An electronic device for embodying a quality prediction and control system of a polymer and a control method thereof

Abstract

An electronic device for implementing a quality prediction and control system is disclosed. The electronic device includes a communication interface, a memory storing a trained neural network model and process history information of a polymer manufacturing device, and one or more processors that, when process information corresponding to a second time point is received from a polymer manufacturing device through the communication interface, identify predicted process information corresponding to a third time point a preset time after the second time point based on the process history information and the process information corresponding to the second time point, input the received process information corresponding to the second time point and the identified predicted process information corresponding to the third time point into the trained neural network model to obtain predicted quality information of the polymer corresponding to the third time point, and provide guide information including the obtained predicted quality information.

Description

Technical Field

[0001] The present disclosure relates to an electronic device and a control method for implementing a quality prediction and control system of a polymer, and more particularly to an electronic device and a control method for predicting the quality of a polymer using preprocessed data and a learned neural network model.

Background Art

[0002] With the development of electronic technology, various types of electronic devices have been developed and popularized, and technological development of electronic devices that provide services to users and the like has become active.

[0003] On the other hand, a polymer means a macromolecule in which one or more monomers are repeatedly linked. The polymer manufacturing process according to the present disclosure is a process of subjecting a catalyst, ethylene, octene, or butene corresponding to a monomer to a polymerization reaction to obtain polyethylene, which is a polymer, for example, POE (Polyolefin Elastomer). Polymers are classified into product groups according to their melting point and density, and the melting index or density is an index that is affected by the amount of raw materials input into the manufacturing process, the ratio of raw materials, or the reaction temperature, and represents the quality of the polymer.

[0004] On the other hand, the quality and yield of the produced polymer obtained through a chemical reaction between monomers can vary due to disturbances that are impossible to control and measure. For example, due to the characteristics of the polymerization reaction, even when the same conditions or the same raw materials are input, the melting index and density of the obtained polymer can be different. Also, in the case of a recovery process for raw materials that have not reacted, since the amount of raw materials re-input into the reaction is not measured, there is a problem that it is difficult to predict the exact quality of the obtained polymer.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure is for solving the above-described problems, and provides an electronic device that preprocesses information on a polymer manufacturing process, inputs the preprocessed information into a learned neural network model, and accurately predicts the quality of a polymer generated thereby, and a control method therefor.

Means for Solving the Problems

[0006] An electronic device for implementing a quality prediction and control system according to an embodiment of the present disclosure may include a communication interface, a memory storing a learned neural network model and process history information of a polymer manufacturing apparatus, and one or more processors that, when process information corresponding to a second time point is received from the polymer manufacturing apparatus through the communication interface, identify prediction process information corresponding to a third time point after a preset time has elapsed from the second time point based on the process history information and the process information corresponding to the second time point.

[0007] The one or more processors may input the received process information corresponding to the second time point and the identified prediction process information corresponding to the third time point into the learned neural network model to obtain prediction quality information of the polymer corresponding to the third time point.

[0008] The one or more processors may provide guide information including the obtained prediction quality information.

[0009] A control method of an electronic device for implementing a quality prediction and control system according to an embodiment of the present disclosure may include identifying prediction process information corresponding to a third time point after a preset time has elapsed from a second time point based on process history information of a polymer manufacturing apparatus and the process information corresponding to the second time point when the process information corresponding to the second time point is received from the polymer manufacturing apparatus.

[0010] The control method may include a step of inputting the received process information corresponding to the second time point and the predicted process information corresponding to the identified third time point into a learned neural network model to obtain predicted quality information of the polymer corresponding to the third time point.

[0011] The control method may include a step of providing guide information including the obtained predicted quality information.

[0012] When executed by a processor of an electronic device for implementing a quality prediction and control system according to an embodiment of the present disclosure, in a non-transitory computer-readable recording medium storing computer instructions for causing the electronic device to perform operations, the operations include: when process information corresponding to a second time point is received from a polymer manufacturing device, identifying predicted process information corresponding to a third time point after a preset time has elapsed from the second time point based on the process history information of the polymer manufacturing device and the process information corresponding to the second time point.

[0013] The operations may include a step of inputting the received process information corresponding to the second time point and the predicted process information corresponding to the identified third time point into a learned neural network model to obtain predicted quality information of the polymer corresponding to the third time point.

[0014] The operations may include a step of providing guide information including the obtained predicted quality information.

Advantages of the Invention

[0015] According to the above-described example, the quality of the polymer obtained through the polymer manufacturing process can be accurately predicted, and guide information can be provided to the user based on the predicted quality.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0017] Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings.

[0018] The terms used in this specification will be briefly explained, and the present disclosure will be specifically described.

[0019] In the embodiments of the present disclosure, while considering the functions in the present disclosure, general terms that are widely used at present are selected as much as possible. However, this may change due to the intentions or precedents of those skilled in the art, the emergence of new technologies, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning thereof will be described in detail in the corresponding description part of the disclosure. Therefore, the terms used in the present disclosure should not be simply the names of terms, but should be defined based on the meaning of the terms and the overall content of the present disclosure.

[0020] In this specification, expressions such as "have", "be able to have", "include" or "be able to include" indicate the existence of the corresponding features (for example, components such as numerical values, functions, operations, or parts), and do not exclude the existence of additional features.

[0021] The expression "at least one of A or / and B" should be understood to indicate any one of "A" or "B" or "A and B".

[0022] Expressions such as "first", "second", "firstly" or "secondly" used in this specification can modify various components regardless of order and / or importance, and are only used to distinguish one component from another component, and do not limit the corresponding component.

[0023] When it is mentioned that a certain component (for example, the first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (for example, the second component), it should be understood that a certain component can be directly coupled to another component or can be coupled through another component (for example, the third component).

[0024] The singular forms include plural referents unless the context clearly dictates otherwise. In the present disclosure, terms such as "including" or "comprising" are intended to specify the presence of the stated features, numbers, steps, actions, components, parts, or combinations thereof, without precluding the presence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0025] In the present disclosure, a "module" or a "unit" performs at least one function or operation and can be implemented in hardware, software, or a combination of hardware and software. Also, multiple "modules" or multiple "units" can be integrated into at least one module and implemented by at least one processor (not shown), except for a "module" or a "unit" that needs to be implemented by specific hardware.

