Data processing apparatus and method for analyzing battery manufacturing process

Abstract

A data processing apparatus for analyzing a battery manufacturing process, according to one embodiment of the present invention, may comprise at least one processor and a memory that stores at least one instruction to be executed through the at least one processor. Herein, the at least one instruction can include instructions for: collecting process data for each process factor for a plurality of batteries; using the process data for each process factor so as to construct a machine learning-based performance prediction model for predicting battery performance; generating analysis information that indicates the effect of at least one of process factors on a performance prediction value of the performance prediction model; and outputting the generated analysis information through a predefined graphical user interface (GUI).

Description

Data processing device and method for analyzing battery manufacturing processes

[0001] This application claims the benefit of Korean Patent Application No. 10-2023-0190095 filed with the Korean Intellectual Property Office on December 22, 2023, the entire disclosure of which is incorporated herein by reference.

[0002] The present invention relates to a data processing device and method, and more particularly, to a data processing device and method for analyzing a battery manufacturing process.

[0003] Secondary batteries are batteries that can be reused by charging even after discharge, and can be used as an energy source for small devices such as mobile phones, tablet PCs, and vacuum cleaners, and are also used as an energy source for medium and large devices such as automobiles and ESS (Energy Storage Systems) for smart grids.

[0004] Batteries can be manufactured through a sequential process involving electrode manufacturing, assembly, and activation. During and after the battery manufacturing process, various performance indicators, such as battery resistance, capacity, and charging time, are reviewed.

[0005] Because various process factors associated with each unit process affect the performance of the battery, and these process factors have very complex correlations, it is very difficult to determine which process factor has a major impact on the performance of the battery and how much of an impact that process factor has.

[0006] As a technology to solve the above problems, an appropriate data processing process is needed that can identify process factors affecting battery performance and analyze the influence of the process factors by using data related to the battery manufacturing process.

[0007] The purpose of the present invention to solve the above problems is to provide a data processing device for analyzing a battery manufacturing process.

[0008] Another object of the present invention to solve the above problems is to provide a data processing method performed in such a data processing device.

[0009] A data processing device for analyzing a battery manufacturing process according to one embodiment of the present invention for achieving the above purpose may include at least one processor; and a memory for storing at least one command executed through the at least one processor.

[0010] Here, the at least one command may include: a command for collecting process data for each process factor for a plurality of batteries; a command for constructing a machine learning-based performance prediction model for predicting the performance of a battery using the process data for each process factor; a command for generating analysis information indicating an influence of at least one of the process factors on a performance prediction value of the performance prediction model; and a command for outputting the generated analysis information through a predefined GUI (Graphical User Interface).

[0011] Here, the process data may include data related to one or more unit processes among an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL (End Of Line) process.

[0012] The command for building the above performance prediction model may include a command for removing process data for one or more process factors among the plurality of process factors based on one of a correlation and an importance for the plurality of process factors.

[0013] The command for building the above performance prediction model may include a command for building a performance prediction model that uses the process data for each process factor as learning data to output a prediction value for one or more performance factors among the capacity and resistance of the battery.

[0014] The command for constructing the above performance prediction model may include a command for generating a plurality of performance prediction models by applying different learning algorithms; and a command for selecting a performance prediction model exhibiting optimal performance among the performance prediction models based on a difference value between a performance prediction value and a performance measurement value for each of the performance prediction models.

[0015] The command for generating the above analysis information may include a command for calculating an influence index for each process factor based on a change in a performance prediction value according to a change in the individual process factor.

[0016] The command for outputting the above analysis information through the GUI may include a command for outputting one or more of the length, size, direction, and color of an object corresponding to a process factor by visualizing them so as to correspond to the influence index of the process factor.

[0017] The command for outputting the above analysis information through the GUI may include a command for selecting the top N process factors (N is a natural number greater than or equal to 2) with a high influence index; and a command for outputting objects corresponding to each of the N process factors by visualizing them so that they correspond to each influence index.

