A furnace black body arrangement method and system
Patent Information
- Application Number
- CN202311132328.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-04
- Publication Date
- 2026-08-18
- Estimated Expiration
- 2043-09-04
AI Technical Summary
[0003]现有的黑体强化辐射传热技术应用比较广泛，但在炉内布置方面只是依据经验设计单位面积的黑体元件数量来进行加热炉的黑体改造，没有考虑到在相同布置密度的情况下，采用不同的布置方法，能够获得不同的效果
[0026] This invention proposes a method and system for arranging blackbody elements in a heating furnace. The method includes the following steps: simulating heating experiments with blackbody elements placed at different positions on the inner wall of the heating furnace, recording experimental data, including observation datasets and response datasets; the observation datasets are furnace temperature data at different heating temperatures; the response datasets are the number of blackbody elements at different positions on the inner wall of the heating furnace; establishing a neural network for predicting the arrangement of blackbody elements in the heating furnace; training the neural network with the observation datasets as input and the response datasets as output to obtain a trained prediction model; inputting the current furnace temperature data into the trained prediction model, outputting the predicted number of blackbody elements based on the predictions of the trained prediction model, and optimizing the furnace arrangement based on the predicted number of blackbody elements. Based on the method for arranging blackbody elements in a heating furnace, a system for arranging blackbody elements in a heating furnace is also proposed. This invention provides a method for arranging blackbody elements on the furnace top and side walls during heating furnace renovation, which can quantitatively measure the radiative heat transfer effect and determine the optimal arrangement scheme by optimizing the arrangement of a certain number of blackbody elements at different positions within the furnace.
Smart Images
Figure CN117171999B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of energy-saving technology for billet heating furnaces, and specifically relates to a method and system for arranging blackbody in a heating furnace. Background Technology
[0002] A heating furnace is a device used to heat materials or workpieces, typically metals, to rolling or forging temperatures; it is also known as an industrial furnace. Heating furnaces are widely used in numerous industries, including petroleum, chemical, metallurgy, machinery, heat treatment, surface treatment, building materials, electronics, materials science, light industry, daily chemicals, and pharmaceuticals. Currently, various industrial furnaces can employ multiple energy-saving technologies to improve heating efficiency, such as regenerative combustion technology, coating technology, preheating utilization technology, and the addition of blackbody radiation materials.
[0003] Existing blackbody enhanced radiation heat transfer technology is widely used, but in terms of furnace arrangement, the number of blackbody elements per unit area is designed based on experience to modify the blackbody of the heating furnace. It does not take into account that different arrangement methods can achieve different effects under the same arrangement density. Summary of the Invention
[0004] To address the aforementioned technical problems, this invention proposes a method and system for arranging blackbody in a heating furnace, which effectively improves the thermal energy utilization efficiency of the furnace and can be applied to various existing heating furnaces at a lower cost.
[0005] To achieve the above objectives, the present invention adopts the following technical solution:
[0006] A method for arranging a blackbody in a heating furnace includes the following steps:
[0007] A heating experiment was conducted simulating the presence of blackbody elements at different locations on the inner wall of a heating furnace. Experimental data were recorded, including an observation dataset and a response dataset. The observation dataset consisted of furnace temperature data at different heating temperatures, while the response dataset contained the number of blackbody elements at different locations on the inner wall of the heating furnace.
[0008] A neural network for predicting the blackbody arrangement of a heating furnace is established; the neural network is trained by using the observation dataset as input and the response dataset as output to obtain a trained prediction model.
[0009] The current furnace temperature data is input into the trained prediction model. Based on the predictions of the trained prediction model, the predicted number of blackbodies is output. The layout of the heating furnace is optimized based on the predicted number of blackbodies.
[0010] Furthermore, the heating furnace is enclosed by a furnace chamber formed by a top and left and right side walls, and the furnace chamber includes a feeding zone, a preheating zone, a heating zone, a soaking zone and a discharging zone;
[0011] Several blackbody elements are provided at the top of the preheating zone, the top of the heating zone, and the top of the soaking zone; each blackbody element is provided on the furnace lining at the top.
