Induction furnace heating control method, equipment and system

Abstract

The invention relates to the technical field of induction heating temperature control, in particular to an induction furnace heating control method, device and system, and the method comprises the steps: obtaining an infrared thermal imaging image in the heating process of an induction furnace; environmental medium interference is obtained through shot noise features and edge gradient features in the infrared thermal imaging image of the induction furnace; obtaining induction heating sufficiency according to skin effect characteristics and temperature change trend characteristics in the infrared thermal imaging image of the induction furnace; obtaining a heating control factor according to the environmental medium interference and the induction heating sufficiency; and evaluating the overall heating condition of the material in the induction furnace through the heating control factor, and adjusting the temperature of an induction coil of the induction furnace according to the overall heating condition. The invention aims to accurately adjust the temperature of the induction coil of the induction furnace, improve the energy transfer efficiency of the induction furnace, improve the automatic control precision and reduce the energy consumption.

Description

Technical Field

[0001] This application relates to the field of induction heating temperature control technology, specifically to an induction furnace heating control method, equipment, and system. Background Technology

[0002] An induction furnace is an electric furnace that uses the induced electrothermal effect of materials to heat or melt them. Based on the principle of electromagnetic induction, an alternating magnetic field is generated through an induction coil, causing eddy currents and hysteresis effects (in ferromagnetic materials) to form inside the heated material, thereby converting electrical energy into heat energy. Induction furnace heating control technology achieves precise temperature control by adjusting the induction power supply, effectively improving heating efficiency, reducing energy waste, meeting the heating precision requirements of different materials and processes, and realizing intelligent production operation of the induction furnace.

[0003] The induction coil is the core component of an induction furnace. By controlling the temperature of the induction coil, energy consumption of the induction furnace can be effectively reduced, energy transfer efficiency improved, and the heating status of materials precisely regulated. Traditional monitoring methods, such as thermocouple sensors, can only acquire discrete point temperatures but cannot capture the temperature field distortion caused by eddy current distribution in the material within the induction furnace. While infrared thermal imaging technology can accurately capture the entire temperature field and transient changes of the material during induction heating, it is susceptible to shot noise generated in the infrared thermal image due to interference from the ambient medium of the induction furnace, leading to misjudgments of the material's induction heating temperature. Furthermore, the skin effect caused by the alternating electromagnetic field of the induction coil results in a much higher eddy current density on the material surface than inside, causing the surface temperature to rise faster and creating temperature distribution distortion, which affects the accurate determination of the temperature field generated by the induction coil. Summary of the Invention

[0004] In view of the above, it is necessary to provide a heating control method, equipment and system for induction furnaces to solve the above problems.

[0005] According to one aspect of this application, a heating control method for an induction furnace is provided, the method comprising: Acquire infrared thermal imaging images of all frames during the heating process of the induction furnace; A neighborhood window of the preset infrared thermal image is used. The gray values ​​of the pixels in each neighborhood window are segmented to obtain dark spot pixels. The difference in gray value distribution between all dark spot pixels and the remaining pixels in each neighborhood window is analyzed. Combined with the positional distribution of all dark spot pixels, the shot noise status of each neighborhood window is obtained. The distribution of gray value gradient and the distribution of gray value gradient direction angle of edge pixels in each neighborhood window are analyzed to obtain the edge gradient blur status of each neighborhood window. The shot noise status and the edge gradient blur status of each neighborhood window are positively fused to obtain the environmental medium interference of each neighborhood window. The distribution characteristics of gray values ​​of pixels in the vertical direction of each edge pixel in each neighborhood window are analyzed to obtain the skin effect severity of each neighborhood window; the degree of heating sufficiency of each neighborhood window is obtained based on the similarity of gray value distribution between each neighborhood window and other neighborhood windows in the current frame and all previous frames of infrared thermal imaging images; the negative correlation mapping result of the heating sufficiency of each neighborhood window is positively fused with the skin effect severity to obtain the inductive heating sufficiency of each neighborhood window. Based on the environmental medium interference and the sufficiency of induction heating in each neighborhood window, the heating control factor of each neighborhood window is obtained; based on the value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging, the heating of the induction furnace is controlled.