[0018] The command for outputting the above analysis information through the GUI may include a command for grouping the plurality of process factors based on the unit process; a command for summing the influence indices of the process factors included in each of the unit processes; and a command for outputting objects corresponding to each of the unit processes in a visualized manner so as to correspond to the influence indices for each unit process.

[0019] The command for outputting the above analysis information through the GUI may include a command for outputting a change in a performance prediction value according to a change in a process factor in the form of a two-dimensional graph.

[0020]

[0021] According to an embodiment of the present invention for achieving the above-described other objects, a data processing method for analyzing a battery manufacturing process may include the steps of collecting process data for each process factor for a plurality of batteries; constructing a machine learning-based performance prediction model for predicting battery performance using the process data for each process factor; generating analysis information indicating an influence of at least one of the process factors on a performance prediction value of the performance prediction model; and outputting the generated analysis information through a predefined GUI (Graphical User Interface).

[0022] Here, the process data may include data related to one or more unit processes among an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL (End Of Line) process.

[0023] The step of building the above performance prediction model may include a step of removing process data for one or more process factors among the plurality of process factors based on one of the correlation and importance for the plurality of process factors.

[0024] The step of constructing the above performance prediction model may include a step of constructing a performance prediction model that uses the process data for each process factor as learning data to output a predicted value for one or more performance factors among the capacity and resistance of the battery.

[0025] The step of constructing the above performance prediction model may include a step of generating a plurality of performance prediction models by applying different learning algorithms; and a step of selecting a performance prediction model exhibiting optimal performance among the performance prediction models based on a difference value between a performance prediction value and a performance measurement value for each of the performance prediction models.

[0026] The step of generating the above analysis information may include a step of calculating an influence index for each process factor based on a change in a performance prediction value according to a change in the individual process factor.

[0027] The step of outputting the above analysis information through the GUI may include a step of visualizing and outputting one or more of the length, size, direction, and color of an object corresponding to a process factor so as to correspond to the influence index of the process factor.

[0028] The step of outputting the above analysis information through the GUI may include the step of selecting the top N process factors (N is a natural number greater than or equal to 2) with a high influence index; and the step of visualizing and outputting objects corresponding to each of the N process factors so that they correspond to each influence index.

[0029] The step of outputting the above analysis information through the GUI may include the step of grouping the plurality of process factors based on the unit process; the step of adding up the influence indices of the process factors included in each of the unit processes; and the step of outputting objects corresponding to each of the unit processes by visualizing them so that they correspond to the influence indices for each unit process.

[0030] The step of outputting the above analysis information through the GUI may include a step of outputting a change in a performance prediction value according to a change in a process factor in the form of a two-dimensional graph.

[0031] According to the above-described embodiment of the present invention, analysis information on process factors affecting the performance of a battery can be provided, thereby helping to improve the battery manufacturing process.

[0032] Figure 1 shows a typical battery manufacturing process.

[0033] Figure 2 is an operation flowchart of a data processing method according to an embodiment of the present invention.

[0034] Figure 3 is an example of process data according to an embodiment of the present invention.

[0035] Figure 4 is an operational flowchart of a performance prediction model construction method according to an embodiment of the present invention.

[0036] Figure 5 is a reference diagram for explaining a data preprocessing method according to an embodiment of the present invention.

[0037] Figure 6 is an example screen of a user terminal for explaining a GUI according to an embodiment of the present invention.

[0038] Figures 7 to 10 are examples of screens of a user terminal for explaining analysis information according to an embodiment of the present invention.

[0039] Figure 11 is a block diagram of a data processing device according to an embodiment of the present invention.

[0040] 610: Output Item Selection Window

[0041] 620: Analysis Information Output Window

[0042] 1100: Data processing unit

[0043] The present invention is susceptible to various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention. Throughout the description of each drawing, similar reference numerals have been used to designate similar components.

