Method for calculating optimum temperature of a heating furnace and electronic device for carrying out the same

Abstract

To provide a method for calculating the optimum temperature of a heating furnace which reduces the heat use quantity of a heating furnace while attaining target quality, and an electronic apparatus.SOLUTION: A method for calculating the optimum temperature of a heating furnace comprises the steps of: acquiring a material target physical property value inputted by an operator; acquiring the plural proper candidate temperatures of a heating furnace from first input data utilizing a training-completed optimum temperature model; acquiring the predicted physical property value of a material from second input data utilizing a training-completed physical property prediction model; acquiring a proper candidate temperature by comparing the target physical property value and the predicted physical property value calculated by the physical property prediction model and sampling the plural proper candidate temperatures; acquiring a proper temperature by acquiring / comparing heat quantity information upon a heating furnace operation at the sampled proper candidate temperatures and filtering the sampled optimum candidate temperatures; acquiring an optimum temperature by executing predetermined calculation with the proper temperature as a target; and transmitting a request to set the acquired optimum temperature to a set temperature value.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to techniques for optimizing furnace operation. Specifically, the present disclosure relates to techniques for using artificial intelligence to calculate optimal temperatures for operating a furnace. [Background technology]

[0002] As artificial intelligence technology advances, it is being used in a variety of industrial fields. In particular, research into optimizing the operation of steel production processes using artificial intelligence models has been attracting attention recently.

[0003] Producing steel products of the desired quality requires appropriate heat treatment in the furnace to change the physical properties of the steel plate. However, the physical properties of steel plate do not change linearly with heat treatment, but rather exhibit a nonlinear relationship that rapidly changes when heat treatment is performed above the appropriate temperature. Furthermore, the effect of heat treatment temperature on changes in physical properties varies depending on various factors, such as the steel plate's constituent elements, thickness, and operating environment. This makes it difficult to precisely perform heat treatment that causes changes in the physical properties of steel plate. Furthermore, because heat treatment is dependent on the operator's know-how, the furnace temperature and operating conditions set by different operators can vary even when producing the same steel product, limiting the ability to ensure consistent steel product quality. While steel process optimization technologies have been developed to address these issues, existing steel process optimization technologies have been limited in that they are only used to stably control the steel process and are unable to calculate the optimal operating temperature of the furnace.

[0004] Therefore, there is a need for a method for calculating the optimum temperature of a heating furnace and an apparatus for carrying out the method, which can improve thermal efficiency while ensuring the stability of quality of steel products. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2023-063967 Summary of the Invention [Problem to be solved by the invention]

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

[0007] The problems to be solved by the present disclosure are not limited to the problems described above, and problems not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from this specification and the accompanying drawings. [Means for solving the problem]

[0008] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace includes: acquiring a target physical property value of a material input by an operator; and acquiring a plurality of optimal candidate temperatures of the heating furnace from first input data using a trained optimal temperature model, the first input data including a thickness of a material to be heated in the heating furnace, a steel type of the material, and a temperature of the material. obtaining predicted physical property values ​​of the material from second input data using a trained physical property prediction model, the second input data including, as variables, at least one of the optimum candidate temperatures calculated through the trained optimum 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; comparing the target physical property values ​​with the predicted physical property values ​​calculated through the trained physical property prediction model to sample the plurality of optimum candidate temperatures to obtain at least one sampled optimum candidate temperature; obtaining heat quantity information when the heating furnace is operated at the sampled optimum candidate temperatures, comparing the heat quantity information, and filtering the sampled optimum candidate temperatures to obtain at least one optimum temperature; performing a predetermined calculation on the at least one optimum temperature to obtain an optimum temperature; and transmitting a request to set the obtained optimum temperature as a set temperature value of the heating furnace.

[0009] According to an embodiment of the present disclosure, an electronic device includes a transceiver unit for acquiring target physical property values ​​of a material input by an operator; and a trained optimal temperature model for acquiring a plurality of suitable candidate temperatures of the heating furnace from first input data, the first input data including a thickness of the material to be heated in the heating furnace, a steel type of the material, and the like. the second input data includes, as variables, at least one of the optimum candidate temperatures calculated through the trained optimum temperature model, a thickness of the material to be heated in the heating furnace, a steel grade of the material, and an operating speed of the heating furnace; the target physical property value is used to obtain predicted physical property values ​​of the material from second input data using a trained physical property prediction model; the second input data includes, as variables, at least one of the optimum candidate temperatures calculated through the trained optimum temperature model, a thickness of the material to be heated in the heating furnace, a steel grade of the material, and an operating speed of the heating furnace; the target physical property value is used to obtain predicted physical property values ​​of the material from second input data using a trained physical property prediction model; the second input data includes, as variables, at least one of the optimum candidate temperatures calculated through the trained optimum temperature model, a thickness of the material to be heated in the heating furnace, a steel grade of the material, and an operating speed of the heating furnace; the target physical property value is used to obtain predicted physical property values ​​of the material from second input data using a trained physical property prediction model; the second input data includes, as variables,

[0010] The solutions to the problems of the present disclosure are not limited to the solutions described above, and solutions not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains from this specification and the attached drawings. [Effects of the Invention]

[0011] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method can provide an effect of calculating an optimal operating temperature of a heating furnace while achieving a target physical property value using an optimal temperature model and a physical property prediction model.

[0012] According to a method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method, the optimal temperature is calculated using heat quantity information when the heating furnace is operated at an appropriate candidate temperature sampled through an optimal temperature model and a physical property prediction model, thereby achieving the target physical property values ​​of a product while improving the thermal efficiency of the heating furnace.

[0013] According to an embodiment of the method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method, the optimal temperature of the heating furnace can be automatically calculated in consideration of the target physical properties of a product through an artificial intelligence model, thereby providing an effect of controlling the operating temperature of the heating furnace to stably produce products having the target physical properties.

