Slurry pressure and filtration apparatus for analyzing slurry and method and

Abstract

Slurry pressurization and filtration apparatus for analyzing slurries, and methods and media for analyzing slurries are provided. The method of analyzing a slurry performed by a processor of a slurry pressurization and filtration apparatus may include: collecting an accumulated discharge amount of a slurry of an active material of a secondary battery at a preset time interval; calculating an hourly discharge amount of the slurry by using the accumulated discharge amount of the slurry at the previous time and the accumulated discharge amount of the slurry at the current time; classifying the state information of the slurry on the basis of the accumulated discharge amount of the slurry and the discharge amount per hour of the slurry; and deriving a discharge rate representing a flow characteristic and a dispersion state of the slurry as an evaluation feature value based on a result of classifying the state information of the slurry.

Description

Technical Field

[0001] Embodiments of this disclosure relate to a slurry pressurization and filtration apparatus for analyzing slurries of active materials in secondary batteries, and a method for analyzing slurries of active materials in secondary batteries performed by the slurry pressurization and filtration apparatus. Background Technology

[0002] In the industrial processing of slurries containing active materials for secondary batteries, the continuous flow characteristics of the slurry are crucial. This is because the design of the entire facility, such as the length, thickness, and angle of the production line piping, may be determined based on the continuous flow characteristics of the slurry containing the active materials for secondary batteries.

[0003] In existing slurry pressurization and filtration equipment, the high viscosity of the slurry presents a possibility of random outliers occurring during data measurement. This could reduce the reliability of discharge volume and discharge rate data provided by the slurry pressurization and filtration equipment.

[0004] The information disclosed in this background section is intended only to enhance the understanding of the background of this disclosure, and therefore may contain information that does not constitute prior art. Summary of the Invention

[0005] Embodiments of this disclosure involve classifying data measured in slurry pressurization and filtration equipment into normal and outlier values ​​and removing outliers.

[0006] Embodiments of this disclosure relate to deriving standardized evaluation characteristic values ​​of slurry using normal values.

[0007] However, the technical objectives of the embodiments of this disclosure are not limited to the above objectives, and those skilled in the art will clearly understand other objectives of the embodiments not described herein by reviewing the following disclosure.

[0008] According to an embodiment, the method for analyzing slurry executed by the processor of the slurry pressurization and filtration equipment includes: collecting the cumulative discharge amount of the slurry of the active material of the secondary battery at preset time intervals; calculating the hourly discharge amount of the slurry by using the cumulative discharge amount of the slurry at a previous time and the cumulative discharge amount of the slurry at the current time; classifying the state information of the slurry based on the cumulative discharge amount and the hourly discharge amount of the slurry; and deriving a discharge rate representing the flow characteristics and dispersion state of the slurry as an evaluation characteristic value based on the result of classifying the state information of the slurry.

[0009] According to an embodiment, a slurry pressurization and filtration device for analyzing slurry includes: one or more processors; and a memory operatively connected to the one or more processors and configured to store at least one code executed by the processors, wherein the memory is configured to store at least one code to, when executed by the processors, cause the processors to: collect the cumulative discharge amount of the slurry of active material from a secondary battery at preset time intervals; calculate the hourly discharge amount of the slurry using the cumulative discharge amount of the slurry at a previous time and the cumulative discharge amount of the slurry at the current time; classify the state information of the slurry based on the cumulative discharge amount and the hourly discharge amount of the slurry; and, based on the result of classifying the state information of the slurry, derive a discharge rate representing the flow characteristics and dispersion state of the slurry as an evaluation characteristic value.

[0010] In implementation, other methods, other systems for carrying out the subject matter of this disclosure, and computer-readable recording media thereon storing computer programs for performing the methods may be further provided.

[0011] Other aspects and features of the embodiments, in addition to those described above, will become apparent from the following drawings, claims and detailed description of this disclosure. Attached Figure Description

[0012] The accompanying drawings illustrate embodiments of the present disclosure and, together with the following detailed description, are intended to provide a further understanding of the technical scope of the present disclosure. However, the present disclosure should not be construed as limited to the details shown in the drawings, in which:

[0013] Figure 1 The illustration shows the construction of a slurry pressurization and filtration apparatus for analyzing slurries according to an embodiment of the present disclosure;

[0014] Figure 2 The illustration shows the structure of a processor in a slurry pressurization and filtration apparatus for analyzing slurry according to an embodiment of the present disclosure;

[0015] Figure 3 An example diagram illustrating a classification unit in a processor according to an embodiment of the present disclosure is shown;