[0044] Terms such as "first," "second," "A," and "B" may be used to describe various components, but these components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, the first component could be referred to as the "second component," and similarly, the second component could also be referred to as the "first component." The term "and / or" includes any combination of multiple related items listed or any one of multiple related items listed.

[0045] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0046] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0047] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0048]

[0049] Figure 1 shows a typical battery manufacturing process.

[0050] A battery can be manufactured by sequentially performing multiple unit processes. More specifically, the battery manufacturing process can be categorized into N unit processes, and the battery can be manufactured by sequentially performing the first through Nth processes.

[0051] For example, a battery cell can be manufactured by sequentially performing unit processes classified as an electrode coating process (first process), an electrode rolling process (second process), an assembly process (third process), an activation process (fourth process), and an EOL (End Of Line) process (fifth process).

[0052] During the individual unit process or after battery manufacturing is complete, performance testing may be conducted to determine whether the battery exhibits the intended performance. Performance indicators of the battery being tested may include its discharge capacity, charge resistance, and discharge resistance.

[0053] If these performance tests reveal that the battery is not performing as intended, changes to the battery design or adjustments to manufacturing process variables may be necessary.

[0054] However, because various process factors associated with each unit process affect battery performance, and these process factors exhibit highly complex correlations, it is difficult to identify the process factors that significantly influence battery performance. Furthermore, even if process factors that influence battery performance are identified, it is extremely difficult to determine the extent to which these process factors influence battery performance.

[0055] The present invention relates to a technology for solving such problems, and relates to a data processing device and method capable of identifying process factors affecting battery performance and analyzing the influence of the process factors by using data related to the battery manufacturing process.

[0056] Hereinafter, with reference to the attached drawings, the operation of the data processing device according to the present invention and various embodiments of the present invention and the data processing method performed in the data processing device will be described in detail.

[0057]

[0058] Figure 2 is an operation flowchart of a data processing method according to an embodiment of the present invention.

[0059] The data processing device can collect process data (S210). Here, the process data may include process data for each process factor for each of a plurality of batteries.

[0060] The process data may include data related to each of a plurality of unit processes. Here, the unit processes may include one or more of an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL process.

[0061] Figure 3 is an example of process data according to an embodiment of the present invention.

[0062] Referring to FIG. 3, the data processing device can collect process data categorized into multiple data instances. Here, a data instance may refer to process data for each process factor for an individual battery. For example, the data processing device can collect process data for each process factor for each of 100,000 battery cells.

[0063] Process factors included in the electrode coating process (first unit process) may include one or more of slurry temperature, slurry flow rate, coating gap, coating speed, and coating thickness.

[0064] Process factors included in the electrode rolling process (second unit process) may include one or more of a rolling roll gap, rolling pressure, rolling speed, and rolling thickness.

[0065] Process factors included in the assembly process (third unit process) may include one or more of lamination plate temperature, lamination force, lamination roller temperature, and lamination speed.

[0066] The process factors included in the activation process (fourth unit process) may include one or more of jig formation temperature, jig formation pressure, and inter-process waiting time.

[0067] Process factors included in the EOL process (5th unit process) may include one or more of electrolyte amount, performance measurement temperature, and cell thickness.

[0068] The data processing device can use the collected process data to produce process data for specific process factors. For example, the data processing device can use the collected process data to produce process data on rolling rate, thickness of the cathode after activation, and porosity of the cathode after activation.

[0069] Meanwhile, the process factors for each unit process illustrated in FIG. 3 are examples for a clear explanation of the present invention, and the scope of the present invention is not limited to the types of process factors.

[0070] Referring again to FIG. 2, the data processing device can build a performance prediction model using process data (S220). Here, the performance prediction model may be a machine learning-based artificial intelligence model that, when specific process data is input, outputs predicted values ​​for one or more battery performance factors.

[0071] Specifically, the data processing device can build a performance prediction model that outputs predicted values ​​for one or more performance factors using process data for each process factor. Here, the data processing device can train the performance prediction model using the process data for each process factor as training data. The performance prediction model can be defined to output predicted values ​​for performance factors of a battery as output data when specific process data is input as input data. Here, the performance predicted values ​​output through the performance prediction model can correspond to predicted values ​​for performance factors including one or more of the capacity and resistance of the battery.

