Method for calculating optimal temperature of heating furnace, device for

Abstract

The method for calculating the optimal temperature of the heating furnace comprises the following steps that a target physical property value, input by an operator, of a material is obtained; acquiring a plurality of appropriate candidate temperatures of the heating furnace from the first input data by using the trained optimal temperature model; acquiring an expected physical property value of the material from the second input data by using the trained physical property prediction model; comparing the target physical property value with an expected physical property value calculated through a trained physical property prediction model, sampling a plurality of proper candidate temperatures, and obtaining at least one sampled proper candidate temperature; acquiring heat information when the heating furnace is operated at the sampled appropriate candidate temperatures, comparing the heat information and filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature; performing a predetermined calculation on at least one appropriate temperature to obtain an optimal temperature; and transmitting a request for instructing to set the acquired optimal temperature as a set temperature value of the heating furnace.

Description

Technical Field

[0001] The present disclosure relates to a technology for optimizing the operation of a heating furnace. Specifically, the present disclosure relates to a technology for calculating the optimal temperature for operating a heating furnace using artificial intelligence. Background Art

[0002] With the development of artificial intelligence technology, artificial intelligence technology is being widely used in various industrial fields. In particular, the research on using artificial intelligence models to optimize the operation of steel product production processes has attracted much attention recently.

[0003] In order to produce steel products of target quality, the physical properties of the steel plate must be changed by performing appropriate heat treatment in a heating furnace. However, the physical properties of the steel plate do not change linearly with the heat treatment, but show a nonlinear relationship of sharp change when the heat treatment is performed above the appropriate temperature, and the effect of the heat treatment temperature on the change of the physical properties varies with various reasons such as the composition of the steel plate, the thickness of the steel plate or the operating environment. Therefore, there is a limitation that it is difficult to accurately handle the heat treatment that causes the change of the physical properties of the steel plate. In addition, since the heat treatment depends on the experience of the operator, even if the same steel product is produced, the furnace temperature and operating conditions set by different operators will be different, so there are limitations in ensuring the stability of the quality of the steel product. In order to solve these problems, although the technology of optimizing the steel process has been developed, the existing steel process optimization technology is only used to stably control the steel process, and it is impossible to calculate the optimal operating temperature of the heating furnace, which is a limitation.

[0004] Therefore, it is necessary to develop a method for calculating the optimal temperature of a heating furnace and a device for executing the method, so as to improve thermal efficiency while ensuring the stability of the quality of steel products. Summary of the invention

[0005] Problem that the invention aims to solve

[0006] One problem to be solved by the present disclosure is to provide a method of calculating an optimal temperature of a heating furnace and an electronic device for executing the method, so as to reduce the heat usage of the heating furnace while achieving a target quality.

[0007] Problems to be solved by the present disclosure are not limited to the above-mentioned problems, and those skilled in the art can clearly understand unmentioned problems from the present specification and the accompanying drawings.

[0008] Means used to solve problems

[0009] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace may include: obtaining a target physical property value of a material input by an operator; obtaining a plurality of suitable candidate temperatures of the heating furnace from first input data using a trained optimal temperature model, wherein the first input data includes the thickness of the material to be heated in the heating furnace, the steel type of the material, and the temperature of the heating furnace. The invention relates to a method for predicting a physical property of a material in a heating furnace, comprising: taking at least one of the suitable candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel grade of the material and the operating speed of the heating furnace as variables; a step of obtaining the expected physical property value of the material from the second input data by using the trained physical property prediction model, wherein the second input data includes at least one of the suitable candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel grade of the material and the operating speed of the heating furnace as variables; a step of comparing the target physical property value with the expected physical property value calculated by the trained physical property prediction model, sampling a plurality of the suitable candidate temperatures to obtain at least one sampled suitable candidate temperature; a step of obtaining heat information when the heating furnace is operated at the sampled suitable candidate temperature, comparing the heat information and filtering the sampled suitable candidate temperatures to obtain at least one suitable temperature; a step of performing a predetermined calculation on the at least one suitable temperature to obtain an optimal temperature; and a step of sending a request for indicating that the obtained optimal temperature is set as a set temperature value of the heating furnace.

[0010] The electronic device according to an embodiment of the present disclosure may include: a transceiver, which obtains a target physical property value of a material input by an operator; and a processor, wherein the processor is configured to: use a trained optimal temperature model to obtain a plurality of suitable candidate temperatures of the heating furnace from first input data, wherein the first input data includes the thickness of the material to be heated in the heating furnace, the steel type of the material, and the temperature of the heating furnace. The method comprises the steps of: using the trained physical property prediction model to obtain the expected physical property value of the material from the second input data, wherein the second input data includes the appropriate candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel grade of the material and the operating speed of the heating furnace as variables; comparing the target physical property value with the expected physical property value calculated by the trained physical property prediction model, sampling a plurality of the appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature; obtaining heat information when the heating furnace is operated at the sampled appropriate candidate temperature, comparing the heat information and filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature; performing a predetermined calculation on the at least one appropriate temperature to obtain an optimal temperature; and sending a request for instructing to set the obtained optimal temperature as the set temperature value of the heating furnace.

[0011] The means for solving the problems of the present disclosure are not limited to the above-mentioned solutions, and those skilled in the art can clearly understand the solutions not mentioned from this specification and the drawings.

[0012] Effects of the Invention

[0013] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effects: by using an optimal temperature model and a physical property prediction model, the optimal operating temperature of the heating furnace can be calculated while achieving the target physical property value.

[0014] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effect: the optimal temperature is calculated by utilizing thermal information when the heating furnace is operated at a sampled appropriate candidate temperature through an optimal temperature model and a physical property prediction model, thereby improving the thermal efficiency of the heating furnace while achieving the target physical property value of the product.

[0015] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effects: the optimal temperature of the heating furnace is automatically calculated by considering the target physical property values ​​of the product through an artificial intelligence model, thereby controlling the operating temperature of the heating furnace to stably produce products with target physical property values.

[0016] The effects of the present disclosure are not limited to the above-mentioned effects, and those skilled in the art can clearly understand unmentioned effects from the present specification and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of a heating furnace operation optimization system according to an embodiment of the present disclosure.

[0018] Figure 2 1 is a diagram for explaining a heating furnace operation optimization system according to an embodiment of the present disclosure.

