Figure 11 However, as mentioned above, the generation and training of deep learning models can also be performed in a separate device (e.g., an external server) instead of electronic device 100.

[0147] Reference Figure 11 In step S1110, the processor 130 can select multiple variables. Specifically, the processor 130 can select multiple variables related to at least one of the operating state of the drying apparatus 200 and the state of the electrodes.

[0148] In step S1120, processor 130 can determine the input variables of the deep learning model from among multiple variables. For example, processor 130 can analyze the correlation between multiple variables and the target temperature of the electrode surface based on the travel speed of the electrode. Furthermore, processor 130 can determine at least a portion of the multiple variables as input variables for the deep learning model based on the analysis results.

[0149] In step S1130, processor 130 may form an input dataset for training a deep learning model and an output dataset for training. For example, processor 130 may form an input dataset for training composed of data from defined input variables.

[0150] In step S1140, the processor 130 can input the input dataset and the output dataset for learning into the deep learning model. That is, the processor 130 can repeatedly train the deep learning model by inputting the input dataset and the output dataset for learning into the deep learning model.

[0151] In step S1150, processor 130 may obtain a trained deep learning model. Processor 130 may obtain a deep learning model optimized for the target characteristics as a result of repeatedly training the deep learning model. For example, processor 130 may obtain a deep learning model optimized for the output of each of the plurality of heating devices 220 in the drying apparatus 200.

[0152] Furthermore, this specification and accompanying drawings have been described with reference to exemplary embodiments of this disclosure. Although specific terminology has been used, it is only for the purpose of readily illustrating the technical content of this disclosure in a general sense and aiding in the understanding of the invention, and is not intended to limit the scope of this application. It will be apparent to those skilled in the art that other modifications based on the technical spirit of this disclosure can be implemented in addition to the embodiments disclosed herein.

[0153] The apparatus or terminal according to the above example embodiments may include: a processor; a memory for storing and executing program data; permanent storage such as a disk drive; a communication port for communicating with external devices; and user object devices such as touch panels, keys, and buttons. Methods implemented by software modules or algorithms can be stored as computer-readable code or program instructions executable in a processor on a computer-readable recording medium. Here, the computer-readable recording medium may include magnetic storage media (e.g., read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM or Digital Versatile Disc (DVD)). The computer-readable recording medium can be distributed across a network-connected computer system, enabling distributed storage and execution of computer-readable code. The medium can be read by a computer, stored in memory, and executed by a processor.

[0154] This example implementation can be represented by functional blocks and various process steps. These functional blocks can be implemented by various numbers of hardware and / or software configurations that perform specific functions. For example, this example implementation can employ integrated circuit configurations such as memory, processors, logic circuits, and look-up tables, which can perform various functions under the control of one or more microprocessors or other control devices. Similar to how components can be implemented by software programming or software elements, this example implementation can be implemented by programming languages ​​or scripting languages ​​such as C, C++, Java, assembly language, and Python, including various algorithms implemented through combinations of data structures, processes, routines, or other programming configurations. Functional aspects can be implemented by algorithms executed by one or more processors. Furthermore, this example implementation can employ, for example, related techniques for electronic environment setup, signal processing, and / or data processing. The terms "mechanism," "component," "method," and "configuration" are used broadly and are not limited to mechanical and physical parts. These terms can include the meaning of a series of routines in processor-related software.

Claims

1. An electronic device comprising: A communication circuit configured to communicate with a drying device, the drying device including multiple drying regions for drying introduced electrodes, and multiple heating devices respectively disposed corresponding to the multiple drying regions and configured to provide heat to the electrodes; A memory configured to store one or more instructions; as well as processor, When one or more of the instructions are executed, the processor is configured to: When the drying device is shut down and then restarted, the operating status information of the drying device is obtained; Obtain the status information of at least one electrode introduced into the drying device; The output of each of the plurality of heating devices is determined based on the operating status information of the drying device and the status information of the at least one electrode. and The plurality of heating devices are controlled based on the output of each of the determined plurality of heating devices.

2. The electronic device according to claim 1, wherein the operating status information of the drying device includes: The shutdown time and previous operating time of the drying device, and the initial temperature of the heating device corresponding to the drying area where the electrodes are discharged, and The state information of the electrodes includes: the initial temperature of the surface of the electrodes located in each of the plurality of drying regions, and the target temperature of the surface of the electrodes at the target time point.

3. The electronic device according to claim 2, wherein the target time point includes: The time elapsed from the moment the electrode is introduced into the drying apparatus until the time required for the introduced electrode to reach the drying zone from which the electrode is discharged among the plurality of drying zones.

4. The electronic device according to claim 1, wherein the processor is configured as: The operating status information of the drying device and the status information of the at least one electrode are input into a trained deep learning model; and Confirm the output of each of the plurality of heating devices output from the deep learning model.

5. The electronic device according to claim 4, wherein the deep learning model is a learning model that is: Multiple state information of multiple electrodes, and multiple operating state information of the drying device corresponding to multiple operations of the drying device, are used as input datasets for learning; The output of each of the plurality of heating devices corresponding to the plurality of operations of the drying apparatus is used as an output dataset for learning; and The correlation between the input dataset used for learning and the output dataset used for learning is modeled.

6. The electronic device of claim 4, wherein the trained deep learning model comprises an LSTM model.

7. The electronic device of claim 4, wherein the processor is configured as: Select multiple variables that are related to at least one of the operating state of the drying device and the state of the electrode; and The input variables of the deep learning model are determined by correlation analysis between the multiple variables and the target temperature of the electrode surface based on the travel speed of the electrode.

8. The electronic device of claim 1, wherein the processor is configured as: When the electrode is negative, the output of all heating devices is controlled; and When the electrode is positive, the output of the heating device among the plurality of heating devices corresponding to the drying area where the electrode is discharged is controlled.

9. The electronic device of claim 1, wherein the plurality of drying regions includes a first drying region, a second drying region, and a third drying region disposed along the travel path of the electrodes.

10. A method for controlling an electronic device, the electronic device comprising a plurality of drying regions for drying an introduced electrode, and configured to control a plurality of heating devices respectively disposed corresponding to the plurality of drying regions and configured to provide heat to the electrode, the method comprising: The step of obtaining the operating status information of the drying device after it has been shut down and is running again. The step of obtaining state information of at least one electrode introduced into the drying apparatus; The steps for determining the output of each of the plurality of heating devices based on the operating status information of the drying device and the status information of the at least one electrode; as well as The steps of controlling the plurality of heating devices based on the determined output of each of the plurality of heating devices.

11. A non-transitory computer-readable recording medium having a program recorded therein for performing the method of claim 10 on a computer.

Images