Electronic device, method for controlling electronic device, and computer-readable recording medium

Abstract

The invention discloses an electronic device, a control method of the electronic device, and a computer readable recording medium. The electronic device is used for realizing a temperature prediction and control system. The electronic device includes: a communication interface; a memory storing the first learning neural network model and the second learning neural network model; and one or more processors that, when receiving process information including input fuel information of the glass melting device through the communication interface, pre-processes the received process information, inputs the pre-processed process information to the first learning neural network model, and inputs the pre-processed process information to the second learning neural network model. Inputting the process information into a first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, and inputting the obtained first predicted temperature information and the process information into a second learning neural network model to obtain second predicted temperature information corresponding to a second position of the glass melting device, guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information is provided.

Description

Technical Field

[0001] The present invention relates to an electronic device for realizing a temperature prediction and control system and a control method thereof. More specifically, the present invention relates to an electronic device for predicting the temperature of the lower end of a glass melting device using a learned neural network model and controlling the fuel fed into the glass melting device based on the predicted temperature and a control method thereof. Background Art

[0002] When glass raw materials are fed from the raw material feeding port (OBC, On Board Charge), the glass melting furnace (or glass melting device) heats the glass water in the melting furnace through a burner (Burner) or an electric booster (Booster) included in the glass melting device. The glass water in the melting furnace is dissolved through the dissolving part.

[0003] On the one hand, there is an appropriate range for the temperature and charging height of the molten glass in the glass melting furnace. In this case, there is a problem that it is difficult to maintain the temperature and charging height of the molten glass due to frequent changes in the amount of dissolution or uncertainty in the water content included in the raw materials. Summary of the invention

[0004] Problem that the invention aims to solve

[0005] The present invention is used to solve the above-mentioned problems. The present invention provides an electronic device and a control method thereof, which predicts the temperature of a specific location in a glass melting device by using a learned neural network model, and provides a user with guidance information for reducing the amount of fuel input while maintaining an appropriate process temperature based on the predicted temperature information.

[0006] Means used to solve problems

[0007] According to one embodiment of the present invention, an electronic device for implementing a temperature prediction and control system may include: a communication interface; a memory storing a first learning neural network model and a second learning neural network model; and one or more processors for preprocessing the received process information when process information including fuel input information of a glass melting device is received through the communication interface.

[0008] The one or more processors may input the pre-processed process information into the first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device.

[0009] The one or more processors may input the acquired first predicted temperature information and the process information into the second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device.

[0010] The one or more processors may provide guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information.

[0011] According to an embodiment of the present invention, a control method of an electronic device for implementing a temperature prediction and control system may include the following steps: when process information including fuel input information of a glass melting device is received, preprocessing the received process information.

[0012] The control method may include the following steps: inputting the preprocessed process information into a first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device.

[0013] The control method may include the step of inputting the acquired first predicted temperature information and the process information into a second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device.

[0014] The control method may include the step of providing guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information.

[0015] A non-transitory computer-readable recording medium according to an embodiment of the present invention stores computer instructions, which, when executed by a processor of an electronic device for implementing a temperature prediction and control system, cause the electronic device to perform actions, wherein the actions may include the following steps: when process information including input fuel information of a glass melting device is received, pre-processing the received process information.

[0016] The action may include the step of inputting the pre-processed process information into a first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device.

[0017] The action may include the step of inputting the acquired first predicted temperature information and the process information into a second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device.

[0018] The action may include the step of providing guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information.

[0019] Effects of the Invention

[0020] According to the present invention, the learned neural network model can be used to predict the internal temperature of the glass melting device and the temperature of the glass water. Based on this, the electronic device 100 can provide the user with guidance information for minimizing the amount of fuel input while keeping the temperature of the glass water within an appropriate range. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. 1 is a diagram schematically illustrating a method for controlling an electronic device according to an embodiment.

[0022] Figure 2 is a block diagram showing a structure of an electronic device according to an embodiment.

[0023] Figure 3 is a flowchart for illustrating a control method of an electronic device according to an embodiment.

[0024] Figure 4 It is a diagram for explaining a first learning neural network model according to an embodiment.

[0025] Figure 5 It is a diagram for explaining a second learning neural network model according to one embodiment.

[0026] Figure 6 It is a diagram for explaining a method for providing guidance information according to an embodiment.

[0027] Figure 7 It is a diagram for explaining a method of acquiring temperature change information according to an embodiment.

[0028] Figure 8 It is a diagram for explaining a method of acquiring temperature change information according to an embodiment.

[0029] 9A to 9D It is a diagram for explaining a method for providing a user interface according to an embodiment.

[0030] Fig.10 It is a diagram for explaining a method of identifying control information and transmitting it to a control engine according to an embodiment.

[0031] Fig.11 is a block diagram showing a detailed structure of an electronic device according to an embodiment.

[0032] Description of Reference Numerals

[0033] Electronics: 100

[0034] Communication interface: 110

[0035] Memory: 120

[0036] More than one processor: 130 DETAILED DESCRIPTION

[0037] Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

[0038] The terms used in this specification are briefly explained, and the present invention is described in detail.

[0039] The terms used in the embodiments of the present invention are currently widely used common terms selected as much as possible in consideration of the effects of the present invention, but the terms can be changed according to the intention of those skilled in the art, precedents or the emergence of new technologies in the field. In addition, the applicant can arbitrarily select some terms in specific cases, and in this case, the meaning of the selected terms will be recorded in detail in the description part of this specification. Therefore, the terms used in the present invention should be defined based on the meaning of the terms and the content of the entire specification, rather than simply the term names.

[0040] In this specification, expressions such as "having", "may have", "including" or "may include" refer to the existence of corresponding features (for example, constituent elements such as values, functions, actions or parts), and do not exclude the existence of additional features.