[0019] Figure 3 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure.

[0020] Figure 4 is a sequence diagram illustrating a method for calculating an optimal temperature of a heating furnace according to an embodiment of the present disclosure.

[0021] Figure 5 The diagram is used to explain a method for training an optimal temperature model according to an embodiment of the present disclosure and a form of calculating an appropriate candidate temperature using the trained optimal temperature model.

[0022] Figure 6It is a diagram for explaining a training method of a physical property prediction model according to an embodiment of the present disclosure and a form of calculating expected physical property values ​​using the trained physical property prediction model.

[0023] Figure 7 FIG. 1 is a diagram for explaining a method of calculating an optimal temperature from appropriate candidate temperatures according to an embodiment of the present disclosure.

[0024] Figure 8 This is a diagram for explaining one form of a user interface (User Interface).

[0025] Fig. 9 This is a diagram for explaining one form of a user interface (User Interface).

[0026] Fig.10 This is a diagram for explaining one form of a user interface (User Interface).

[0027] Fig.11 This is a diagram for explaining one form of a user interface (User Interface). DETAILED DESCRIPTION

[0028] The above-mentioned purpose, features and advantages of the present disclosure will become more apparent through the following detailed description in conjunction with the accompanying drawings. However, the present disclosure can be modified in various ways and has various embodiments. Specific embodiments are described in detail below in conjunction with the accompanying drawings.

[0029] In principle, the same reference numerals throughout the specification refer to the same constituent elements. In addition, constituent elements with the same functions within the scope of the same concept shown in the drawings of each embodiment are described using the same reference numerals, and repeated descriptions thereof will be omitted.

[0030] If it is determined that the detailed description of known functions or configurations related to the present disclosure may unnecessarily obscure the gist of the present disclosure, the detailed description will be omitted. In addition, the numbers (e.g., first, second, etc.) used in the description of this specification are merely identifiers for distinguishing one constituent element from another constituent element.

[0031] In addition, the suffixes "module" and "section" of constituent elements used in the following embodiments are given or used interchangeably only for convenience in writing the specification, and they themselves do not have different meanings or roles.

[0032] In the following embodiments, a singular expression includes a plural expression unless the context clearly dictates otherwise.

[0033] In the following embodiments, terms such as “including” or “having” indicate that the features or constituent elements described in the specification exist, and do not exclude the possibility that one or more other features or constituent elements may be added.

[0034] In the drawings, the size of the constituent elements may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each constituent shown in the drawings are arbitrarily shown for convenience of explanation, and the present disclosure is not necessarily limited to the contents shown.

[0035] If the embodiment can be implemented differently, the order of a specific process can be performed differently from the order described. For example, two processes described in succession can be performed substantially at the same time, or can be performed in the order opposite to the order described.

[0036] In the following embodiments, when components are connected to each other, this includes not only a case where the components are directly connected but also a case where the components are indirectly connected with the components interposed therebetween.

[0037] For example, in this specification, when it is mentioned that components or the like are electrically connected, this includes not only a case where the components or the like are directly electrically connected but also a case where the components or the like are indirectly electrically connected with components or the like interposed therebetween.

[0038] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace may include: obtaining a target physical property value of a material input by an operator; obtaining a plurality of suitable candidate temperatures of the heating furnace from first input data using a trained optimal temperature model, wherein the first input data includes the thickness of the material to be heated in the heating furnace, the steel type of the material, and the temperature of the heating furnace. The method comprises the steps of: using the trained physical property prediction model to obtain the expected physical property value of the material from the second input data, wherein the second input data includes the suitable candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel grade of the material and the operating speed of the heating furnace as variables; comparing the target physical property value with the expected physical property value calculated by the trained physical property prediction model, and sampling a plurality of the suitable candidate temperatures to obtain at least one sampled suitable candidate temperature; obtaining thermal information when the heating furnace is operated at the sampled suitable candidate temperature, comparing the thermal information and filtering the sampled suitable candidate temperatures to obtain at least one suitable temperature; calculating the optimal temperature based on the appropriate temperature; and sending a request for instructing to set the calculated optimal temperature as the set temperature value of the heating furnace.

[0039] According to one embodiment of the present disclosure, the step of sampling a plurality of the appropriate candidate temperatures to obtain a plurality of sampled appropriate candidate temperatures may also include: comparing the target physical property value with the expected physical property value, and sorting the plurality of the appropriate candidate temperatures in order of the difference between the target physical property value and the expected physical property value from small to large; and based on the sorting result, determining a plurality of appropriate candidate temperatures that fall within a predetermined order as the sampled appropriate candidate temperatures.

[0040] According to one embodiment of the present disclosure, the step of sampling a plurality of the appropriate candidate temperatures to obtain a plurality of sampled appropriate candidate temperatures may also include: a step of comparing the target physical property value with the expected physical property value, and calculating the difference between the target physical property value and the expected physical property value; and a step of determining the corresponding plurality of appropriate candidate temperatures whose calculated differences are within a predetermined value as the sampled appropriate candidate temperatures.

[0041] According to one embodiment of the present disclosure, the step of filtering the sampled appropriate candidate temperatures to obtain multiple appropriate temperatures may also include: the step of sorting the sampled appropriate candidate temperatures in order of heat from small to large according to the heat information; and the step of determining the multiple sampled appropriate candidate temperatures that fall within a predetermined order as the multiple appropriate temperatures based on the sorting result.

[0042] According to an embodiment of the present disclosure, the step of calculating the optimal temperature based on the appropriate temperature may further include: calculating an average value of the appropriate temperatures as the optimal temperature.

[0043] According to one embodiment of the present disclosure, the optimal temperature model can be configured as: training based on first learning data related to at least one of the thickness of the material, the steel type of the material, the operating speed of the heating furnace and / or the target physical property value, and a learning data set consisting of the operating temperature of the heating furnace corresponding to the first learning data; training is performed by updating the parameters of the optimal temperature model based on the first learning data so as to output a value that is approximate to the operating temperature of the heating furnace.

[0044] According to one embodiment of the present disclosure, the physical property prediction model can be configured to: be trained based on second learning data related to at least one of the thickness of the material, the steel type of the material, the operating speed of the heating furnace and the operating temperature of the heating furnace, and a learning data set consisting of physical property information when the material is heat treated under the operating conditions corresponding to the second learning data; and be trained by updating the parameters of the physical property prediction model based on the second learning data so as to output a value that is approximate to the physical property information.

