Electronic device and control method for implementing prediction and control system for industrial process

Abstract

To provide an electronic device and control method for implementing a temperature prediction and a control system.SOLUTION: An electronic device 100 includes: a communication interface; a memory in which a first learned neural network model and a second learned neural network model are stored; and one or more processors for receiving process information including input fuel information for a cement production device via a communication interface, inputting the preprocessed process information into a second learned neural network model to obtain first predicted temperature information output by the first learned neural network model and error information related to measured temperatures in a first preheating chamber in the cement production device, identifying predicted calorific value information for first recycled fuel among the input fuels based on the acquired error information and input fuel information, inputting the updated input fuel information into the first learned neural network model to acquire second predicted temperature information for the first preheating chamber, and providing guide information including the acquired second predicted temperature information.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to an electronic device for implementing a prediction and control system for an industrial process, and more particularly to an electronic device and a control method thereof for predicting the calorific value of recycled fuel and the temperature of a preheating chamber in a cement manufacturing apparatus using a trained neural network model, and controlling the input fuel of cement based on the prediction. [Background technology]

[0002] Recently, technological developments have been made to reduce carbon emissions and unnecessary energy consumption in industrial processes by optimizing indicators such as electricity and coal consumption, aiming for environmentally friendly processes.

[0003] In the case of the cement process, the need to reduce carbon emissions and unnecessary energy consumption is even more emphasized due to the characteristics of the fuel used.The cement process is composed of a mining process to excavate limestone, which is the raw material for cement, a crushing process to crush the mined limestone blocks, a mixing process to mix the crushed limestone to reduce quality variations, a raw material crushing process to finely crush the mixed limestone into powder with natural resources (e.g. clay, silica, iron ore, etc.) or recycled resources (coal ash, slag, casting sand, desulfurized gypsum, etc.), a preheating process in which fine powdered raw materials supplied from a raw material storage facility are fed into a preheating chamber to produce calcium oxide required for the firing process, a firing process in which the produced calcium oxide is heated to a predetermined temperature to produce clinker through a chemical reaction, a cooling process to cool the produced clinker, and a crushing process in which gypsum is added to the clinker and further crushed to complete cement.

[0004] In particular, the preheating process and the calcination process are carried out in a preheating chamber and a calcination furnace, respectively, included in the cement manufacturing equipment, and the preheating chamber must maintain an appropriate process temperature in order to produce high-quality clinker. If the temperature is lower than the appropriate process temperature, chemical reactions do not proceed well, and if the temperature is higher than the appropriate process temperature, unnecessary fuel consumption and increased emissions of air polluting gases may occur. Therefore, a method for maintaining the appropriate process temperature is required.

[0005] In addition, in order to reduce carbon emissions, there has been active development of processes for producing cement using recycled fuels (e.g., waste synthetic resins). When using recycled fuels, there is a problem that the components of the recycled fuel are not constant and the calorific value changes depending on factors such as the moisture content. This makes it difficult to identify the calorific value of the recycled fuel, which makes it difficult to maintain the appropriate process temperature. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Korean Patent Publication No. 10-2022-0147028 Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure is intended to solve the above-mentioned problems, and provides an electronic device and a control method thereof that predicts the calorific value of regenerated fuel using a trained neural network model, predicts the temperature of a preheating chamber using the predicted calorific value of the regenerated fuel, and provides a user with guide information for maintaining an appropriate process temperature based on the predicted temperature. [Means for solving the problem]

[0008] An electronic device for implementing a temperature prediction and control system according to one embodiment of the present disclosure may include a communication interface, a memory in which a first trained neural network model and a second trained neural network model are stored, and one or more processors that pre-process the received process information, including input fuel information of a cement manufacturing apparatus, when the process information is received via the communication interface.

[0009] The one or more processors can input the preprocessed process information to the second trained neural network model and obtain first predicted temperature information output from the first trained neural network model and error information regarding the measured temperature of a first preheating chamber in the cement manufacturing equipment.

[0010] The one or more processors may identify predicted calorific value information of a first regenerated fuel among the input fuels based on the obtained error information and the input fuel information.

[0011] The one or more processors may input updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber.

[0012] The one or more processors may provide guide information including the obtained second predicted temperature information.

[0013] A method for controlling an electronic device for implementing a temperature prediction and control system according to an embodiment of the present disclosure may include, when process information including input fuel information of a cement manufacturing apparatus is received, performing pre-processing of the received process information.

[0014] The control method may include inputting the pre-processed process information into a second trained neural network model, and obtaining first predicted temperature information output from the first trained neural network model and error information relating to a measured temperature of a first pre-heating chamber in the cement manufacturing apparatus.

[0015] The control method may include identifying predicted calorific value information of a first regeneration fuel among the input fuels based on the acquired error information and the input fuel information.

[0016] The control method may include inputting updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber.

[0017] The control method may include providing guide information including the obtained second predicted temperature information.

[0018] A non-transitory computer-readable recording medium according to one embodiment of the present disclosure stores computer instructions that, when executed by a processor of an electronic device for implementing a temperature prediction and control system, cause the electronic device to perform operations, the operations may include, when process information including input fuel information for a cement manufacturing apparatus is received, pre-processing the received process information.

[0019] The operations may include inputting the pre-processed process information into a second trained neural network model and obtaining first predicted temperature information output from the first trained neural network model and error information related to a measured temperature of a first pre-heating chamber in the cement manufacturing apparatus.

[0020] The operations may include identifying predicted calorific value information of a first regenerated fuel among the input fuels based on the obtained error information and the input fuel information.

[0021] The operations may include inputting updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber.

[0022] The operations may include providing guide information including the obtained second predicted temperature information. Effect of the Invention

[0023] According to the present disclosure, it is possible to predict the calorific value of recycled fuel that can reduce carbon emissions using an artificial intelligence model that has been trained based on data on the manufacturing process, and to accurately predict the temperature of the preheating chamber using the predicted calorific value of the recycled fuel. According to the present disclosure, it is possible to provide the user with guide information for maintaining an appropriate process temperature based on the accurately predicted temperature. [Brief description of the drawings]

[0024] [Figure 1] 1 is a diagram for illustrating a control method for an electronic device according to an embodiment; [Diagram 2] FIG. 1 is a block diagram showing a configuration of an electronic device according to an embodiment. [Diagram 3] 1 is a flowchart illustrating a method for controlling an electronic device according to an embodiment. [Figure 4] FIG. 2 is a diagram for explaining a first trained neural network model and its training method according to one embodiment. [Diagram 5] FIG. 2 is a diagram for explaining a second trained neural network model and its training method according to one embodiment. [Figure 6] 1 is a diagram illustrating a method for providing guide information according to an embodiment. [Figure 7] 11A and 11B are diagrams illustrating a method for obtaining and providing guide information according to an embodiment. [Figure 8a] 1 is a diagram illustrating a method for providing a UI according to an embodiment. [Figure 8b] Same as above. [Figure 9a] 1 is a diagram illustrating a method for providing a UI according to an embodiment. [Figure 9b] Same as above. [Figure 9c] Same as above. [Figure 10] 1 is a diagram illustrating a method for identifying and transmitting control information to a control engine according to an embodiment. [Figure 11]FIG. 2 is a block diagram showing a detailed configuration of an electronic device according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] The present disclosure will now be described in detail with reference to the accompanying drawings.

[0026] The terms used in this specification will be briefly explained below to specifically explain the present disclosure.