[0014] The effects of the present disclosure are not limited to the effects described above, and unmentioned effects will be clearly understood by those having ordinary skill in the art to which the present disclosure pertains from this specification and the accompanying drawings. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a schematic diagram of a system for optimizing operation of a heating furnace according to one embodiment of the present disclosure. [Figure 2] 1 is a diagram illustrating a heating furnace operation optimization system according to an embodiment of the present disclosure. [Figure 3] 1 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure. [Figure 4] 1 is a flowchart illustrating a method for calculating an optimal temperature of a furnace according to one embodiment of the present disclosure. [Figure 5] 10 is a diagram illustrating a method for training an optimal temperature model according to an embodiment of the present disclosure, and a method for calculating an appropriate candidate temperature using the trained optimal temperature model. [Figure 6] 1 is a diagram illustrating a method for training a physical property prediction model according to an embodiment of the present disclosure, and a method for calculating predicted physical property values ​​using a trained physical property prediction model. [Figure 7] 10 is a diagram illustrating an embodiment of calculating an optimal temperature from an appropriate candidate temperature according to an embodiment of the present disclosure. [Figure 8] 1 is a diagram illustrating an embodiment of a user interface; [Figure 9] 1 is a diagram illustrating an embodiment of a user interface; [Figure 10] 1 is a diagram illustrating an embodiment of a user interface; [Figure 11] 1 is a diagram illustrating an embodiment of a user interface; DETAILED DESCRIPTION OF THE INVENTION

[0016] The above-mentioned objects, features, and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. However, since the present disclosure can be modified in various ways and can have various embodiments, the following will be described in detail by way of example with reference to the drawings.

[0017] The same reference numerals will generally refer to the same elements throughout the specification. In addition, elements having the same function within the same concept shown in the drawings of each embodiment will be described using the same reference numerals, and redundant description thereof will be omitted.

[0018] If it is determined that a detailed description of a known function or configuration related to the present disclosure may unnecessarily obscure the gist of the present disclosure, the detailed description will be omitted. Furthermore, numbers (e.g., 1, 2, etc.) used in the description of this specification are merely identification symbols for distinguishing one component from another.

[0019] Furthermore, the suffixes "module" and "section" used in the following examples for components are given or used interchangeably solely for the sake of ease of writing the specification, and do not have any distinct meanings or roles in themselves.

[0020] In the following examples, the singular expression includes the plural expression unless the context clearly indicates otherwise.

[0021] In the following examples, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0022] In the drawings, the size of elements may be exaggerated or reduced for the sake of convenience of explanation. For example, the size and thickness of each element shown in the drawings are arbitrarily shown for the sake of convenience of explanation, and the present disclosure is not necessarily limited to what is shown in the drawings.

[0023] If an embodiment can be implemented differently, the order of certain processes may be performed differently than described. For example, two processes described in succession may be performed substantially simultaneously or may be performed in the reverse order from that described.

[0024] In the following examples, when elements are said to be connected, this includes not only the case where the elements are directly connected, but also the case where the elements are indirectly connected through an intervening element.

[0025] For example, when it is stated in this specification that components are electrically connected, this includes not only cases where the components are directly electrically connected, but also cases where the components are indirectly electrically connected through an intervening component.

[0026] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace includes: acquiring a target physical property value of a material input by an operator; and acquiring a plurality of optimal candidate temperatures of the heating furnace from first input data using a trained optimal temperature model, the first input data including a thickness of a material to be heated in the heating furnace, a steel type of the material, and the target physical property value is calculated based on the optimum candidate temperature, and the optimum candidate temperature is calculated based on the optimum candidate temperature. The method may further include the steps of: obtaining predicted physical property values ​​of the material from second input data using a trained physical property prediction model, the second input data including, as variables, at least one of the optimum candidate temperature calculated through the trained optimum 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; comparing the target physical property value with the predicted physical property value calculated through the trained physical property prediction model, and sampling the plurality of optimum candidate temperatures to obtain at least one sampled optimum candidate temperature; obtaining heat quantity information when operating the heating furnace at the sampled optimum candidate temperatures, comparing the heat quantity information, and filtering the sampled optimum candidate temperatures to obtain at least one optimum temperature; calculating an optimum temperature based on the optimum temperature; and transmitting a request to set the calculated optimum temperature as the set temperature value of the heating furnace.

[0027] According to one embodiment of the present disclosure, the step of sampling the plurality of appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature may further include the steps of: comparing the target physical property value with the predicted physical property value, and sorting the plurality of appropriate candidate temperatures in order of smallest difference between the target physical property value and the predicted physical property value; and determining the appropriate candidate temperature corresponding to a predetermined ranking as the sampled appropriate candidate temperature based on the sorting result.

[0028] According to an embodiment of the present disclosure, the step of sampling the plurality of appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature may further include the steps of: comparing the target physical property value with the predicted physical property value and calculating a difference between the target physical property value and the predicted physical property value; and determining, as the sampled appropriate candidate temperature, a suitable candidate temperature corresponding to the calculated difference within a predetermined value.

[0029] According to one embodiment of the present disclosure, the step of filtering the sampled appropriate candidate temperatures to obtain at least one appropriate temperature may further include the steps of: sorting the sampled appropriate candidate temperatures in order of decreasing calorific value based on the calorific value information; and determining the sampled appropriate candidate temperatures corresponding to a predetermined ranking based on the sorting result as the at least one appropriate temperature.

[0030] According to an embodiment of the present disclosure, calculating the optimum temperature based on the appropriate temperatures may further include calculating an average value of the appropriate temperatures as the optimum temperature.

[0031] According to one embodiment of the present disclosure, the optimal temperature model is trained based on a training data set consisting of first training data for 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 the operating temperature of the heating furnace corresponding to the first training data, and the parameters of the optimal temperature model may be updated and trained to output a value that approximates the operating temperature of the heating furnace based on the first training data.

[0032] According to one embodiment of the present disclosure, the physical property prediction model is trained based on a learning data set consisting of second learning data for 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 physical property information when the material is heat-treated under operating conditions corresponding to the second learning data, and the parameters of the physical property prediction model can be updated and trained based on the second learning data to output values ​​that approximate the physical property information.

[0033] According to one embodiment of the present disclosure, the target physical property value and the expected physical property value may relate to at least one of tensile strength, yield strength, hardness, and elongation of the material heat-treated through the heating furnace.

[0034] According to an embodiment of the present disclosure, a computer-readable recording medium having a program recorded thereon for executing the method for calculating the optimum temperature of a heating furnace may be provided.