[0016] Figure 4 An example diagram illustrating a derived unit in a processor according to an embodiment of the present disclosure is shown; and

[0017] Figure 5 This is a flowchart illustrating a method for analyzing slurry executed by a processor of a slurry pressurization and filtration apparatus according to an embodiment of the present disclosure. Detailed Implementation

[0018] In the following description, embodiments of the present disclosure will be described with reference to the accompanying drawings. Before the following description, it should be understood that the terminology used in the specification and appended claims should not be construed as limited to its general and dictionary meaning, but rather should be interpreted based on the meaning and concept corresponding to the technical aspects of the present disclosure, on the principle of allowing inventors to act as their own lexicographers and to define terms appropriately or aptly for the best description. Accordingly, the embodiments disclosed in this specification and the constructions illustrated in the drawings are merely exemplary embodiments of the present disclosure and do not represent all the technical ideas of the present disclosure; therefore, it should be understood that various suitable equivalents and modifications may be made to replace these at the time of filing this application. Furthermore, the terms “comprising and including” and / or “including and comprising” as used in this specification should be interpreted as specifying the presence of the described shapes, quantities, steps, operations, components, elements, and / or groups thereof, and do not exclude the presence or addition of other shapes, quantities, operations, components, elements, and / or groups thereof. Additionally, the use of “may” and “may be” in describing embodiments of the present disclosure (e.g., when) refers to “one or more embodiments of the present disclosure”.

[0019] In embodiments, for better understanding of this disclosure, the drawings may not be shown to scale, and the dimensions of some elements may be exaggerated. In embodiments, the same reference numerals may be assigned to the same parts in different embodiments.

[0020] The statement that two comparison objects are "identical" means that the two comparison objects are "substantially identical." Therefore, "substantially identical" can include deviations that are considered low in the art (e.g., deviations of less than 5%). In an implementation, the uniformity of parameters in a region can mean uniformity from an average perspective.

[0021] It will be understood that although the terms first and second, etc., are used herein to describe various components, these components should not be limited by these terms. These terms are used only to distinguish one component from another, and unless otherwise specifically described, the first component may also be the second component.

[0022] Throughout this instruction manual, unless otherwise specified, each component may be singular or plural.

[0023] The arrangement of any component at the "top (or bottom)" of a component includes not only the arrangement in which any component is in contact with the top (or bottom) of the component, but also the arrangement in which other components may be located between the component and any component disposed on (or below) the component.

[0024] Furthermore, when referring to one component as “connected” or “linked” to another component, this can mean that the components are directly connected or linked to each other, but it should be understood that another component may be “between” these components, or that these components may be “connected” or “linked” to each other via another component. In addition, the term “electrical connection” can mean not only “direct connection” but also “connection via other inserting components.”

[0025] Unless otherwise stated, when “A and / or B” is mentioned (for example, when) throughout the specification, it means A, B, or A and B. For example, “and / or” includes all or any combination of the listed items. Unless otherwise specified, “C to D” means above C and below D.

[0026] Figure 1 The illustration shows the construction of a slurry pressurization and filtration apparatus 100 for analyzing slurries according to an embodiment of the present disclosure. (Reference) Figure 1 The slurry pressurization and filtration device 100 (hereinafter referred to as the slurry pressurization and filtration device) for analyzing slurries may include a pressurization and filtration module 110, a sensing module 120, a memory 130, and a processor 140.

[0027] The pressurization and filtration module 110 can apply a set or specific pressure to the slurry to allow it to pass through a filter. In this embodiment, the pressurization and filtration module 110 may use a pump to apply a set or specific pressure to the slurry and deliver it to the filter. The filter typically includes a fine mesh and / or porous media and can allow only suitable or desired particles of a suitable or desired size to pass through while blocking larger particles. The slurry passes through the filter, allowing impurities to be removed.

[0028] A sensing module 120 may be provided at the output of the pressurization and filtration module 110 and may sense the cumulative discharge volume of slurry passing through the filter. The sensing module 120 may calculate the cumulative discharge volume of slurry at preset time intervals (e.g., 1 second). In this embodiment, the sensing module 120 may include at least one selected from a flow meter and a load unit. The flow meter may detect the flow rate and volume of slurry passing through the filter. The load unit may detect the cumulative discharge volume by measuring the weight of the slurry passing through the filter.