[0045] According to one embodiment of the present disclosure, the target physical property value and the expected physical property value may be related to at least one of the tensile strength, yield strength, hardness, and elongation of the material subjected to heat treatment in the heating furnace.

[0046] According to an embodiment of the present disclosure, there may be provided a computer-readable recording medium having recorded thereon a program for executing the method of calculating an optimal temperature of a heating furnace.

[0047] According to an embodiment of the present disclosure, the electronic device may include: a transceiver unit, which obtains the target physical property value of the material input by the operator; and a processor, which uses a trained optimal temperature model to obtain multiple appropriate candidate temperatures of the heating furnace from the first input data, and uses a trained physical property prediction model to obtain the expected physical property value of the material from the second input data, and compares the target physical property value with the expected physical property value calculated by the trained physical property prediction model, samples multiple appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature, and obtains thermal information when the heating furnace is operated at the sampled appropriate candidate temperature, compares the thermal information and filters the sampled appropriate candidate temperatures to obtain at least one appropriate temperature, calculates the optimal temperature based on the appropriate temperature, and sends a request to instruct to set the calculated optimal temperature as the set temperature value of the heating furnace. The first input data includes at least one of the thickness of the material to be heated in the heating furnace, the steel grade of the material, the operating speed of the heating furnace and the target physical property value as variables, and the second input data includes at least one of the appropriate candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel grade of the material and the operating speed of the heating furnace as variables.

[0048] Refer to the following Figures 1 to 7 , describing a method for calculating the optimal temperature of a heating furnace according to an embodiment of the present disclosure, an electronic device (or server, hereinafter referred to as an electronic device) for executing the method, and / or a heating furnace operation optimization system.

[0049] Figure 1 is a schematic diagram of a heating furnace operation optimization system 10 according to an embodiment of the present disclosure. Figure 2 1 is a diagram for explaining a heating furnace operation optimization system 10 according to an embodiment of the present disclosure.

[0050] According to an embodiment of the present disclosure, a heating furnace operation optimization system 10 may include a heating furnace 100 (Furnace), a heating furnace controller 200 , a client terminal 300 and / or an electronic device 1000 .

[0051] The heating furnace 100 according to an embodiment of the present disclosure can send the operation data to any external device including the heating furnace operation database and / or the electronic device 1000 or to any external server through any transceiver. The operation data may refer to any data related to the operation of the heating furnace, which covers the operation conditions of the heating furnace including the thickness of the material, the steel type of the material, the operation speed of the heating furnace, the operation temperature of the heating furnace, and the physical property values ​​of the products manufactured according to the operation conditions. In addition, the heating furnace 100 sets the optimal temperature calculated by the electronic device 1000 as the set temperature value, and performs heat treatment on the material (e.g., steel).

[0052] According to an embodiment of the present disclosure, the electronic device 1000 can perform an action of calculating a plurality of appropriate candidate temperatures using a trained optimal temperature model. In addition, the electronic device 1000 can perform an action of calculating the expected physical property values ​​of the product when the heating furnace is operated based on the appropriate candidate temperatures, wherein the appropriate candidate temperatures are calculated using the trained physical property prediction model. In addition, the electronic device 1000 can perform an action of calculating the optimal temperature based on the calculated expected physical property values ​​and the target physical property values. At this time, the electronic device 1000 can perform an action of sending a request for indicating that the operating temperature of the heating furnace 100 is controlled based on the calculated optimal temperature to the heating furnace controller 200 through the transceiver 1100. Alternatively, the electronic device 1000 can perform an action of sending the calculated optimal temperature information, predicted physical property information, and decision basis to the client terminal 300 through the transceiver 1100.

[0053] The heating furnace controller 200 according to an embodiment of the present disclosure may receive a request for instructing to control the operating temperature of the heating furnace 100 from the electronic device 1000 through any transceiver. At this time, the heating furnace controller 200 may set the calculated optimal temperature as the set temperature value of the heating furnace 100, and automatically control the operating temperature of the heating furnace 100 to the set temperature value based on the operating temperature of the heating furnace 100 and the set temperature value. On the other hand, in Figure 1 and Figure 2, the heating furnace controller 200 is described as a device separate from the heating furnace 100, the client terminal 300, and the electronic device 1000. However, this is for the convenience of description, and the heating furnace controller 200 may be configured integrally with the heating furnace 100, the client terminal 300, and / or the electronic device 1000. In addition, the heating furnace controller 200 may be provided in the form of a program that can be executed on the heating furnace 100, the client terminal 300, and / or the electronic device 1000.

[0054] According to an embodiment of the present disclosure, the client terminal 300 may receive the calculated optimal temperature information from the electronic device 1000 through any transceiver. At this time, the client terminal 300 may receive a user's request for instructing to set the calculated optimal temperature information as the set temperature value of the heating furnace 100 through any input unit (e.g., a mouse, a keyboard, a touch pad, etc.). At this time, the client terminal 300 may send a message for instructing to control the operating temperature of the heating furnace 100 to be set to the set temperature value (e.g., set to the optimal temperature) through any transceiver based on the user's request. Figure 2 On the other hand, the client terminal 300 can receive the calculated optimal temperature information, predicted physical property information and / or decision basis through any transceiver, and provide the received information to the user through a user interface.

[0055] Refer again Figure 1 According to an embodiment of the present disclosure, the electronic device 1000 may include a transceiver unit 1100 , a memory 1200 , and a processor 1300 .

[0056] The transceiver unit 1100 of the electronic device 1000 can communicate with any external device or external server. As an example, the electronic device 1000 can obtain operation data from the heating furnace 100 through the transceiver unit 1100. Wherein, as described above, the operation data may refer to any data related to the operation of the heating furnace, which covers the operating conditions of the heating furnace including the thickness of the material, the steel type of the material, the operating speed of the heating furnace, the operating temperature of the heating furnace, and the physical property values ​​of the products manufactured according to the operating conditions. As an example, the electronic device 1000 can receive the execution data for appropriately executing the trained optimal temperature model including the structural information, layer information, calculation information and / or parameter information of the trained optimal temperature model through the transceiver unit 1100. As an example, the electronic device 1000 can receive the execution data for appropriately executing the trained physical property prediction model including the structural information, layer information, calculation information and / or parameter information of the trained physical property prediction model through the transceiver unit 1100. As an example, the electronic device 1000 can send any analysis information including the calculated optimal temperature information, predicted physical property information and / or decision basis to any external device or any external server including the client terminal 300 through the transceiver unit 1100. As an example, the electronic device 1000 can send a request for instructing to set the calculated optimal temperature as the set temperature value of the heating furnace to any external device or any external server including the heating furnace controller 200 through the transceiver unit 1100.