[0035] According to an embodiment of the present disclosure, an electronic device includes a transceiver unit for acquiring target physical property values ​​of a material input by an operator; and a trained optimal temperature model for acquiring a plurality of suitable candidate temperatures of the heating furnace from first input data, the first input data including a thickness of the material to be heated in the heating furnace, a steel type of the material, and a temperature model for acquiring a plurality of suitable candidate temperatures of the heating furnace from first input data using the trained optimal temperature model. the second input data includes, as variables, at least one of the optimum candidate temperatures calculated through the trained optimum temperature model, a thickness of the material to be heated in the heating furnace, a steel grade of the material, and an operating speed of the heating furnace; and a processor configured to compare the target physical property value with the predicted physical property value calculated through the trained physical property prediction model; sample the plurality of optimum candidate temperatures to obtain at least one sampled optimum candidate temperature; obtain heat quantity information when the heating furnace is operated at the sampled optimum candidate temperatures; compare the heat quantity information; filter the sampled optimum candidate temperatures to obtain at least one optimum temperature; calculate an optimum temperature based on the optimum temperature; and send a request to set the calculated optimum temperature as a set temperature value of the heating furnace.

[0036] Hereinafter, with reference to Figures 1 to 7, a method for calculating the optimal temperature of a heating furnace according to one embodiment of the present disclosure, an electronic device (or server, hereinafter referred to as the electronic device) for performing the method, and / or a heating furnace operation optimization system will be described.

[0037] Fig. 1 is a schematic diagram of a heating furnace operation optimization system 10 according to an embodiment of the present disclosure. Fig. 2 is a diagram for explaining the heating furnace operation optimization system 10 according to an embodiment of the present disclosure.

[0038] The system 10 for optimizing operation of a heating furnace according to one embodiment of the present disclosure may include a heating furnace (100, Furnace), a heating furnace controller 200, a client terminal 300, and / or an electronic device 1000.

[0039] The heating furnace 100 according to an embodiment of the present disclosure can transmit operation data to a heating furnace operation database and / or an external device or server, including the electronic device 1000, via an optional transceiver. Here, the operation data may encompass any data related to the operation of the heating furnace, including operating conditions of the heating furnace, such as 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, as well as physical properties of the product manufactured under the operating conditions. Furthermore, the heating furnace 100 can heat-treat a material (e.g., a steel material) by setting the optimal temperature calculated through the electronic device 1000 to a set temperature value.

[0040] The electronic device 1000 according to an embodiment of the present disclosure may perform an operation of calculating an appropriate candidate temperature using a trained optimal temperature model. Furthermore, the electronic device 1000 may perform an operation of calculating a predicted physical property value of a product when operating a heating furnace based on the appropriate candidate temperature calculated using the trained physical property prediction model. Furthermore, the electronic device 1000 may perform an operation of calculating an optimal temperature based on the calculated predicted physical property value and a desired target physical property value. In this case, the electronic device 1000 may perform an operation of transmitting a request to the furnace controller 200 to instruct control of the operating temperature of the heating furnace 100 based on the calculated optimal temperature via the transceiver 1100. Alternatively, the electronic device 1000 may perform an operation of transmitting calculated optimal temperature information, predicted physical property information, and decision-making basis to the client terminal 300 via the transceiver 1100.

[0041] The furnace controller 200 according to an embodiment of the present disclosure can receive a request for controlling the operating temperature of the furnace 100 from the electronic device 1000 via an optional transceiver. At this time, the furnace controller 200 can set the calculated optimal temperature as the set temperature of the furnace 100 and automatically control the operating temperature of the furnace 100 to the set temperature based on the operating temperature of the furnace 100 and the set temperature. Meanwhile, in FIGS. 1 and 2, the furnace controller 200 is described as being separate from the furnace 100, the client terminal 300, and the electronic device 1000. However, this is for convenience of explanation, and the furnace controller 200 can be integrated with the furnace 100, the client terminal 300, and / or the electronic device 1000. Furthermore, the furnace controller 200 can be provided in the form of a program that can be executed on the furnace 100, the client terminal 300, and / or the electronic device 1000.

[0042] The client terminal 300 according to an embodiment of the present disclosure may receive calculated optimal temperature information from the electronic device 1000 through an optional transceiver. At this time, the client terminal 300 may receive a user request to set the calculated optimal temperature information as the set temperature value of the furnace 100 through an optional input unit (e.g., a mouse, a keyboard, a touchpad, etc.). At this time, the client terminal 300 may transmit a request to control the operating temperature of the furnace 100 to the set temperature value set at the optimal temperature (e.g., user control in FIG. 2 ) based on the user request through the optional transceiver. Meanwhile, the client terminal 300 may receive the calculated optimal temperature information, predicted physical property information, and / or decision-making basis through the optional transceiver and provide the received information to the user through a user interface.

[0043] Referring again to FIG. 1, an electronic device 1000 according to an embodiment of the present disclosure may include a transceiver 1100, a memory 1200, and a processor 1300.

[0044] The transceiver 1100 of the electronic device 1000 can communicate with any external device or external server. For example, the electronic device 1000 can acquire operation data from the heating furnace 100 through the transceiver 1100. Here, the operation data may refer to any data related to the operation of the heating furnace, including the operating conditions of the heating furnace, such as 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, as well as the physical properties of the product manufactured under the operating conditions. For example, the electronic device 1000 can receive, through the transceiver 1100, execution data for properly executing the trained optimal temperature model, including structural information, hierarchical information, calculation information, and / or parameter information of the trained optimal temperature model. For example, the electronic device 1000 can receive, through the transceiver 1100, execution data for properly executing the trained physical property prediction model, including structural information, hierarchical information, calculation information, and / or parameter information of the trained physical property prediction model. For example, the electronic device 1000 may transmit any analytical information including the calculated optimal temperature information, predicted physical property information, and / or decision-making basis to any external device including the client terminal 300 or any external server via the transceiver 1100. For example, the electronic device 1000 may transmit a request to set the calculated optimal temperature as the set temperature value of the furnace via the transceiver 1100 to any external device including the furnace controller 200 or any external server.