[0026] An electronic device according to an embodiment of the present disclosure can include an artificial intelligence model (or an artificial neural network model or a learning network model) composed of at least one neural network layer. The artificial neural network can include a deep neural network (DNN), for example, a CNN (Convolutional Neural Network), an RNN (Recurrent Neural Network), an RBM (Restricted Boltzmann Machine), a DBN (Deep Belief Network), a BRDNN (Bidirectional Recurrent Deep Neural Network), or a deep Q-network (Deep Q-Networks), etc., but is not limited to the above examples.

[0027] In addition, in this specification, a "parameter" is a value used in the calculation process of each layer constituting a neural network, and can include, for example, a weight value used when applying an input value to a predetermined arithmetic expression. Also, a parameter can be expressed in matrix form. A parameter is a value set as a result of training and can be updated through separate training data as needed.

[0028] On the other hand, the parameter described below means a variable corresponding to at least one Layer constituting a neural network model and at least one node included in the Layer.

[0029] FIG. 1 is a drawing for schematically explaining a control method of an electronic device according to an embodiment.

[0030] According to FIG. 1, according to an embodiment, when raw materials are input into the polymer manufacturing apparatus 10, a polymer (production product) can be produced based on this. The polymer manufacturing apparatus 10 can be composed of a plurality of manufacturing units including an input unit, a reaction unit, a moving unit, a molding unit, a recovery unit, and a purification unit. On the other hand, the polymer manufacturing apparatus 10 can include a sensor 10-1 indicating a plurality of states, and the sensor 10-1 can be included in each of the plurality of manufacturing units.

[0031] According to an embodiment, the sensor 10-1 can acquire information on the amount and ratio of raw materials of a plurality of types of input raw materials (for example, hydrogen, catalyst, butene, octene, etc.) input into the polymer manufacturing apparatus 10. Also, information on the process state of the polymer manufacturing apparatus 10, for example, at least one of information on the pressure temperature, flow rate, and power consumption of the manufacturing unit of the polymer manufacturing apparatus 10 can be acquired. Alternatively, the sensor 10-1 can also acquire information on the polymer produced by the polymer manufacturing apparatus 10.

[0032] On the one hand, according to one embodiment, the electronic device 100 can receive information acquired through sensors and predict the quality of polymers produced at a preset time based on the received information. Here, the quality can be, for example, the MI (Melting Index), density, or MFR (Melt flow index) type of the produced polymer.

[0033] In the following, various embodiments regarding a method of preprocessing information generated in the polymer manufacturing process and inputting the preprocessed information into a learned neural network model to accurately predict the quality of polymers produced by the polymer manufacturing apparatus 10 will be described.

[0034] FIG. 2 is a block diagram showing the configuration of an electronic device according to one embodiment.

[0035] According to FIG. 2, the electronic device 100 can include a communication interface 110, a memory 120, and one or more processors 130.

[0036] According to one embodiment, the electronic device 100 can be implemented as a device that processes data like a server and performs communication with external devices, but is not limited thereto. For example, the electronic device 100 can be implemented as various devices such as a smart TV, a tablet, a monitor, a smartphone, a desktop computer, a laptop computer, etc. The electronic device 100 according to one embodiment of the present disclosure is not limited to the aforementioned devices, and the electronic device 100 can be implemented as an electronic device 100 having two or more functions of the aforementioned devices.

[0037] On the other hand, the electronic device 100 can communicate and connect with external devices and external servers in various ways. According to one embodiment, a communication module for communication with external devices and external servers can be identically implemented. For example, the electronic device 100 can communicate with an external device using a Bluetooth (registered trademark) module, and the external server can also communicate using the Bluetooth module in the same way.

[0038] According to other embodiments, the communication module for communication with an external device and an external server may be implemented separately. For example, the electronic device 100 may communicate with an external device using a Bluetooth module and communicate with an external server using an Ethernet (registered trademark) modem or a Wi-Fi module.

[0039] On the other hand, the external device may be implemented by at least one of the polymer manufacturing apparatus 10 or the control engine for controlling the polymer manufacturing apparatus 10, but is not limited thereto.

[0040] The communication interface 110 can input and output various types of data. For example, the communication interface 110 can transmit and receive various types of data with an external device (e.g., a source device), an external storage medium (e.g., a USB memory), and an external server (e.g., a web hard) through communication methods such as Wi-Fi (Wireless LAN network) based on an AP, Bluetooth, Zigbee (registered trademark), wired / wireless LAN (Local Area Network), WAN (Wide Area Network), Ethernet, IEEE 1394, HDMI (registered trademark) (High-Definition Multimedia Interface), USB (Universal Serial Bus), MHL (Mobile High-Definition Link), AES / EBU (Audio Engineering Society / European Broadcasting Union), Optical, Coaxial, etc.

[0041] In one example, the communication interface 110 can include a BLE (Bluetooth Low Energy) module. BLE means a Bluetooth technology that can transmit and receive low-power and low-capacity data in the 2.4 GHz frequency band with a reach radius of about 10 m. However, it is not limited thereto, and the communication interface 110 may include a Wi-Fi communication module. That is, the communication interface 110 can include at least one of a BLE (Bluetooth Low Energy) module or a Wi-Fi communication module.

[0042] In one example, the communication interface 110 can utilize different communication modules to communicate with external devices such as a remote control device and an external server. For example, the communication interface 110 can utilize at least one of an Ethernet module or a Wi-Fi module to communicate with an external server, and may utilize a Bluetooth module to communicate with an external device such as a remote control device. However, this is only one embodiment, and when the communication interface 110 communicates with a plurality of external devices or external servers, it can utilize at least one communication module among various communication modules.

[0043] In one embodiment, one or more processors 130 can receive process information from the polymer manufacturing apparatus 10 through the communication interface 110.

[0044] The memory 120 can store data necessary for various embodiments. The memory 120 may be embodied in the form of a memory embedded in the electronic device 100 or in the form of a detachable memory for the electronic device 100 according to the storage purpose of the data. For example, in the case of data for driving the electronic device 100, it may be stored in a memory embedded in the electronic device 100, and in the case of data for an extended function of the electronic device 100, it may be stored in a detachable memory for the electronic device 100.