[0027] The terms used in the embodiments of the present disclosure are currently common terms that are widely used as much as possible, taking into consideration the functions in the present disclosure, but these may change depending on the intentions or precedents of engineers in the field, the emergence of new technologies, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meanings are described in detail in the description of the relevant disclosure. Therefore, the terms used in the present disclosure should be defined based on the meanings that the terms have and the overall content of the present disclosure, rather than simply the names of the terms.

[0028] In this specification, expressions such as "have," "may have," "include," or "may include" refer to the presence of a given feature (e.g., a value, a function, an operation, or a component such as a part) and do not exclude the presence of additional features.

[0029] The phrase "at least one of A and / or B" should be understood to indicate either "A" or "B" or "A and B."

[0030] As used in this specification, expressions such as "first," "second," "primary," or "second" may modify various components regardless of order and / or importance, and are only used to distinguish one component from other components, and do not limit the component in question.

[0031] When a component (e.g., a first component) is referred to as being "operatively or communicatively coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the component may be directly coupled to the other component or may be coupled through another component (e.g., a third component).

[0032] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, the terms "comprise" or "comprise" and the like are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0033] In this disclosure, a "module" or "unit" performs at least one function or operation and may be embodied in hardware or software, or a combination of hardware and software. Furthermore, multiple "modules" or multiple "units" may be integrated into at least one module and embodied in at least one processor (not shown), except for "modules" or "units" that need to be embodied in specific hardware.

[0034] According to an embodiment of the present disclosure, an electronic device may include an artificial intelligence model (or artificial neural network model or learning network model) that is composed of at least one neural network layer. The artificial neural network may include a deep neural network (DNN), such as, but not limited to, 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 (BRRDNN), or a deep Q-network.

[0035] In addition, in this specification, a "parameter" is a value used in the calculation process of each layer constituting a neural network, and may include, for example, a weighting value used when applying an input value to a predetermined calculation formula. Also, the parameter may be expressed in the form of a matrix. The parameter is a value set as a result of training, and may be updated via separate training data as necessary.

[0036] FIG. 1 is a diagram for explaining a control method for an electronic device according to an embodiment.

[0037] Referring to FIG. 1, first, according to one embodiment, a calcination process is performed in a kiln included in the cement manufacturing apparatus 1. In order for the cement manufacturing process to be performed successfully, the temperature of the kiln in which the calcination process is performed must be within a predetermined range (1500°C to 2000°C according to one embodiment). The cement manufacturing apparatus 1 may include a plurality of preheating chambers. Among these, if the temperature of the first preheating chamber 10 connected to the pyro rotor and the kiln is also within a predetermined range, an efficient process can be performed.

[0038] The cement manufacturing apparatus 1 may include a plurality of fuel inlets. For example, the cement manufacturing apparatus may include an auxiliary fuel inlet, a main fuel inlet, and a recycled fuel inlet 20. By feeding recycled fuel into the cement manufacturing apparatus 1, carbon emissions are reduced and energy emissions are decreased. However, due to the characteristics of recycled fuel, it is difficult to measure the accurate calorific value, which acts as a factor making it difficult to control the temperatures of the preheating chamber and the calciner.

[0039] Hereinafter, various embodiments will be described in which the calorific value of the recycled fuel input into the cement manufacturing apparatus is predicted, and based on this, the temperature of the first preheating chamber 10 connected to the pyro rotor and the calciner is predicted, and guide information is provided for increasing the proportion of recycled fuel while maintaining the temperature of the first preheating chamber within a predetermined range.

[0040] FIG. 2 is a block diagram showing a configuration of an electronic device according to an embodiment.

[0041] With reference to FIG. 2, electronic device 100 may include a communication interface 110, a memory 120, and one or more processors 130.

[0042] According to an embodiment, the electronic device 100 may be embodied as a device that processes data and communicates with an external device, such as a server, but is not limited thereto. For example, the electronic device 100 may be embodied 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 an embodiment of the present disclosure is not limited to the above-mentioned devices, and the electronic device 100 may be embodied as an electronic device 100 having two or more functions of the above-mentioned devices.

[0043] The electronic device 100 may communicate with an external device and an external server in various ways. According to an embodiment, a communication module for communicating with an external device and an external server may be implemented as a single module. For example, the electronic device 100 may communicate with an external device using a Bluetooth module, and may also communicate with an external server using a Bluetooth module.

[0044] In other embodiments, the communication modules for communicating with the external device and the external server may be embodied separately. For example, the electronic device 100 may communicate with the external device using a Bluetooth module and with the external server using an Ethernet modem or a Wi-Fi module.

[0045] According to an embodiment, the external device (not shown) may be embodied as a cement manufacturing device, but is not limited thereto.

[0046] 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 to and from 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 disk) via communication methods such as AP-based Wi-Fi (Wireless LAN network), Bluetooth, Zigbee, wired / wireless LAN (Local Area Network), WAN (Wide Area Network), Ethernet, IEEE 1394, HDMI (High-Definition Multimedia Interface), USB (Universal Serial Bus), MHL (Mobile High-Definition Link), AES / EBU (Audio Engineering Society / European Broadcasting Union), optical, coaxial, and the like.

[0047] As an example, the communication interface 110 may include a Bluetooth Low Energy (BLE) module. BLE refers to a Bluetooth technology capable of transmitting and receiving low-power, low-volume data in the 2.4 GHz frequency band having a reach radius of approximately 10 m. However, without being limited 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 Bluetooth Low Energy (BLE) module or a Wi-Fi communication module.

[0048] According to an example, the communication interface 110 can 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 can use at least one of an Ethernet module or a Wi-Fi module to communicate with an external server, and can use a Bluetooth module to communicate with an external device such as a remote control device. However, this is only one embodiment, and the communication interface 110 can use at least one of various communication modules when communicating with multiple external devices or servers.

[0049] The memory 120 may store data required for various embodiments. The memory 120 may be implemented as a memory embedded in the electronic device 100 or a memory removable from the electronic device 100 depending on the purpose of data storage. For example, data for driving the electronic device 100 is stored in a memory embedded in the electronic device 100, and data for an extended function of the electronic device 100 is stored in a memory removable from the electronic device 100.

[0050] In addition, the memory embedded in the electronic device 100 may be embodied as at least one of a volatile memory (e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), a non-volatile memory (e.g., one time programmable ROM (OTPROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash), a hard drive, or a solid state drive (SSD). In addition, the memory removable from the electronic device 100 may be embodied as at least one of a memory card (e.g., compact flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (Mini-SD), extreme digital (xD), multi-media (MMC), or a combination of a memory card and a memory card). The image forming apparatus may be implemented in the form of an external memory that can be connected to a USB port (e.g., a USB memory), or the like.

[0051] According to one embodiment, the memory 120 may store a first trained neural network model and a second trained neural network model, which are described in more detail with reference to Figures 4 and 5.

[0052] One or more processors 130 (hereinafter, processors) are electrically connected to the communication interface 110 and the memory 120 and control the overall operation of the electronic device 100. The processor 130 may be composed of one or more processors. Specifically, the processor 130 may perform the operation of the electronic device 100 according to various embodiments of the present disclosure by executing at least one instruction stored in the memory 120.

[0053] According to an embodiment, the processor 130 may be implemented as a digital signal processor (DSP) for processing digital video signals, a microprocessor, a graphics processing unit (GPU), an artificial intelligence (AI) processor, a neural processing unit (NPU), or a time controller (TCON). However, the processor 130 may be implemented as one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, without being limited thereto. The processor 130 may be implemented as a system on chip (SoC) or large scale integration (LSI) having 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).