[0012] Several blackbody elements are provided on the sides of the preheating zone, the heating zone, and the homogenizing zone.
[0013] Furthermore, the process of simulating the heating experiment with blackbody elements placed at different positions on the inner wall of the heating furnace and recording the experimental data includes: using finite element software to simulate multiple sets of heating furnace blackbody material arrangement schemes and recording the experimental data.
[0014] Furthermore, after recording the experimental data, the method also includes converting both the observation dataset and the response dataset into double-precision floating-point data.
[0015] Furthermore, the furnace temperature data at different heating temperatures includes the furnace temperature during the first heating time period, the furnace temperature during the second heating time period, and the furnace temperature during the Nth heating time period.
[0016] Where N is a natural number; the first time period is 15 minutes; the second time period is 30 minutes; and the Nth time period is 15*N minutes.
[0017] Furthermore, the number of blackbody elements at different positions on the inner wall of the heating furnace includes: the number of blackbody elements on the left inner wall of the heating furnace, the number of blackbody elements on the upper inner wall of the heating furnace, and the number of blackbody elements on the right inner wall of the heating furnace.
[0018] Furthermore, the number of neurons in the input layer of the neural network is equal to the temperature data corresponding to each blackbody; the temperature data also corresponds to the position and time information of each blackbody.
[0019] Furthermore, the number of neurons in the hidden layer of the neural network is set to 2, and nonlinear features are introduced through the Sigmoid activation function.
[0020] Furthermore, the post-trained prediction model uses mean absolute error to measure the difference between the prediction results of the prediction model and the actual number of black bodies, and employs the Adam optimizer to minimize the loss function.
[0021] The present invention also proposes a blackbody arrangement system for a heating furnace, the system comprising an acquisition module, an establishment module, and a prediction module;
[0022] The acquisition module is used to simulate a heating experiment when blackbody elements are placed at different positions on the inner wall of the heating furnace, and to record experimental data. The experimental data includes an observation dataset and a response dataset. The observation dataset is the furnace temperature data at different heating temperatures. The response dataset is the number of blackbody elements at different positions on the inner wall of the heating furnace.
[0023] The establishment module is used to establish a neural network for predicting the blackbody arrangement of a heating furnace; the neural network is trained by using the observation dataset as the input and the response dataset as the output to obtain a trained prediction model.
[0024] The prediction module is used to input the current furnace temperature data into the trained prediction model, and output the predicted number of blackbodies based on the prediction of the trained prediction model. The layout of the heating furnace is then optimized based on the predicted number of blackbodies.
[0025] The effects described in the invention are merely those of the embodiments, and not all the effects of the invention. One of the above technical solutions has the following advantages or beneficial effects:
[0026] This invention proposes a method and system for arranging blackbody elements in a heating furnace. The method includes the following steps: simulating heating experiments with blackbody elements placed at different positions on the inner wall of the heating furnace, recording experimental data, including observation datasets and response datasets; the observation datasets are furnace temperature data at different heating temperatures; the response datasets are the number of blackbody elements at different positions on the inner wall of the heating furnace; establishing a neural network for predicting the arrangement of blackbody elements in the heating furnace; training the neural network with the observation datasets as input and the response datasets as output to obtain a trained prediction model; inputting the current furnace temperature data into the trained prediction model, outputting the predicted number of blackbody elements based on the predictions of the trained prediction model, and optimizing the furnace arrangement based on the predicted number of blackbody elements. Based on the method for arranging blackbody elements in a heating furnace, a system for arranging blackbody elements in a heating furnace is also proposed. This invention provides a method for arranging blackbody elements on the furnace top and side walls during heating furnace renovation, which can quantitatively measure the radiative heat transfer effect and determine the optimal arrangement scheme by optimizing the arrangement of a certain number of blackbody elements at different positions within the furnace.