[0045] On the one hand, in the case of the memory embedded in the electronic device 100, it can be implemented by at least one of a volatile memory (e.g., DRAM (dynamic RAM), SRAM (static RAM), or SDRAM (synchronous dynamic RAM), etc.), a non-volatile memory (e.g., OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash, etc.), hard drive, or solid state drive (SSD)). Also, in the case of the memory detachable from the electronic device 100, it can be implemented in forms such as a memory card (e.g., CF (compact flash), SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.), an external memory connectable to a USB port (e.g., USB memory), etc.

[0046] On the other hand, according to one embodiment, the memory 120 may store the learned neural network model and the process history information of the polymer manufacturing apparatus. Here, the process history information can include, for example, the amount of input raw materials input into the polymer manufacturing apparatus 10, the amount of produced polymer produced by the polymer manufacturing apparatus 10, and the history information regarding the process state of the polymer manufacturing apparatus 10. For example, the process history information can include the input raw material information, the produced polymer information, the process state information, and the quality information regarding the produced polymer corresponding to each of a plurality of time points before the second time point.

[0047] On the one hand, the learned neural network model is a neural network model learned to output quality information when process history is input. This will be described in detail through FIG. 4.

[0048] One or more processors 130 (hereinafter referred to as processors) are electrically connected to the communication interface 110 and the memory 120 to control the overall operation of the electronic device 100. The processor 130 may be composed of one or more processors. Specifically, the processor 130 can perform the operations of the electronic device 100 according to various embodiments of the present disclosure by executing at least one instruction stored in the memory 120.

[0049] According to an embodiment, the processor 130 may be implemented as a digital signal processor (DSP), a microprocessor, a GPU (Graphics Processing Unit), an AI (Artificial Intelligence) processor, an NPU (Neural Processing Unit), or a TCON (Time controller) that processes digital video signals. However, it is not limited thereto, and may include one or more of a central processing unit (CPU), an MCU (Micro Controller Unit), an MPU (micro processing unit), a controller, an application processor (AP), or a communication processor (CP), or may be defined by the corresponding terms. Further, the processor 130 may be implemented as a SoC (System on Chip) or an LSI (large scale integration) having a built-in processing algorithm, or may be implemented in the form of an ASIC (application specific integrated circuit) or an FPGA (Field Programmable gate array).

[0050] According to an embodiment, the processor 130 may be implemented as a digital signal processor (DSP), a microprocessor, or a TCON (Time controller). However, the present invention is not limited thereto, and may include one or more of a central processing unit (CPU), a microcontroller unit (MCU), a microprocessing unit (MPU), a controller, an application processor (AP), or a communication processor (CP), or may be defined by the corresponding terms. Further, the processor 130 may be implemented as a system on chip (SoC) or a large scale integration (LSI) having a built-in processing algorithm, or may be implemented in the form of a field programmable gate array (FPGA).

[0051] According to an embodiment, the processor 130 may receive process information corresponding to a second point in time from a polymer manufacturing apparatus 10 (not shown) through the communication interface 110.

[0052] In one example, the second time point can be, but is not limited to, the current time point. The process information can include at least one of the input raw material information input into the polymer manufacturing apparatus 10, the production polymer information produced (or acquired) by the polymer manufacturing apparatus 10, and information regarding the process state of the polymer manufacturing apparatus 10. Here, the input raw material information means the amount of raw material input into the polymer manufacturing apparatus 10 during a preset time interval, and the production polymer information means the amount of polymer produced by the polymer manufacturing apparatus 10 during a preset time interval. The information regarding the process state can include, but is not limited to, information regarding the flow rate of the compound present in the polymer manufacturing apparatus 10, the power consumption of at least one control unit included in the manufacturing apparatus, the temperature of the manufacturing apparatus, and the pressure within the manufacturing apparatus.

[0053] In one example, the process information corresponding to the second time point can include the input raw material information input into the polymer manufacturing apparatus 10 during a preset time interval from the second time point, the production polymer information produced by the polymer manufacturing apparatus 10 during a preset time interval from the second time point, and the process state information of the polymer manufacturing apparatus 10 at the second time point.

[0054] According to one embodiment, the processor 130 can identify predicted process information corresponding to a third time point after a preset time has elapsed from the second time point based on the process history information and the process information corresponding to the second time point.

[0055] The process history information means the history information regarding the processes before the second time point performed by the polymer manufacturing apparatus 10. In one example, it can include the amount of input raw material input into the polymer manufacturing apparatus 10 (not shown), the amount of polymer produced by the polymer manufacturing apparatus 10 (not shown), and the history information before the second time point regarding the process state of the polymer manufacturing apparatus 10 (not shown). The predicted process information means the process information at the third time point predicted based on the process history information and the process information corresponding to the second time point. This will be described in detail through FIG. 4.

[0056] According to one embodiment, the processor 130 can input the process information corresponding to the received second time point and the predicted process information corresponding to the identified third time point into the learned neural network model to obtain the predicted quality information of the polymer corresponding to the third time point. Here, the quality information refers to information regarding the quality of the produced polymer obtained by the polymer manufacturing apparatus 10. According to one example, the quality information can include at least one of information regarding the MI (Melting Index) value, the Density value, or the MFR (Melt flow index) value of the produced polymer.

[0057] According to one example, when the learned neural network model receives the process information corresponding to the second time point and the predicted process information corresponding to the third time point as input, it can obtain the predicted quality information of the polymer corresponding to the third time point. Here, the predicted quality information can include at least one of information regarding the MI (Melting Index) value, the Density value, or the MFR (Melt flow index) value of the polymer produced by the polymer manufacturing apparatus 10 at the third time point after a preset time has elapsed from the second time point.

[0058] According to one embodiment, the processor 130 can provide guide information including the obtained predicted quality information. According to one example, the guide information can be information for guiding such that the predicted quality at the third time point becomes equal to or greater than a preset value when the predicted quality at the third time point is less than the preset value based on the predicted quality information, but is not limited thereto. The method of providing the guide information will be described in detail through FIGS. 6 to 9.

[0059] FIG. 3 is a flowchart for explaining a control method of an electronic device according to one embodiment.