[0054] According to an embodiment, the processor 130 may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON). However, the term may include or be defined as one or more of a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), a communication processor (CP), or an ARM processor, without being limited thereto. The processor 130 may also be implemented as a system on chip (SoC) or large scale integration (LSI) having a built-in processing algorithm, or may be implemented in the form of a field programmable gate array (FPGA).

[0055] According to one embodiment, the processor 130 may receive process information including input fuel information of the cement manufacturing apparatus 1 via the communication interface 110. Here, the process information is information related to various environments of the cement manufacturing apparatus 1 in which the cement process is performed, and according to one example, the process information may include input fuel information input to the cement manufacturing apparatus 1 for cement production or process status information corresponding to the cement manufacturing apparatus 1.

[0056] The input fuel information may include, for example, information on the input amount corresponding to each of a plurality of types of fuel input for cement production and calorific value information corresponding to each of the plurality of types of input fuel. The plurality of types of fuel may include, for example, a bituminous coal type main fuel, a bituminous coal type auxiliary fuel, and a plurality of types of recycled fuel. Here, the main fuel and the auxiliary fuel are the same type of fuel, but the main fuel is the fuel input via a first fuel input unit provided on one side of the calcination furnace in the cement production apparatus 1, and the auxiliary fuel is the fuel input via a second fuel input unit provided on the other side of the calcination furnace. The auxiliary fuel is a fuel that supplements the main fuel.

[0057] The recycled fuel is a fuel that is input for environmentally friendly processes and carbon emission reduction, and is a fuel that can reduce carbon emissions and unnecessary energy consumption because it has a relatively low carbon content compared to bituminous coal-type main fuels and auxiliary fuels. According to one example, the recycled fuel may include at least one of a waste synthetic resin type, a waste tire type, a waste oil type, and a sewage sludge type.

[0058] In addition, the process status information corresponding to the cement manufacturing apparatus 1 may include, for example, process environment information related to the cement manufacturing apparatus 1, and as an example, the process status information may include at least one of the oxygen concentration, carbon dioxide concentration, and nitrogen oxide concentration in the exhaust gas discharged from the inlet of the kiln in the cement manufacturing apparatus 1. Alternatively, the process status information may include, but is not limited to, the temperature of air input into the pyro rotor and the kiln after the cooling process has progressed, pressure information of a fan in the cooler, speed information of the conveyor belt, speed information and current amount information of the pyro rotor and the kiln, and information on raw materials (e.g., lime powder) input into the cement manufacturing apparatus 1.

[0059] According to an example, the processor 130 may receive process information including input fuel information of the cement manufacturing apparatus 1 from an external server (not shown) storing process information of the cement manufacturing apparatus 1 via the communication interface 110. Alternatively, the processor 130 may receive process information from a sensor provided in the cement manufacturing apparatus 1 via the communication interface 110, but is not limited thereto.

[0060] According to an embodiment, when the process information is received, the processor 130 may perform pre-processing of the received process information. According to an example, the processor 130 may identify anomalous data (outliers) among a plurality of data included in the received process information using a predetermined algorithm, and may obtain process information from which the identified anomalous data (outliers) are removed. Alternatively, if the process information corresponding to a predetermined time period during the time when the process is performed is not received, the processor 130 may perform pre-processing by receiving the process information that was not received from the communication interface 110. However, the present invention is not limited to this.

[0061] According to one embodiment, the processor 130 can input the pre-processed process information into a second trained neural network model and obtain first predicted temperature information output from the first trained neural network model and error information regarding the measured temperature of the first pre-heating chamber in the cement manufacturing equipment 1.

[0062] According to one example, the second trained neural network model may be a neural network model trained to output error information related to the predicted temperature information output from the first trained neural network model and the measured temperature information of the first preheating chamber when process information including input fuel information and process state information is input. The processor 130 may input the preprocessed process information including input fuel information and process state information to the second trained neural network model to obtain the error information.

[0063] Here, the error information regarding the predicted temperature information output from the first trained neural network model and the measured temperature information of the first preheating chamber means an error caused by a change in the calorific value of waste synthetic resin among the multiple recycled fuel types. That is, in the case of waste synthetic resin, it is difficult to accurately identify the magnitude of the calorific value due to the characteristics of the fuel, and since the calorific value of the waste synthetic resin is not accurately identified, an error occurs between the predicted temperature and the measured temperature of the first preheating chamber. In the present disclosure, an attempt is made to accurately predict the temperature of the first preheating chamber by accurately identifying the magnitude of the calorific value of waste synthetic resin among the recycled fuels.

[0064] According to an example, the multiple types of temperature information including the first predicted temperature information and the second predicted temperature information may include information related to the temperature value.

[0065] According to one embodiment, the processor 130 can identify predicted calorific value information of the first recycled fuel among the input fuels based on the acquired error information and the input fuel information. Here, the first recycled fuel may be waste synthetic resin, for example, and the processor 130 can identify predicted calorific value information of the first recycled fuel based on the acquired error information and information on the input amount of the first recycled fuel included in the input fuel information. For example, the processor 130 can identify the predicted calorific value of the waste synthetic resin using the following Equation (1).

[0066]

number

[0067] Here, A means the predicted calorific value of the waste synthetic resin, B means the calorific value of the existing waste synthetic resin for predicting the temperature of the existing first pre-heating chamber, C means the error information on the temperature of the first pre-heating chamber outputted through the second trained neural network model, and D means the input amount of the waste synthetic resin. As an example, assume that the calorific value of the existing waste synthetic resin is 10, the magnitude of the error is 50, and the input amount is 100. The processor 130 can identify the magnitude of the predicted calorific value of the waste synthetic resin as 10.5 (10 + (50 / 100)) through the formula (1). Through this, the processor 130 can identify the accurate calorific value of the waste synthetic resin.

[0068] According to one embodiment, the processor 130 may input the input fuel information updated based on the identified predicted calorific value information into the first trained neural network model to obtain the second predicted temperature information of the first preheating chamber. According to one example, the processor 130 may input the input fuel information updated with the predicted calorific value information of the identified waste synthetic resin into the first trained neural network model to obtain the second predicted temperature information of the first preheating chamber from the first trained neural network model. Here, the first predicted temperature information is the predicted temperature information of the first preheating chamber corresponding to the input fuel information before the first regenerated fuel, i.e., the waste synthetic resin calorific value information is updated, and the second predicted temperature information is the predicted temperature information of the first preheating chamber corresponding to the input fuel information after the first regenerated fuel, i.e., the waste synthetic resin calorific value information is updated.

[0069] According to one embodiment, the processor 130 can provide guide information including the acquired second predicted temperature information. According to one example, the processor 130 can obtain guide information to guide the input amount of at least one of the main fuel and the auxiliary fuel to be decreased when the acquired second predicted temperature information is identified as exceeding the target temperature value. Alternatively, according to one example, the processor 130 can obtain guide information to guide the input amount of the first regenerative fuel to be increased when the acquired second predicted temperature information is identified as being less than the target temperature value. The processor 130 can provide the obtained guide information.

[0070] FIG. 3 is a flowchart illustrating a method for controlling an electronic device according to an embodiment.