[0072] The data processing device can use the performance prediction model constructed in S220 to generate analysis information indicating the influence of one or more process factors on the performance prediction value of the performance prediction model (S230). Here, the analysis information may include an influence index for one or more process factors. The influence index may be a numerical value indicating the degree of influence of an individual process factor on the performance prediction value of the performance prediction model.

[0073] In an embodiment, the data processing device can calculate an influence index for each process factor based on a change in a performance prediction value according to a change in the individual process factor.

[0074] For example, the data processing device can calculate an influence index for a process factor based on the difference between a performance prediction value of a performance prediction model and an average value of performance prediction values ​​calculated by randomly changing a feature value of a specific process factor.

[0075] As another example, the data processing device can calculate an influence index for a process factor based on the difference between a performance prediction value of a performance prediction model and a performance prediction value calculated by removing a feature value of the specific process factor.

[0076] In another embodiment, the data processing device may calculate an influence index for a particular process factor based on the contribution of the process factor calculated by propagating the performance prediction value backwards to the performance prediction model.

[0077] The influence index can be calculated as a positive or negative number. Here, a positive influence index means that it has a positive effect on the performance prediction value (i.e., it contributes to increasing the performance prediction value), and a negative influence index means that it has a negative effect on the performance prediction value (i.e., it contributes to decreasing the performance prediction value).

[0078] The data processing device can output the analysis information generated in S230 through a predefined GUI (Graphical User Interface) (S240).

[0079] The data processing device can select the top N process factors (N is a natural number greater than or equal to 1, which is either predefined or input by the user) with high influence indices, and output the selected process factors and the influence indices of each process factor through a GUI.

[0080] A data processing device can generate visual content corresponding to output items input by a user and output the visual content through a GUI. Here, the visual content can be composed of a combination of objects that can be visually recognized by the user (e.g., lines, arrows, shapes, N-dimensional graphs, etc.). For example, when a user inputs a specific output item (e.g., influence by instance, influence by process factor, influence by unit process), the data processing device can collect and process analysis information related to the input output item to generate visual content and output the visual content through a GUI.

[0081] The data processing device can output one or more of the length, size, direction, and color of an object corresponding to a process factor, visualized so as to correspond to the influence index of the corresponding process factor. For example, when a request for outputting the influence index for each process factor is received, the data processing device can output the influence index for each of the plurality of process factors in the form of a horizontal bar graph. In this case, the data processing device can group the process factors by unit process and output each group in a different color.

[0082] Users can identify process factors affecting battery performance or intuitively understand the extent to which process factors affect battery performance through analysis information output through the GUI according to the present invention.

[0083]

[0084] Figure 4 is a flowchart illustrating a method for constructing a performance prediction model according to an embodiment of the present invention. Figure 5 is also a reference diagram illustrating a data preprocessing method according to an embodiment of the present invention.

[0085] The data processing device can perform a preprocessing process defined for the process data collected in S210 (S410).

[0086] The preprocessing process may include a data engineering process that processes data instances and a feature engineering process that processes process factors included in each data instance.

[0087] First, in the data engineering process, one or more data instances may be removed based on predefined criteria.

[0088] For example, the data processing device can remove, from among 100,000 data instances, data instances for batteries manufactured from a predefined coating lot (LOT) and batteries having feature values ​​that deviate from predefined domain knowledge.

[0089] Next, in the feature engineering process, process data for one or more process factors may be removed based on predefined criteria. Specifically, the data processing device may remove process data for one or more process factors among the plurality of process factors based on one of the correlations and importances of the plurality of process factors.

[0090] For example, as illustrated in FIG. 5, the data processing device may calculate correlation coefficients between process factors (#1 to #30) and remove process data of process factors having correlation coefficients exceeding a predefined threshold. Here, the correlation coefficient may include a Pearson correlation coefficient. In addition, the data processing device may calculate an importance index for each process factor and remove process data of process factors having an importance index less than a predefined threshold. Here, the importance index may include a permutation importance score.