[0057] The electronic device 1000 can be connected to the network through the transceiver 1100, and send and receive various data. The transceiver 1100 can mainly include a wired type and a wireless type. Since the wired type and the wireless type have their own advantages and disadvantages, in some cases, the electronic device 1000 can be provided with a wired type and a wireless type at the same time. Among them, in the case of the wireless type, the communication method of the wireless local area network (Wireless Local Area Network, WLAN) series such as Wi-Fi can be mainly utilized. Alternatively, in the case of the wireless type, cellular communication, such as LTE or 5G communication methods, can be used. However, the wireless communication protocol is not limited to the above examples, and any appropriate wireless type of communication method can be used. In the case of the wired type, the local area network (Local Area Network, LAN) or the universal serial bus (Universal Serial Bus, USB) communication is a representative example, but other methods are also possible.

[0058] The memory 1200 of the electronic device 1000 can store various types of information. Various data can be temporarily or semi-permanently stored in the memory 1200. Examples of the memory 1200 may include a hard disk drive (HDD), a solid state drive (SSD), a flash memory (flash memory), a read-only memory (ROM), a random access memory (RAM), etc. The memory 1200 may be provided in a manner embedded in the electronic device 1000 or in a detachable manner. Various data required for the action of the electronic device 1000 may be stored in the memory 1200, including an operating system (OS, Operating System) for driving the electronic device 1000 or a program for causing each configuration of the electronic device 1000 to act.

[0059] The processor 1300 can control the overall action of the electronic device 1000. For example, the processor 1300 can control the overall action of the electronic device 1000, which includes the action of obtaining the target physical property value described later, the action of obtaining multiple suitable candidate temperatures of the heating furnace using the trained optimal temperature model, the action of obtaining the expected physical property value of the material using the trained physical property prediction model, the action of obtaining the sampled suitable candidate temperature by sampling multiple suitable candidate temperatures, the action of obtaining the suitable temperature according to the heat information when the heating furnace is operated at the sampled suitable candidate temperature, and / or the action of calculating the optimal temperature based on the suitable temperature, etc. Specifically, the processor 1300 can load and execute the program for the overall action of the electronic device 1000 from the memory 1200. The processor 1300 can be implemented as an application processor (AP), a central processing unit (CPU), a microcontroller unit (MCU) or a similar device according to hardware, software or a combination thereof. At this time, in terms of hardware, it can be provided in the form of an electronic circuit that processes electrical signals and performs control functions, and in terms of software, it can be provided in the form of a program or code that drives the hardware circuit.

[0060] Figure 3 is a diagram illustrating an operation of the electronic device 1000 according to an embodiment of the present disclosure.

[0061] According to an embodiment of the present disclosure, the electronic device 1000 can obtain the target property value through the transceiver 1100. More specifically, the electronic device 1000 can obtain the target property value related to the target property information of the manufactured product input by the operator of the heating furnace 100 through the transceiver 1100. The target property value can be a value related to any target property of the heat-treated material (or the heat-treated product), including the tensile strength, yield strength, hardness and / or elongation of the material heat-treated by the heating furnace.

[0062] According to an embodiment of the present disclosure, the electronic device 1000 can obtain the execution data of the trained optimal temperature model through the transceiver unit 1100. The execution data of the trained optimal temperature model may include any data for appropriately executing the trained optimal temperature model, including structural information, layer information, calculation information and / or parameter information of the trained optimal temperature model.

[0063] According to an embodiment of the present disclosure, the electronic device 1000 can use the trained optimal temperature model to obtain multiple suitable candidate temperatures of the heating furnace. More specifically, the electronic device 1000 can input the first input data into the input layer of the trained optimal temperature model, and obtain multiple suitable candidate temperatures through the output layer of the trained optimal temperature model. Among them, the first input data can include the thickness of the material to be heated in the heating furnace, the steel grade of the material, the operating speed of the heating furnace, the target physical property value and / or their combination as variables. On the other hand, the optimal temperature model can be trained based on the first learning data related to the thickness of the material, the steel grade of the material, the operating speed of the heating furnace and / or the target physical property value obtained from the heating furnace operation database and the learning data set consisting of the actual operating temperature of the heating furnace corresponding to the first learning data. More specifically, the optimal temperature model can be configured to be trained by updating the parameters (or weights) of the optimal temperature model based on the first learning data so as to output a value that is close to the actual operating temperature corresponding to the first learning data. Therefore, the trained optimal temperature model can be configured to calculate an appropriate candidate temperature corresponding to the actual operating temperature of the heating furnace based on the first input data corresponding to the variables of the first learning data. Figure 5 The training method and / or execution (inference) modality of the optimal temperature model is described in more detail.

[0064] According to an embodiment of the present disclosure, the electronic device 1000 can obtain the execution data of the trained physical property prediction model through the transceiver unit 1100. The execution data of the trained physical property prediction model may include any data for appropriately executing the trained physical property prediction model, including structural information, layer information, calculation information and / or parameter information of the trained physical property prediction model.

[0065] According to an embodiment of the present disclosure, the electronic device 100 can obtain the expected physical property value of the material using the trained physical property prediction model. Specifically, the electronic device 1000 can input the second input data into the input layer of the trained physical property prediction model, and obtain the expected physical property value of the material through the output layer of the trained physical property prediction model. Among them, the second input data may include the appropriate candidate temperature calculated by the trained optimal temperature model, the thickness of the material, the steel type of the material, the operating speed of the heating furnace and / or their combination as variables. On the other hand, the physical property prediction model can be trained based on the second learning data related to the thickness of the material, the steel type of the material, the operating speed and / or the operating temperature of the heating furnace obtained from the heating furnace operation database, and the physical property information (such as the tensile strength, yield strength, hardness and / or elongation of the material) when the material is heat treated under the operating conditions corresponding to the second learning data. More specifically, the physical property prediction model can be configured to be trained by updating the parameters (or weights) of the physical property prediction model based on the second learning data so as to output a value that approximates the physical property information when the material is heat treated under the operating conditions corresponding to the second learning data. Therefore, the trained physical property prediction model can be configured to calculate the expected physical property value corresponding to the physical property information when the material is heat treated under the operating conditions corresponding to the second input data based on the second input data corresponding to the variables of the second learning data. Figure 6 The training method and / or execution (inference) form of the physical property prediction model are described in more detail.