[0060] According to FIG. 3, according to one embodiment, the control method can identify whether process information corresponding to a second time point is received from a polymer manufacturing apparatus (S310). According to an example, the processor 130 can receive process information corresponding to the second time point of the polymer manufacturing apparatus 10 from at least one of an external device (not shown), such as the polymer manufacturing apparatus 10 or an external server (not shown), through the communication interface 110.

[0061] Subsequently, according to one embodiment, when the process information is received (Y), the control method can identify predicted process information corresponding to a third time point after a preset time has elapsed from the second time point based on the process history information of the polymer manufacturing apparatus 10 and the process information corresponding to the second time point (S320).

[0062] According to an example, first, the processor 130 can obtain process information including input raw material information and produced polymer information corresponding to each of a plurality of time points before the second time point based on the process history information. Subsequently, according to an example, the processor 130 can obtain relationship information between the input raw material information and the produced polymer information by using a statistical analysis application stored in the memory 120. Here, the relationship information can be a mathematical formula corresponding to the relationship between the input raw material information and the produced polymer information obtained by using a regression analysis model. Subsequently, the processor 130 can obtain predicted produced polymer information at the third time point based on the input raw materials at the second time point based on the obtained relationship information.

[0063] However, without being limited thereto, it goes without saying that the processor 130 can also obtain relationship information among the input raw materials, the process state, and the produced polymer information by using a statistical analysis application, and obtain predicted produced polymer information at the third time point based on this.

[0064] Alternatively, by way of example, the processor 130 can obtain predicted input raw material information, predicted process state information, and predicted production polymer information corresponding to the third time point based on the process history information. For example, the processor 130 can use a statistical analysis application to obtain trend information for the input raw material information, the process state information, and the production polymer information respectively. Here, the trend information can be a mathematical formula obtained using a regression analysis model. The processor 130 may obtain predicted input raw material information, predicted process state information, or predicted production polymer information corresponding to the third time point based on the obtained trend information and the process information corresponding to the second time point.

[0065] Continuing, according to one embodiment, the control method can input the received process information corresponding to the second time point and the identified predicted process information corresponding to the third time point into the learned neural network model to obtain predicted quality information of the polymer corresponding to the third time point (S330).

[0066] By way of example, the processor 130 can input the input raw material information at the second time point, the process state information at the second time point, and the obtained predicted production polymer information at the third time point into the learned neural network model to obtain predicted quality information for the production polymer at the third time point.

[0067] Continuing, according to one embodiment, the control method can provide guide information including the obtained predicted quality information (S340). By way of example, the electronic device 100 can further include a display (not shown), and the processor 130 can display a UI including the guide information through the display.

[0068] According to the above-described example, a preprocessing process for the obtained process information can be performed, and the preprocessed process information can be input into the learned neural network model to obtain predicted process information. Accordingly, the quality of the polymer obtained through the polymer manufacturing process can be accurately predicted, and guide information can be provided to the user based on the predicted quality.

[0069] FIG. 4 is a drawing for explaining a method of acquiring prediction quality information according to an embodiment.

[0070] According to FIG. 4, first, according to an embodiment, the control method can identify predicted production polymer information at a third time point by using process history information, input raw material information corresponding to a second time point, production polymer information corresponding to the second time point, and process state information corresponding to the second time point (S410).

[0071] According to an example, first, the processor 130 can acquire process information including input raw material information and production polymer information corresponding to each of a plurality of time points before the second time point based on the process history information stored in the memory 120. Subsequently, according to an example, the processor 130 can acquire relationship information among the input raw material information, production state information, and production polymer information by using a statistical analysis application stored in the memory 120. Here, the relationship information can be a mathematical formula obtained by using a regression analysis model. Subsequently, the processor 130 can acquire predicted production polymer information at a third time point based on the input raw material at the second time point based on the acquired relationship information.

[0072] For example, the processor 130 can input the input raw material information and production state information at the second time point into the mathematical formula included in the acquired relationship information to acquire predicted production polymer information at a third time point.

[0073] Subsequently, according to an embodiment, the control method can input the input raw material information corresponding to the second time point, the process state information corresponding to the second time point, and the identified predicted production polymer information at the third time point into a learned neural network model to acquire predicted quality information corresponding to the third time point (S420).

[0074] Here, the neural network model can be a neural network model that is trained to output predicted quality information when input with process information including input raw material information, production polymer information, and process state information, and predicted production polymer information. By way of example, a dataset including input raw material information at the n-th time point, process state information at the n-th time point, and production polymer information at the (n + 1)-th time point resulting therefrom can be input as training data into the neural network model to train the neural network model. In this case, the dataset can include a label corresponding to the quality information of the polymer produced at the (n + 1)-th time point.

[0075] On the other hand, the artificial neural network (or neural network model) according to an embodiment of the present disclosure can include a deep neural network (DNN: Deep Neural Network), for example, CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), or deep Q-networks, etc., but is not limited to the examples described above.

[0076] However, it is not limited thereto. By way of example, the neural network model trained thereby is also a neural network model trained to output predicted quality information when input with process information including input raw material information, production polymer information, and process state information. That is, even without input of the predicted production polymer information, it may receive input of the process information including the input raw material information, production polymer information, and process state information and output the predicted quality information.

[0077] On the one hand, according to one embodiment, the processor 130 can use the process history information to train a neural network model. By way of example, the processor 130 can parse the process information and quality information corresponding to each of a plurality of time points before the second time point included in the process history information to obtain a dataset for training the neural network model, and it goes without saying that the obtained dataset can be used as training data to train the neural network model. In this case, the label of each dataset can be the quality information of the produced polymer.

[0078] FIG. 5 is a drawing for explaining a method of identifying prediction process information according to one embodiment.

[0079] According to one embodiment, the control method can first obtain the input raw material information and process state information corresponding to the first time point before a preset time from the second time point based on the process history information stored in the memory 120 (S510). That is, when a preset time elapses from the first time point, the second time point is reached, and when a preset time elapses from the second time point, the third time point can be reached. However, it is not limited thereto.

[0080] Subsequently, according to one embodiment, the control method can update the input raw material information corresponding to the second time point and the process state information corresponding to the second time point by using the input raw material information and process state information corresponding to the first time point and the production polymer information corresponding to the second time point (S520).