[0071] According to one embodiment, first, when process information including input fuel information of the cement manufacturing apparatus 1 is received (S310: Y), the control method may perform pre-processing of the received process information (S320). According to one example, the processor 130 may identify outlier data from a plurality of data included in the received process information using a predetermined algorithm, and may obtain process information from which the identified outlier data has been removed.

[0072] Next, according to one embodiment, the control method inputs the preprocessed process information into a second trained neural network model, and obtains first predicted temperature information output from the first trained neural network model and error information regarding the measured temperature of the first preheating chamber in the cement manufacturing apparatus 1 (S330).

[0073] Next, according to one embodiment, the control method can identify predicted calorific value information of the first regenerated fuel among the input fuels based on the acquired error information and input fuel information (S340). According to one example, the processor 130 can identify predicted calorific value information of the first regenerated fuel based on error information on the temperature of the first preheating chamber output from the second trained neural network model, information on the input amount of the first regenerated fuel corresponding to waste synthetic resin among the multiple types of input fuels, and calorific value information on the existing waste synthetic resin.

[0074] Next, according to one embodiment, the control method can input the updated fuel input information based on the identified predicted heat quantity information into a first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber (S350). According to one example, the processor 130 can update the fuel input information based on the identified predicted heat quantity information using Equation (1), and input the updated fuel input information into a first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber.

[0075] Next, according to one embodiment, the control method can provide guide information including the acquired second predicted temperature information (S360). According to one example, the processor 130 can obtain guide information to guide the input amount of at least one of the main fuel and the auxiliary fuel to be reduced when the acquired second predicted temperature information is identified as exceeding the target temperature value. Alternatively, according to one example, the processor 130 can obtain guide information to guide the input amount of the first regenerated fuel to be increased when the acquired second predicted temperature information is identified as being less than the target temperature value. The processor 130 can provide the obtained guide information.

[0076] However, without being limited thereto, in one embodiment, the processor 130 may provide guide information regarding the input amount for different types of fuel other than the main fuel, the auxiliary fuel, and the regenerative fuel. Alternatively, in one embodiment, the processor 130 may also provide guide information regarding the pressure of a cooler fan included in the cement manufacturing apparatus 1.

[0077] According to the above example, the electronic device 100 can predict the calorific value of the recycled fuel using the trained neural network model, and can predict the temperature of the first pre-heating chamber based on the predicted calorific value. This allows the electronic device 100 to provide guidance information to the user based on the accurately predicted pre-heating chamber temperature, thereby enabling an environmentally friendly and efficient process.

[0078] FIG. 4 is a diagram for explaining a first trained neural network model and a training method thereof according to one embodiment.

[0079] The artificial neural network (or neural network model) including the first trained neural network model and the second trained neural network model according to an embodiment of the present disclosure may include a deep neural network (DNN), such as 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 (BRRDNN), or a deep Q-network, but is not limited to the aforementioned examples.

[0080] According to one embodiment, a first trained neural network model may be stored in the memory 120. The first trained neural network model may be trained to output predicted temperature information of the first pre-heating chamber when input fuel information including information regarding input amounts corresponding to each of different types of input fuels including a first regenerative fuel and calorific value information corresponding to each of the input fuels is input.

[0081] 4, according to one embodiment, a data set including input fuel information 40 including fuel input amount information and calorific value information corresponding to each of a main fuel, an auxiliary fuel, and a plurality of regenerative fuels is input as learning data to a first neural network model 400, and the neural network model can be trained. In this case, the data set may include temperature information 41 of the first pre-heating chamber, which is output based on (or caused by) the input fuel, as a label.

[0082] For example, a data set (set) including fuel input amount information and calorific value information corresponding to each of the main fuel, the auxiliary fuel, and the plurality of regenerative fuels at the nth time point may be input as learning data to the first neural network model, and the neural network model may be trained. In this case, the data set (set) may include temperature information of the first pre-heating chamber at the n+1th time point, which is measured based on the fuel input at the nth time point, as a label, and training may be performed.

[0083] FIG. 5 is a diagram for explaining a second trained neural network model and its training method according to one embodiment.

[0084] According to an embodiment, a second trained neural network model may be stored in the memory 120. According to an example, the second trained neural network model may be trained to output error information related to predicted temperature information output from the first trained neural network model and measured temperature information of the first pre-heating chamber when process information including input fuel information and process state information is input. Here, the measured temperature information of the first pre-heating chamber is information related to the temperature of the first pre-heating chamber measured via an actual sensor.

[0085] Referring to FIG. 5, according to an embodiment, a data set including process information 50 including input fuel information and process status information is input as learning data to the second neural network model 500, and the second neural network model 500 can be trained. Here, the input fuel information may include, for example, fuel input amount information and calorific value information corresponding to each of the main fuel, the auxiliary fuel, and the plurality of regenerative fuels. The process status information may include, for example, process environment information regarding the cement manufacturing apparatus 1, and, for example, the process status information may include at least one of the oxygen concentration, the carbon dioxide concentration, and the nitrogen oxide concentration in the exhaust gas discharged from the inlet of the kiln in the cement manufacturing apparatus 1. Alternatively, the process status information may include the temperature of air input into the pyro rotor and the kiln after the cooling process has progressed, pressure information of the fan in the cooler, speed information of the conveyor belt, speed information and current amount information of the pyro rotor and the kiln, and information on the raw material (e.g., lime powder) input into the cement manufacturing apparatus 1.

[0086] In addition, the data set (set) may include in its label (Label) a difference value between the predicted temperature information 51 of the first pre-heating chamber output from the first trained neural network model and the measured temperature information 52 of the first pre-heating chamber. That is, the second neural network model 500 may perform learning using the predicted temperature information output from the first trained neural network model as learning data. In addition, in one example, the process information may include temperature history information of the first pre-heating chamber and history information of the input fuel, and the measured temperature information 52 of the first pre-heating chamber may be obtained based on the temperature history information of the first pre-heating chamber included in the process information.

[0087] FIG. 6 is a diagram illustrating a method for providing guide information according to an embodiment.

[0088] Referring to FIG. 6, first, according to one embodiment, the control method may receive a target temperature value of a first preheating chamber in the cement manufacturing apparatus via a user interface (not shown) (S610).

[0089] Next, according to one embodiment, the control method can identify, based on the acquired second predicted temperature information and the received target temperature value, the input amounts corresponding to each of the different types of input fuel for the temperature value of the first pre-heating chamber to reach the target temperature value (S620), and obtain guide information corresponding to the identified input amounts (S630).

[0090] According to an example, the memory 120 may already store information on the change value of the temperature of the first preheating chamber due to the change in the unit input amount corresponding to each of a plurality of types of input fuel including the main fuel and the auxiliary fuel. According to an example, the processor 130 may obtain information on the change value of the temperature of the first preheating chamber due to the change in the unit input amount through the process information including the process history information using a predetermined algorithm. The processor 130 may identify the input amount of the main fuel or the auxiliary fuel to be input based on the information stored in the memory 120 and the difference value between the second predicted temperature information and the target temperature value, and obtain guide information including information on the identified input amount. Alternatively, the processor 130 may identify the input amount of the first regenerated fuel to be input based on the information stored in the memory 120 and the difference value between the second predicted temperature information and the target temperature value, and obtain guide information including information on the identified input amount.