[0066] According to an embodiment of the present disclosure, the electronic device 1000 may perform an action of acquiring a sampled appropriate candidate temperature by sampling a plurality of appropriate candidate temperatures. Specifically, the electronic device 1000 may be configured to obtain at least one sampled appropriate candidate temperature by comparing the target property value input by the operator with the expected property value calculated by the trained property prediction model, and sampling a plurality of appropriate candidate temperatures calculated by the trained optimal temperature model. As an example, the electronic device 1000 may compare the target property value with the expected property value, and sort the plurality of appropriate candidate temperatures in the order of the difference between the target property value and the expected property value from small to large. At this time, the electronic device 1000 may be configured to determine the plurality of appropriate candidate temperatures corresponding to the expected property value falling within a predetermined order as the sampled appropriate candidate temperature based on the sorting result. As an example, the electronic device 1000 may compare the target property value with the expected property value to calculate the difference between the target property value and the expected property value. At this time, the electronic device 1000 may be configured to determine a plurality of suitable candidate temperatures corresponding to the expected physical property values ​​whose calculated differences fall within a predetermined value as suitable candidate temperatures for sampling. Figure 7 The contents of sampling a plurality of suitable candidate temperatures are described in more detail.

[0067] According to one embodiment, the electronic device 1000 can perform an action of obtaining multiple appropriate temperatures based on the heat information when the heating furnace is operated at the sampled appropriate candidate temperature. Specifically, the electronic device 1000 can be configured to obtain each heat information when the heating furnace is operated at each sampled appropriate candidate temperature, compare each heat information, and filter the multiple sampled appropriate candidate temperatures to obtain at least one appropriate temperature. As an example, the electronic device 1000 can sort the multiple sampled appropriate candidate temperatures in order from small to large heat based on the heat information. At this time, the electronic device 1000 can be configured to determine the multiple sampled appropriate candidate temperatures corresponding to the heat that fall within the predetermined order as at least one appropriate temperature based on the sorting result. On the other hand, the heat information can be calculated based on the sum of the appropriate candidate temperatures of each area of ​​the heating furnace, or based on the usage of fuel (e.g., liquefied natural gas (LNG)) or the usage of electric energy required to reach the appropriate candidate temperature of each area. Reference will be made to Figure 7 The contents of sampling a plurality of sampled suitable candidate temperatures are described in more detail.

[0068] The electronic device 1000 according to an embodiment of the present disclosure may perform an operation of calculating an optimal temperature based on a plurality of appropriate temperatures. As an example, the electronic device 1000 may be configured to calculate an average value of the appropriate temperatures as the optimal temperature. Figure 7 The contents of calculating the optimum temperature are described in more detail.

[0069] The electronic device 1000 according to an embodiment of the present disclosure may be configured to send a request for instructing to set the calculated optimal temperature as the set temperature value of the heating furnace to the heating furnace controller 200 through the transceiver unit 1100. At this time, the heating furnace controller 200 may be configured to set the set temperature value of the heating furnace 100 to the calculated optimal temperature in response to the request. In addition, the heating furnace controller 200 may perform an action of controlling the operating temperature of the heating furnace to the set temperature value based on the operating temperature of the heating furnace 100 and the set temperature value.

[0070] On the other hand, the electronic device 1000 according to an embodiment of the present disclosure may be configured to send the calculated optimal temperature information to the client terminal 300 through the transceiver 1100. At this time, the client terminal 300 may receive an input from the user for instructing to control the operating temperature of the heating furnace using the calculated optimal temperature information. In addition, the client terminal 300 may send a request for instructing to set the set temperature value of the heating furnace 100 to the calculated optimal temperature to the heating furnace 100 in response to the received input.

[0071] In the following, reference is made to Figures 4 to 7 , the operation of the electronic device 1000 according to an embodiment of the present disclosure and the method for calculating the optimal temperature of the heating furnace performed by the electronic device 1000 will be described in more detail. On the other hand, when describing the method for calculating the optimal temperature of the heating furnace, the above-mentioned Figures 1 to 3 The contents described are repeated in some embodiments. However, this is only for the convenience of explanation and should not be construed as limiting.

[0072] Figure 4 is a sequence diagram illustrating a method for calculating an optimal temperature of a heating furnace according to an embodiment of the present disclosure.

[0073] According to one embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace may include: a step S1000 of obtaining a target physical property value of a material input by an operator; a step S2000 of obtaining a plurality of appropriate candidate temperatures of a heating furnace from first input data using a trained optimal temperature model; a step S3000 of obtaining an expected physical property value of a material from a second input data using a trained physical property prediction model; a step S4000 of sampling a plurality of appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature; a step S5000 of obtaining thermal information when the heating furnace is operated at the sampled appropriate candidate temperatures, comparing the thermal information, and filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature; a step S6000 of calculating an optimal temperature based on the appropriate temperatures; and / or a step S7000 of sending a request for indicating that the calculated optimal temperature is set as the set temperature value of the heating furnace.

[0074] In step S1000 of obtaining the target property value of the material input by the operator, the electronic device 1000 may obtain the target property value related to the target property information of the product input by the operator of the heating furnace through the transceiver 1100. The target property value may be a value related to any target property of the heat-treated material, including tensile strength, yield strength, hardness and / or elongation of the material heat-treated by the heating furnace.

[0075] In step S2000 of obtaining multiple appropriate candidate temperatures of the heating furnace from the first input data using the trained optimal temperature model, the electronic device 1000 can obtain multiple appropriate candidate temperatures of the heating furnace from the first input data including the thickness of the material to be heated in the heating furnace, the steel type of the material, the operating speed of the heating furnace, the target physical property value obtained by step S1000 and / or their combination as variables.