[0091] Referring again to Figure 4, the data processing device can construct a machine learning-based performance prediction model using process data that has undergone a preprocessing process (S420). Here, the data processing device can generate multiple performance prediction models by applying different learning algorithms.

[0092] For example, the data processing device can generate a performance prediction model based on a Random Forest, a performance prediction model based on an XGBoost, and a performance prediction model based on a Deep Neural Network, and train each of the performance prediction models using process data for each process factor as learning data.

[0093] Thereafter, the data processing device may calculate a model evaluation index for each performance prediction model (S430) and determine a performance prediction model exhibiting optimal performance among the performance prediction models based on the model evaluation index (S440). Here, the model evaluation index may be calculated based on the difference value between the performance prediction value and the performance measurement value.

[0094] In an embodiment, the data processing device may calculate RMSE (Root Mean Square Error) and R^2 (R Squared Score) based on the difference value between the performance prediction value and the performance measurement value for each of the Random Forest-based performance prediction model, the XGBoost-based performance prediction model, and the Deep Neural Network-based performance prediction model. Here, the data processing device may determine the performance prediction model having the lowest RMSE or the R^2 closest to 1 as the optimal performance prediction model.

[0095] For example, if the RMSE of the Random Forest-based charging resistance prediction model is calculated as 0.441 and R^2 is 0.625, the RMSE of the XGBoost-based charging resistance prediction model is calculated as 0.311 and R^2 is 0.814, and the RMSE of the Deep Neural Network-based charging resistance prediction model is calculated as 0.395 and R^2 is 0.669, the data processing device can determine the XGBoost-based charging resistance prediction model with the lowest RMSE and the closest R^2 to 1 as the optimal charging resistance prediction model.

[0096] In an embodiment, the data processing device may perform an optimization process for the optimal performance prediction model determined in step S440. Here, the data processing device may derive an optimal combination of multiple hyperparameters included in the performance prediction model using a Bayesian optimization algorithm.

[0097] Thereafter, the data processing device can generate analysis information for identifying process factors affecting battery performance using an optimized performance prediction model (S230) and output the analysis information through a GUI (S240).

[0098]

[0099] Figure 6 is an example screen of a user terminal for explaining a GUI according to an embodiment of the present invention.

[0100] Referring to FIG. 6, analysis information corresponding to output items input by a user can be visualized and output through a GUI. Here, the GUI may include an output item selection window (610) and an analysis information output window (620).

[0101] The data processing device can receive a selection signal for an output item input by a user through an output item selection window (610). Here, the output item can include one or more of an instance-specific influence, a process factor-specific influence, and a unit process-specific influence.

[0102] When a specific output item is input by a user, the data processing device can collect and process analysis information related to the input output item to generate visual content, and output the visual content through the analysis information output window (620).

[0103] When an instance-specific influence is selected as an output item and a specific data instance (e.g., a battery identifier) ​​is input, the data processing device can visualize and output an influence index by process factor for the corresponding data instance (the corresponding battery).

[0104] When the influence index by process factor is selected as an output item, the data processing device can visualize and output the influence index for each of the multiple process factors.

[0105] When the influence by process factor is selected as an output item and a specific process factor (e.g., coating speed) is input, the data processing device can visualize and output changes in performance prediction values ​​according to changes in the corresponding process factor.

[0106] When the influence index by unit process is selected as an output item, the data processing device can group process factors by unit process and output the influence index for each unit process in a visualized manner.

[0107]

[0108] Figures 7 to 10 are examples of screens of a user terminal for explaining analysis information according to an embodiment of the present invention.

[0109] Referring to FIG. 7, when an influence index by instance is selected as an output item by a user and a specific data instance (e.g., bat #266) is input, the data processing device can visualize and output an influence index by process factor for the corresponding data instance (bat #266).