[0006] Specifically, the obtained dark spot pixels are as follows: The grayscale values ​​of all pixels in each neighborhood window are used for segmentation to obtain a grayscale segmentation threshold. Pixels with grayscale values ​​greater than the grayscale segmentation threshold are designated as dark spot pixels.

[0007] The process of obtaining the shot noise status of each neighborhood window includes: The difference between the mean gray value of all non-dark spot pixels and the mean gray value of all dark spot pixels in each neighborhood window is recorded as the gray value difference; the disorder level of the two-dimensional coordinates of all dark spot pixels in each neighborhood window is obtained; the result of forward fusion of the gray value difference and the disorder level is used as the shot noise status of each neighborhood window.

[0008] Specifically, obtaining the edge gradient blurring status of each neighborhood window involves: Calculate the mean gray-level gradient of all edge pixels in each neighborhood window, and obtain the degree of dispersion of the gray-level gradient direction angle of all edge pixels in each neighborhood window; the result of positively fusing the mean gray-level gradient of each neighborhood window with the degree of dispersion is used as the edge gradient blur status of each neighborhood window.

[0009] Specifically, obtaining the skin effect severity of each neighborhood window involves: Starting from each edge cell within the neighborhood window, obtain any edge cell within the neighborhood window and all cells whose vertical coordinates are less than the vertical coordinates of each edge cell. The sequence of gray values ​​of all cells obtained from any edge cell is recorded as the skin depth sequence of any edge cell. Calculate the product of the element range and the coefficient of variation of the skin depth sequence corresponding to each edge cell within each neighborhood window. Sum all the products obtained for each neighborhood window to obtain the skin effect severity of each neighborhood window.

[0010] The specific process for obtaining the degree of heating of each neighboring window is as follows: Calculate the average gray value of all pixels in each neighborhood window in each frame of infrared thermal imaging image. Record the sequence of average gray values ​​of each neighborhood window in the current frame and all previous frames of infrared thermal imaging images of the corresponding induction furnace as the gray value average sequence of each neighborhood window in the current frame. The similarity between each neighboring window and the grayscale mean sequence of the other neighboring windows in the current frame is obtained. All similarity values ​​obtained for each neighboring window are accumulated and multiplied with the grayscale mean of all pixels in each neighboring window to obtain the degree of heating of each neighboring window.

[0011] Specifically, the heating control factor for each neighborhood window is the reciprocal of the product of the environmental medium interference and the sufficiency of induction heating, and then normalized.

[0012] The process of controlling the heating of the induction furnace includes: Calculate the mean value of the heating control factor of all neighboring windows in the infrared thermal imaging image. If the mean value is less than the preset heating control threshold, it is determined that the temperature of the induction furnace does not need to be adjusted; otherwise, the temperature of the induction furnace is increased by the preset temperature range.

[0013] According to another aspect of this application, an induction furnace heating control device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0014] According to another aspect of this application, an induction furnace heating control system is provided, wherein the system stores a computer program that, when executed by a processor, implements any of the methods described above.

[0015] This application has at least the following beneficial effects: This application addresses the shortcomings of technologies that use infrared thermal imaging to capture the full-range temperature field of materials during induction heating for controlling the temperature of induction coils in induction furnaces. These shortcomings stem from the inability to accurately identify the sufficiency of material heating due to interference from the environmental medium within the furnace and the skin effect caused by the alternating electromagnetic field of the induction coil. The application provides a quantitative method for calculating environmental interference and the sufficiency of induction heating, which more accurately assesses the environmental interference, the severity of the skin effect, and the sufficiency of material heating in infrared thermal imaging images within the induction furnace.