[0076] Figure 5 1 is a diagram for explaining a method for training an optimal temperature model according to an embodiment of the present disclosure and a form of calculating an appropriate candidate temperature using the trained optimal temperature model. Specifically, Figure 5 (a) is a diagram showing a form of calculating an appropriate candidate temperature using a trained optimal temperature model according to an embodiment of the present disclosure, Figure 5 (b) is a diagram illustrating a training method of an optimal temperature model according to an embodiment of the present disclosure.

[0077] The trained optimal temperature model can obtain the first input data through the input layer, and calculate multiple appropriate candidate temperatures ( Figure 5 (a) T1, T2 to Tn), and output the calculated multiple suitable candidate temperatures through the output layer. At this time, the electronic device 1000 can obtain multiple suitable candidate temperatures through the output layer of the trained optimal temperature model.

[0078] On the other hand, the optimal temperature model can be trained based on a first learning data consisting of the thickness of the material, the steel type of the material, the operating speed of the heating furnace, the target physical property value and / or a combination thereof obtained from the heating furnace operation database, and a learning data set consisting of the operating temperature of the heating furnace corresponding to the first learning data. More specifically, the optimal temperature model can be configured to output a predicted temperature based on the first learning data. At this time, the optimal temperature model is trained by updating the parameters (or weights) of the optimal temperature model based on the difference between the predicted temperature and the operating temperature of the heating furnace contained in the learning data set so as to output the predicted temperature at a value approximating the operating temperature of the heating furnace. Therefore, the trained optimal temperature model can be configured to calculate an appropriate candidate temperature corresponding to the actual operating temperature of the heating furnace based on the first input data corresponding to the variables of the first learning data.

[0079] In step S3000 of obtaining the expected physical property value of the material from the second input data using the trained physical property prediction model, the electronic device 1000 can obtain the expected physical property value of the material from the second input data including the appropriate candidate temperature calculated in step S2000, the thickness of the material, the steel type of the material, the operating speed of the heating furnace and / or a combination thereof as variables using the trained physical property prediction model. The expected physical property value may be an expected value related to any physical property of the material to be heat treated, including the tensile strength, yield strength, hardness and / or elongation of the material to be heat treated by the heating furnace.

[0080] Figure 6 is a diagram for illustrating a method for training a physical property prediction model according to an embodiment of the present disclosure and a form of calculating expected physical property values ​​using a trained physical property prediction model. Specifically, Figure 6 (a) is a diagram showing a form of calculating expected physical property values ​​using a trained physical property prediction model according to an embodiment of the present disclosure, Figure 6 (b) is a diagram illustrating a method for training a physical property prediction model according to an embodiment of the present disclosure.

[0081] The trained physical property prediction model can obtain the second input data through the input layer, and calculate the expected physical property value (for example, Figure 6(a) The expected physical property value Q1 related to the tensile strength, the expected physical property value Q2 related to the yield strength, the expected physical property value Q3 related to the hardness, and the expected physical property value Q4 related to the elongation), and the calculated expected physical property values ​​are output through the output layer. At this time, the electronic device 1000 can obtain the expected physical property values ​​through the output layer of the trained physical property prediction model.

[0082] On the other hand, the physical property prediction model can be trained based on the second learning data consisting of the thickness of the material, the steel type of the material, the operating speed of the heating furnace, the operating temperature of the heating furnace and / or a combination thereof obtained from the heating furnace operation database and a learning data set consisting of the physical property information when the material is heat treated under the operating conditions corresponding to the second learning data. More specifically, the physical property prediction model can be configured to output the physical property information as a related predicted value based on the second learning data. At this time, the physical property prediction model can update the parameters (or weights) of the physical property prediction model based on the difference between the predicted value and the physical property information contained in the learning data set so as to output the predicted value as a value approximating the physical property information. Therefore, for example, the trained physical property prediction model can be configured to calculate the expected physical property value when the material is heat treated at an appropriate candidate temperature calculated by the trained optimal temperature model based on the second input data corresponding to the variables of the second learning data and under the operating conditions corresponding to the second input data.

[0083] Figure 7 FIG. 1 is a diagram for explaining a method of calculating an optimal temperature from appropriate candidate temperatures according to an embodiment of the present disclosure.

[0084] In step S4000 of sampling multiple appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature, the electronic device 1000 may perform the action of sampling multiple appropriate candidate temperatures and obtaining the sampled appropriate candidate temperatures. Specifically, the electronic device 1000 may be configured to compare the target property value input by the operator with the expected property value calculated by the trained property prediction model according to the appropriate candidate temperature, and sample multiple appropriate candidate temperatures calculated by the trained optimal temperature model. For example, the electronic device 1000 may calculate the target property value input by the operator and the expected property value calculated by the trained property prediction model according to the first appropriate candidate temperature (for example, Figure 7 For example, the electronic device 1000 may calculate the target property value input by the operator and the first expected property value calculated by the trained property prediction model according to the second appropriate candidate temperature (e.g., Figure 7For example, the electronic device 1000 may calculate the target property value input by the operator and the second expected property value calculated by the trained property prediction model according to the nth appropriate candidate temperature (e.g., Figure 7 The nth difference between the nth expected property values ​​calculated by Tn).

[0085] As an example, the electronic device 1000 may sort the multiple suitable candidate temperatures in ascending order of the difference between the target property value and the expected property value based on the difference between the target property value and the expected property value. In addition, the electronic device 1000 may be configured to determine, based on the sorting result, the multiple suitable candidate temperatures corresponding to the expected property values ​​that fall within the predetermined order as the sampled suitable candidate temperatures ( Figure 7 As an example, the electronic device 1000 may be configured to determine a plurality of suitable candidate temperatures corresponding to the expected physical property values ​​whose calculated differences fall within a predetermined value as suitable candidate temperatures for sampling ( Figure 7 ST1, ST2 to STm).

[0086] However, the above is merely an example, and the electronic device 1000 may be configured to sample a plurality of suitable candidate temperatures based on any suitable method.

[0087] In step S5000 of obtaining heat information when the heating furnace is operated at the sampled appropriate candidate temperature, comparing the heat information, and filtering the sampled appropriate candidate temperature to obtain at least one appropriate temperature, the electronic device 1000 may obtain each heat information when the heating furnace is operated at each sampled appropriate candidate temperature. For example, the electronic device 1000 may obtain the heat information when the heating furnace is operated at the sampled first appropriate candidate temperature (e.g., Figure 7 The heat information used when the heating furnace is operated under ST1 of Figure 7 For example, the electronic device 1000 may obtain a second suitable candidate temperature (eg, Figure 7 The heat information used when operating the heating furnace under ST2) (for example, Figure 7 For example, the electronic device 1000 may obtain the mth appropriate candidate temperature (eg, Figure 7 The heat information used when operating the heating furnace under STm (for example, Figure 7 mth heat).