[0091] For example, the processor 130 may obtain guide information for guiding the temperature value of the first preheating chamber to reach the target temperature value by changing the input amount of at least one of the main fuel and the auxiliary fuel of the bituminous coal type when the second predicted temperature information exceeds the target temperature value. Alternatively, for example, if the second predicted temperature information is less than the target temperature value, the processor 130 may obtain guide information for guiding the input amount of the first recycled fuel to be increased. When the processor 130 identifies that the second predicted temperature information is less than the target temperature value based on the information stored in the memory 120, it may obtain guide information for guiding the input amount of the waste synthetic resin corresponding to the first recycled fuel to be increased.

[0092] However, without being limited thereto, the processor 130 may obtain guide information corresponding to the magnitude of the temperature information predicted using the first and second trained neural network models, respectively, which will be described in detail with reference to FIG.

[0093] Next, according to one embodiment, the control method may provide a UI including the obtained guide information (S640). A specific method of providing the UI will be described in detail with reference to Figures 8, 9a, and 9b.

[0094] FIG. 7 is a diagram for explaining a method for obtaining and providing guide information according to an embodiment.

[0095] 7, according to one embodiment, the control method may first identify sub-input fuel information in which the input amount corresponding to each input fuel included in the input fuel information has been changed (S710). Here, the sub-input fuel information may be process information in which the ratio of the input fuel has been changed by a predetermined value, but is not limited thereto, and according to one example, the sub-input fuel information may be process information in which the process state (e.g., the magnitude of pressure in the cement manufacturing apparatus) has been changed. For example, the processor 130 may identify sub-input fuel information in which the input amount of the main fuel or the auxiliary fuel has been reduced by a predetermined value.

[0096] Next, according to one embodiment, the control method may input the sub-input fuel information into the first trained neural network model to obtain second sub-predicted temperature information (S720).

[0097] Next, according to an embodiment, the control method may obtain guidance information regarding the input fuel using the acquired second predicted temperature information and second sub-predicted temperature information (S730). Here, the guidance information means information regarding a recommended input ratio corresponding to each input fuel for increasing the ratio of the regenerative fuel input in a state where the temperature of the first pre-heating chamber maintains the target temperature value. According to an example, the processor 130 may obtain guidance information regarding the input fuel through a dataset including the acquired second predicted temperature information and process information corresponding to the second predicted temperature information, and a dataset including process information corresponding to the second sub-predicted temperature information and the second predicted temperature information, using a predetermined algorithm.

[0098] However, without being limited thereto, according to one embodiment, the processor 130 may obtain guidance information regarding the input fuel based on information regarding the change in temperature of the first pre-heating chamber due to a change in unit input amount corresponding to each of a plurality of types of input fuel including main fuel and auxiliary fuel stored in the memory 120.

[0099] Alternatively, according to an embodiment, the processor 130 may identify guidance information regarding the input fuel based on at least one of the temperature history information of the first pre-heating chamber and the process environment information regarding the cement manufacturing apparatus 1, and provide the identified guidance information. According to an example, the processor 130 may identify the guidance information regarding the input fuel based on at least one of the acquired second predicted temperature information, the second sub-predicted temperature information, the temperature history information of the first pre-heating chamber, and the process environment information regarding the cement manufacturing apparatus 1. Here, the process environment information may include at least one of the oxygen concentration, the carbon monoxide concentration, the carbon dioxide concentration, and the nitrogen oxide concentration in the exhaust gas discharged from the inlet of the calciner in the cement manufacturing apparatus 1.

[0100] According to one example, when the current temperature value of the first pre-heating chamber is identified based on the temperature history information of the first pre-heating chamber, the processor 130 can identify guidance information based on a difference value between the current temperature value of the first pre-heating chamber and the target temperature value. For example, when the difference value between the current temperature value of the first pre-heating chamber and the target temperature value is equal to or greater than a threshold, the processor 130 can identify guidance information that minimizes the time for the temperature value of the first pre-heating chamber to reach the target temperature value while maintaining the temperature of the first pre-heating chamber at the target temperature value.

[0101] Alternatively, according to one example, the processor 130 can identify a current temperature value of the first pre-heating chamber and a temperature value of the first pre-heating chamber at a first time point a predetermined time before the present based on temperature history information of the first pre-heating chamber, and provide guidance information based thereon.

[0102] For example, the processor 130 may identify the current temperature value of the first pre-heating chamber and the temperature value of the first pre-heating chamber one minute before the present (or the past temperature value of the first pre-heating chamber), and compare the identified current temperature value of the first pre-heating chamber and the past temperature value of the first pre-heating chamber to obtain trend information regarding the temperature of the first pre-heating chamber. The processor 130 may identify guidance information for increasing the time for the temperature value of the first pre-heating chamber to reach the target temperature value while the temperature of the first pre-heating chamber is maintained at the target temperature value, if the magnitude of the time for the temperature value of the first pre-heating chamber to reach the target temperature value is less than a threshold based on the acquired trend information. Alternatively, the processor 130 may identify guidance information for decreasing the time for the temperature value of the first pre-heating chamber to reach the target temperature value while the temperature of the first pre-heating chamber is maintained at the target temperature value, if the magnitude of the time for the temperature value of the first pre-heating chamber to reach the target temperature value is equal to or greater than a threshold based on the acquired trend information.

[0103] Alternatively, according to an example, the processor 130 may identify guidance information using process environment information related to the cement manufacturing apparatus 1. For example, when the processor 130 identifies that the concentration of carbon monoxide (CO) in the exhaust gas discharged from the inlet of the kiln is equal to or greater than a predetermined value, the processor 130 may update the guidance information so that the amount of regenerative fuel input, which is input in a state where the temperature of the first preheating chamber maintains a target temperature value, is reduced from the amount of regenerative fuel input already identified. That is, when the kiln is in a poor condition, such as when the concentration of carbon monoxide is equal to or greater than a predetermined value, the processor 130 may provide the user with guidance information to reduce the amount of regenerative fuel input, thereby guiding the amount of regenerative fuel input in consideration of the kiln condition.

[0104] However, in this case, when the processor 130 identifies that the magnitude of the current applied to the main motor included in the kiln is equal to or greater than a predetermined value based on the process environment information, it may provide guidance information to maintain the previously identified amount of recycled fuel input, because when the current value of the main motor of the kiln is equal to or greater than a predetermined value, it means that the kiln is in a good condition.

[0105] Alternatively, for example, the processor 130 may identify guidance information using the concentration of oxygen in the exhaust gas included in the process environment information. Specifically, the processor 130 may identify trend information of the concentration of oxygen in the exhaust gas based on the process environment information, and when it is identified that the concentration of oxygen in the exhaust gas decreases over time, it may provide guidance information for decreasing the amount of regenerative fuel input. That is, since a decrease in the concentration of oxygen in the exhaust gas means that the temperature of the preheating chamber increases, the processor 130 may identify the amount of regenerative fuel input based on the concentration of oxygen in the exhaust gas.

[0106] However, the present invention is not limited thereto, and in one embodiment, the processor 130 may identify guidance information using a predefined algorithm. For example, the processor 130 may provide a function for feedback control in which an output maintains a reference value based on an error between a control variable and a reference input. The processor 130 may also identify guidance information regarding the input fuel using as input values ​​the target temperature value of the first preheating chamber, the current temperature value, and information for identifying the temperature value of the first preheating chamber (e.g., information on the input amounts of the main fuel, the auxiliary fuel, and the regenerative fuel, information on the concentration of oxygen, carbon dioxide, and nitrogen oxide in the exhaust gas at the inlet of the kiln, information on the temperature of the air input to the pyro rotor and the kiln after cooling, information on the control variables corresponding to different types of cement manufacturing apparatus 1 including process information such as the pressure of the fan in the cooler, the speed of the conveyor belt, and the speed information of the pyro rotor and the kiln).