[0045] The electronic device 1000 can connect to a network through the transceiver 1100 to transmit and receive various data. The transceiver 1100 can be broadly classified into a wired type and a wireless type. Since the wired type and the wireless type each have advantages and disadvantages, the electronic device 1000 may be provided with both a wired type and a wireless type. Here, the wireless type may mainly use a communication method of the WLAN (Wireless Local Area Network) series such as Wi-Fi. Alternatively, the wireless type may use a cellular communication method, for example, a LTE or 5G series communication method. However, the wireless communication protocol is not limited to the above examples, and any appropriate wireless communication method may be used. Typical examples of the wired type include a local area network (LAN) and a universal serial bus (USB) communication, but other methods are also possible.

[0046] The memory 1200 of the electronic device 1000 can store various information. Various data can be temporarily or semi-permanently stored in the memory 1200. Examples of the memory 1200 include a hard disk drive (HDD), a solid state drive (SSD), a flash memory, a read-only memory (ROM), and a random access memory (RAM). The memory 1200 can be provided in a form built into the electronic device 1000 or in a removable form. The memory 1200 can store various data necessary for the operation of the electronic device 1000, including an operating system (OS) for driving the electronic device 1000 and programs for operating each component of the electronic device 1000.

[0047] The processor 1300 may control the overall operation of the electronic device 1000. For example, the processor 1300 may control the overall operation of the electronic device 1000, including an operation of acquiring a target physical property value (described below), an operation of acquiring a plurality of suitable candidate temperatures for a heating furnace using a trained optimal temperature model, an operation of acquiring a predicted physical property value of a material using a trained physical property prediction model, an operation of sampling a plurality of suitable candidate temperatures to acquire the sampled suitable candidate temperatures, an operation of acquiring a suitable temperature based on heat quantity information when operating a heating furnace at the sampled suitable candidate temperatures, and / or an operation of calculating an optimal temperature based on the suitable temperatures. Specifically, the processor 1300 may load and execute programs for the overall operation of the electronic device 1000 from the memory 1200. The processor 1300 may be embodied as an application processor (AP), a central processing unit (CPU), a microcontroller unit (MCU), or similar devices using hardware, software, or a combination thereof. In this case, the hardware may be provided in the form of an electronic circuit that processes electrical signals to perform a control function, and the software may be provided in the form of a program or code that drives the hardware circuit.

[0048] FIG. 3 is a diagram illustrating the operation of the electronic device 1000 according to an embodiment of the present disclosure.

[0049] The electronic device 1000 according to an embodiment of the present disclosure may acquire a target physical property value through the transceiver 1100. More specifically, the electronic device 1000 may acquire a target physical property value for target physical property information of a manufactured product input by an operator of the heating furnace 100 through the transceiver 1100. Here, the target physical property value may be a value for any target physical property of the heat-treated material (or the heat-treated product), including tensile strength, yield strength, hardness, and / or elongation of the material heat-treated in the heating furnace.

[0050] The electronic device 1000 according to an embodiment of the present disclosure may acquire execution data of the trained optimal temperature model via the transceiver 1100. Here, the execution data of the trained optimal temperature model may include any data for properly executing the trained optimal temperature model, including structural information, hierarchical information, calculation information, and / or parameter information of the trained optimal temperature model.

[0051] An electronic device 1000 according to an embodiment of the present disclosure may acquire multiple candidate optimum temperatures for a heating furnace using a trained optimal temperature model. More specifically, the electronic device 1000 may input first input data to the input layer of the trained optimal temperature model and acquire multiple candidate optimum temperatures through the output layer of the trained optimal temperature model. Here, the first input data may include variables such as 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, a target physical property, and / or a combination thereof. Meanwhile, the optimal temperature model may be trained based on a training dataset including first learning data for the material thickness, the steel grade of the material, the operating speed of the heating furnace, and / or the target physical property acquired from a furnace operation database and an actual operating temperature of the heating furnace corresponding to the first learning data. More specifically, the optimal temperature model may be trained by updating the parameters (or weights) of the optimal temperature model based on the first learning data to output a value that approximates the actual operating temperature corresponding to the first learning data. Therefore, the trained optimal temperature model may be configured to calculate an appropriate candidate temperature corresponding to the actual operating temperature of the furnace based on the first input data corresponding to the variables of the first learning data. Aspects of the training and / or inference of the optimal temperature model will be described in more detail with reference to FIG. 5.

[0052] The electronic device 1000 according to an embodiment of the present disclosure may acquire execution data of a trained physical property prediction model via the transceiver 1100. Here, the execution data of a trained physical property prediction model may include any data for appropriately executing the trained physical property prediction model, including structural information, hierarchical information, computation information, and / or parameter information of the trained physical property prediction model.

[0053] An electronic device 1000 according to an embodiment of the present disclosure may acquire predicted physical property values ​​of a material using a trained physical property prediction model. Specifically, the electronic device 1000 may input second input data to an input layer of the trained physical property prediction model and acquire predicted physical property values ​​of the material through an output layer of the trained physical property prediction model. Here, the second input data may include, as variables, an appropriate candidate temperature calculated through the trained optimal temperature model, a material thickness, a material steel type, a furnace operating speed, and / or a combination thereof. Meanwhile, the physical property prediction model may be trained based on a training dataset including second learning data for the material thickness, the material steel type, the furnace operating speed, and / or the operating temperature acquired from a furnace operation database and physical property information (e.g., the tensile strength, yield strength, hardness, and / or elongation of the material) when the material is heat-treated under operating conditions corresponding to the second learning data. More specifically, the physical property prediction model may be trained by updating the parameters (or weights) of the physical property prediction model based on the second learning data so as to output values ​​that approximate the physical property information when the material is heat-treated under the operating conditions corresponding to the second learning data. Thus, the trained physical property prediction model may be configured to calculate predicted physical property values ​​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. Aspects of the training method and / or inference of the physical property prediction model will be described in more detail with reference to FIG. 6.