[0088] At this time, the electronic device 1000 can compare the acquired heat information and filter the multiple sampled appropriate candidate temperatures to obtain at least one appropriate temperature. Specifically, the electronic device 1000 can sort the multiple sampled appropriate candidate temperatures in order of heat from small to large based on the heat information. At this time, the electronic device 1000 can be configured to determine the multiple sampled appropriate candidate temperatures corresponding to the heat that fall into the predetermined order as at least one appropriate temperature based on the sorting result (for example, Figure 7 OT1 to OTk).

[0089] However, the above is merely an example, and the electronic device 1000 may be configured to acquire a plurality of appropriate temperatures from a plurality of sampled appropriate candidate temperatures based on any appropriate method.

[0090] In step S6000 of calculating the optimal temperature based on a plurality of appropriate temperatures, the electronic device 1000 may be configured to calculate an average value of the appropriate temperatures as the optimal temperature. For example, the electronic device 1000 may calculate a plurality of appropriate temperatures (eg, Figure 7 The average value of the first appropriate temperature (OT1) to the kth appropriate temperature (OTk) is calculated, and the average value of the calculated appropriate temperatures is determined as the optimal temperature.

[0091] On the other hand, although Figure 4 Although not shown in the figure, the method for calculating the optimal temperature of the heating furnace according to an embodiment of the present disclosure may be configured to calculate the optimal temperature by repeating steps S2000 to S6000 multiple times.

[0092] In step S7000 of sending a request for instructing to set the calculated optimal temperature as the set temperature value of the heating furnace, the electronic device 1000 may be configured to send a request for instructing to set the calculated optimal temperature as the set temperature value of the heating furnace to the heating furnace controller 200 through the transceiver 1100. At this time, the heating furnace controller 200 may be configured to set the set temperature value of the heating furnace 100 to the calculated optimal temperature in response to the request. In addition, the heating furnace controller 200 may perform an operation of controlling the operating temperature of the heating furnace to the set temperature value based on the operating temperature of the heating furnace 100 and the set temperature value.

[0093] In the following, reference will be made to Figures 8 to 11 A user interface (UI) that can be provided to the client terminal 300 according to an embodiment of the present disclosure is described. Figures 8 to 11 This is a diagram for explaining one form of a user interface (User Interface).

[0094] Reference Figure 8According to an embodiment of the present disclosure, the user interface may be configured to output the first expected physical property information ( Figure 8 I1) and / or the second expected physical property information when the heating furnace is operated at the optimal temperature ( Figure 8 I2) is output to the user. Specifically, the electronic device 1000 can use the trained physical property prediction model to obtain the first expected physical property information I1 from the current operating conditions related to the material thickness, steel type, current operating speed and / or current operating temperature. In addition, the electronic device 1000 can use the trained physical property prediction model to obtain the second expected physical property information I2 from the current operating conditions related to the material thickness, steel type, operating speed and / or optimal temperature. At this time, the electronic device 1000 can be configured to provide the first expected physical property information I1 and the second expected physical property information I2 to the user through the user interface.

[0095] In addition, the user interface according to an embodiment of the present disclosure can transmit the real-time temperature information ( Figure 8 I3) and optimal temperature information ( Figure 8 Specifically, the electronic device 1000 can obtain the real-time temperature information of the heating furnace from the operation data of the heating furnace 100. In addition, as described above, the electronic device 1000 can calculate the optimal temperature of the heating furnace through the trained optimal temperature model. At this time, the electronic device 1000 can be configured to provide the user with the real-time temperature information I3 and the optimal temperature information I4 of the heating furnace through the user interface.

[0096] Reference Fig. 9 The user interface according to an embodiment of the present disclosure may be configured to output the current operating conditions (such as the time, material thickness, operating speed, and / or target physical properties of the material) to the user through any output unit (such as a display) of the client terminal 300. Fig. 9 I5) and information comparing the current operating temperature with the optimal temperature (or appropriate candidate temperature, etc.) calculated under the operating conditions using the trained optimal temperature model ( Fig. 9 On the other hand, the heating furnace 100 may be composed of a plurality of zones. In this case, the electronic device 1000 may be configured to calculate the optimal temperature of each zone using the above method. In this case, the electronic device 1000 may be configured to provide the user with information I6 comparing the current operating temperature of the first zone with the optimal temperature of the first zone and / or information I6 comparing the current operating temperature of the second zone with the optimal temperature of the second zone through the user interface.

[0097] Reference Fig.10 According to an embodiment of the present disclosure, the user interface outputs the operation conditions ( Fig.10 I7) and the optimal temperature calculated from the operating conditions associated with each running process using the trained optimal temperature model ( Fig.10 I8). The operating conditions I7 associated with each operation process may include a code (ID) of the material (coil), an operation start time, an operation end time, operation subject information, a thickness of the material, an expected physical property of the material, a target physical property of the material, and / or an operation speed. In addition, the electronic device 1000 can calculate the optimal temperature of each area of ​​the heating furnace based on the operating conditions associated with each operation process using a trained optimal temperature model. At this time, the electronic device 1000 can be configured to provide the user with the optimal temperature I8 associated with each operation process of the heating furnace to be executed through a user interface.

[0098] Reference Fig.11 According to an embodiment of the present disclosure, the user interface may be configured to obtain the target property value ( Fig.11 Specifically, the user interface may be configured to obtain inputs related to target property values ​​(e.g., steel quality, material thickness (e.g., upper thickness, lower thickness, EI, YP, TS, HD, stdspec, pumj, etc.). At this time, the electronic device 1000 may be configured to calculate an appropriate candidate temperature or calculate an expected property value using the target property value.

[0099] on the other hand, Figures 8 to 11 The user interface shown in is only an example, and the heating furnace operation optimization system 10 according to an embodiment of the present disclosure may be configured to obtain any appropriate information from the user through any appropriate form of user interface, or to provide any appropriate information to the user. On the other hand, although not shown, according to an embodiment of the present disclosure, as a basis for the calculated optimal temperature, information comparing the expected physical properties according to the current operating temperature and the expected physical properties of the optimal temperature may be provided to the user through the user interface.