[0041] The expression at least one of A and / or B should be understood to mean any one of “A”, “B” and “A and B”.

[0042] The expressions "first", "second", "first" or "second" etc. used in this specification may modify various constituent elements regardless of order and / or importance, and are only used to distinguish one constituent element from another rather than to limit the constituent element.

[0043] When referring to a certain component (for example, a first component) being "(operatively or communicatively) connected" or "coupled" to another component (for example, a second component), it should be understood that the certain component is directly connected to the other component or may be connected through another component (for example, a third component).

[0044] Unless otherwise clearly defined in the context, a singular expression includes a plural expression. In this application, the terms "including", "comprising", etc. are used to specify the existence of features, numbers, steps, actions, constituent elements, components or combinations thereof recorded in the specification, and do not preclude the existence or additional possibility of one or more other features, numbers, steps, actions, constituent elements, components or combinations thereof.

[0045] In the present invention, a "module" or "unit" performs at least one function or action, and can be implemented by hardware or software, or by a combination of hardware and software. In addition, in addition to the "module" or "unit" that needs to be implemented by specific hardware, multiple "modules" or multiple "units" can be integrated into at least one module and implemented by at least one processor (not shown).

[0046] An electronic device according to an embodiment of the present invention may 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 may include a deep neural network (DNN: Deep Neural Network), for example, a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN) or a deep Q-network (Deep Q-Networks), etc., but is not limited to the above examples.

[0047] In addition, in this specification, "parameter" is a value used in the calculation process of each layer constituting a neural network, and may include, for example, a weighted value used when an input value is applied to a predetermined calculation formula. In addition, a parameter may be represented in a matrix form. A parameter is a value set as a training result, and may be updated as needed through separate training data.

[0048] Figure 1 FIG. 1 is a diagram schematically illustrating a method for controlling an electronic device according to an embodiment.

[0049] according to Figure 1 According to one embodiment, the glass melting device 1 may include a plurality of fuel input parts, and the plurality of fuel input parts include a plurality of burners 10 and an electric booster 20. The burner 10 is a heat source corresponding to the relatively upper side of the glass melting device 1, and the electric booster 20 is a heat source corresponding to the relatively lower side of the glass melting device 1. According to the amount of fuel input into the burner and the electric booster, the temperature of the glass water included in the glass melting device 1 can be maintained.

[0050] According to one embodiment, the electronic device 100 can obtain predicted temperature information corresponding to a specific position of the glass melting device based on process information of the glass melting device 1, and can provide guidance information for guiding the amount of fuel to be added to multiple fuel introduction parts based on the obtained predicted temperature information.

[0051] Various embodiments are described below for predicting the temperature of a specific location in the glass melting device 1 using a learned neural network model and providing guidance information for reducing the amount of input fuel while maintaining an appropriate process temperature to the user based on the predicted temperature information.

[0052] Figure 2 is a block diagram showing a structure of an electronic device according to an embodiment.

[0053] according to Figure 2 , the electronic device 100 may include a communication interface 110 , a memory 120 and one or more processors 130 .

[0054] According to one embodiment, the electronic device 100 may be implemented by a device that processes data and communicates with external devices, such as a server, but is not limited thereto. For example, the electronic device 100 may be implemented by various devices such as a smart TV, a tablet computer, a monitor, a smart phone, a desktop computer, and a laptop computer. According to one embodiment of the present invention, the electronic device 100 is not limited to the above devices, and the electronic device 100 may be implemented by an electronic device 100 having two or more functions of the above devices.

[0055] On the other hand, the electronic device 100 can communicate with the external device and the external server in various ways. According to one embodiment, the communication module for communicating with the external device and the external server can be implemented in the same manner. For example, the electronic device 100 can communicate with the external device using a Bluetooth module, and can communicate with the external server using a Bluetooth module.

[0056] According to another embodiment, the communication modules for communicating with the external device and the external server may be implemented separately. For example, the electronic device 100 may communicate with the external device using a Bluetooth module, and may communicate with the external server using an Ethernet modem or a Wi-Fi module.

[0057] On the other hand, according to an embodiment, the external device (not shown) may be implemented by the glass melting device 1 , but is not limited thereto.

[0058] The communication interface 110 can input and output various types of data. For example, the communication interface 110 can send 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 network hard disk) through communication methods such as Wi-Fi (wireless local area network) based on AP, Bluetooth, Zigbee, wired / wireless local area network (Local Area Network), wide area network (Wide Area Network), Ethernet, IEEE 1394, High-Definition Multimedia Interface (HDMI), Universal Serial Bus (USB), Mobile High-Definition Link (MHL), Audio Engineering Society / European Broadcasting Union (AES / EBU), optical fiber, coaxial, etc.

[0059] According to an example, the communication interface 110 may include a Bluetooth Low Energy (BLE) module. BLE refers to a Bluetooth technology capable of sending and receiving low-power, low-capacity data on a 2.4 GHz frequency band with a radius of about 10 m. However, without limitation thereto, the communication interface 110 may also include a Wi-Fi communication module. That is, the communication interface 110 may include at least one of a BLE module and a Wi-Fi communication module.

[0060] According to an example, the communication interface 110 may use different communication modules to communicate with an external device such as a remote control device and an external server. For example, the communication interface 110 may use at least one of an Ethernet module and a Wi-Fi module to communicate with an external server, and may use a Bluetooth module to communicate with an external device such as a remote control device. However, this is only an embodiment, and when communicating with multiple external devices or external servers, the communication interface 110 may use at least one communication module among various communication modules.

[0061] The memory 120 can store data required by various embodiments. According to the data storage purpose, the memory 120 can be implemented as a memory form embedded in the electronic device 100, and can also be implemented as a memory form that can be removed from the electronic device 100. For example, in the case of data for driving the electronic device 100, it can be stored in the memory embedded in the electronic device 100, and in the case of data for the expansion function of the electronic device 100, it can be stored in the memory that can be removed from the electronic device 100.