[0027] This invention securely mounts numerous blackbody elements onto the furnace lining without altering the original furnace structure, thereby increasing the heat transfer area and improving the heat transfer capacity of the furnace lining. Attached Figure Description
[0028] Figure 1 This is a flowchart of a blackbody arrangement method for a heating furnace according to Embodiment 1 of the present invention;
[0029] Figure 2 This is a perspective view of the heating furnace proposed in Embodiment 1 of the present invention;
[0030] Figure 3 This is a front view of the heating furnace proposed in Embodiment 1 of the present invention;
[0031] Figure 4 This is a schematic diagram of the neural network sequence model proposed in Embodiment 1 of the present invention;
[0032] Figure 5 This is the curve showing the change of the loss function during the training process of the neural network proposed in Embodiment 1 of the present invention;
[0033] Figure 6 This is a schematic diagram of a heating furnace blackbody arrangement system proposed in Embodiment 2 of the present invention. Detailed Implementation
[0034] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the invention. To simplify the disclosure of the invention, components and arrangements of specific examples are described below. Furthermore, reference numerals and / or letters may be repeated in different examples. This repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. It should be noted that the components illustrated in the drawings are not necessarily drawn to scale. Descriptions of well-known components, processing techniques, and processes are omitted in this invention to avoid unnecessarily limiting the invention.
[0035] Example 1
[0036] Embodiment 1 of the present invention proposes a method for arranging blackbody elements in a heating furnace, providing a method for arranging blackbody elements on the furnace top and side walls during the renovation of a heating furnace. Under the condition of the same number of blackbody elements, the optimal blackbody element arrangement scheme can be found, effectively improving the thermal energy utilization efficiency of the furnace and kiln, and can be applied to various existing heating furnaces at a lower cost.
[0037] Figure 1 This is a flowchart of a blackbody arrangement method for a heating furnace according to Embodiment 1 of the present invention;
[0038] In step S100, a heating experiment is simulated with blackbody elements placed at different positions on the inner wall of the heating furnace, and experimental data is recorded. The experimental data includes an observation dataset and a response dataset. The observation dataset contains furnace temperature data at different heating temperatures. The response dataset contains the number of blackbody elements at different positions on the inner wall of the heating furnace.
[0039] Figure 2 This is a perspective view of the heating furnace proposed in Embodiment 1 of the present invention; Figure 3 This is a front view of the heating furnace proposed in Embodiment 1 of the present invention; the heating furnace is a furnace chamber surrounded by a top and left and right side walls, and the furnace chamber includes a feeding zone, a preheating zone, a heating zone, a soaking zone and a discharging zone;
[0040] Several blackbody elements are installed at the top of the preheating zone, the top of the heating zone, and the top of the soaking zone; each blackbody element is installed on the furnace lining at the top.
[0041] Several blackbody elements are installed on the sides of the preheating zone, the heating zone, and the heat spreader.
[0042] The blackbody element is bonded to the refractory layer of the furnace lining using a high-temperature binder. This high-temperature binder is then sintered with the blackbody element and furnace lining after furnace drying. The high absorption and high emission properties of the blackbody element regulate the diffusely reflected heat rays within the furnace chamber into ordered heat rays, improving the heat ray delivery rate. This invention uses numerous blackbody elements installed at appropriate locations on the inner wall of the furnace, increasing the heat transfer area, improving the furnace emissivity, preventing aging, and effectively regulating the heat rays within the furnace chamber. This regulates the diffuse, disordered heat rays to an ordered state, allowing them to directly target the heated object, improving the heat ray delivery rate, enhancing radiative heat transfer, and achieving significant energy-saving effects.
[0043] The experiments were conducted using finite element method software to simulate multiple blackbody material arrangement schemes for heating furnaces, and the experimental data were recorded.
[0044] Experiments were conducted using finite element method (FEM) software to simulate 200 different blackbody material arrangement schemes for the heating furnace, and experimental data were collected. This included: the number of blackbodies on the left inner wall, the number of blackbodies on the upper inner wall, the number of blackbodies on the right inner wall, and the furnace temperatures after 15 minutes, 30 minutes, 45 minutes, 60 minutes, 75 minutes, 90 minutes, 105 minutes, and 120 minutes of heating.
[0045] The furnace temperatures after heating for 15 minutes, 30 minutes, 45 minutes, 60 minutes, 75 minutes, 90 minutes, 105 minutes, and 120 minutes are the observation datasets. The number of black bodies on the left inner wall, the upper inner wall, and the right inner wall of the furnace are the response datasets. Both the observation and response datasets are converted into double-precision floating-point data.