[0029] The memory 130 can store data used for slurry analysis. In this embodiment, the memory 130 can store the cumulative discharge volume detected by the sensing module 120. In some embodiments, the memory 130 can store the results of processing by the processor 140 to calculate the hourly discharge volume, generate a first graph, classify the slurry state information, calculate the hourly discharge rate, and derive evaluation feature values. In some embodiments, an artificial intelligence algorithm for classifying the slurry state information can be stored in the memory 130.

[0030] In this embodiment, memory 130 may be operatively connected to processor 140 and may store at least one code associated with operations performed by processor 140.

[0031] In some embodiments, memory 130 may perform the function of temporarily or permanently storing data processed by processor 140. In embodiments, memory 130 may include magnetic storage media and / or flash memory media, but the scope of this disclosure is not limited thereto. Memory 130 may include internal and / or external memory, and may include volatile memory such as dynamic random access memory (DRAM), static RAM (SRAM), and / or synchronous DRAM (SDRAM), and non-volatile memory such as one-time programmable read-only memory (OTPROM), programmable read-only memory (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), mask ROM, flash ROM, NAND flash memory and / or NOR flash memory, flash drives such as solid-state drives (SSD), compressed flash (CF) cards, secure digital (SD) cards, micro SD cards, mini SD cards, extreme digital (xD) cards, and / or memory sticks, and / or storage devices such as hard disk drives (HDDs).

[0032] The processor 140 can collect the cumulative discharge amount of slurry from the sensing module 120 at preset time intervals, and can calculate the hourly discharge amount of slurry. Based on the cumulative discharge amount and the hourly discharge amount, the processor 140 can classify the state information of the slurry. Based on the classification of the slurry state information, the processor 140 can derive a discharge rate representing the flow characteristics and dispersion state of the slurry as an evaluation feature value.

[0033] In this embodiment, processor 140 can process computer program instructions by performing basic arithmetic, logic, and input / output operations. In some embodiments, processor 140 can control the overall operation of other components associated with pressurization and filtering module 110.

[0034] For example, processor 140 can perform at least some of the above operations by using at least one of machine learning, neural network, and deep learning algorithms as a rule-based or artificial intelligence algorithm to perform data analysis, processing, and result information generation. Examples of neural networks may include models such as convolutional neural networks (CNN), deep neural networks (DNN), and recurrent neural networks (RNN).

[0035] For example, processor 140 may be implemented as an array of logic gates, or it may be implemented as a combination of a general-purpose microprocessor and memory storing programs that can be executed on the microprocessor. For example, processor 140 may include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, and / or a state machine. In some embodiments, processor 140 may include an application-specific integrated circuit (ASIC), a programmable logic device (PLD), and / or a field-programmable gate array (FPGA). For example, processor 140 may refer to a combination of processing devices such as a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors together with a DSP core, or any other suitable combination of such constructions.

[0036] In this embodiment, the pressurization and filtration device 100 may further include a communication unit. The communication unit, along with a network, can transmit data processed by the processor 140 to an external device (e.g., a user terminal). In this embodiment, under the control of the processor 140, the communication unit can transmit data processed in the process of obtaining the cumulative discharge rate of the slurry, the hourly discharge rate of the slurry, the results of classifying the state information of the slurry, and the results of obtaining the evaluation characteristic values ​​of the slurry to the user terminal.

[0037] Figure 2 The diagram illustrates the configuration of a processor 140 in a slurry pressurization and filtration apparatus 100 for analyzing slurry according to an embodiment of the present disclosure. Figure 3 An example diagram is shown illustrating a classification unit 144 in a processor 140 according to an embodiment of the present disclosure. Figure 4 An example diagram is shown illustrating the derivation unit 145 in a processor 140 according to an embodiment of the present disclosure. In the following description, references may be omitted. Figure 1 The part described is repeated.

[0038] refer to Figures 2 to 4 The processor 140 may include a collection unit 141, a calculation unit 142, a generation unit 143, a classification unit 144, and a result unit 145.

[0039] The collection unit 141 can collect the cumulative discharge (cumulative output (g)) of the slurry at preset time intervals (e.g., 1 second). After a preset pressure is applied to the slurry, the collection unit 141 can collect the cumulative discharge of the slurry that has passed through the filter from the sensing module 120 (e.g., at least one selected from a flow meter and a load unit).

[0040] The calculation unit 142 can calculate the hourly discharge rate of the slurry based on the cumulative discharge rate of the slurry (output [g]). The calculation unit 142 can calculate the difference between the cumulative discharge rate of the slurry at a previous time and the cumulative discharge rate of the slurry at the current time as the hourly discharge rate.