[0016] Furthermore, by assessing the overall heating status of the material in the induction furnace through heating control factors, and adjusting the temperature of the induction coil of the induction furnace accordingly, the method comprehensively considers the degree of environmental noise interference and the uniformity of the temperature field of the material's induced heating. This effectively avoids the drawbacks of using infrared thermal imaging technology to assess the temperature control of the induction coil of the induction furnace, which is affected by environmental interference and the skin effect of the material, resulting in incorrect adjustments. Based on an accurate assessment of the sufficient uniformity of the material's induced heating, the method can precisely adjust the temperature of the induction coil of the induction furnace, thereby improving the energy transfer efficiency of the induction furnace, the accuracy of automated control, and reducing energy consumption. Attached Figure Description

[0017] Figure 1 A flowchart of the steps of an induction furnace heating control method provided in this application; Figure 2 A schematic diagram illustrating the process for obtaining the heating control factor provided in this application. Detailed Implementation

[0018] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0020] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0021] Please see Figure 1 The diagram illustrates a flowchart of an induction furnace heating control method according to an embodiment of this application, the method comprising the following steps: Step 1: Acquire infrared thermal imaging images of all frames during the heating process of the induction furnace.

[0022] To avoid interference from the strong magnetic field of the induction coil in this induction furnace and to ensure coverage of the material's viewing angle, this application deploys an infrared thermal imager at an angle parallel to the material. This allows for the acquisition of infrared thermal images of the material during the heating process on the side of the induction furnace. The frame rate of the infrared thermal imager must match the heating rate of the induction furnace to ensure that each frame captures temperature changes. In this embodiment, the acquisition frame rate of the infrared thermal imager is set to 20fps, and the triggering mode is set to continuous triggering to ensure that the infrared thermal imager continuously acquires infrared thermal imaging images of the induction furnace materials.

[0023] To improve the accuracy of temperature field identification in subsequent infrared thermal imaging of the induction furnace, the aforementioned infrared thermal imaging image of the induction furnace is used as input. A gamma transform algorithm is employed to obtain an induction furnace infrared thermal imaging image with enhanced image contrast. The Lucas-Kanade algorithm is then used to detect feature points in adjacent image frames, calculate the motion vectors of the feature points, and adjust the image coordinates of the current frame to align the material position with the previous frame, ensuring the continuity of induction heating monitoring and control of the induction furnace. Since both the gamma transform algorithm and the Lucas-Kanade algorithm are well-known technologies, the specific acquisition process will not be elaborated further.

[0024] Thus, real-time infrared thermal imaging images of the induction furnace heating process can be obtained through the above methods.

[0025] Step 2: Preset a neighborhood window for the infrared thermal imaging image, segment the grayscale values ​​of pixels in each neighborhood window to obtain dark spot pixels; analyze the grayscale distribution differences between all dark spot pixels and the remaining pixels in each neighborhood window, and combine the positional distribution of all dark spot pixels to obtain the shot noise status of each neighborhood window; analyze the distribution of grayscale gradients and the distribution of grayscale gradient direction angles of edge pixels in each neighborhood window to obtain the edge gradient blur status of each neighborhood window; based on the shot noise status and the edge gradient blur status of each neighborhood window, obtain the environmental medium interference of each neighborhood window.

[0026] During the heating process in an induction furnace, the moisture contained within the material gradually releases water vapor. Furthermore, the material may decompose or volatilize during the high-temperature heating process, releasing solid particles that remain suspended in the furnace, forming dust. The scattering of infrared radiation by this dust increases with particle concentration, and the water vapor strongly absorbs infrared radiation. Both of these factors cause distortion and interference in the contrast and temperature distribution of the infrared thermal imaging image of the material being heated in the induction furnace, making it impossible to accurately determine the temperature field formed by the induction coil.