[0062] On the other hand, in the case of a memory embedded in the electronic device 100, it can be implemented by at least one of a volatile memory (e.g., a dynamic random access memory (DRAM), a static random access memory (SRAM), or a synchronous dynamic random access memory (SDRAM), etc.), a non-volatile memory (e.g., a one-time programmable read-only memory (OTPROM), a programmable read-only memory (PROM), an erasable and programmable ROM (EPROM), an electrically erasable and programmable ROM (EEPROM), a mask read-only memory (mask ROM), a flash ROM, a flash memory (e.g., a NAND flash or a NOR flash), etc.), a hard disk drive, or a solid state drive (SSD). In addition, in the case of a memory that can be removed from the electronic device 100, it can be implemented in the form of a memory card (e.g., a compact flash memory). flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (Mini-SD), extreme digital (xD), multi-media card (MMC), etc.), external memory that can be connected to a USB port (for example, USB memory), etc.

[0063] According to one embodiment, the first learning neural network model and the second learning neural network model may be stored in the memory 120. Figure 4 and Figure 5 The first learning neural network model and the second learning neural network model are described in detail.

[0064] One or more processors 130 (hereinafter, processors) are electrically connected to the communication interface 110 and the memory 120 and control the overall action of the electronic device 100. The processor 130 may be composed of one or more processors. Specifically, the processor 130 may perform actions of the electronic device 100 according to various embodiments of the present invention by executing at least one instruction stored in the memory 120.

[0065] According to one embodiment, the processor 130 may be implemented by a digital signal processor (DSP) for processing digital image signals, a microprocessor, a graphics processing unit (GPU), an artificial intelligence (AI) processor, a neural processing unit (NPU), and a time controller (TCON). However, it is not limited thereto, and includes one or more of a central processing unit (CPU), a microcontroller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), and an ARM processor, or may be defined by corresponding terms. In addition, the processor 130 may be implemented by a system on chip (SoC) or a large scale integration (LSI) with a built-in processing algorithm, or may be implemented in the form of an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0066] According to an embodiment, the processor 130 may be implemented by a digital signal processor, a microprocessor, or a time controller. However, it is not limited thereto and may include one or more of a central processing unit, a microcontroller unit, a microprocessing unit, a controller, an application processor, a communication processor, and an ARM processor, or may be defined by corresponding terms. In addition, the processor 130 may be implemented by a system on chip or a large-scale integration with a built-in processing algorithm, or may be implemented in the form of a field programmable gate array.

[0067] According to an embodiment, the processor 130 may receive process information including fuel input information of the glass melting device 1 through the communication interface 110. Here, the process information is information about the overall environment of the glass melting device 1 that performs the glass melting process, and according to an example, the process information may include fuel input information input into the glass melting device 1 for the glass melting process or process status information corresponding to the glass melting device 1.

[0068] According to one example, the input fuel information may include information about the input amount of fuel input in order to perform the glass melting process. According to one example, the input fuel information may include information about the input amount of fuel corresponding to a plurality of fuel input parts included in the glass melting device 1. On the other hand, the process state information corresponding to the glass melting device 1 may include, for example, process environment information about the glass melting device 1. According to one example, the process state information may include at least one of input oxygen amount information input into the glass melting device 1, dissolved amount (or production amount) information dissolved from the glass melting device 1, environmental information around the glass melting device 1, and power information of an electronic booster (ElectronicBooster) included in the glass melting device 1. For example, the environmental information around the glass melting device 1 may include temperature information or humidity information in the glass melting device 1.

[0069] According to an embodiment, when the process information is received, the processor 130 may preprocess the received process information. According to an example, the processor 130 may use a preset algorithm to identify abnormal data (Outlier) among the multiple data included in the received process information, and may obtain the process information from which the identified abnormal data is removed. Alternatively, if the process information corresponding to the preset time interval during the execution of the process is not received, the processor 130 may perform preprocessing by receiving the process information not received from the communication interface 110. However, it is not limited thereto.

[0070] According to one embodiment, the processor 130 may input the preprocessed process information into the first learning neural network model, thereby acquiring first predicted temperature information corresponding to the first position of the glass melting device 1 .

[0071] Here, according to an example, the first position of the glass melting device 1 may be a position corresponding to the relatively upper side (or top plate) of the glass melting device 1. A temperature sensor may be provided at the first position of the glass melting device 1, and the temperature of the relatively upper side of the glass melting device 1 may be identified by the sensor corresponding to the first position. In this case, the temperature of the relatively upper side may be the temperature of the gas vaporized from the melted molten water. According to an example, the processor 130 inputs the preprocessed process information into the first learning neural network model stored in the memory 120, so that the first predicted temperature information corresponding to the first position of the glass melting device 1 may be acquired. Here, the plurality of types of temperature information including the first predicted temperature information and the second predicted temperature information may include information on the temperature value.

[0072] On the other hand, through Figure 4 The first learning neural network model is described in detail.

[0073] According to one embodiment, the processor 130 may input the acquired first predicted temperature information and process information into the second learning neural network model, thereby acquiring second predicted temperature information corresponding to the second position of the glass melting device 1 .

[0074] Here, according to an example, the second position of the glass melting device 1 may be a position corresponding to the relatively lower side of the glass melting device 1 (or the bottom surface provided at the lower end and in contact with the glass water). A temperature sensor may be provided at the second position of the glass melting device 1, and the temperature of the relatively lower side of the glass melting device 1 may be identified by the sensor corresponding to the second position. In this case, the temperature of the relatively lower side may be the temperature of the melted molten water (or glass water). According to an example, the processor 130 inputs the preprocessed process information and the first predicted temperature information into the second learning neural network model stored in the memory 120, so that the second predicted temperature information corresponding to the second position of the glass melting device 1 may be acquired. That is, in order to accurately measure the temperature of the glass water, information on the temperature of the gas in the glass melting device 1 (or the temperature of the upper end of the glass melting device 1) is required.