[0081] By way of example, the processor 130 can obtain the input raw material information and process state information in which the accumulated processes before the second time point are reflected based on the input raw material information, process state information, and production polymer information corresponding to each of a plurality of time points included in the process history information.

[0082] For example, assuming that the input raw material corresponding to the nth time point is 1 and there is no disturbance, consider the case of a process where the amount of the polymer produced at the (n + 1)th time point due to the input raw material at the nth time point is 2 (where n is an integer). When the processor 130 identifies based on the process history information that the input raw material corresponding to the first time point is 1 and the amount of the polymer produced corresponding to the second time point is 1.8 (i.e., only 90% of the input raw material is produced as the polymer), accordingly, it can identify that the amount of the recovered raw material is 10% of the total input amount, and accordingly, update the amount of the input raw material at the second time point to 1.1. Subsequently, when the updated input raw material information and process state information at the second time point are identified, the processor 130 can identify the predicted polymer information at the third time point by using the obtained relationship information.

[0083] However, not limited thereto, it goes without saying that the updated value of the input raw material corresponding to the first time point can be identified by the processes corresponding to a plurality of time points before the first time point, and accordingly, the amount of the input raw material and the process state information at the second time point can be updated to different values.

[0084] Subsequently, according to one embodiment, the control method can identify prediction process information including predicted polymer information at the third time point by using the updated input raw material information and the updated process state information (S530).

[0085] According to one example, the processor 130 can identify prediction process information including predicted polymer information at the third time point by using the process information obtained based on the process information and the process history information including the updated input raw material information and the process state information at the second time point.

[0086] According to the example described above, the data input to the neural network model learned by reflecting the accumulated process history information can be updated, and the updated data can be input to the learned neural network model to predict a more accurate quality.

[0087] FIG. 6 is a drawing for explaining a method of acquiring guide information according to an embodiment.

[0088] According to FIG. 6, according to an embodiment, the control method can identify whether there is a difference between the predicted quality information obtained based on the target value information corresponding to each of a plurality of quality types stored in the memory 120 and the target value that is greater than or equal to a preset value (S610).

[0089] In one example, the memory 120 may store information on the target values corresponding to each of the plurality of quality types. The processor 130 can compare the predicted quality information obtained through the neural network model with the target values stored in the memory 120 to identify whether there is a difference between the predicted quality information obtained and the target value that is greater than or equal to a preset value. For example, at least one of the information on the MI (Melting Index) value, density value, or MFR (Melt flow index) value of the production polymer included in the predicted quality information is compared with the corresponding value of the MI (Melting Index) target value, density target value, or MFR (Melt flow index) target value of the production polymer stored in the memory 120 to identify whether there is a difference between the predicted quality information obtained and the target value that is greater than or equal to a preset value.

[0090] Subsequently, the processor 130 can acquire guide information for guiding the predicted quality information and the target value to have a difference less than a preset value based on the priority information of the raw materials corresponding to each of the plurality of quality types included in the quality information stored in the memory 120 (S620).

[0091] In one example, the memory 120 may store the priority information of the raw materials corresponding to each quality type. For example, the highest priority corresponding to MI may be a catalyst, and the highest priority corresponding to density may be the ratio of butene to ethylene.

[0092] In one example, when the predicted MI value has a difference greater than or equal to a preset value from the target value, the processor 130 can identify the amount of catalyst for causing the difference between the MI value and the target value to be less than the preset value, and can obtain guide information including information on the identified amount of catalyst.

[0093] In this case, in one example, the memory 120 may store in advance information on the change in quality due to the change in the unit input amount corresponding to each of a plurality of raw material types, and the processor 130 can identify guide information for causing the predicted quality value to have a difference less than the preset value from the target value based on the information stored in the memory 120.

[0094] However, without being limited thereto, the processor 130 may obtain guide information corresponding to each of a plurality of types of quality information predicted using the learned neural network model. This will be described in detail through FIG. 7.

[0095] Subsequently, according to one embodiment, the control method can provide a UI including the obtained guide information (S630). In one example, the UI can include process information corresponding to the second time point, process history information, and predicted quality information of the polymer corresponding to the third time point.

[0096] On the other hand, according to one embodiment, the processor 130 can further include a user interface (not shown). When a user input corresponding to the obtained guide information is received through the user interface (not shown), the processor 130 can identify control information corresponding to the received user input and transmit the identified control information to a control engine through the communication interface 110. Here, the control engine means an engine for controlling the polymer manufacturing apparatus 10.

[0097] In one example, after a UI including guide information is provided, when a user input for reducing the catalyst input amount to a preset value is received through the user interface, the processor 130 can identify control information for reducing the catalyst input amount to the preset value and transmit this through the communication interface 110 to the control engine.

[0098] FIG. 7 is a drawing for explaining a method of acquiring guide information according to an embodiment.

[0099] According to one embodiment, first, the control method can identify sub-process information in which the input raw material information among the information included in the process information corresponding to the received second time point is changed (S710). Here, the sub-process information may be process information in which the ratio of the input raw materials is changed by a preset value, but is not limited thereto. According to one example, the sub-process information may be process information in which the process state (for example, the magnitude of the pressure in the polymer manufacturing apparatus 10) is changed.

[0100] Subsequently, according to one embodiment, the control method can identify sub-prediction process information based on the sub-process information (S720).

[0101] Subsequently, according to one embodiment, the control method can input the sub-process information and the sub-prediction process information into a learned neural network model to obtain at least one sub-prediction quality information corresponding to the third time point (S730).

[0102] Subsequently, according to one embodiment, the control method can use the acquired prediction quality information and the acquired at least one sub-prediction quality information to obtain guide information (S740).

[0103] In one example, the processor 130 can obtain guidance information by comparing the obtained prediction quality information and sub-prediction quality information. For example, the processor 130 can compare the obtained sub-prediction quality information and prediction quality information to obtain information on the amount of change in the MI value due to the change in the unit input amount of the catalyst.

[0104] However, not limited thereto, the processor 130 can obtain guidance information through the obtained prediction quality information and sub-prediction quality information using a preset algorithm. The processor 130 can obtain guidance information including the obtained guidance information.