[0107] Next, according to one embodiment, the control method may provide guide information including the obtained guidance information (S740).

[0108] 8a and 8b are diagrams illustrating a method for providing a UI according to an embodiment.

[0109] 8a-8b, according to one embodiment, the processor 130 can provide a UI 800. According to one example, the electronic device 100 can include a display (not shown), and the processor 130 can provide the UI 800 via the display (not shown).

[0110] Also, according to one embodiment, the processor 130 may identify temperature history information of the first pre-heating chamber based on the information stored in the memory 120, and provide the UI 800 including graph information corresponding to the temperature history of the first pre-heating chamber based on the identified temperature history information. In this case, according to one example, the processor 130 may provide the UI 800 including graph information for comparing the acquired second predicted temperature information with the temperature history information of the first pre-heating chamber.

[0111] Additionally, in one embodiment, the processor 130 may provide the obtained guidance information along with graph information for comparing the second predicted temperature information with the temperature history information of the first pre-heating chamber.

[0112] In this case, according to one example, the processor 130 may also provide effect information 904 corresponding to a predicted preheat chamber temperature change based on the guidance information, where the effect information 904 includes a contribution value to the temperature change corresponding to each of a plurality of types of fuel.

[0113] In addition, according to an example, the processor 130 may also provide a UI 810 for inputting a target temperature value of the first pre-heating chamber. Here, the guidance information means information on a recommended input ratio corresponding to each input fuel for increasing the ratio of the regenerative fuel input in a state where the temperature of the first pre-heating chamber maintains the target temperature value, and the processor 130 may provide the UI 810 for inputting a target temperature value corresponding to the first pre-heating chamber from the user together with a UI 800 including graph information for comparing the acquired second predicted temperature information with temperature history information of the first pre-heating chamber. The processor 130 may receive information on the target temperature value from the user based on the provided UI 810, and perform an operation based on the received information.

[0114] It should be noted that, according to one embodiment, the processor 130 may provide a UI for providing historical information corresponding to each of a plurality of types of input fuels and a UI 820 for receiving user input corresponding to maximum and minimum values ​​for each input amount of the main or auxiliary fuel. According to one example, the processor 130 may provide the above-mentioned UI 820 via a display (not shown), and when a corresponding user input is received, provide a UI corresponding to FIG. 8b. This will be described in more detail with reference to FIG. 8c.

[0115] 8b, according to one embodiment, the processor 130 may provide a UI for providing historical information corresponding to each of a plurality of types of input fuels and a UI 820 for receiving a user input corresponding to a maximum value and a minimum value for each of the input amounts of the main fuel or the auxiliary fuel. When the UI 820 is provided and a user input is received, the processor 130 may provide a UI 823 corresponding to historical information corresponding to each of the plurality of types of input fuels and a UI 822 corresponding to a user input corresponding to a maximum value and a minimum value for each of the input amounts of the main fuel or the auxiliary fuel. In this case, when the processor 130 receives a user input corresponding to a maximum value and a minimum value for each of the input amounts of the main fuel or the auxiliary fuel via the UI 822 corresponding to a user input corresponding to a maximum value and a minimum value for each of the input amounts of the main fuel or the auxiliary fuel, the processor 130 may input information corresponding to the received user input into the trained neural network model, thereby obtaining guidance information reflecting the received user input.

[0116] According to an embodiment, the process information may include process history information including temperature history information of the first pre-heating chamber and history information of input fuel. According to an example, the processor 130 may identify history information regarding input amounts corresponding to each of a plurality of types of input fuel based on the information stored in the memory 120, and provide a UI 823 including graph information corresponding to the input history of at least one of the main fuel or the auxiliary fuel based on the identified history information.

[0117] In one embodiment, a UI 823 corresponding to historical information corresponding to each of a plurality of types of input fuel and a UI 822 corresponding to user input corresponding to maximum and minimum values ​​for each of the input amounts of main fuel or auxiliary fuel can be provided, but this is not limited to this, and it is of course possible to provide both the above-mentioned UIs 822 and 823.

[0118] 9a, 9b, and 9c are diagrams for explaining a method for providing a UI according to an embodiment.

[0119] Referring to FIG. 9a, according to an embodiment, the processor 130 may provide a UI 900 including guide information. According to an example, the UI 900 may include input amount information 901 corresponding to each of a plurality of types of input fuels currently input. "MCOAL", "PCOAL", "MRDF", and "PRDF" shown in FIG. 9a are examples of the plurality of types of input fuels, but are not limited thereto. Alternatively, according to an example, the UI 900 may include acquired guidance information 903. The guidance information 903 means information on a recommended input ratio corresponding to each input fuel for increasing the ratio of the regenerative fuel input in a state where the temperature of the first preheating chamber is maintained within a predetermined range. In addition, according to an example, the UI 900 may also provide change information 902 corresponding to a difference value between the input amount information 901 corresponding to each of a plurality of types of input fuels currently input and the acquired guidance information 903.

[0120] 9b, according to an embodiment, the processor 130 may provide a UI 910 including information 911 on the pre-heating chamber temperature improvement value after a predetermined time (e.g., 5 minutes) corresponding to the currently input fuel regardless of the guidance information and the pre-heating chamber temperature improvement value after a predetermined time (e.g., 5 minutes) corresponding to the currently input fuel based on the guidance information based on the acquired guidance information. In this case, a UI 910 including the magnitude of the current pre-heating chamber temperature and the magnitude of the pre-heating chamber temperature predicted through a neural network model may be provided. Note that the pre-heating chamber temperature improvement value after a predetermined time (e.g., 5 minutes) corresponding to the currently input fuel means a value for the predicted temperature of the pre-heating chamber after a predetermined time based on the currently input fuel regardless of the guidance information, and the pre-heating chamber temperature improvement value after the guidance information when the fuel is input based on the guidance information means a value for the predicted temperature of the pre-heating chamber after a predetermined time in the case of the fuel input based on the guidance information.

[0121] In addition, according to one example, when fuel is added based on the guidance information, the processor 130 may provide as "effect" information information regarding the improved pre-heating chamber temperature improvement value and the difference value of the pre-heating chamber temperature improvement value after a predetermined time (e.g., 5 minutes) corresponding to the currently added fuel, regardless of the guidance information.

[0122] FIG. 9c is an example of a user interface for providing a control method according to an embodiment of the present disclosure.

[0123] 9c shows an example of a UI element for displaying temperature information of the pre-heating chamber 921. The temperature information may be provided in a graph format reflecting time information as shown in 921, and may be provided in a format that makes it easy to distinguish between actual measurement information and predicted information.

[0124] 9c shows an example of a UI element for providing a function for setting a fuel input amount. A user can set a minimum value and / or a maximum value for the fuel input amount via 922. In this case, the fuel may include a plurality of types, and a user can set the input amount of each of the auxiliary fuel and / or the regenerative fuel via 922.

[0125] 923 in FIG. 9c is an example of a UI element for providing fuel input amount information. The fuel input amount information may be provided in a graph form reflecting time information, and may be provided in a form that makes it easy to distinguish a comparison between an actual value and a guide value. In this case, the fuel may include a plurality of types, and the user may check the input amount of each of the auxiliary fuel and / or the regenerative fuel via 923.