[0041] The generation unit 143 can generate a first graph by plotting the cumulative discharge amount of slurry (cumulative output (g)) on the X-axis and the hourly discharge amount of slurry (output [g]) corresponding to the X-axis on the Y-axis. The hourly discharge amount corresponding to any cumulative discharge amount can be shown on the first graph. The discharge characteristics of the slurry over time can be analyzed using the first graph.

[0042] The classification unit 144 can classify the state information of the slurry based on the cumulative discharge volume and the hourly discharge volume. The classification unit 144 can classify the state information of the slurry corresponding to the cumulative discharge volume and the hourly discharge volume using an unsupervised deep learning model. This unsupervised deep learning model is pre-trained to classify the state information of the slurry by taking the cumulative discharge volume and the hourly discharge volume as input. In this embodiment, the state information of the slurry can include normal values ​​and abnormal values.

[0043] In this embodiment, the unsupervised learning-based deep learning model can use one or more algorithms such as autoencoders, K-means clustering, self-organizing maps, deep trust networks, and / or support vector machines. In some embodiments, depending on the type or kind of algorithm, the slurry state information ultimately output from the unsupervised learning-based deep learning model can be classified into normal values ​​and outliers, and can also be represented in the form of mean squared error (MSE), indicating how much the state information deviates from the normal value.

[0044] Figure 3A first graph 310 is shown, including the cumulative discharge rate and the hourly discharge rate of the slurry. Classification unit 144 can generate a result 320 in which normal and outlier values ​​are classified, using the first graph 310 as input. The result 320, where normal and outlier values ​​are classified, can be an example of the output of a K-means clustering model, and can be an example where data is classified into one of two groups and displayed (K=2). The K-means clustering model can perform the task of classifying the cumulative discharge rate and the hourly discharge rate of the slurry into the closer group among the two groups.

[0045] The determining unit 145 can derive an evaluation feature value representing the flow characteristics and dispersion state of the slurry based on the classification results of the slurry state information. In this embodiment, the determining unit 145 can remove outliers from the classification results of the slurry state information received from the classification unit 144 and can use normal values.

[0046] The unit 145 can calculate the hourly discharge rate (output rate [%) of the slurry based on the hourly discharge volume of the slurry included in the normal value and a first reference value. In this embodiment, the first reference value may be represented by a value selected from the cumulative discharge volume of the slurry (e.g., Figure 3 The hourly discharge corresponding to the cumulative discharge volume in the range of 310g to 500g.

[0047] The equation used to calculate the hourly discharge rate of the slurry can be Equation 1 below.

[0048] Equation 1

[0049] Output rate [%] = Discharge per hour (output [g]) / First reference value × 100

[0050] Unit 145 can generate a second graph by plotting the cumulative discharge amount of slurry (cumulative output (g)) on the X-axis and the hourly discharge rate of slurry (output rate [%)) corresponding to the X-axis on the Y-axis. The hourly discharge rate corresponding to any cumulative discharge amount can be shown on the second graph. The discharge rate characteristics of the slurry over time can be analyzed using the second graph.

[0051] Unit 145 can determine the hourly discharge rate of the slurry as an evaluation characteristic value, corresponding to a second reference value (e.g., 2000 g) representing the maximum cumulative discharge on the second graph.

[0052] Figure 4The diagram shows a 2-1 graph 410, which includes both outliers and normal values, and comprises the cumulative discharge volume and hourly discharge rate of the slurry. It also shows a 2-2 graph 420, which removes outliers and includes only normal values, and comprises the cumulative discharge volume and hourly discharge rate of the slurry. The second graph described above in this embodiment may be designated as 2-2 graph 420.

[0053] When evaluating feature values ​​(for example, when) they are determined using a 2-1 graph 410, the reliability of the evaluated feature values ​​may be reduced because the evaluated feature values ​​are selected as outliers. In this embodiment, however, the reliability of the evaluated feature values ​​can be improved because the evaluated feature values ​​can be determined using a 2-2 graph 420 and the evaluated feature values ​​are selected as normal values.

[0054] Figure 5 This is a flowchart illustrating a method for analyzing slurry executed by the processor 140 of a slurry pressurization and filtration apparatus 100 according to an embodiment of the present disclosure. In the following description, references to the document will not be repeated. Figure 1 and Figure 4 The description repeats some parts. The following will be described assuming that the method for analyzing the slurry according to this embodiment is performed by the processor 140 of the pressurization and filtration device 100 with the help of peripheral components.