[0027] Specifically, during the heating process of an induction furnace, when the infrared thermal imaging image is more severely affected by the environmental medium, the local area of ​​the infrared thermal imaging image is affected by infrared radiation scattering, resulting in significant shot noise. That is, the dark spot areas in the local area of ​​the infrared thermal imaging image are obviously randomly distributed. The gray value of the dark spot area is affected by the scattering or absorption of the environmental medium, making it significantly different from the gray value of the local area. At the same time, the main scattering effect of the environmental medium in the vertical direction makes the material edge gradient intensity in the infrared thermal imaging image more blurred and the edge gradient change trend more random.

[0028] Based on the above analysis, this application takes an arbitrary frame of an induction furnace infrared thermal imaging image as an example for subsequent processing to construct environmental medium interference characteristics. This is used to characterize the severity of shot noise and the degree of edge gradient blurring caused by interference from the furnace's internal environmental medium in the infrared thermal imaging image within the neighborhood. This application divides the infrared thermal imaging image into N neighborhood windows of equal size, with each neighborhood window having a size of 7. 7, for those who are not satisfied with 7 The neighborhood window of 7 is expanded by linear interpolation. Alternatively, the implementer can set the size of the neighborhood window according to the actual situation. The gray values ​​of all pixels in each neighborhood window in the infrared thermal imaging image of the induction furnace are used as input. The gray value segmentation threshold of each neighborhood window is obtained by using OTSU threshold segmentation. All pixels in each neighborhood window with gray values ​​less than the gray value segmentation threshold are recorded as dark spot pixels of each neighborhood window, and their position coordinates are obtained.

[0029] An edge detection algorithm based on the Canny operator is used to obtain all edge pixels in the infrared thermal imaging image of the induction furnace. The gray-level gradient direction angle and gray-level gradient value in the vertical direction of all edge pixels in each neighborhood window of the infrared thermal imaging image are obtained by the Sobel operator.

[0030] The difference between the mean grayscale value of all non-dark spot pixels and the mean grayscale value of all dark spot pixels in each neighborhood window is denoted as grayscale difference. The disorder level of the two-dimensional coordinates of all dark spot pixels in each neighborhood window is obtained. The grayscale difference and the disorder level are positively fused to obtain the shot noise status of each neighborhood window. In this embodiment, the difference between variables is calculated using the difference value, and the grayscale difference is denoted as 'a'. In this embodiment, the disorder level between multiple variables is calculated using information entropy, and the disorder level is denoted as 'b'. The shot noise status of each neighborhood window is denoted as... Its formula is as follows: In the formula, Represents the natural constant.

[0031] The mean grayscale gradient of all edge pixels in each neighborhood window is calculated to obtain the dispersion of the grayscale gradient direction angle of all edge pixels in each neighborhood window. The mean grayscale gradient of each neighborhood window and the dispersion are positively fused to obtain the edge gradient blur status of each neighborhood window. In this embodiment, the dispersion between multiple variables is calculated using variance. It should be noted that if the neighborhood window does not contain any edge pixels or only has one edge pixel, the edge gradient blur status of the neighborhood window is set to 1. The edge gradient blur status of each neighborhood window is denoted as... Its formula is as follows: In the formula, c represents the mean gray-level gradient of all edge pixels within each neighborhood window; d represents the variance of the gray-level gradient direction angle of all edge pixels within each neighborhood window.

[0032] Furthermore, the environmental medium interference of each neighborhood window is obtained by normalizing the product of the shot noise condition and the edge gradient blur condition. In this embodiment, the sigmoid function is used as the normalization function, but the implementer can determine the normalization function according to the actual situation.