[0054] An electronic device 1000 according to an embodiment of the present disclosure may perform an operation of sampling a plurality of appropriate candidate temperatures and acquiring a sampled appropriate candidate temperature. Specifically, the electronic device 1000 may be configured to compare a target physical property value input by a driver with a predicted physical property value calculated through a trained physical property prediction model, and to sample a plurality of appropriate candidate temperatures calculated through a trained optimal temperature model to acquire at least one sampled appropriate candidate temperature. As an example, the electronic device 1000 may compare a target physical property value with a predicted physical property value and sort the plurality of appropriate candidate temperatures in order of smallest difference between the target physical property value and the predicted physical property value. In this case, the electronic device 1000 may be embodied to determine an appropriate candidate temperature corresponding to a predicted physical property value within a predetermined ranking based on the sorting result as the sampled appropriate candidate temperature. As an example, the electronic device 1000 may compare a target physical property value with a predicted physical property value and calculate a difference between the target physical property value and the predicted physical property value. In this case, the electronic device 1000 may be configured to determine, as the sampled appropriate candidate temperature, an appropriate candidate temperature corresponding to a predicted physical property value whose calculated difference falls within a predetermined value. Sampling of a plurality of appropriate candidate temperatures will be described in more detail with reference to FIG. 7.

[0055] According to an embodiment, the electronic device 1000 may acquire an appropriate temperature based on heat quantity information when the heating furnace is operated at the sampled appropriate candidate temperature. Specifically, the electronic device 1000 may acquire heat quantity information when the heating furnace is operated at each sampled appropriate candidate temperature, compare the heat quantity information, and filter the sampled appropriate candidate temperatures to acquire at least one appropriate temperature. For example, the electronic device 1000 may sort the sampled appropriate candidate temperatures in ascending order of heat quantity based on the heat quantity information. In this case, the electronic device 1000 may determine the sampled appropriate candidate temperatures corresponding to the heat quantities corresponding to a predetermined ranking based on the sorting result as at least one appropriate temperature. Meanwhile, the heat quantity information may be calculated based on the sum of the appropriate candidate temperatures for each region of the heating furnace, or based on the amount of fuel (e.g., LNG) consumed or the amount of electric energy consumed to reach the appropriate candidate temperature for each region. The filtering of the sampled appropriate candidate temperatures will be described in more detail with reference to FIG. 7.

[0056] The electronic device 1000 according to an embodiment of the present disclosure may calculate an optimal temperature based on the appropriate temperature. For example, the electronic device 1000 may be configured to calculate the optimal temperature as an average of the appropriate temperatures. The details of calculating the optimal temperature will be described in more detail with reference to FIG. 7.

[0057] The electronic device 1000 according to an embodiment of the present disclosure may be embodied to transmit a request to the furnace controller 200 to instruct the furnace to set the set temperature value to the calculated optimal temperature via the transceiver 1100. In this case, the furnace controller 200 may be embodied to set the set temperature value of the furnace 100 to the calculated optimal temperature in response to the request. Furthermore, the furnace controller 200 may perform an operation of automatically controlling the operating temperature of the furnace 100 to the set temperature value based on the operating temperature and set temperature value of the furnace 100.

[0058] Meanwhile, the electronic device 1000 according to an embodiment of the present disclosure may be embodied to transmit 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 a user instructing the operation temperature of the furnace to be controlled based on the calculated optimal temperature information. Furthermore, the client terminal 300 may transmit a request to the furnace 100 instructing the furnace 100 to set the set temperature value of the furnace 100 to the calculated optimal temperature in response to the received input.

[0059] Hereinafter, with reference to Figures 4 to 7, the operation of the electronic device 1000 according to an embodiment of the present disclosure and a method for calculating the optimal temperature of a furnace performed by the electronic device 1000 will be described in more detail. Meanwhile, in describing the method for calculating the optimal temperature of a furnace, some embodiments that overlap with the contents previously described with reference to Figures 1 to 3 may be omitted. However, this is merely for the convenience of description and should not be construed as limiting.

[0060] FIG. 4 is a flow chart illustrating a method for calculating an optimal temperature for a furnace according to one embodiment of the present disclosure.

[0061] A method for calculating an optimum temperature of a heating furnace according to an embodiment of the present disclosure may include: acquiring a target physical property value of a material input by an operator (S1000); acquiring a plurality of optimum candidate temperatures of the heating furnace from first input data using a trained optimum temperature model (S2000); acquiring a predicted physical property value of the material from second input data using a trained physical property prediction model (S3000); sampling the plurality of optimum candidate temperatures to obtain at least one sampled optimum candidate temperature (S4000); acquiring heat value information when operating the heating furnace at the sampled optimum candidate temperatures, comparing the heat value information, and filtering the sampled optimum candidate temperatures to obtain at least one optimum temperature (S5000); calculating an optimum temperature based on the optimum temperature (S6000); and / or transmitting a request to set the calculated optimum temperature as the set temperature value of the heating furnace (S7000).

[0062] In the step S1000 of acquiring target physical property values ​​of the material input by the operator, the electronic device 1000 may acquire target physical property values ​​for the target physical property information of the product input by the operator of the heating furnace through the transceiver 1100. Here, the target physical property value may be a value for any target physical property of the heat-treated material, including tensile strength, yield strength, hardness, and / or elongation of the material heat-treated in the heating furnace.

[0063] In the step of acquiring a plurality of suitable candidate temperatures for the heating furnace from the first input data using the trained optimal temperature model (S2000), the electronic device 1000 can acquire a plurality of suitable candidate temperatures for the heating furnace from the first input data including, as variables, 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 acquired through step S1000, and / or a combination thereof.

[0064] 5A and 5B are diagrams illustrating a method for training an optimal temperature model according to an embodiment of the present disclosure, and a method for calculating an appropriate candidate temperature using the trained optimal temperature model. Specifically, FIG. 5A illustrates a method for calculating an appropriate candidate temperature using the trained optimal temperature model according to an embodiment of the present disclosure, and FIG. 5B illustrates a method for training an optimal temperature model according to an embodiment of the present disclosure.

[0065] The trained optimal temperature model may acquire first input data through an input layer, calculate a plurality of appropriate candidate temperatures (T1, T2 to Tn in FIG. 5(a)) using parameters (or weights) updated according to the training results, and output the calculated appropriate candidate temperatures through an output layer. In this case, the electronic device 1000 may acquire a plurality of appropriate candidate temperatures through the output layer of the trained optimal temperature model.