[0105] FIG. 8 is a diagram for explaining a UI providing method according to an embodiment.

[0106] According to FIG. 8, in one example, the processor 130 can provide a UI 800 including process history information. In one example, the processor 130 can provide a UI 800 including information in which input raw material information (for example, the input amount corresponding to each of a plurality of types of raw materials), process state information, and production polymer information corresponding to each of a plurality of time points before the second time point are embodied in a graph form.

[0107] In this case, in one example, the electronic device 100 can further include a display (not shown), and the processor 130 can display the UI through the display (not shown).

[0108] FIG. 9 is a diagram for explaining a UI providing method according to an embodiment.

[0109] According to FIG. 9, in one example, the processor 130 can provide a UI 900 including guidance information including prediction quality information 910 corresponding to the third time point, trend information 920 corresponding to each of a plurality of types of quality, guidance information 930 for control variables, and explanatory function information 940 corresponding to each of a plurality of quality.

[0110] Here, the prediction quality information 910 can include predicted quality information and previous quality information when the current input amount is completed into the production polymer reflecting the latest process state. The trend information 920 can include history information for each of a plurality of qualities. The processor 130 can acquire history information for each of a plurality of qualities based on the process history information. The control variable guidance information 930 can include information for the input amount corresponding to each of a plurality of types of control variables and guidance information corresponding to each of a plurality of types of quality information predicted using the learned neural network model. Alternatively, by way of example, it may include guidance information corresponding to each of a plurality of types of quality information stored in the memory 120. The explanation function information 940 can include information on the target value corresponding to each of a plurality of qualities and the amount of change in the quality value due to the change in the unit input amount of each of the plurality of qualities. In this case, information on the control variable with the highest priority corresponding to each of the plurality of qualities may be included.

[0111] FIG. 10 is a block diagram showing a detailed configuration of an electronic device according to an embodiment.

[0112] According to FIG. 10, the electronic device 100' can include a communication interface 110, a memory 120, one or more processors 130, a microphone 140, a speaker 150, a display 160, a user interface 170, and at least one sensor 180. Regarding the configuration overlapping with the configuration shown in FIG. 2 among the configurations shown in FIG. 10, detailed description will be omitted.

[0113] The microphone 140 may refer to a module that acquires sound and converts it into an electrical signal, and it may be a condenser microphone, a ribbon microphone, a moving coil microphone, a piezoelectric element microphone, a carbon microphone, or a MEMS (Micro Electro Mechanical System) microphone. Further, it may be implemented in an omnidirectional, bidirectional, unidirectional, sub-cardioid, super-cardioid, or hyper-cardioid mode.

[0114] There may be various embodiments in which the electronic device 100’ performs an operation corresponding to the user voice signal received through the microphone 140.

[0115] As an example, the electronic device 100’ can control the display 160 based on the user voice signal received through the microphone 140. For example, when a user voice signal for displaying content A is received, the electronic device 100’ can control the display 160 to display content A.

[0116] As another example, the electronic device 100' can control an external display device connected to the electronic device 100' based on a user voice signal received through the microphone 140. Specifically, the electronic device 100' can provide a control signal for controlling the external display device so that an operation corresponding to the user voice signal is performed on the external display device, and can transmit the provided control signal to the external display device. Here, the electronic device 100' can store a remote control application for controlling the external display device. Then, the electronic device 100' can transmit the provided control signal to the external display device using at least one communication method among Bluetooth, Wi-Fi, or infrared. For example, when a user voice signal for displaying content A is received, the electronic device 100' can transmit a control signal for controlling the external display device so that content A is displayed on the external display device. Here, the electronic device 100' can mean various terminal devices on which a remote control application can be installed, such as a smartphone or an AI speaker.

[0117] As yet another example, the electronic device 100' can use a remote control device to control an external display device connected to the electronic device 100' based on a user voice signal received through the microphone 140. Specifically, the electronic device 100' can transmit a control signal for controlling the external display device so that an operation corresponding to the user voice signal is performed on the external display device to the remote control device. Then, the remote control device can transmit the control signal received from the electronic device 100' to the external display device. For example, when a user voice signal for displaying content A is received, the electronic device 100' transmits a control signal for controlling the external display device so that content A is displayed on the external display device to the remote control device, and the remote control device can transmit the received control signal to the external display device.

[0118] Speaker 150 may include a tweeter for reproducing sounds in the high frequency band, a midrange for reproducing sounds in the mid frequency band, a woofer for reproducing sounds in the low frequency band, a subwoofer for reproducing sounds in the ultra-low frequency band, an enclosure for controlling resonance, a crossover network for separating the frequency of the electrical signal input to the speaker by band, and the like.

[0119] Speaker 150 can output an acoustic signal to the outside of the electronic device 100'. Speaker 150 can output multimedia playback, recording playback, various notification sounds, voice messages, and the like. The electronic device 100' can include an audio output device such as Speaker 150, but can also include an output device such as an audio output terminal. In particular, Speaker 150 can provide the acquired information, the information processed and produced based on the acquired information, the response result or operation result for the user voice, etc. in the form of sound.

[0120] The display 160 may be implemented as a display including a self-emitting element or a display including a non-self-emitting element and a backlight. For example, it may be implemented as various types of displays such as an LCD (Liquid Crystal Display), an OLED (Organic Light Emitting Diodes) display, an LED (Light Emitting Diodes), a micro LED, a Mini LED, a PDP (Plasma Display Panel), a QD (Quantum dot) display, a QLED (Quantum dot light-emitting diodes), etc. A driving circuit, a backlight unit, etc., which may be implemented in the form of an a-si TFT, an LTPS (low temperature poly silicon) TFT, an OTFT (organic TFT), etc., may also be included in the display 160. On the other hand, the display 160 may be implemented as a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display (3D display), a display in which a plurality of display modules are physically connected, etc. The processor 130 may control the display 160 to output the output video obtained according to the various embodiments described above. Here, the output video may be a high-resolution video of 4K or 8K or higher.

[0121] On the other hand, according to another embodiment, the electronic device 100' may not include the display 160. The electronic device 100' may be connected to an external display device and may transmit an image or content stored in the electronic device 100' to the external display device. Specifically, the electronic device 100' may transmit an image or content to the external display device together with a control signal for controlling the image or content to be displayed on the external display device.