[0100] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effects: by using an optimal temperature model and a physical property prediction model, the optimal operating temperature of the heating furnace can be calculated while achieving the target physical property value.

[0101] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effect: the optimal temperature is calculated by using the thermal information when the heating furnace is operated at a sampled appropriate candidate temperature through an optimal temperature model and a physical property prediction model, thereby improving the thermal efficiency of the heating furnace while achieving the target physical property value of the product.

[0102] According to an embodiment of the present disclosure, a method for calculating the optimal temperature of a heating furnace and an electronic device for executing the method can provide the following effects: the optimal temperature of the heating furnace is automatically calculated by considering the target physical property values ​​of the product through an artificial intelligence model, thereby controlling the operating temperature of the heating furnace to stably produce products with target physical property values.

[0103] The various actions of the electronic device 1000 described above may be stored in the memory 1200 of the electronic device 1000 , and the processor 1300 of the electronic device 1000 may execute the actions stored in the memory 1200 .

[0104] The features, structures, effects, etc. described in the above embodiments are included in at least one embodiment of the present disclosure, and are not necessarily limited to one embodiment. In addition, the features, structures, effects, etc. shown in each embodiment can be implemented by a person of ordinary skill in the art to which the embodiments belong, by combining or modifying other embodiments. Therefore, the contents related to such combinations and modifications should be understood to be included in the scope of the present disclosure.

[0105] In addition, although the above description is centered on the embodiment, this is only an example and does not limit the present disclosure. A person of ordinary skill in the art to which the present disclosure belongs will recognize that various modifications and applications not illustrated above can be implemented without departing from the basic features of the present embodiment. That is, each constituent element specifically shown in the embodiment can be modified and implemented. And the differences related to these modifications and applications should be interpreted as being included in the scope of the present disclosure as defined by the appended claims.

Claims

1. A method for calculating the optimum temperature of a heating furnace, the method being calculated by an electronic device, wherein: include: The step of obtaining a target physical property value of a material input by an operator; The step of obtaining a plurality of suitable candidate temperatures of the heating furnace from first input data using the trained optimal temperature model, wherein the first input data includes at least one of the thickness of the material to be heated in the heating furnace, the steel grade of the material, the operating speed of the heating furnace and the target physical property value as a variable; A step of obtaining expected physical property values ​​of the material from second input data using the trained physical property prediction model, wherein the second input data includes at least one of the appropriate candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel type of the material, and the operating speed of the heating furnace as a variable; The step of comparing the target physical property value with the expected physical property value calculated by the trained physical property prediction model, and sampling a plurality of the appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature; The steps of obtaining thermal information when the heating furnace is operated at the sampled appropriate candidate temperatures, comparing the thermal information and filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature; a step of performing a predetermined calculation on the at least one appropriate temperature to obtain an optimal temperature; and The step of sending a request for instructing to set the acquired optimal temperature as a set temperature value of the heating furnace.

2. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The step of sampling a plurality of the suitable candidate temperatures to obtain at least one sampled suitable candidate temperature further comprises: The step of comparing the target property value with the expected property value, and sorting the plurality of suitable candidate temperatures in ascending order of the difference between the target property value and the expected property value; and Based on the sorting result, a suitable candidate temperature falling within a predetermined sequence is determined as a suitable candidate temperature for the sampling.

3. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The step of sampling a plurality of the suitable candidate temperatures to obtain at least one sampled suitable candidate temperature further comprises: A step of comparing the target property value with the expected property value, and calculating the difference between the target property value and the expected property value; and The step of determining the appropriate candidate temperature corresponding to the calculated difference within a predetermined value as the appropriate candidate temperature of the sample.

4. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The step of filtering the sampled suitable candidate temperatures to obtain at least one suitable temperature also includes: The step of sorting the sampled appropriate candidate temperatures in ascending order of heat according to the heat information; and The step of determining appropriate candidate temperatures of the samples falling within a predetermined sequence as a plurality of appropriate temperatures based on the sorting result.

5. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The optimal temperature is an average value of the at least one appropriate temperature.

6. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The optimal temperature model is configured as: Training is performed based on first learning data related to at least one of a material thickness, a steel grade of the material, an operating speed of a heating furnace, and / or a target physical property value, and a learning data set consisting of an operating temperature of the heating furnace corresponding to the first learning data; Training is performed by updating the parameters of the optimal temperature model based on the first learning data so as to output a value approximating the operating temperature of the heating furnace.

7. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The physical property prediction model is configured as follows: Training is performed based on second learning data related to at least one of the thickness of the material, the steel type of the material, the operating speed of the heating furnace, and the operating temperature of the heating furnace, and a learning data set consisting of physical property information when the material is heat-treated under the operating conditions corresponding to the second learning data; The training is performed by updating the parameters of the physical property prediction model based on the second learning data so as to output a value approximating the physical property information.

8. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein: The target physical property value and the expected physical property value are related to at least one of tensile strength, yield strength, hardness, and elongation of the material to be heat-treated in the heating furnace. 9 . A computer-readable recording medium having recorded thereon instructions for causing a computer to execute the method according to claim 1 .

10. An electronic device for calculating the optimum temperature of a heating furnace, wherein: include: The transceiver section obtains the target physical property values ​​of the materials input by the operator; as well as processor, The process is configured to: Using the trained optimal temperature model, a plurality of suitable candidate temperatures of the heating furnace are obtained from first input data, wherein the first input data includes at least one of the thickness of the material to be heated in the heating furnace, the steel type of the material, the operating speed of the heating furnace, and the target physical property value as a variable; Using the trained physical property prediction model, obtaining expected physical property values ​​of the material from second input data, wherein the second input data includes at least one of the appropriate candidate temperature calculated by the trained optimal temperature model, the thickness of the material to be heated in the heating furnace, the steel type of the material, and the operating speed of the heating furnace as a variable; Comparing the target physical property value with the expected physical property value calculated by the trained physical property prediction model, sampling a plurality of the appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature; acquiring thermal information when the heating furnace is operated at the sampled appropriate candidate temperatures, comparing the thermal information and filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature; performing a predetermined calculation on the at least one appropriate temperature to obtain an optimal temperature; A request for instructing to set the acquired optimal temperature as a set temperature value of the heating furnace is sent.

Images