[0066] Meanwhile, the optimal temperature model may be trained based on first learning data including material thickness, material steel type, furnace operating speed, target physical property values, and / or a combination thereof obtained from the furnace operation database, and a learning data set including furnace operating temperatures corresponding to the first learning data. More specifically, the optimal temperature model may be configured to output a predicted temperature based on the first learning data. In this case, the optimal temperature model may be trained by updating the parameters (or weights) of the optimal temperature model to output a predicted temperature that is a value that approximates the furnace operating temperature based on the difference between the predicted temperature and the furnace operating temperature included in the learning data set. Thus, the trained optimal temperature model may be configured to calculate an appropriate candidate temperature corresponding to the actual operating temperature of the furnace based on the variables of the first learning data and the corresponding first input data.

[0067] In step S3000 of obtaining predicted physical property values ​​of the material from second input data using the trained physical property prediction model, the electronic device 1000 may obtain predicted physical property values ​​of the material from second input data including, as variables, 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, using the trained physical property prediction model. Here, the predicted physical property values ​​may be predicted values ​​for 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 in the heating furnace.

[0068] 6A and 6B are diagrams illustrating a method for training a physical property prediction model according to an embodiment of the present disclosure, and an aspect of calculating predicted physical property values ​​using the trained physical property prediction model. Specifically, FIG. 6A illustrates an aspect of calculating predicted physical property values ​​using the trained physical property prediction model according to an embodiment of the present disclosure, and FIG. 6B illustrates a method for training a physical property prediction model according to an embodiment of the present disclosure.

[0069] The trained physical property prediction model may acquire second input data through an input layer, calculate predicted physical property values ​​(e.g., predicted physical property value Q1 related to tensile strength, predicted physical property value Q2 related to yield strength, predicted physical property value Q3 related to hardness, and predicted physical property value Q4 related to elongation in FIG. 6(a)) using parameters (or weights) updated according to the training results, and output the calculated predicted physical property values ​​through an output layer. In this case, the electronic device 1000 may acquire predicted physical property values ​​through the output layer of the trained physical property prediction model.

[0070] Meanwhile, the physical property prediction model may be trained based on second learning data obtained from the heating furnace operation database, including the material thickness, the material steel type, the heating furnace operating speed, the heating furnace operating temperature, and / or a combination thereof, and a learning dataset including physical property information obtained when the material is heat-treated under operating conditions corresponding to the second learning data. More specifically, the physical property prediction model may be configured to output a predicted value associated with the physical property information based on the second learning data. The physical property prediction model may be trained by updating the parameters (or weights) of the physical property prediction model to output a predicted value that approximates the physical property information based on the difference between the predicted value and the physical property information included in the learning dataset. Thus, the trained physical property prediction model may be configured to calculate predicted physical property values ​​when the material is heat-treated under operating conditions corresponding to the second input data, for example, at the optimal candidate temperature calculated through the trained optimal temperature model, based on second input data corresponding to the variables of the second learning data.

[0071] FIG. 7 is a diagram illustrating an embodiment of calculating an optimum temperature from suitable candidate temperatures according to an embodiment of the present disclosure.

[0072] In the step S4000 of sampling a plurality of appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature, electronic device 1000 may perform an operation of sampling a plurality of appropriate candidate temperatures to obtain the sampled appropriate candidate temperature. Specifically, electronic device 1000 may be configured to compare a target physical property value input by the driver with a predicted physical property value calculated through a trained physical property prediction model based on the appropriate candidate temperatures, and sample a plurality of appropriate candidate temperatures calculated through a trained optimal temperature model. For example, electronic device 1000 may calculate a first difference value between a target physical property value input by the driver and a first predicted physical property value calculated based on a first appropriate candidate temperature (e.g., T1 in FIG. 7) through the trained physical property prediction model. For example, electronic device 1000 may calculate a second difference value between a target physical property value input by the driver and a second predicted physical property value calculated based on a second appropriate candidate temperature (e.g., T2 in FIG. 7) through the trained physical property prediction model. For example, the electronic device 1000 may calculate an nth difference value between a target physical property value input by the driver and an nth predicted physical property value calculated based on an nth appropriate candidate temperature (e.g., Tn in FIG. 7) through a trained physical property prediction model.

[0073] As an example, the electronic device 1000 may sort a plurality of appropriate candidate temperatures in order of increasing difference between the target physical property value and the predicted physical property value based on the difference between the target physical property value and the predicted physical property value. Furthermore, the electronic device 1000 may be embodied to determine appropriate candidate temperatures corresponding to predicted physical property values ​​falling within a predetermined rank based on the sorting result as sampled appropriate candidate temperatures (ST1, ST2, . . . STm in FIG. 7). As an example, the electronic device 1000 may be embodied to determine appropriate candidate temperatures corresponding to predicted physical property values ​​whose calculated difference value falls within a predetermined value as sampled appropriate candidate temperatures (ST1, ST2, . . . STm in FIG. 7).

[0074] However, the foregoing is merely an example, and electronic device 1000 may be implemented to sample suitable candidate temperatures based on any suitable method.

[0075] In step S5000 of acquiring heat quantity information for operating the furnace at the sampled appropriate candidate temperatures and filtering the sampled appropriate candidate temperatures by comparing the heat quantity information to acquire at least one appropriate temperature, the electronic device 1000 may acquire each heat quantity information for operating the furnace at each sampled appropriate candidate temperature. For example, the electronic device 1000 may acquire heat quantity information (e.g., the first heat quantity in FIG. 7) used for operating the furnace at the sampled first appropriate candidate temperature (e.g., ST1 in FIG. 7). For example, the electronic device 1000 may acquire heat quantity information (e.g., the second heat quantity in FIG. 7) used for operating the furnace at the sampled second appropriate candidate temperature (e.g., ST2 in FIG. 7). For example, the electronic device 1000 may acquire heat quantity information (e.g., the mth heat quantity in FIG. 7) used for operating the furnace at the sampled mth appropriate candidate temperature (e.g., STm in FIG. 7).

[0076] At this time, the electronic device 1000 may compare the acquired heat quantity information and filter the sampled appropriate candidate temperatures to acquire at least one appropriate temperature. Specifically, the electronic device 1000 may sort the sampled appropriate candidate temperatures in ascending order of heat quantity based on the heat quantity information. At this time, the electronic device 1000 may be embodied to determine the sampled appropriate candidate temperatures corresponding to the heat quantities within a predetermined ranking based on the sorting result as at least one appropriate temperature (e.g., OT1 to OTk in FIG. 7).