[0075] On the other hand, through Figure 5 The second learning neural network model is described in detail.

[0076] According to an embodiment, the processor 130 may provide guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information. According to an example, when it is identified that the acquired second predicted temperature information exceeds a preset range, the processor 130 may obtain guidance information indicating that the second predicted temperature information belongs to the preset range based on information stored in the memory 120. According to an example, the memory 120 may store information about reference temperature ranges corresponding to the first position and the second position, respectively.

[0077] Figure 3 is a flowchart for illustrating a control method of an electronic device according to an embodiment.

[0078] according to Figure 3 According to one embodiment, the control method may identify whether process information including fuel input information of the glass melting device 1 is received (step S310 ).

[0079] Next, according to an embodiment, when process information is received (step S310: yes), the control method may pre-process the received process information (step S320). According to an example, the processor 130 may identify abnormal data among the multiple data included in the received process information by using a preset algorithm, and may obtain process information from which the identified abnormal data is removed.

[0080] Next, according to an embodiment, the control method inputs the preprocessed process information into the first learning neural network model, so as to obtain the first predicted temperature information corresponding to the first position of the glass melting device 1 (step S330). According to an example, the processor 130 inputs the process information including the preprocessed input fuel information and the process state information into the first learning neural network model stored in the memory 120, so as to obtain the first predicted temperature information.

[0081] Next, according to an embodiment, the control method inputs the acquired first predicted temperature information and process information into the second learning neural network model, thereby acquiring the second predicted temperature information corresponding to the second position of the glass melting device 1 (step S340). According to an example, the processor 130 inputs the first predicted temperature information and the process information received through the communication interface 110 into the second learning neural network model stored in the memory 120, thereby acquiring the second predicted temperature information.

[0082] Next, according to an embodiment, the control method may provide guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information (step S350 ).

[0083] According to an example, when it is identified that the acquired second predicted temperature information exceeds a preset range, the processor 130 may acquire guidance information indicating that the second predicted temperature information is within the preset range based on information stored in the memory 120 .

[0084] For example, when it is identified that the acquired second predicted temperature information exceeds the first threshold, the processor 130 may acquire guidance information for making the second predicted temperature information below the first threshold, and provide the guidance information. Or, for example, when it is identified that the acquired second predicted temperature information is less than the second threshold, the processor 130 may acquire guidance information for making the second predicted temperature information above the second threshold, and provide the guidance information.

[0085] According to the above embodiment, the internal temperature of the glass melting device 1 and the temperature of the glass water can be predicted using the learned neural network model. Based on this, the electronic device 100 can provide the user with guidance information for minimizing the amount of fuel input while keeping the temperature of the glass water within an appropriate range.

[0086] Figure 4 It is a diagram for explaining a first learning neural network model according to an embodiment.

[0087] According to an embodiment of the present invention, the artificial neural network (or neural network model) including the first learning neural network model and the second learning neural network model may include a deep neural network, for example, a convolutional neural network, a recurrent neural network, a restricted Boltzmann machine, a deep belief network, a bidirectional recurrent deep neural network or a deep Q-network, etc., but is not limited to the above examples.

[0088] According to an embodiment, the first learning neural network model may be stored in the memory 120. When process information including information on the amount of fuel fed into the glass melting device 1 is input, the first learning neural network model may learn to output first predicted temperature information according to the amount of fuel fed.

[0089] according to Figure 4 According to an embodiment, a data set (Set) including process information 410 including input fuel information and process state information may be input as learning data to the first neural network model 400, so that the first neural network model may be learned. In this case, the data set may include first temperature information 420 output based on (or due to) the input fuel as a label (Label).

[0090] For example, a data set including process information including input fuel amount information and process state information at the nth time point is input as learning data to the first neural network model, so that the neural network model can be learned. In this case, in the data set, temperature information corresponding to the first position of the glass melting device 1 at the n+1th time point of the first preheating chamber measured based on the amount of fuel input at the nth time point is included as a label, so that learning can be performed.

[0091] Figure 5It is a diagram for explaining a second learning neural network model according to one embodiment.

[0092] According to an embodiment, the second learning neural network model may be stored in the memory 120. According to an example, when the first predicted temperature information output by the first learning neural network model and the received process information are input, the second learning neural network model may learn to output the second predicted temperature information according to the amount of fuel input. Here, the second predicted temperature information is the predicted temperature information corresponding to the lower end portion (or glass water) of the glass melting device 1.

[0093] according to Figure 5 According to an embodiment, a data set including process information 520 and first predicted temperature information 530 is input as learning data to the second neural network model 500, so that the second neural network model 500 can be learned. Here, the first predicted temperature information 530 is information output from the first learning neural network model 400. According to an example, the process information 520 may include input fuel information and process state information. In this case, according to an example, the data set may include second temperature information 510 output based on (or due to) the input fuel as a label. The second temperature information is temperature information measured by a sensor provided at a second position of the glass melting device 1.

[0094] For example, a data set including process information including input fuel amount information and process state information at the nth time point and first predicted temperature information corresponding to the first position output from the first learning neural network model 400 is input as learning data to the second neural network model, so that the neural network model can be learned. In this case, in the data set, temperature information corresponding to the first position of the glass melting device 1 at the n+1th time point of the first preheating chamber measured based on the amount of fuel input at the nth time point is included as a label, so that learning can be performed.

[0095] Figure 6 It is a diagram for explaining a method for providing guidance information according to an embodiment.

[0096] according to Figure 6 According to one embodiment, the control method may identify whether the acquired second predicted temperature information exceeds a preset range (step S610).