[0110] Here, the data processing device can select the top N process factors (N is a natural number greater than or equal to 2, which is either predefined or input by the user) with high influence indices, and output objects corresponding to each of the selected process factors by visualizing them so that they correspond to each influence indices.

[0111] For example, as illustrated in FIG. 7, the data processing device can select the top 7 process factors (#10, #15, #7, #4, #19, #27, #21) with high influence indices, and output the objects (arrows) corresponding to each process factor in descending order. Here, each object (arrow) can have a length corresponding to the size of the influence indices and indicate a direction corresponding to the sign of the influence indices.

[0112] In addition, the data processing device can define the average predicted value of the performance prediction model as a starting point based on the x-axis, and calculate the starting point and end point of each object based on the influence index of the process factors, and visualize it as shown in Fig. 7. Accordingly, the user can intuitively recognize the main process factors affecting the performance of a selected specific battery, and the influence (magnitude and direction) of each of the process factors on the battery performance.

[0113]

[0114]

[0115] *Referring to Figure 8, when the user selects the influence index by process factor as an output item, the data processing device can visualize and output the influence index for each of a plurality of process factors.

[0116] Here, the data processing device can select the top N process factors with high influence indices, and output objects corresponding to each of the selected process factors by visualizing them so that they correspond to each influence indices.

[0117] For example, as illustrated in FIG. 8, the data processing device can select the top 7 process factors (#10, #15, #7, #4, #19, #27, #21) with high influence indices, and output objects (bars) corresponding to each process factor in descending order. Here, each object (bar) can be expressed with a length corresponding to the absolute value of the influence indices. Accordingly, the user can intuitively recognize the main process factors affecting battery performance and the level of influence each of the process factors has on battery performance.

[0118]

[0119] Referring to FIG. 9, when the user selects the influence of each process factor as an output item and a specific process factor (e.g., #4) is input, the data processing device can visualize and output a change in the performance prediction value according to a change in the corresponding process factor.

[0120] For example, as illustrated in FIG. 9, the data processing device can output a visualization of a change in a performance prediction value according to a change in a feature value of a selected process factor (#4) in the form of a two-dimensional graph. Here, the data processing device can output a relationship graph of the feature value-performance prediction value for each data instance, as well as a relationship graph for the average value of the data instances. Accordingly, the user can intuitively recognize a change trend in battery performance according to a change in a specific process factor, and a location of a feature value where battery performance changes rapidly.

[0121]

[0122] Referring to FIG. 10, when the user selects the influence index for each unit process as an output item, the data processing device can visualize and output the influence index for each unit process.

[0123] Here, the data processing device can group multiple process factors based on unit processes, then add up the influence indices of the process factors included in each of the unit processes, and output objects corresponding to each of the unit processes by visualizing them so that they correspond to the influence indices for each unit process.

[0124] For example, as illustrated in FIG. 10, the data processing device can group process factors into an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL process, add up the influence indices of the process factors included in each unit process, and then output objects (bars) corresponding to each unit process in a visualized manner corresponding to the influence indices of each unit process. Here, each object (bar) can be expressed as a length corresponding to the absolute value of the influence indices of each unit process. Accordingly, the user can intuitively recognize the influence of each unit process on battery performance.

[0125]

[0126] Figure 11 is a block diagram of a data processing device according to an embodiment of the present invention.

[0127] A data processing device (1100) for analyzing a battery manufacturing process according to an embodiment of the present invention may include at least one processor (1110), a memory (1120) for storing at least one command executed through the processor, and a transmission / reception device (1130) connected to a network to perform communication.

[0128] The at least one command may include: a command for collecting process data for each process factor for a plurality of batteries; a command for constructing a machine learning-based performance prediction model for predicting the performance of a battery using the process data for each process factor; a command for generating analysis information indicating an effect of one or more of the process factors on a performance prediction value of the performance prediction model; and a command for outputting the generated analysis information through a predefined GUI (Graphical User Interface).