[0077] However, the above is merely an example, and the electronic device 1000 may be embodied to obtain the appropriate temperature from the sampled appropriate candidate temperatures based on any appropriate method.

[0078] In the step of calculating the optimum temperature based on the appropriate temperatures (S6000), the electronic device 1000 may be configured to calculate an average value of the appropriate temperatures as the optimum temperature. For example, the electronic device 1000 may be configured to calculate an average value of the appropriate temperatures (e.g., the first appropriate temperature OT1 to the k-th appropriate temperature OTk in FIG. 7) acquired in the step S5000, and determine the average value of the calculated appropriate temperatures as the optimum temperature.

[0079] Meanwhile, although not shown in FIG. 4, the method for calculating the optimum temperature of a heating furnace according to an embodiment of the present disclosure may be configured to calculate the optimum temperature by repeating steps S2000 to S6000 several times.

[0080] In the step S7000 of transmitting a request to instruct to set the calculated optimal temperature as the set temperature value of the furnace, the electronic device 1000 may be embodied to transmit the request to instruct to set the calculated optimal temperature as the set temperature value of the furnace to the furnace controller 200 via the transceiver 1100. At this time, the furnace controller 200 may be embodied to set the set temperature value of the furnace 100 to the calculated optimal temperature in response to the request. Furthermore, the furnace controller 200 may perform an operation of automatically controlling the operating temperature of the furnace 100 to the set temperature value based on the operating temperature and set temperature value of the furnace 100.

[0081] Hereinafter, a user interface that may be provided to the client terminal 300 according to an embodiment of the present disclosure will be described with reference to Figures 8 to 11. Figures 8 to 11 are diagrams for explaining an embodiment of the user interface.

[0082] 8, a user interface according to an embodiment of the present disclosure may be provided to a user through an output unit (e.g., a display) of the client terminal 300 to output first predicted physical property information (I1 in FIG. 8) when the heating furnace is operated under current operating conditions and / or second predicted physical property information (I2 in FIG. 8) when the heating furnace is operated under optimal temperatures. Specifically, the electronic device 1000 may obtain the first predicted physical property information I1 from current operating conditions, such as material thickness, steel grade, current operating speed, and / or current operating temperature, using a trained physical property prediction model. Furthermore, the electronic device 1000 may obtain the second predicted physical property information I2 from current operating conditions, such as material thickness, steel grade, operating speed, and / or optimal temperature, using a trained physical property prediction model. In this case, the electronic device 1000 may be embodied to provide the first predicted physical property information I1 and the second predicted physical property information I2 to the user through the user interface.

[0083] Furthermore, the user interface according to an embodiment of the present disclosure may be provided to output real-time temperature information (I3 in FIG. 8) and optimal temperature information (I4 in FIG. 8) of the furnace to the user through an output unit (e.g., a display, etc.) of the client terminal 300. Specifically, the electronic device 1000 may acquire real-time temperature information of the furnace from operation data of the furnace 100. Furthermore, the electronic device 1000 may calculate the optimal temperature of the furnace through the optimal temperature model that has been trained as described above. At this time, the electronic device 1000 may be embodied to provide the real-time temperature information I3 and optimal temperature information I4 of the furnace to the user through the user interface.

[0084] 9, a user interface according to an embodiment of the present disclosure may be provided to a user through an output unit (e.g., a display) of the client terminal 300, by outputting information (e.g., I6 in FIG. 9, in the form of a table) comparing current operating conditions (I5 in FIG. 9) related to time, material thickness, operating speed, and / or target physical properties of the material, the current operating temperature, and an optimal temperature (or suitable candidate temperature, etc.) calculated from the current operating conditions using a trained optimal temperature model. Meanwhile, the heating furnace 100 may be configured with multiple zones. In this case, the electronic device 1000 may be configured to calculate the optimal temperature for each zone using the above-described method. In this case, the electronic device 1000 may be configured to provide a user with information I6 comparing the current operating temperature of the first zone with the optimal temperature of the first zone and / or the current operating temperature of the second zone with the optimal temperature of the second zone through the user interface.

[0085] 10 , a user interface according to an embodiment of the present disclosure may be provided to a user through an output unit (e.g., a display) of the client terminal 300 to output to the user the operating conditions (I7 in FIG. 10 ) for each operation schedule of the furnace to be performed in the future and the optimal temperature (I8 in FIG. 10 ) calculated from the operating conditions for each operation schedule using the trained optimal temperature model. The operating conditions (I7) for each operation schedule may include the material (coil) ID, operation start time, operation end time, operating entity information, material thickness, expected material properties, target material properties, and / or operation speed. Furthermore, the electronic device 1000 may calculate the optimal temperature for each zone of the furnace using the trained optimal temperature model based on the operating conditions for each operation schedule. At this time, the electronic device 1000 may be embodied to provide the user with the optimal temperature (I8) for each operation schedule of the furnace to be performed in the future through the user interface.

[0086] 11 , a user interface according to an embodiment of the present disclosure may be provided to receive an input for a target physical property value (I9 in FIG. 11 ) through an input unit (e.g., a mouse, a touchpad, a keyboard, etc.) of a client terminal 300. Specifically, the user interface may be provided to receive an input for a target physical property value (e.g., steel quality, material thickness (e.g., upper thickness, lower thickness, EI, YP, TS, HD, stdspec, pumj, etc.)). In this case, the electronic device 1000 may be embodied to calculate an appropriate candidate temperature or a predicted physical property value using the target physical property value.

[0087] 8 to 11 are merely examples, and the heating furnace operation optimization system 10 according to an embodiment of the present disclosure may be embodied to acquire any appropriate information from a user or provide any appropriate information to a user through any appropriate user interface. Although not shown, according to an embodiment of the present disclosure, information comparing predicted physical properties based on the current operating temperature with predicted physical properties based on the optimal temperature based on the calculated optimal temperature may be provided to the user through the user interface.

[0088] According to an embodiment of the present disclosure, a method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method can provide an effect of calculating an optimal operating temperature of a heating furnace while achieving a target physical property value using an optimal temperature model and a physical property prediction model.