[0126] 9c shows an example of a UI element for providing a function for setting the temperature of the pre-heating chamber, 924. The user can set a target temperature of the pre-heating chamber via 924.

[0127] 9c shows an example of a UI element for providing guidance information, which may include first information on a current fuel input amount, second information on a recommended fuel input amount for increasing the proportion of regenerative fuel input while the temperature of the preheating chamber is maintained within a predetermined range, and change information corresponding to a difference between the first information and the second information.

[0128] In this case, the fuel may include multiple types, and "MCOAL", "PCOAL", "MRDF", and "PRDF" shown in 925 may be examples of multiple types of input fuel, but are not limited thereto. Also, 925 may include information regarding the degree to which each type of fuel contributes to a change in temperature.

[0129] 926 in Fig. 9c is an example of a UI element for providing predicted temperature information. 926 may include information regarding a predicted temperature value of the pre-heating chamber after a predetermined time (5 minutes in the example of Fig. 9c) corresponding to the currently added fuel, information regarding a predicted temperature value of the pre-heating chamber after the time if fuel is added based on the guidance information, and / or information regarding the amount of temperature change.

[0130] FIG. 10 is a diagram illustrating a method for identifying and transmitting control information to a control engine according to an embodiment.

[0131] 10, according to an embodiment, when a user input corresponding to the acquired guide information is received, the control method may identify control information corresponding to the received user input (S1010). Here, the control information refers to a control signal for controlling a control engine, and the control engine refers to an engine for controlling the cement manufacturing apparatus 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 guide information via the user interface (not shown). Then, the processor 130 may identify the control information corresponding to the received user input based on the information stored in the memory 120.

[0132] Next, according to one embodiment, the control method can transmit the identified control information to a control engine (S1020). According to one example, the processor 130 can transmit the identified control information to the control engine via the communication interface 110.

[0133] According to the above example, the temperature of the first pre-heating chamber is predicted by considering the calorific value of the recycled fuel, and based on this, guide information for an efficient operation of the cement manufacturing apparatus 1 can be provided to the user. This makes it easier to implement an environmentally friendly process and a carbon reduction process.

[0134] FIG. 11 is a block diagram showing a detailed configuration of an electronic device according to an embodiment.

[0135] 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. A detailed description of the configurations shown in FIG. 11 that overlap with the configurations shown in FIG. 2 will be omitted.

[0136] The microphone 140 refers to a module that captures sound and converts it into an electric signal, and may be a condenser microphone, a ribbon microphone, a moving coil microphone, a piezoelectric element microphone, a carbon microphone, or a Micro Electro Mechanical System (MEMS) microphone. Also, it may be implemented in an omnidirectional, bidirectional, unidirectional, subcardioid, supercardioid, or hypercardioid type.

[0137] Various embodiments are possible in which the electronic device 100 ′ performs an action in response to a user voice signal received via the microphone 140 .

[0138] As an example, the electronic device 100′ may control the display 160 based on a user voice signal received via the microphone 140. For example, when a user voice signal for displaying the A content is received, the electronic device 100′ may control the display 160 to display the A content.

[0139] 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 operation corresponding to the user voice signal is performed on the external display device, and may transmit the provided control signal to the external display device. Here, the electronic device 100' may store a remote control application for controlling the external display device. Also, the electronic device 100' may transmit the provided control signal to the external display device using at least one communication method of Bluetooth, Wi-Fi, or infrared. For example, when a user voice signal for displaying content A is received, the electronic device 100' may transmit a control signal to the external display device for controlling content A to be displayed on the external display device. Here, the electronic device 100' refers to various terminal devices on which a remote control application can be installed, such as a smartphone, an AI speaker, etc.

[0140] As yet 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 via the microphone 140. Specifically, the electronic device 100' may transmit a control signal to the remote control device for controlling the external display device so that an operation corresponding to the user voice signal is performed on the external display device. Also, the remote control device may 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' may transmit a control signal to the remote control device for controlling content A to be displayed on the external display device, and the remote control device may transmit the received control signal to the external display device.

[0141] The speaker 150 comprises a tweeter for reproducing high tones, a midrange for reproducing mid tones, a woofer for reproducing low tones, a subwoofer for reproducing extremely low tones, an enclosure for controlling resonance, and a crossover network that divides the electrical signal frequencies input to the speaker into bands.

[0142] The speaker 150 can output an audio signal to the outside of the electronic device 100'. The speaker 150 can output multimedia playback, recording playback, various notification sounds, 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 can provide acquired information, information processed or produced based on the acquired information, a response result or an operation result to a user's voice, etc. in the form of voice.

[0143] 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, the display may be implemented as various types of displays such as a liquid crystal display (LCD), an organic light emitting diode (OLED) display, a light emitting diode (LED), a micro LED, a mini LED, a plasma display panel (PDP), a quantum dot (QD) display, and quantum dot light-emitting diodes (QLED). The display 160 may also include a driving circuit and a backlight unit implemented as an a-si TFT, a low temperature poly silicon (LTPS) TFT, an organic TFT (OTFT), and the like. The display 160 may also be implemented as a touch screen combined with a touch sensor, a flexible display, a rollable display, a 3D display, a display in which a plurality of display modules are physically connected, and the like. The processor 130 may control the display 160 to output an output image acquired according to the various embodiments described above. Here, the output image may be a high-resolution image of 4K or 8K or higher.

[0144] 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 images or content stored in the electronic device 100' to the external display device. Specifically, the electronic device 100' may transmit images 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.

[0145] Here, the external display device may be connected to the electronic device 100' via a communication interface 110 or an input / output interface (not shown). For example, the electronic device 100' may not include a display like a set top box (STB). Also, the electronic device 100' may only include a small display capable of displaying 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 in a wired or wireless manner, or may transmit the image or content to the external display device via the input / output interface (not shown).

[0146] The user interface 170 is a configuration for allowing the electronic device 100′ to interact with a 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, or a speaker, but is not limited thereto.

[0147] 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 sense an operating state of the electronic device 100' and convert the measured or sensed 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 an object onto the image sensor, and an image sensor that can sense visible light or other optical signals. Here, the image sensor may include a 2D pixel array divided into a plurality of pixels.

[0148] According to the above example, the electronic device 100' can predict the calorific value of the regenerated fuel using the trained neural network model, and can predict the temperature of the first pre-heating chamber based on the predicted calorific value. This allows the electronic device 100' to provide guide information to the user based on the accurately predicted temperature of the pre-heating chamber, thereby enabling an environmentally friendly and efficient process.

[0149] The methods according to the various embodiments of the present disclosure may be implemented in the form of an application that can be installed in a conventional electronic device. Alternatively, the methods according to the various embodiments of the present disclosure may be implemented using a deep learning-based trained neural network (or a deep trained neural network), i.e., a trained network model. The methods according to the various embodiments of the present disclosure may be implemented only as a software upgrade or hardware upgrade for a conventional electronic device. The various embodiments of the present disclosure may be implemented via an embedded server provided in an electronic device or an external server of the electronic device.

[0150] According to an embodiment of the present disclosure, the various embodiments described above may be embodied in software including instructions stored in a machine-readable storage medium. The machine is a device capable of calling up the stored instructions from the storage medium and operating according to the called instructions, and may include a display device (e.g., display device (A)) according to the disclosed embodiments. When instructions are executed by a processor, the processor may perform a function corresponding to the instructions directly or using other components under the control of the processor. The instructions may include code provided or executed by a compiler or an 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 and is tangible, and does not distinguish between data being stored semi-permanently or temporarily in the storage medium.