[0129] Here, the process data may include data related to one or more unit processes among an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL (End Of Line) process.

[0130] The command for building the above performance prediction model may include a command for removing process data for one or more process factors among the plurality of process factors based on one of a correlation and an importance for the plurality of process factors.

[0131] The command for building the above performance prediction model may include a command for building a performance prediction model that uses the process data for each process factor as learning data to output a prediction value for one or more performance factors among the capacity and resistance of the battery.

[0132] The command for constructing the above performance prediction model may include a command for generating a plurality of performance prediction models by applying different learning algorithms; and a command for selecting a performance prediction model exhibiting optimal performance among the performance prediction models based on a difference value between a performance prediction value and a performance measurement value for each of the performance prediction models.

[0133] The command for generating the above analysis information may include a command for calculating an influence index for each process factor based on a change in a performance prediction value according to a change in the individual process factor.

[0134] The command for outputting the above analysis information through the GUI may include a command for outputting one or more of the length, size, direction, and color of an object corresponding to a process factor by visualizing them so as to correspond to the influence index of the process factor.

[0135] The command for outputting the above analysis information through the GUI may include a command for selecting the top N process factors (N is a natural number greater than or equal to 2) with a high influence index; and a command for outputting objects corresponding to each of the N process factors by visualizing them so that they correspond to each influence index.

[0136] The command for outputting the above analysis information through the GUI may include a command for grouping the plurality of process factors based on the unit process; a command for summing the influence indices of the process factors included in each of the unit processes; and a command for outputting objects corresponding to each of the unit processes in a visualized manner so as to correspond to the influence indices for each unit process.

[0137] The command for outputting the above analysis information through the GUI may include a command for outputting a change in a performance prediction value according to a change in a process factor in the form of a two-dimensional graph.

[0138] The data processing device (1100) may also include an input interface device (1140), an output interface device (1150), a storage device (1160), etc. Each component included in the data processing device (1100) may be connected by a bus (1170) and communicate with each other.

[0139] Here, the processor (1110) may refer to a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed. The memory (or storage device) may be composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory may be composed of at least one of a read-only memory (ROM) and a random access memory (RAM).

[0140]

[0141] The operations of the method according to an embodiment of the present invention can be implemented as a computer-readable program or code on a computer-readable recording medium. A computer-readable recording medium includes any type of recording device that stores data readable by a computer system. Furthermore, a computer-readable recording medium can be distributed across network-connected computer systems, allowing the computer-readable program or code to be stored and executed in a distributed manner.

[0142]

[0143] While some aspects of the present invention have been described in the context of a device, they may also represent a description of a corresponding method, wherein a block or device corresponds to a method step or a feature of a method step. Similarly, aspects described in the context of a method may also be described as a corresponding block or item or a feature of a corresponding device. Some or all of the method steps may be performed by (or using) a hardware device, such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, one or more of the most significant method steps may be performed by such a device.

[0144] Although the present invention has been described with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. As a data processing device for analyzing the battery manufacturing process, at least one processor; and A memory comprising at least one instruction to be executed via at least one processor, At least one of the above commands, Command to collect process data by process factor for multiple batteries; A command for constructing a machine learning-based performance prediction model for predicting battery performance using process data for each process factor; A command for generating analysis information indicating the influence of one or more of the above process factors on the performance prediction value of the performance prediction model; and A data processing device including a command for outputting the generated analysis information through a predefined GUI (Graphical User Interface).

2. In claim 1, The above process data is, A data processing device including data related to one or more unit processes of an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL (End Of Line) process.

3. In claim 2, The command to build the above performance prediction model is: A data processing device comprising a command to remove process data for one or more process factors among a plurality of process factors based on one of a correlation and an importance for the plurality of process factors.

4. In claim 2, The command to build the above performance prediction model is: A data processing device including a command for constructing a performance prediction model that outputs a prediction value for one or more performance factors among the capacity and resistance of a battery by using the process data for each of the above process factors as learning data.