[0097] According to an example, the memory 120 may store reference range information corresponding to the second predicted temperature information. According to an example, when acquiring the second predicted temperature information, the processor 130 may identify whether the acquired second predicted temperature is within the reference range based on the information stored in the memory 120.

[0098] Next, according to an embodiment, when the second predicted temperature information exceeds the preset range (step S610: yes), the control method can obtain guidance information indicating that the second predicted temperature information belongs to the preset range based on the information stored in the memory 120 (step S620). According to an example, the memory 120 may also include temperature change information corresponding to the second position according to the unit fuel input amount. That is, information about the temperature change magnitude of the second position when the fuel corresponding to the preset unit is input into the glass melting device 1 may be stored in the memory 120. The processor 130 may use the temperature change information stored in the memory 120 to obtain guidance information for indicating that the second predicted temperature information belongs to the preset range.

[0099] On the other hand, according to one embodiment, the processor 130 may also use a learned neural network model to obtain temperature change information. Figure 7 This is explained in detail.

[0100] Next, according to an embodiment, the control method may provide a user interface including the acquired guide information (step S630 ).

[0101] Figure 7 It is a diagram for explaining a method of acquiring temperature change information according to an embodiment.

[0102] according to Figure 7 According to one embodiment, the control method may identify sub-input fuel information obtained by changing the information about the input amount of fuel included in the input fuel information (step S710). Here, the sub-input fuel information may be process information in which the input fuel amount is changed by a preset value.

[0103] Next, according to an embodiment, the control method obtains the second sub-predicted temperature information by inputting the sub-process information including the sub-input fuel information into the second learning neural network model (step S720). According to an example, when the sub-input fuel information is identified, the processor 130 can obtain the sub-process information with the size of the identified input fuel amount updated. The processor 130 can obtain the second sub-predicted temperature information by inputting the sub-process information into the second learning neural network model. Here, the second sub-predicted temperature information refers to the predicted temperature information corresponding to the sub-input fuel information obtained by changing the input fuel amount.

[0104] Next, according to an embodiment, the control method may use the sub-process information and the second sub-predicted temperature information to obtain the temperature change information corresponding to the second position according to the unit fuel input amount (step S730). According to an example, the processor 130 compares the second predicted temperature information output by the second learning neural network model with the second sub-predicted temperature information, thereby obtaining the second temperature change information corresponding to the second position according to the unit fuel input amount.

[0105] However, it is not limited thereto, and according to one embodiment, the second temperature change information corresponding to the second position according to the unit fuel input amount may be stored in the memory 120. Or of course, according to one embodiment, the processor 130 may obtain the second temperature change information corresponding to the second position according to the unit fuel input amount by using the process history information about the glass melting device 1 through a preset algorithm. Here, the process history information may include history information about the input fuel and history information about the process state.

[0106] Figure 8 It is a diagram for explaining a method of acquiring temperature change information according to an embodiment.

[0107] according to Figure 8 According to one embodiment, the control method may identify the relationship information between the amount of fuel input and the temperature of the second location based on the process history information (step S810). Here, the process history information may include history information about the input fuel, history information about the process state, and history information about the temperature of the second location.

[0108] On the other hand, the relationship information may be a mathematical expression corresponding to the relationship between the input fuel information and the temperature value of the second location obtained using the regression analysis model. According to one example, the processor 130 uses a preset algorithm (e.g., a regression analysis model) to obtain the relationship information between the input fuel information and the temperature value of the second location from the process history information, wherein the process history information includes history information about the input fuel, history information about the process state, and history information about the temperature of the second location.

[0109] Next, according to an embodiment, the control method may acquire and store temperature change information corresponding to the second position according to the unit fuel input amount based on the identified relationship information (step S820). According to an example, the processor 130 may acquire temperature change information corresponding to the second position according to the unit fuel input amount based on the relationship information between the input fuel information and the temperature value of the second position, and may use the temperature change information to provide guidance information.

[0110] 9A to 9D It is a diagram for explaining a method for providing a user interface according to an embodiment.

[0111] According to an embodiment, the memory 120 may store process history information. According to an example, the process history information may include temperature history information of the first position and temperature history information of the second position. Alternatively, according to an embodiment, the process history information may also include history information about input fuel and history information about process status.

[0112] according to Fig.9A According to an embodiment, the processor 130 may provide a user interface 900 including process history information. According to an example, the processor 130 may obtain the temperature history information of the first position ARCH#3 and the temperature history information of the second position MELTER BT#11 included in the process history information based on the information stored in the memory 120. For example, the processor 130 may provide a user interface 900 including chart information corresponding to the temperature history of the first position. Or, for example, the processor 130 may also provide a user interface 900 including chart information corresponding to the temperature history of the second position.

[0113] On the other hand, according to an embodiment, the electronic device 100 may further include a display (not shown). According to an example, the processor 130 may display the user interface 900 through the display (not shown).

[0114] according to Fig. 9B According to one embodiment, the processor 130 may provide a user interface 910 including guidance information about the amount of fuel input. According to one example, the guidance information may include information 911 about the current amount of fuel input corresponding to each of the plurality of fuel input parts (including the first fuel input part and the second fuel input part) in the glass melting device 1. Or according to one example, the guidance information about the amount of fuel input may include guidance information 912 about the amount of fuel input into each of the plurality of fuel input parts (including the first fuel input part and the second fuel input part) in the glass melting device 1. Here, each item (e.g., "MAIN", "1L", "2L", "3L", ..., "4R") displayed on the user interface is an item corresponding to the plurality of fuel input parts including the plurality of burners 10 included in the glass melting device 1.