[0046] In step S200, a neural network for predicting the blackbody arrangement of the heating furnace is established; the neural network is trained by using the observation dataset as the input and the response dataset as the output to obtain the trained prediction model.
[0047] This application establishes an optimizable feedforward neural network model based on a particle swarm optimization algorithm coupled with a neural network algorithm. When it comes to optimizing heating furnaces and predicting blackbody arrangement schemes, neural networks are a powerful tool, capable of predicting output data by learning patterns in input data. The training process of the neural network involves progressively adjusting the model to better fit the data. We used the TensorFlow framework to build and train the neural network. The neural network model is defined as a sequence model consisting of multiple layers. Figure 4 This is a schematic diagram of the neural network sequence model proposed in Embodiment 1 of the present invention.
[0048] The number of neurons in the neural network input layer is equal to the temperature data corresponding to each blackbody; the temperature data also corresponds to the position and time information of each blackbody.
[0049] The input layer is where the neural network receives data. In furnace optimization, the input data includes temperature data and position information. `num_features` represents the number of temperature data points, while `num_blackbodies` represents the number of blackbodies and the amount of position information. The number of neurons in the input layer is equal to `num_features`, meaning it receives the temperature data, position information, and time information corresponding to each blackbody.
[0050] The number of neurons in the hidden layer of the neural network is set to 2, and non-linear features are introduced through the Sigmoid activation function so that the model can capture complex relationships in the data.
[0051] The number of neurons in the output layer is equal to `num_blackbodies`, matching the number of blackbodies. The output layer uses a linear activation function so that the actual number of blackbodies can be predicted.
[0052] After training, the prediction model uses mean absolute error to measure the difference between the prediction results of the prediction model and the actual number of black bodies, and the Adam optimizer is used to minimize the loss function.
[0053] The results of the training process were recorded, forming a graph showing how the loss function changes over time. Figure 5 The curve showing the change of the loss function during the training process of the neural network proposed in Embodiment 1 of the present invention is shown. The loss decreases steadily during the 100 epochs of training, indicating that the model is effectively trained and has achieved a good training effect.
[0054] In step S300, the current furnace temperature data is input into the trained prediction model. The predicted number of blackbodies is output based on the prediction of the trained prediction model. The layout of the heating furnace is optimized based on the predicted number of blackbodies.
[0055] The prediction process refers to inputting new temperature data into the model after training to obtain a prediction of the number of blackbodies. In the example code, we use a trained neural network model to predict the number of blackbodies. Inputting new temperature data (with the same number of features as the training data) will return the predicted number of blackbodies. This can be used to optimize the layout of heating furnaces, thereby improving heat transfer efficiency and energy-saving performance.
[0056] In this application, the burner position, the initial blackbody arrangement position, and the billet position are first determined. A furnace combustion model is established by integrating physical processes such as gas flow, mixing, chemical reaction, thermal convection, and thermal radiation. The simulation results of the radiation heat transfer model are analyzed, and the influence of blackbody elements on the billet heating rate is investigated. The model is continuously modified to achieve the optimal effect.
[0057] The present invention provides a method for arranging blackbody elements in a heating furnace according to Embodiment 1. This method provides a method for arranging blackbody elements on the furnace top and side walls during the modification of the heating furnace. It can quantitatively measure the radiation heat transfer effect and determine the optimal arrangement scheme by optimizing the arrangement of a certain number of blackbody elements in different positions in the furnace.
[0058] The method for arranging blackbody elements in a heating furnace proposed in Embodiment 1 of the present invention can securely install numerous blackbody elements on the furnace lining without changing the original furnace structure, thereby increasing the heat transfer area and improving the heat transfer capacity of the furnace lining.
[0059] Example 2
[0060] Based on the blackbody arrangement method for a heating furnace proposed in Embodiment 1 of the present invention, Embodiment 2 of the present invention also proposes a blackbody arrangement system for a heating furnace. Figure 6 This is a schematic diagram of a heating furnace blackbody arrangement system proposed in Embodiment 2 of the present invention. The system includes: an acquisition module, an establishment module, and a prediction module.