5. In claim 4, The command to build the above performance prediction model is: A command for generating multiple performance prediction models by applying different learning algorithms; and A data processing device including a command for selecting a performance prediction model exhibiting optimal performance among the performance prediction models based on a difference value between a performance prediction value and a performance measurement value for each of the performance prediction models.

6. In claim 1, The command to generate the above analysis information is: A data processing device including a command for calculating an influence index for each process factor based on a change in a performance prediction value according to a change in the individual process factor.

7. In claim 6, The command to output the above analysis information through the GUI is: A data processing device including a command for visualizing and outputting one or more of the length, size, direction, and color of an object corresponding to a process factor so as to correspond to an influence index of the process factor.

8. In claim 6, The command to output the above analysis information through the GUI is: A command to select the top N (N is a natural number greater than or equal to 2) process factors with high influence indices; and A data processing device including a command for visualizing and outputting objects corresponding to each of the N process factors so as to correspond to each influence index.

9. In claim 6, The command to output the above analysis information through the GUI is: A command to group the above multiple process factors based on the unit process; A command to sum the influence indices of process factors included in each of the unit processes; and A data processing device including a command for visualizing and outputting objects corresponding to each of the unit processes so as to correspond to an influence index for each unit process.

10. In claim 6, The command to output the above analysis information through the GUI is: A data processing device including a command that outputs changes in performance prediction values ​​according to changes in process factors in the form of a two-dimensional graph.

11. A data processing method for analyzing a battery manufacturing process, A step of collecting process data by process factor for multiple batteries; A step of building a machine learning-based performance prediction model for predicting battery performance using process data for each process factor; A step of generating analysis information indicating the influence of one or more of the above process factors on the performance prediction value of the performance prediction model; and A data processing method, comprising a step of outputting the generated analysis information through a predefined GUI (Graphical User Interface).

12. In claim 11, The above process data is, A data processing method comprising data related to one or more unit processes of an electrode coating process, an electrode rolling process, an assembly process, an activation process, and an EOL (End Of Line) process.

13. In claim 12, The steps for building the above performance prediction model are: A data processing method, comprising the step of removing process data for one or more process factors among a plurality of process factors based on one of a correlation and an importance for the plurality of process factors.

14. In claim 12, The steps for building the above performance prediction model are: A data processing method comprising a step of constructing a performance prediction model that outputs a prediction value for one or more performance factors among the capacity and resistance of a battery by using the process data for each of the above process factors as learning data.

15. In claim 14, The steps for building the above performance prediction model are: A step of generating multiple performance prediction models by applying different learning algorithms; and A data processing method, comprising a step of selecting a performance prediction model exhibiting optimal performance among the performance prediction models based on a difference value between a performance prediction value and a performance measurement value for each of the above performance prediction models.

16. In claim 11, The steps for generating the above analysis information are: A data processing method, comprising a step of calculating an influence index for each process factor based on a change in a performance prediction value according to a change in each process factor.

17. In claim 16, The step of outputting the above analysis information through the GUI is: A data processing method, comprising the step of visualizing and outputting one or more of the length, size, direction, and color of an object corresponding to a process factor so as to correspond to an influence index of the process factor.

18. In claim 16, The step of outputting the above analysis information through the GUI is: A step of selecting the top N process factors with high influence indices (N is a natural number greater than or equal to 2); and A data processing method, comprising a step of visualizing and outputting objects corresponding to each of the N process factors so as to correspond to each influence index.

19. In claim 16, The step of outputting the above analysis information through the GUI is: A step of grouping the above multiple process factors based on the unit process; A step of summing the influence indices of process factors included in each of the unit processes; and A data processing method, comprising a step of visualizing and outputting objects corresponding to each unit process so as to correspond to an influence index for each unit process.

20. In claim 16, The step of outputting the above analysis information through the GUI is: A data processing method, comprising a step of outputting a change in a performance prediction value according to a change in a process factor in the form of a two-dimensional graph.

Images