[0122] Here, the external display device can be connected to the electronic device 100' through the communication interface 110 or an input / output interface (not shown). For example, the electronic device 100' may not include a display, such as a Set Top Box (STB). Also, the electronic device 100' can include only a small display that can display only simple information such as text information. Here, the electronic device 100' can transmit images or content to the external display device either wired or wirelessly through the communication interface 110, or transmit it to the external display device through an input / output interface (not shown).

[0123] The user interface 170 is a configuration for the electronic device 100' to interact with the user. For example, the user interface 170 can include at least one of a touch sensor, a motion sensor, a button, a Jog dial, a switch, a microphone, or a speaker, but is not limited thereto.

[0124] At least one sensor (180, hereinafter referred to as the sensor) can include a plurality of sensors of various types. The sensor 180 can measure a physical quantity or sense the operating state of the electronic device 100', and convert the measured or sensed information into an electrical signal. The sensor 180 can include a camera, and the camera can include a lens that focuses visible light or other optical signals reflected and received by an object onto an image sensor, and an image sensor that can sense visible light or other optical signals. Here, the image sensor can include a 2D pixel array divided into a plurality of pixels.

[0125] According to the above-described example, it is possible to perform a preprocessing process on the acquired process information and input the preprocessed process information into the learned neural network model to obtain predicted process information. Along with this, it becomes possible to accurately predict the quality of the polymer obtained through the polymer manufacturing process, and it becomes possible to provide guide information to the user based on the predicted quality.

[0126] On the other hand, the methods according to the various embodiments of the present disclosure described above can be implemented in the form of an application that can be installed on an existing electronic device. Or the methods according to the various embodiments of the present disclosure described above can be performed using a learned neural network (or a deeply learned neural network) of a deep learning infrastructure, that is, a learning network model. Also, the methods according to the various embodiments of the present disclosure described above can be implemented only by software upgrade or hardware upgrade for an existing electronic device. Also, the various embodiments of the present disclosure described above may be performed through an embedded server provided in the electronic device or an external server of the electronic device.

[0127] On the one hand, according to an embodiment of the present disclosure, the various embodiments described above can be implemented by software including instruction words stored in a machine-readable storage medium (e.g., a computer). The machine is a device that can call the instruction words stored from the storage medium and can operate according to the called instruction words, and can include a display device (e.g., display device (A)) according to the disclosed embodiment. When the instruction is executed by a processor, the processor can directly or utilize other components under the control of the processor to perform the functions corresponding to the instruction. The instruction can include code provided or executed by a compiler or an interpreter. The machine-readable storage medium can be provided in the form of a non-transitory storage medium. Here, "non-transitory" only means that the storage medium does not include a signal and is tangible, and does not distinguish whether the data is stored semi-permanently or temporarily in the storage medium.

[0128] Also, according to an embodiment, the methods according to the various embodiments described above can be provided included in a computer program product. The computer program product can be traded as a commodity between a seller and a purchaser. The computer program product can be distributed online in the form of a machine-readable storage medium (e.g., compact disc read only memory (CD-ROM)) or through an application store (e.g., Play StoreTM). In the case of online distribution, at least a part of the computer program product can be at least temporarily stored or temporarily provided in a storage medium such as the memory of the manufacturer's server, the application store's server, or a relay server.

[0129] In addition, each of the components (e.g., modules or programs) according to the various embodiments described above may be composed of one or more individuals. Some of the corresponding sub-components among the sub-components described above may be omitted, or other sub-components may be further included in the various embodiments. Generally or additionally, some components (e.g., modules or programs) are integrated into one individual and can perform the functions performed by each of the corresponding components before integration in the same or similar manner. The operations performed by modules, programs, or other components according to the various embodiments may be executed sequentially, in parallel, repeatedly, or heuristically, or at least some of the operations may be executed in a different order, omitted, or other operations may be added.

[0130] The preferred embodiments of the present disclosure have been illustrated and described above. However, the present disclosure is not limited to the specific embodiments described above. It goes without saying that various modifications can be made by those with ordinary knowledge in the technical field to which the present disclosure pertains without departing from the gist of the present disclosure claimed in the claims. Such modifications should not be individually understood from the technical idea and perspective of the present disclosure.

Industrial Applicability

[0131] An electronic device and a control method for implementing a polymer quality prediction and control system as described above can be applied to the field of polymer manufacturing processes.

Claims

1. 1. An electronic device for implementing a quality prediction and control system, Communication interface; a memory storing process history information of the trained neural network model and a polymer manufacturing apparatus, the process history information including input raw material information, produced polymer information, process status information, and quality information for the produced polymer corresponding to a first time point; raw material priority information corresponding to each of a plurality of types of quality information included in the quality information and target value information corresponding to each of the plurality of types of quality information, the plurality of types of quality information including at least one of information on the MI (Melting Index) value, density value, and MFR (Melt flow index) value of the produced polymer; and When process information including input material information, produced polymer information, and process status information corresponding to a second time point is received from the polymer production apparatus through the communication interface, input material information corresponding to the first time point prior to a preset time from the second time point and process status information corresponding to the first time point are acquired based on the process history information; updating the input raw material information corresponding to the second time point and the process status information corresponding to the second time point using input raw material information corresponding to the first time point, process status information corresponding to the first time point, and produced polymer information corresponding to the second time point - updating the input raw material information corresponding to the second time point means reflecting the amount of raw material recovered from the amount of input raw material at the first time point in the amount of input raw material at the second time point -; identifying predicted process information including predicted polymer production information at a third time point a predetermined time after the second time point using the updated input material information and the updated process status information; inputting the updated input material information, the updated process status information, and the predicted polymer production information at the third time point into the trained neural network model to obtain predicted polymer quality information corresponding to the third time point; When the difference between the acquired predicted quality information and the target value is equal to or greater than a preset value, guide information is acquired based on priority order information of the raw material to guide the difference between the acquired predicted quality information and the target value to be less than the preset value; one or more processors for providing a UI including the retrieved guide information; The UI includes: an electronic device including at least one of the process history information, predicted quality information of the polymer corresponding to the third time point, trend information corresponding to each of the plurality of types of quality information, explanatory function information corresponding to each of the plurality of types of quality information, and controlled variable guidance information corresponding to each of the plurality of types of quality information.