[0151] According to one embodiment, the methods according to the various embodiments described above may be provided in a computer program product. The computer program product may be traded as a commodity between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read only memory (CD-ROM)) or online via an application store (e.g., Play Store™). In the case 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 server, or a relay server.

[0152] Also, each of the components (e.g., modules or programs) according to the various embodiments described above may be composed of one or more entities, and some of the subcomponents described above may be omitted, or other subcomponents may be further included in the various embodiments. Alternatively or additionally, some components (e.g., modules or programs) may be integrated into one entity and perform the same or similar functions as those performed by the respective components before being integrated. According to various embodiments, operations performed by modules, programs, or other components may be performed sequentially, in parallel, iteratively, or heuristically, or at least some operations may be performed in other orders, omitted, or other operations may be added.

[0153] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary knowledge in the technical field to which the disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical ideas and perspectives of the present disclosure. [Explanation of symbols]

[0154] 100 Electronic equipment 110 Communication Interface 120 Memory 130 One or more processors

Claims

1. An electronic device for implementing a temperature prediction and control system, comprising: A communication interface; a memory in which the first trained neural network model and the second trained neural network model are stored; When process information including input fuel information of the cement manufacturing apparatus is received via the communication interface, the process information is pre-processed; inputting the pre-processed process information into the second trained neural network model; and obtaining first predicted temperature information output from the first trained neural network model and error information relating to a measured temperature of a first preheating chamber in the cement manufacturing apparatus; Identifying predicted calorific value information of a first regenerated fuel among the input fuels based on the acquired error information and the input fuel information; inputting updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber; and one or more processors that provide guide information including the obtained second predicted temperature information.

2. The first trained neural network model When input fuel information including information on input amounts corresponding to different types of input fuels including the first regenerated fuel and calorific value information corresponding to each input fuel is input, the input fuel information is learned to output predicted temperature information of the first preheating chamber, The second trained neural network model 2. The electronic device of claim 1, wherein when the pre-processed process information including the input fuel information and process status information is input, the electronic device is trained to output error information regarding the predicted temperature information output from the first trained neural network model and the measured temperature information of the first pre-heating chamber.

3. a user interface; The input fuel information is information regarding input amounts corresponding to different types of input fuels, including at least one of the first regenerating fuel, the main fuel, and the auxiliary fuel, and calorific value information corresponding to each input fuel; The one or more processors: receiving a target temperature value for a first preheat chamber in the cement manufacturing apparatus via the user interface; Identifying, based on the obtained second predicted temperature information and the received target temperature value, an input amount corresponding to each of the different types of input fuel for the temperature value of the first pre-heating chamber to reach the target temperature value; Obtaining guide information corresponding to the identified input amount; The electronic device according to claim 1 , wherein the electronic device provides a UI including the acquired guide information.

4. The one or more processors: Identifying sub-fuel input information in which the input amount corresponding to each of the input fuels included in the input fuel information has been changed; The sub-fuel input information is input to the first trained neural network model to obtain second sub-predicted temperature information; obtaining guidance information regarding an input fuel using the obtained second predicted temperature information and the second sub-predicted temperature information; The electronic device according to claim 3 , wherein the electronic device provides guide information including the obtained guidance information.

5. The process information of the pretreatment is temperature history information of the first pre-heating chamber and history information of the input fuel; The one or more processors: The electronic device of claim 3 , further comprising: a UI including the received temperature history information of the first pre-heating chamber, the input fuel history information, and the obtained second predicted temperature information.

6. The one or more processors: The electronic device according to claim 1 , further comprising: identifying predicted calorific value information of the first regenerated fuel based on the acquired error information and information on an input amount of the first regenerated fuel included in the input fuel information.

7. a user interface; The one or more processors: when a user input corresponding to the obtained guide information is received via the user interface, identifying control information corresponding to the received user input; The electronic device of claim 1 , further comprising: a communication interface configured to transmit the identified control information to a control engine.

8. A method for controlling an electronic device to realize a temperature prediction and control system, comprising: When process information including input fuel information of the cement manufacturing apparatus is received, pre-processing the received process information; inputting the pre-processed process information into a second trained neural network model, and obtaining first predicted temperature information output from the first trained neural network model and error information related to a measured temperature of a first preheating chamber in the cement manufacturing apparatus; identifying predicted calorific value information of a first regenerated fuel among the input fuels based on the acquired error information and the input fuel information; inputting updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber; providing guide information including the acquired second predicted temperature information.

9. The first trained neural network model When input fuel information including information on input amounts corresponding to different types of input fuels including the first regenerated fuel and calorific value information corresponding to each input fuel is input, the input fuel information is learned to output predicted temperature information of the first preheating chamber, The second trained neural network model 9. The control method according to claim 8, wherein when the pre-processed process information including the input fuel information and the process status information is input, the method is trained to output error information regarding the predicted temperature information output from the first trained neural network model and the measured temperature information of the first pre-heating chamber.

10. The input fuel information is information regarding input amounts corresponding to different types of input fuels, including at least one of the first regenerating fuel, the main fuel, and the auxiliary fuel, and calorific value information corresponding to each input fuel; The step of providing the guide information includes: receiving a target temperature value for a first preheat chamber within the cement manufacturing apparatus; identifying, based on the obtained second predicted temperature information and the received target temperature value, input amounts corresponding to each of the different types of input fuel for the temperature value of the first pre-heating chamber to reach the target temperature value; obtaining guide information corresponding to the identified input amount; The control method includes: The method of claim 8 , further comprising: providing a UI including the obtained guide information.

11. The step of acquiring guide information includes: identifying sub-fuel input information in which the input amount corresponding to each of the input fuels included in the input fuel information has been changed; inputting the sub-fuel input information into the first trained neural network model to obtain second sub-predicted temperature information; obtaining guidance information regarding an input fuel by using the obtained second predicted temperature information and the second sub-predicted temperature information; The control method according to claim 10 , further comprising: providing guide information including the obtained guidance information.

12. The process information of the pretreatment is temperature history information of the first pre-heating chamber and history information of the input fuel; The step of providing the UI includes: The control method of claim 10 , further comprising providing a UI including the received temperature history information of the first pre-heating chamber, the history information of the input fuel, and the obtained second predicted temperature information.

13. The step of identifying predicted heat quantity information comprises: The control method according to claim 8 , further comprising identifying predicted calorific value information of the first regenerated fuel based on the acquired error information and information on an input amount of the first regenerated fuel included in the input fuel information.

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

15. 1. A non-transitory computer-readable recording medium storing computer instructions that, when executed by a processor of an electronic device for implementing a temperature prediction and control system, cause the electronic device to perform operations, the operations including: When process information including input fuel information of the cement manufacturing apparatus is received, pre-processing the received process information; inputting the pre-processed process information into a second trained neural network model, and obtaining first predicted temperature information output from the first trained neural network model and error information related to a measured temperature of a first preheating chamber in the cement manufacturing apparatus; identifying predicted calorific value information of a first regenerated fuel among the input fuels based on the acquired error information and the input fuel information; inputting updated fuel input information based on the identified predicted heat quantity information into the first trained neural network model to obtain second predicted temperature information of the first pre-heating chamber; and providing guide information including the obtained second predicted temperature information.

Images