[0115] Here, the guidance information 912 on the amount of fuel to be input refers to information on the recommended amount of fuel to be input corresponding to the fuel to be input into each of the multiple positions (or multiple fuel input parts), so that the amount of fuel to be input is reduced while the temperature at the second position is maintained within a preset range. That is, the guidance information 912 on the amount of fuel to be input refers to the recommended amount of fuel to be input that minimizes the amount of fuel to be input into each of the multiple positions while the temperature at the second position is maintained within a preset range. On the other hand, according to an example, the processor 130 can use a preset algorithm to obtain the guidance information 912 on the amount of fuel to be input from the process information, the process history information, and the second predicted temperature information. Alternatively, the guidance information 912 on the amount of fuel to be input can also be pre-stored in the memory 120.

[0116] according to Fig. 9C According to an embodiment, the processor 130 may provide a user interface 910-1 including guidance information about the oxygen amounts respectively corresponding to the plurality of fuel input parts. According to an example, the guidance information about the oxygen amounts respectively corresponding to the plurality of fuel input parts may include information 911-1 about the current oxygen amounts respectively corresponding to the plurality of fuel input parts (including the first fuel input part and the second fuel input part) in the glass melting device 1. Or according to an example, the guidance information about the oxygen amounts respectively corresponding to the plurality of fuel input parts may include guidance information 912-1 about the oxygen amount of each of the plurality of fuel input parts (including the first fuel input part and the second fuel input part) input into the glass melting device 1. Here, each item (e.g., "MAIN", "1L", "2L", "3L", ..., "4R") displayed in the user interface is an item corresponding to the plurality of fuel input parts including the plurality of burners 10 included in the glass melting device 1.

[0117] Here, the guidance information 912-1 on the oxygen amounts corresponding to the multiple fuel input parts respectively refers to information on the recommended oxygen amounts corresponding to the multiple fuel input parts respectively, which reduces the amount of fuel input when the temperature at the second position is kept within a preset range. That is, the guidance information 912-1 on the oxygen amounts corresponding to the multiple fuel input parts respectively refers to the recommended input amounts that minimize the recommended oxygen amounts corresponding to the multiple fuel input parts respectively, under the condition that the temperature at the second position is kept within a preset range. On the other hand, according to an example, the processor 130 can use a preset algorithm to obtain the guidance information 912-1 on the oxygen amounts corresponding to the multiple fuel input parts respectively from the process information, the process history information, and the second predicted temperature information. Alternatively, the guidance information 912-1 on the oxygen amounts corresponding to the multiple fuel input parts respectively can also be pre-stored in the memory 120.

[0118] On the other hand, according to one embodiment, of course, the processor 130 may Fig. 9BThe user interface 910 including guidance information about the amount of fuel input and the user interface 910-1 including guidance information about the amount of oxygen corresponding to multiple fuel input parts are provided together, or the user interface 910 including guidance information about the amount of fuel input and the user interface 910-1 including guidance information about the amount of oxygen corresponding to multiple fuel input parts can be provided separately.

[0119] according to Fig.9D According to an embodiment, the processor 130 may provide a user interface 920 including predicted temperature information. According to an example, the processor 130 may obtain a user interface 920 including first predicted temperature information corresponding to the acquired first position Arch#3 and second predicted temperature information corresponding to the second position Melter BT#11. In this case, the processor 130 may identify current temperature information corresponding to the first position and the second position based on the received process information, and may also provide a user interface 920 including current temperature information corresponding to the identified first position and the second position. In this case, the processor 130 may use the first learning neural network model and the second learning neural network model to obtain an expected value (effect) when the fuel corresponding to the guidance information 912 is injected. According to an example, the expected value may include temperature information of the first position corresponding to the guidance information 912 and temperature information of the second position corresponding to the guidance information 912.

[0120] Fig.10 It is a diagram for explaining a method of identifying control information and transmitting it to a control engine according to an embodiment.

[0121] according to Fig.10 In a control method according to an embodiment, when a user input corresponding to the acquired guidance information is received, control information corresponding to the received user input can be identified (step S1010). Here, the control information refers to a control signal for controlling a control engine, and the control engine (Engine) refers to an engine for controlling the cement manufacturing device 1. According to an example, the electronic device 100 may further include a user interface (not shown), and the processor 130 may receive the user input corresponding to the acquired guidance information through the user interface (not shown). Next, the processor 130 may identify the control information corresponding to the received user input based on the information stored in the memory 120.

[0122] Next, according to an embodiment, the control method may transmit the identified control information to the control engine (step S1020). According to an example, the processor 130 may transmit the identified control information to the control engine through the communication interface 110. Here, the control engine is an engine for controlling the glass melting device 1.

[0123] Fig.11 is a block diagram showing a detailed structure of an electronic device according to an embodiment.

[0124] according to Fig.11 , the electronic device 100' may 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. Figure 2 The structure shown is repeated Fig.11 Detailed description of the structure shown.

[0125] The microphone 140 may refer to a module that acquires sound and converts it into an electrical signal, and may be a condenser microphone, a ribbon microphone, a dynamic microphone, a piezoelectric element microphone, a carbon microphone, or a micro-electromechanical system (MEMS) microphone. In addition, it may be implemented in an omnidirectional, bidirectional, unidirectional, sub-cardioid, super-cardioid, or hyper-cardioid manner.

[0126] There may be various embodiments in which the electronic device 100 ′ performs an action corresponding to a user voice signal received through the microphone 140 .

[0127] As an example, the electronic device 100' may control the display 160 based on a user voice signal received through the microphone 140. For example, when a user voice signal for displaying A content is received, the electronic device 100' may control the display 160 to display the A content.

[0128] As another example, the electronic device 100' may 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' may provide a control signal for controlling the external display device so that an action corresponding to the user voice signal is performed on the external display device, and the provided control signal may be transmitted to the external display device. Here, the electronic device 100' may store a remote control application for controlling the external display device. In addition, the electronic device 100' may transmit the provided control signal to the external display device using at least one communication method among Bluetooth, Wi-Fi, and infrared. For example, when a user voice signal for displaying content A is received, the electronic device 100' may transmit a control signal for controlling the display of content A on the external display device to the external display device. Here, the electronic device 100' may refer to various terminal devices on which remote control applications such as smartphones and AI speakers may be installed.