[0055] In operation S510, the processor 140 can collect the cumulative discharge of slurry at preset time intervals. In this embodiment, the processor 140 can collect the cumulative discharge of slurry that has passed through the filter after a preset pressure has been applied from at least one selected from a flow meter and a load unit.

[0056] In operation S520, the processor 140 can calculate the hourly discharge rate of the slurry by using the cumulative discharge rate of the slurry at the previous time and the cumulative discharge rate of the slurry at the current time.

[0057] In this embodiment, the processor 140 can generate a first graph by plotting the cumulative discharge of slurry (cumulative output (g)) on the X-axis and plotting the hourly discharge of slurry (output [g]) corresponding to the X-axis on the Y-axis.

[0058] In operation S530, the processor 140 can classify the state information of the slurry based on the cumulative discharge rate and hourly discharge rate of the slurry included in the first curve. In this embodiment, the processor 140 can classify the state information of the slurry corresponding to the cumulative discharge rate and hourly discharge rate of the slurry using an unsupervised learning-based deep learning model, which is pre-trained to classify the state information of the slurry by taking the cumulative discharge rate and hourly discharge rate of the slurry as input. In this embodiment, the state information of the slurry can be classified into normal values ​​and outliers, and the processor 140 can remove outliers from the state information of the slurry that includes both normal and outliers.

[0059] In operation S540, processor 140 can derive an evaluation feature value representing the flow characteristics and dispersion state of the slurry based on the results of classifying the slurry's state information. In this embodiment, processor 140 can remove outliers from the results of classifying the slurry's state information and can apply normal values. Processor 140 can calculate the hourly discharge rate of the slurry using the hourly discharge rate of the slurry based on the normal value and a first reference value, which represents the hourly discharge rate corresponding to the cumulative discharge rate selected from the cumulative discharge rates of the slurry. Processor 140 can generate a second graph by plotting the cumulative discharge rate of the slurry (cumulative output (g)) on the X-axis and the hourly discharge rate of the slurry (output rate [%)) corresponding to the X-axis on the Y-axis. Processor 140 can determine the hourly discharge rate of the slurry corresponding to the second reference value representing the maximum value of the cumulative discharge rate on the second graph as the evaluation feature value.

[0060] Although the subject matter of this disclosure has been described with reference to exemplary embodiments and accompanying drawings, this disclosure is not limited thereto, and rather, those skilled in the art will understand that various suitable modifications and alterations may be made to these embodiments without departing from the principles and spirit of this disclosure as defined by the appended claims and their equivalents.

[0061] According to embodiments of this disclosure, the reliability of the measured data can be improved by removing outliers from the data measured in the slurry pressurization and filtration equipment.

[0062] In some implementations, outliers can be minimized or reduced in the analysis results by removing outliers from the data measured in the slurry pressurization and filtration equipment, thereby providing more accurate information for process determination or adjustment.

[0063] In some implementations, by standardizing the characteristic values ​​of the slurry, each batch of slurry can be kept in the same quality, thereby ensuring or improving process consistency.

[0064] In some implementations, by removing outliers and standardizing characteristic values ​​from data measured in slurry pressurization and filtration equipment, data processing biases that may occur with each operator in existing methods can be eliminated, and data processing time can be reduced.

[0065] However, the effects that can be achieved through the embodiments of this disclosure are not limited to the effects described above, and those skilled in the art will clearly understand other technical effects not described herein by reviewing this disclosure.

Claims

1. A method for analyzing a slurry, executed by a processor of a slurry pressurization and filtration device, the method comprising: The cumulative discharge of the slurry of active material from the secondary battery is collected at preset time intervals; The hourly discharge rate of the slurry is calculated by using the cumulative discharge rate of the slurry at a previous time and the cumulative discharge rate of the slurry at the current time. The state information of the slurry is classified based on the cumulative discharge amount and the hourly discharge amount of the slurry; as well as Based on the classification of the state information of the slurry, the discharge rate, which represents the flow characteristics and dispersion state of the slurry, is obtained as an evaluation feature value.

2. The method according to claim 1, wherein, The collection of the cumulative discharge of the slurry includes: collecting the cumulative discharge of the slurry after passing through a filter following the application of a preset pressure from at least one selected from a flow meter and a load unit.

3. The method according to claim 1, further comprising: After the calculation of the hourly discharge rate of the slurry, a first graph is generated by plotting the cumulative discharge rate of the slurry on the X-axis and plotting the hourly discharge rate of the slurry corresponding to the X-axis on the Y-axis.