2. The process history information includes: The information includes input raw material information, produced polymer information, process status information, and produced polymer quality information corresponding to each of a plurality of time points before the second time point, The trained neural network model is The electronic device of claim 1 , trained to output predicted quality information when process information and predicted produced polymer information, including input raw material information, produced polymer information, and process status information, are input.

3. The UI includes: The electronic device of claim 1 , further comprising process information corresponding to the second point in time.

4. The one or more processors: Identifying sub-process information in which input material information has been changed from information included in the process information corresponding to the received second time point; Identifying sub-predicted process information based on the sub-process information; inputting the sub-process information and the sub-predicted process information into the trained neural network model to obtain at least one sub-predicted quality information corresponding to the third time point; The electronic device of claim 3 , further comprising: an electronic device for acquiring the guide information by utilizing the acquired predicted quality information and the acquired at least one sub-predicted quality information.

5. a user interface; The one or more processors: when a user input corresponding to the acquired guide information is received through the user interface, identifying control information corresponding to the received user input; The electronic device of claim 3 , further comprising: a communication interface configured to transmit the identified control information to a control engine.

6. 1. A method for controlling an electronic device to realize a quality prediction and control system, comprising: storing process history information of a polymer manufacturing apparatus, the process history information including input raw material information, produced polymer information, process status information, and quality information for the produced polymer corresponding to a first time point, raw material priority information corresponding to each of a plurality of types of quality information included in the quality information, and target value information corresponding to each of the plurality of types of quality information in a memory, the plurality of types of quality information including at least one of information on a melting index (MI) value, a density value, and a melt flow index (MFR) value of the produced polymer; When process information including input material information, produced polymer information, and process status information corresponding to a second time point is received from the polymer production apparatus, acquiring input material information corresponding to the first time point, which is a predetermined time before the second time point, and process status information corresponding to the first time point, based on process history information of the polymer production apparatus; updating the input raw material information corresponding to the second time point and the process status information corresponding to the second time point using the input raw material information corresponding to the first time point, the process status information corresponding to the first time point, and the produced polymer information corresponding to the second time point - updating the input raw material information corresponding to the second time point means reflecting the amount of the raw material recovered from the amount of the input raw material at the first time point in the amount of the input raw material at the second time point -; identifying predicted process information including predicted polymer production information at a third time point a predetermined time after the second time point using the updated input material information and the updated process status information; inputting the updated input material information, the updated process status information, and the predicted polymer production information at the third time point into a trained neural network model to obtain predicted polymer quality information corresponding to the third time point; When the difference between the acquired predicted quality information and the target value is equal to or greater than a preset value, acquiring guide information for guiding the difference between the acquired predicted quality information and the target value to be less than the preset value based on priority information of the raw material; and providing a UI including the acquired guide information; The UI includes: the control method including at least one of the process history information, predicted quality information of the polymer corresponding to the third time point, trend information corresponding to each of the plurality of types of quality information, explanatory function information corresponding to each of the plurality of types of quality information, and controlled variable guidance information corresponding to each of the plurality of types of quality information.

7. The process history information includes: The information includes input raw material information, produced polymer information, process status information, and produced polymer quality information corresponding to each of a plurality of time points before the second time point, The trained neural network model is A control method, which is trained to output the predicted quality information according to claim 6 when process information including input raw material information, produced polymer information, and process status information, and predicted produced polymer information are input.

8. The UI includes: The method of claim 6 , further comprising process information corresponding to the second time point.

9. The step of acquiring guide information includes: identifying sub-process information in which input material information has been changed from information included in the process information corresponding to the received second time point; identifying sub-predicted process information based on the sub-process information; inputting the sub-process information and the sub-predicted process information into the trained neural network model to obtain at least one sub-predicted quality information corresponding to the third time point; and The control method of claim 8 , further comprising: obtaining the guide information by using the obtained predicted quality information and the obtained at least one sub-predicted quality information.

10. when a user input corresponding to the obtained guide information is received, identifying control information corresponding to the received user input; and The method of claim 8 , further comprising: transmitting the identified control information to a control engine.

11. A non-transitory computer-readable medium storing computer instructions that, when executed by a processor of an electronic device for implementing a quality prediction and control system, cause the electronic device to perform operations, the operations comprising: storing process history information of a polymer manufacturing apparatus, the process history information including input raw material information, produced polymer information, process status information, and quality information for the produced polymer corresponding to a first time point, raw material priority information corresponding to each of a plurality of types of quality information included in the quality information, and target value information corresponding to each of the plurality of types of quality information in a memory, the plurality of types of quality information including at least one of information on a melting index (MI) value, a density value, and a melt flow index (MFR) value of the produced polymer; When process information including input material information, produced polymer information, and process status information corresponding to a second time point is received from the polymer production apparatus, acquiring input material information corresponding to the first time point, which is a predetermined time before the second time point, and process status information corresponding to the first time point, based on process history information of the polymer production apparatus; updating the input raw material information corresponding to the second time point and the process status information corresponding to the second time point using the input raw material information corresponding to the first time point, the process status information corresponding to the first time point, and the produced polymer information corresponding to the second time point - updating the input raw material information corresponding to the second time point means reflecting the amount of the raw material recovered from the amount of the input raw material at the first time point in the amount of the input raw material at the second time point -; identifying predicted process information including predicted polymer production information at a third time point a predetermined time after the second time point using the updated input material information and the updated process status information; inputting the updated input material information, the updated process status information, and the predicted polymer production information at the third time point into a trained neural network model to obtain predicted polymer quality information corresponding to the third time point; When the difference between the acquired predicted quality information and the target value is equal to or greater than a preset value, acquiring guide information for guiding the difference between the acquired predicted quality information and the target value to be less than the preset value based on priority information of the raw material; and providing a UI including the acquired guide information; The UI includes: a computer readable storage medium comprising at least one of the process history information, predicted quality information for the polymer corresponding to the third time point, trend information corresponding to each of the plurality of types of quality information, explanatory function information corresponding to each of the plurality of types of quality information, and controlled variable guidance information corresponding to each of the plurality of types of quality information.

Images