[0089] According to a method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method, the optimal temperature is calculated using heat quantity information when the heating furnace is operated at an appropriate candidate temperature sampled through an optimal temperature model and a physical property prediction model, thereby achieving the target physical property values ​​of a product while improving the thermal efficiency of the heating furnace.

[0090] According to an embodiment of the method for calculating an optimal temperature of a heating furnace and an electronic device for performing the method, the optimal temperature of the heating furnace can be automatically calculated in consideration of the target physical properties of a product through an artificial intelligence model, thereby providing an effect of controlling the operating temperature of the heating furnace to stably produce products having the target physical properties.

[0091] The various operations of the electronic device 1000 described above may be stored in a memory 1200 of the electronic device 1000, and a processor 1300 of the electronic device 1000 may be configured to perform the operations stored in the memory 1200.

[0092] 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 only one embodiment. Furthermore, the features, structures, effects, etc. exemplified in each embodiment can be combined or modified in other embodiments by a person skilled in the art to which the embodiments belong. Therefore, content related to such combinations and modifications should be interpreted as being included in the scope of the present disclosure.

[0093] Furthermore, although the above description focuses on the embodiments, these are merely examples and do not limit the present disclosure. Those skilled in the art will recognize that various modifications and applications not exemplified above are possible within the scope of the essential characteristics of the present disclosure. In other words, each component specifically illustrated in the embodiments can be modified and implemented. Differences related to such modifications and applications should be construed as being included within the scope of the present disclosure as defined by the appended claims.

Claims

1. 1. A method for calculating an optimum temperature for a furnace by an electronic device, comprising: obtaining target physical property values ​​of the material input by the operator; obtaining a plurality of suitable candidate temperatures for the heating furnace from first input data using the trained optimal temperature model, the first input data including at least one of a thickness of the material to be heated in the heating furnace, a steel grade of the material, an operating speed of the heating furnace, and the target physical property value as a variable; obtaining predicted physical property values ​​of the material from second input data using the trained physical property prediction model, the second input data including at least one of the optimum candidate temperature calculated through 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 predicted physical property value calculated through the trained physical property prediction model, and sampling the plurality of appropriate candidate temperatures to obtain at least one sampled appropriate candidate temperature; acquiring heat quantity information when the heating furnace is operated at the sampled suitable candidate temperatures, comparing the heat quantity information, and filtering the sampled suitable candidate temperatures to acquire at least one suitable temperature; performing a predetermined calculation on the at least one appropriate temperature to obtain the optimum temperature; and A method for calculating an optimum temperature of a heating furnace, comprising: transmitting a request to set the obtained optimum temperature as a set temperature value of the heating furnace.

2. Sampling the plurality of suitable candidate temperatures to obtain at least one sampled suitable candidate temperature includes: comparing the target physical property value with the predicted physical property value and sorting the plurality of suitable candidate temperatures in order of smallest difference between the target physical property value and the predicted physical property value; and 2. The method of claim 1, further comprising determining, as the sampled optimum candidate temperature, a suitable candidate temperature that corresponds within a predetermined ranking based on the sorting result.

3. Sampling the plurality of suitable candidate temperatures to obtain at least one sampled suitable candidate temperature includes: comparing the target property value with the predicted property value and calculating a difference between the target property value and the predicted property value; and 2. The method for calculating an optimum temperature of a heating furnace according to claim 1, further comprising the step of determining, as the sampled optimum candidate temperature, a suitable candidate temperature to which the calculated difference corresponds within a predetermined value.

4. The step of filtering the sampled suitable candidate temperatures to obtain at least one suitable temperature comprises: sorting the sampled suitable candidate temperatures in ascending order of heat quantity based on the heat quantity information; and 2. The method of claim 1, further comprising determining the sampled suitable candidate temperatures corresponding to a predetermined ranking based on the sorting result as the at least one suitable temperature.

5. The optimum temperature is 2. The method for calculating the optimum temperature of a heating furnace according to claim 1, wherein the optimum temperature is an average value of the at least one optimum temperature.

6. The optimal temperature model is the method is trained based on a learning data set that is configured with first learning data for 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 the operating temperature of the heating furnace corresponding to the first learning data; 2. The method for calculating the optimal temperature of a heating furnace according to claim 1, wherein parameters of the optimal temperature model are updated and trained to output a value that approximates the operating temperature of the heating furnace based on the first learning data.

7. The physical property prediction model is the method is trained based on a learning dataset that includes second learning data for 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 physical property information when the material is heat-treated under operating conditions corresponding to the second learning data; 2. The method for calculating the optimal temperature of a heating furnace according to claim 1, wherein parameters of the physical property prediction model are updated and trained to output a value that approximates the physical property information based on the second learning data.

8. The target physical property value and the predicted physical property value are 2. The method of claim 1, wherein the optimum temperature of the heating furnace is related to at least one of tensile strength, yield strength, hardness, and elongation of the material heat-treated in the heating furnace.

9. A computer-readable recording medium containing a program for causing a computer to execute the method according to claim 1.

10. 1. An electronic device for calculating an optimum temperature of a heating furnace, a transceiver for acquiring target physical property values ​​of the material input by the driver; and Using the trained optimal temperature model, a plurality of suitable candidate temperatures of the heating furnace are obtained from first input data, and the first input data includes the thickness of the material to be heated in the heating furnace, the steel type of the material, and and a processor configured to: acquire predicted physical property values ​​of the material from second input data using a trained physical property prediction model, the second input data including at least one of the optimum candidate temperatures calculated through the trained optimum temperature model, a thickness of the material to be heated in the heating furnace, a steel type of the material, and an operating speed of the heating furnace as variables; compare the target physical property value with the predicted physical property value calculated through the trained physical property prediction model; sample the plurality of optimum candidate temperatures to acquire at least one sampled optimum candidate temperature; acquire heat quantity information when the heating furnace is operated at the sampled optimum candidate temperatures; compare the heat quantity information; filter the sampled optimum candidate temperatures to acquire at least one optimum temperature; perform a predetermined operation on the at least one optimum temperature to acquire the optimum temperature; and send a request to set the acquired optimum temperature as a set temperature value of the heating furnace.

Images