4. The method according to claim 1, wherein, The classification of the state information of the slurry includes: classifying the state information of the slurry corresponding to the cumulative discharge amount and the hourly discharge amount of the slurry by using a deep learning model based on unsupervised learning, wherein the deep learning model based on unsupervised learning is pre-trained to classify the state information of the slurry by inputting the cumulative discharge amount and the hourly discharge amount of the slurry.

5. The method according to claim 4, wherein, The state information of the slurry is classified into normal values ​​and abnormal values, and The method further includes: after classifying the state information of the slurry, removing the outliers from the state information of the slurry.

6. The method according to claim 1, wherein, The conclusions drawn from the evaluation feature values ​​include: The hourly discharge rate of the slurry is calculated by using the hourly discharge rate of the slurry and a first reference value representing the hourly discharge rate corresponding to the cumulative discharge rate selected from the cumulative discharge rate of the slurry. A second graph is generated by plotting the cumulative discharge volume of the slurry on the X-axis and the hourly discharge rate of the slurry corresponding to the X-axis on the Y-axis; and The hourly discharge rate of the slurry, corresponding to a second reference value representing the maximum cumulative discharge on the second graph, is determined as the evaluation characteristic value.

7. The method of claim 6, further comprising: Before calculating the hourly discharge rate of the slurry, outliers are removed from the results of classifying the state information of the slurry, and normal values ​​are applied.

8. A computer-readable recording medium having a program recorded thereon, the program causing the method according to any one of claims 1 to 7 to be executed on a computer.

9. A slurry pressurization and filtration device, comprising: One or more processors; as well as A memory, operatively connected to the one or more processors and configured to store at least one piece of code executed by the one or more processors. The memory is configured to store the at least one piece of code to enable the one or more processors to: The cumulative discharge of the slurry of active material from the secondary battery is collected at preset time intervals; The hourly discharge rate of the slurry is calculated by using the cumulative discharge rate of the slurry at a previous time and the cumulative discharge rate of the slurry at the current time. Based on the cumulative discharge rate and the hourly discharge rate of the slurry, the state information of the slurry is classified; and Based on the classification of the state information of the slurry, the discharge rate, which represents the flow characteristics and dispersion state of the slurry, is obtained as an evaluation feature value.

10. The slurry pressurization and filtration equipment according to claim 9, wherein, The memory is configured to store the at least one code such that, when collecting the cumulative discharge of the slurry, the one or more processors collect the cumulative discharge of the slurry after passing through the filter following the application of a preset pressure from at least one selected from a flow meter and a load unit.

11. The slurry pressurization and filtration equipment according to claim 9, wherein, The memory is configured to store the at least one code such that, after calculating the hourly discharge rate of the slurry, the one or more processors generate a first graph by plotting the cumulative discharge rate of the slurry on the X-axis and plotting the hourly discharge rate of the slurry corresponding to the X-axis on the Y-axis.

12. The slurry pressurization and filtration equipment according to claim 9, wherein, The memory is configured to store the at least one code such that, when classifying the state information of the slurry, the one or more processors classify the state information of the slurry corresponding to the cumulative discharge amount and the hourly discharge amount of the slurry by using a deep learning model based on unsupervised learning, the deep learning model based on unsupervised learning being pre-trained to classify the state information of the slurry by inputting the cumulative discharge amount and the hourly discharge amount of the slurry.

13. The slurry pressurization and filtration equipment according to claim 12, wherein, The state information of the slurry is classified into normal values ​​and abnormal values, and The memory is configured to store the at least one code so that the one or more processors remove the outlier from the state information of the slurry after classifying the state information of the slurry.

14. The slurry pressurization and filtration equipment according to claim 9, wherein, The memory is configured to store the at least one code, so that the one or more processors: When deriving the evaluation feature value: The hourly discharge rate of the slurry is calculated by using the hourly discharge rate of the slurry and a first reference value representing the hourly discharge rate corresponding to the cumulative discharge rate selected from the cumulative discharge rate of the slurry. A second graph is generated by plotting the cumulative discharge volume of the slurry on the X-axis and the hourly discharge rate of the slurry corresponding to the X-axis on the Y-axis; and The hourly discharge rate of the slurry, corresponding to a second reference value representing the maximum cumulative discharge on the second graph, is determined as the evaluation characteristic value.

15. The slurry pressurization and filtration equipment according to claim 14, wherein, The memory is configured to store the at least one code such that the one or more processors remove outliers from the results of classifying the state information of the slurry and apply normal values ​​before calculating the hourly discharge rate of the slurry.

Images