[0061] The acquisition module is used to simulate heating experiments when blackbody elements are placed at different positions on the inner wall of the heating furnace, and to record experimental data. The experimental data includes an observation dataset and a response dataset. The observation dataset is the furnace temperature data at different heating temperatures. The response dataset is the number of blackbody elements at different positions on the inner wall of the heating furnace.
[0062] The module is used to build a neural network for predicting the blackbody arrangement of a heating furnace; the neural network is trained by using the observation dataset as input and the response dataset as output to obtain the trained prediction model.
[0063] The prediction module is used to input the current furnace temperature data into the trained prediction model. Based on the prediction of the trained prediction model, the predicted number of blackbodies is output, and the layout of the heating furnace is optimized based on the predicted number of blackbodies.
[0064] In the acquisition module: the heating furnace is a furnace chamber enclosed by a top and left and right side walls, and the furnace chamber includes a feeding zone, a preheating zone, a heating zone, a soaking zone and a discharging zone;
[0065] Several blackbody elements are installed at the top of the preheating zone, the top of the heating zone, and the top of the soaking zone; each blackbody element is installed on the furnace lining at the top; several blackbody elements are installed on the sides of the preheating zone, the sides of the heating zone, and the sides of the soaking zone.
[0066] The process of simulating heating experiments with blackbody elements placed at different positions on the inner wall of the heating furnace and recording experimental data includes: using finite element software to simulate experiments with multiple blackbody material arrangement schemes in the heating furnace and recording the experimental data.
[0067] After recording the experimental data, the process also includes converting both the observation dataset and the response dataset into double-precision floating-point data.
[0068] The furnace temperature data for different heating temperatures includes the furnace temperature during the first heating time period, the furnace temperature during the second heating time period, and the furnace temperature during the Nth heating time period.
[0069] Where N is a natural number; the first time period is 15 minutes; the second time period is 30 minutes; and the Nth time period is 15*N minutes.
[0070] The number of blackbody elements at different locations on the inner wall of the heating furnace includes: the number of blackbody elements on the left inner wall of the heating furnace, the number of blackbody elements on the upper inner wall of the heating furnace, and the number of blackbody elements on the right inner wall of the heating furnace.
[0071] In the module: the number of neurons in the neural network input layer is equal to the temperature data corresponding to each blackbody; the temperature data also corresponds to the position and time information of each blackbody.
[0072] The number of neurons in the hidden layer of the neural network is set to 2, and non-linear features are introduced through the Sigmoid activation function.
[0073] After training, the prediction model uses mean absolute error to measure the difference between the prediction results of the prediction model and the actual number of black bodies, and the Adam optimizer is used to minimize the loss function.
[0074] In the prediction module, the prediction process refers to inputting new temperature data into the model after training to obtain a prediction of the number of blackbodies. In the example code, we use a trained neural network model to predict the number of blackbodies. Inputting new temperature data (with the same number of features as the training data) will return the predicted number of blackbodies. This can be used to optimize the layout of the heating furnace, thereby improving heat transfer efficiency and energy-saving performance.
[0075] The present invention provides a heating furnace blackbody arrangement system in embodiment 2, which provides a method for arranging blackbody elements on the furnace top and side walls during heating furnace renovation. It can quantitatively measure the radiation heat transfer effect and determine the optimal arrangement scheme by optimizing the arrangement of a certain number of blackbody elements in different positions in the furnace.
[0076] The heating furnace blackbody arrangement system proposed in Embodiment 2 of the present invention can firmly install numerous blackbody elements on the furnace lining without changing the original furnace structure, thereby increasing the heat transfer area and improving the heat transfer capacity of the furnace lining.
[0077] For a description of the relevant parts of the heating furnace blackbody arrangement method provided in this application embodiment, please refer to the detailed description of the corresponding parts of the heating furnace blackbody arrangement system provided in embodiment 1 of this application, and will not be repeated here.
[0078] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that the elements inherent in a process, method, article, or apparatus that includes a list of elements are included. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Additionally, portions of the technical solutions provided in the embodiments of this application that are consistent with the implementation principles of corresponding technical solutions in the prior art have not been described in detail to avoid excessive elaboration.