[0129] As another example, the electronic device 100' may 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' may transmit a control signal for controlling the external display device to the remote control device so that an action corresponding to the user voice signal is performed on the external display device. In addition, the remote control device may transmit a 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' may transmit a control signal for controlling the display of content A on the external display device to the remote control device, and the remote control device may transmit the received control signal to the external display device.

[0130] The speaker 150 can be implemented by a tweeter for reproducing high sounds, a midrange speaker for reproducing middle sounds, a woofer for reproducing low sounds, a sub-woofer for reproducing ultra-low sounds, accessories for controlling resonance, a crossover network for dividing the frequency of an electrical signal input to the speaker by frequency band, and the like.

[0131] The speaker 150 may output a sound signal to the outside of the electronic device 100'. The speaker 150 may output multimedia playback, recording playback, various notification sounds and voice messages, etc. The electronic device 100' may include an audio output device such as the speaker 150, or may include an output device such as an audio output terminal. In particular, the speaker 150 may provide acquired information, information processed and generated based on the acquired information, response results or action results to user voice, etc. in the form of voice.

[0132] The display 160 may be implemented by a display including a self-luminous device or a display including a non-self-luminous device and a backlight. For example, it may be implemented by various forms of displays such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a light emitting diode (LED), a micro LED, a mini LED, a plasma display panel (PDP), a quantum dot (QD) display, and a quantum dot light-emitting diode (QLED). The display 160 may also include a driving circuit, a backlight unit, etc. that may be implemented in the form of an amorphous silicon thin film transistor (a-si TFT), a low temperature polysilicon (LTPS) TFT, an organic thin film transistor (OTFT), etc. On the other hand, the display 160 can be implemented by a display physically connected to a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display, and a plurality of display modules. The processor 130 can control the display 160 to output the output image obtained according to the above various embodiments. Here, the output image can be a high-resolution image of 4K or 8K or more.

[0133] 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, and the control signal is used to control the image or content to be displayed on the external display device.

[0134] Here, the external display device may be connected to the electronic device 100' via 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 digital video converter box (Set Top Box, STB). In addition, the electronic device 100' may only include a small display that can only display simple information such as text information. Here, the electronic device 100' may transmit an image or content to the external display device via the communication interface 110 by wire or wirelessly, or may transmit an image or content to the external display device via an input / output interface (not shown).

[0135] The user interface 170 is a structure for the electronic device 100' to interact with the user. For example, the user interface 170 may include at least one of a touch sensor, a motion sensor, a button, a jog dial, a switch, a microphone, and a speaker, but is not limited thereto.

[0136] At least one sensor 180 (hereinafter, sensor) may include a plurality of sensors of various types. The sensor 180 may measure a physical quantity or detect an operating state of the electronic device 100', and may convert the measured or detected information into an electrical signal. The sensor 180 may include a camera, and the camera may include a lens that focuses visible light or other optical signals reflected and received by a target to an image sensor and an image sensor capable of detecting visible light or other optical signals. Here, the image sensor may include a 2D pixel array divided into a plurality of pixels.

[0137] According to the above embodiment, the internal temperature of the glass melting device and the temperature of the glass water can be predicted using the learned neural network model. Based on this, the electronic device 100' can provide the user with guidance information for minimizing the amount of fuel input while keeping the temperature of the glass water within an appropriate range.

[0138] On the other hand, the method according to the various embodiments of the present invention described above can be implemented in the form of an application that can be installed in an existing electronic device. Alternatively, the method according to the various embodiments of the present invention described above can be performed using a learning neural network based on deep learning (or a neural network based on deep learning), that is, a learning network model. In addition, the method according to the various embodiments of the present invention described above can be implemented only by software upgrades or hardware upgrades of existing electronic devices. In addition, the various embodiments of the present invention described above can also be performed by an embedded server set in an electronic device or an external server of the electronic device.

[0139] On the other hand, according to an example of the present invention, the various embodiments described above may be implemented by software including instructions stored in a machine (e.g., computer) readable storage medium. A machine is a device that calls stored instructions from a storage medium and can act according to the called instructions, and may include a display device (e.g., display device (A)) according to the disclosed embodiment. When the instructions are executed by a processor, the processor may use other constituent elements directly or under the control of the processor to perform functions corresponding to the instructions. The instructions may include code provided or executed by a compiler or interpreter. The machine-readable storage medium may 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 but is tangible, and does not distinguish whether the data is semi-permanently or temporarily stored in the storage medium.

[0140] In addition, according to an embodiment, the method according to the various embodiments described above may be included in a computer program product and provided. The computer program product may be traded between a seller and a buyer as a commodity. The computer program product may be distributed online in the form of a machine-readable storage medium (e.g., a compact disc read only memory (CD-ROM)) or through an application store (e.g., Google Store (play storeTM)). In terms of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily provided in a storage medium such as a memory of a manufacturer's server, an application store's server, or a relay server.

[0141] In addition, each constituent element (e.g., module or program) according to the various embodiments described above may be composed of a single or multiple entities, some of the corresponding sub-constituent elements described above may be omitted, or other sub-constituent elements may also be included in various embodiments. Alternatively or additionally, a portion of the constituent elements (e.g., module or program) may be integrated into one entity, and the functions performed by each corresponding constituent element before integration may be performed in the same or similar manner. According to various embodiments, the actions performed by modules, programs or other constituent elements may be performed sequentially, in parallel, iteratively or heuristically, or at least a portion of the actions may be performed in a different order, omitted or additional actions may be performed.