[0079] While specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art can make other modifications or variations based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.
Claims
1. A method for arranging a blackbody in a heating furnace, characterized in that, Includes the following steps: A heating experiment was conducted simulating the presence of blackbody elements at different locations on the inner wall of a heating furnace. Experimental data was recorded, including an observation dataset and a response dataset. The observation dataset contained furnace temperature data at different heating temperatures. The response dataset contained the number of blackbody elements at different locations on the inner wall of the furnace. The furnace temperature data at different heating temperatures included the furnace temperature during the first heating time period, the furnace temperature during the second heating time period, and the furnace temperature during the Nth heating time period. Where N is a natural number; the first time period is 15 minutes; the second time period is 30 minutes; and the Nth time period is 15*N minutes. A neural network for predicting the blackbody arrangement in a heating furnace was established. The neural network is trained by using the observation dataset as input and the response dataset as output to obtain a trained prediction model. The current furnace temperature data is input into the training prediction model. The predicted number of blackbodies is output based on the prediction of the training prediction model. The layout of the heating furnace is optimized based on the predicted number of blackbodies at different positions on the inner wall of the heating furnace. The current furnace temperature data has the same number of characteristics as the temperature data during training.
2. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The heating furnace is enclosed by a furnace chamber formed by a top and left and right side walls, and the furnace chamber includes a feeding zone, a preheating zone, a heating zone, a soaking zone and a discharging zone; Several blackbody elements are provided at the top of the preheating zone, the top of the heating zone, and the top of the soaking zone; each blackbody element is provided on the furnace lining at the top. Several blackbody elements are provided on the sides of the preheating zone, the heating zone, and the homogenizing zone.
3. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The process of simulating heating experiments with blackbody elements placed at different positions on the inner wall of the heating furnace and recording experimental data includes: using finite element software to simulate experiments with multiple blackbody material arrangement schemes in the heating furnace and recording experimental data.
4. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The process of recording experimental data also includes converting both the observation dataset and the response dataset into double-precision floating-point data.
5. The method for arranging a blackbody in a heating furnace according to claim 3, characterized in that, The number of blackbody elements at different positions on the inner wall of the heating furnace includes: the number of blackbody elements on the left inner wall of the heating furnace, the number of blackbody elements on the upper inner wall of the heating furnace, and the number of blackbody elements on the right inner wall of the heating furnace.
6. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The number of neurons in the input layer of the neural network is equal to the temperature data corresponding to each blackbody; the temperature data also corresponds to the position and time information of each blackbody.
7. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The hidden layer of the neural network has two neurons, and non-linear features are introduced through the Sigmoid activation function.
8. The method for arranging a blackbody in a heating furnace according to claim 1, characterized in that, The trained prediction model uses mean absolute error to measure the difference between the prediction results of the prediction model and the actual number of black bodies, and employs the Adam optimizer to minimize the loss function.
9. A blackbody arrangement system for a heating furnace, characterized in that, Acquisition module, creation module, and prediction module; The acquisition module is used to simulate a heating experiment with blackbody elements placed at different positions on the inner wall of the heating furnace, and to record experimental data. The experimental data includes an observation dataset and a response dataset. The observation dataset contains furnace temperature data at different heating temperatures. The response dataset contains the number of blackbody elements at different positions on the inner wall of the heating furnace. The furnace temperature data at different heating temperatures includes the furnace temperature during a first heating time period, the furnace temperature during a second heating time period, and the furnace temperature during an Nth heating time period, where N is a natural number. The first heating time period is 15 minutes; the second heating time period is 30 minutes; and the Nth heating time period is 15*N minutes. The establishment module is used to establish a neural network for predicting the blackbody arrangement of the heating furnace; The neural network is trained by using the observation dataset as input and the response dataset as output to obtain a trained prediction model. The prediction module is used to input the current furnace temperature data into the trained prediction model. Through the prediction of the trained prediction model, the predicted number of blackbodies is output. The layout of the heating furnace is optimized by the predicted number of blackbodies at different positions on the inner wall of the heating furnace. The current furnace temperature data has the same number of characteristics as the temperature data during training.