[0142] The preferred embodiments of the present invention are shown and described above. The present invention is not limited to the above-mentioned specific embodiments, and a person skilled in the art can make various modified implementations without departing from the main purpose of the present invention as claimed in the claims. Such modified implementations should not be understood solely from the technical ideas or prospects of the present invention.

Claims

1. An electronic device for implementing a temperature prediction and control system, wherein: The electronic device comprises: Communication interface, a memory storing a first learning neural network model and a second learning neural network model, and More than one processor; the one or more processors, When process information including fuel input information of a glass melting device is received through the communication interface, the received process information is preprocessed. inputting the preprocessed process information into the first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, inputting the acquired first predicted temperature information and the preprocessed process information into the second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device, Guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information is provided.

2. The electronic device according to claim 1, wherein: The pre-processed process information includes the input fuel information and process status information, The fuel input information includes information on the amount of fuel input into the glass melting device. The first learning neural network model is learned in the following manner: when the pre-processed process information including information on the amount of fuel fed into the glass melting device is input, first predicted temperature information based on the amount of fuel fed into the glass melting device is output; The second learning neural network model is learned in the following manner: when the first predicted temperature information and the pre-processed process information are input, the second predicted temperature information according to the input fuel amount is output.

3. The electronic device according to claim 1, wherein: The memory further includes temperature change information corresponding to the second position according to the unit fuel input amount; the one or more processors, When it is identified that the acquired second predicted temperature information exceeds a preset range, obtaining guidance information indicating that the second predicted temperature information belongs to the preset range based on the information stored in the memory, A user interface including the obtained guide information is provided.

4. The electronic device according to claim 3, wherein: the one or more processors, identifying sub-injected fuel information obtained by changing information on the injected amount of fuel included in the injected fuel information, The second sub-predicted temperature information is obtained by inputting the sub-process information including the sub-input fuel information into the second learning neural network model, The temperature change information corresponding to the second position according to the unit fuel input amount is acquired using the second predicted temperature information and the second sub-predicted temperature information.

5. The electronic device according to claim 3, wherein: The pre-processed process information further includes process history information, wherein the process history information includes history information on the input amount of fuel and history information on the temperature of the second position; the one or more processors, identifying, based on the process history information, information on a relationship between the amount of fuel injected and the temperature at the second location, The temperature change information corresponding to the second position according to the unit fuel input amount is acquired and stored based on the identified relationship information.

6. The electronic device according to claim 3, wherein: the one or more processors, A user interface is provided that includes process history information, the process history information including temperature history information of the first location and temperature history information of the second location.

7. The electronic device according to claim 1, wherein: It also includes the user interface; the one or more processors, When receiving a user input corresponding to the acquired guidance information through the user interface, identifying control information corresponding to the received user input, The identified control information is transmitted to a control engine through the communication interface.

8. A control method for an electronic device, the electronic device being used to implement a temperature prediction and control system, wherein: The control method of the electronic device comprises the following steps: When receiving process information including fuel input information of a glass melting device, pre-processing the received process information is performed. inputting the preprocessed process information into a first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, inputting the acquired first predicted temperature information and the preprocessed process information into a second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device, and Guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information is provided.

9. The control method of the electronic device according to claim 8, wherein: The pre-processed process information includes the input fuel information and process status information, The fuel input information includes information on the amount of fuel input into the glass melting device. The first learning neural network model is learned in the following manner: when the pre-processed process information including information on the amount of fuel fed into the glass melting device is input, first predicted temperature information based on the amount of fuel fed into the glass melting device is output; The second learning neural network model is learned in the following manner: when the first predicted temperature information and the pre-processed process information are input, the second predicted temperature information according to the input fuel amount is output.

10. The control method of the electronic device according to claim 8, wherein: In the step of providing the guidance information, when it is identified that the acquired second predicted temperature information exceeds a preset range, based on the temperature change information corresponding to the second position according to the unit fuel input amount stored in the memory, guidance information indicating that the second predicted temperature information belongs to the preset range is acquired; The control method of the electronic device further comprises the following step: providing a user interface including the acquired guide information.

11. The control method of an electronic device according to claim 10, wherein: The following steps are also included: identifying sub-injected fuel information obtained by changing information on the injected amount of fuel included in the injected fuel information, acquiring second sub-predicted temperature information by inputting sub-process information including the sub-input fuel information into the second learning neural network model, and The temperature change information corresponding to the second position according to the unit fuel input amount is acquired using the second predicted temperature information and the second sub-predicted temperature information.

12. The control method of an electronic device according to claim 10, wherein: The following steps are also included: identifying relationship information between the input amount of the fuel and the temperature of the second location based on process history information including history information on the input amount of the fuel and history information on the temperature of the second location, and The temperature change information corresponding to the second position according to the unit fuel input amount is acquired and stored based on the identified relationship information.

13. The control method of an electronic device according to claim 10, wherein: In the step of providing the user interface, a user interface including process history information is provided, the process history information including temperature history information of the first position and temperature history information of the second position.

14. The control method of an electronic device according to claim 8, wherein: The following steps are also included: When receiving a user input corresponding to the acquired guidance information, identifying control information corresponding to the received user input, and The identified control information is transmitted to a control engine.

15. A computer-readable recording medium, which is a non-transitory computer-readable recording medium, wherein the computer-readable recording medium stores computer instructions, which, when executed by a processor of an electronic device for implementing a temperature prediction and control system, cause the electronic device to perform actions including the following steps: When receiving process information including fuel input information of a glass melting device, pre-processing the received process information is performed. inputting the preprocessed process information into a first learning neural network model to obtain first predicted temperature information corresponding to a first position of the glass melting device, inputting the acquired first predicted temperature information and the preprocessed process information into a second learning neural network model to acquire second predicted temperature information corresponding to a second position of the glass melting device, and Guidance information including the acquired first predicted temperature information and the acquired second predicted temperature information is provided.

Images