[0033] It should be understood that the environmental medium interference reflects the differences in grayscale distribution of shot noise and the abnormality of edge gradient intensity caused by environmental medium interference within each neighborhood window of the induction furnace infrared thermal imaging image; the shot noise condition reflects the degree of grayscale difference of dark spot pixels and the discreteness of dark spot pixel distribution within each neighborhood window of the induction furnace infrared thermal imaging image; while the edge gradient blurring condition characterizes the degree of blurring of the vertical edge gradient intensity and the randomness of the edge gradient direction caused by the scattering effect of the environmental medium in the induction furnace infrared thermal imaging image. During the heating process of the induction furnace, the more severe the interference of the environmental medium in the infrared thermal imaging image of the material, the more discrete the distribution of dark spots caused by infrared radiation scattering in the infrared thermal imaging image, and the smaller the grayscale value corresponding to the dark spot area, that is, the shot noise condition becomes larger; at the same time, due to the influence of the main scattering effect of the environmental medium in the vertical direction, the grayscale gradient value of the material edge in the vertical direction within the neighborhood window becomes smaller, and the gradient direction difference of the material edge pixels becomes stronger, that is, the edge gradient blurring condition becomes larger.

[0034] Thus, the environmental medium interference of each neighboring window in any frame of infrared thermal imaging image during the heating process of the induction furnace can be obtained through the above method.

[0035] Step 3: Analyze the distribution characteristics of gray values ​​of pixels in the vertical direction of each edge pixel in each neighborhood window to obtain the skin effect severity of each neighborhood window; based on the similarity of gray value distribution between each neighborhood window and other neighborhood windows in the current frame and all previous frames of infrared thermal imaging images, obtain the heating sufficiency of each neighborhood window; positively fuse the negative correlation mapping result of the heating sufficiency of each neighborhood window with the skin effect severity to obtain the inductive heating sufficiency of each neighborhood window.

[0036] During induction furnace heating control, the alternating electromagnetic field of the induction coil causes the material to undergo skin effect during induction heating. The eddy current density on the material surface is higher than that inside, resulting in a faster temperature rise on the surface while the actual internal temperature remains lower. This hinders the identification of the temperature field in infrared thermal imaging. Relying solely on environmental interference to control induction furnace heating is insufficient because it lacks quantitative analysis of the induction heating state of the material inside the furnace, making it impossible to accurately assess the actual heating situation. This approach may lead to errors in the execution of heating control strategies, thereby affecting the heating quality of the material.

[0037] Specifically, during the heating process in an induction furnace, the milder the skin effect generated by the alternating electromagnetic field of the induction coil and the higher the degree of induction heating of the material, the greater the skin depth of the material edge in the vertical direction in the infrared thermal imaging image of the induction furnace. That is, the smaller the difference between the gray values ​​of the material edge pixels and the pixels in the vertical direction, and the more uniform the gray value change of the material edge pixels in the vertical direction. At the same time, the more the material is affected by induction heating, the more obvious the high gray value situation in the infrared thermal imaging image, and the smaller the difference in gray value change trend between different neighborhood ranges in the infrared thermal imaging image of the material over time.

[0038] Based on the above analysis, this application constructs an induction heating sufficiency model to characterize the severity of the skin effect of materials and the degree of induction heating within each neighborhood window of an infrared thermal imaging image of an induction furnace. Taking any neighborhood window in the infrared thermal imaging image of an induction furnace as an example, subsequent processing is performed. Starting from each edge pixel within the neighborhood window, any edge pixel within the neighborhood window and all pixels whose vertical coordinates are less than the vertical coordinates of each edge pixel are obtained. The sequence of gray values ​​of all pixels obtained from the obtained edge pixel is recorded as the skin depth sequence of the obtained edge pixel.

[0039] Calculate the average gray value of all pixels in each neighborhood window in each frame of the infrared thermal imaging image of the induction furnace. Record the sequence of average gray values ​​of each neighborhood window in the current frame and all previous frames of the corresponding infrared thermal imaging images of the induction furnace as the gray value sequence of each neighborhood window in the current frame.

[0040] The similarity between each neighboring window and the grayscale mean sequence of other neighboring windows in the current frame is obtained. All similarity scores obtained for each neighboring window are summed and multiplied by the average grayscale value of all pixels in that window to obtain the heating sufficiency of each neighboring window, denoted as . In this embodiment, the similarity between sequences is measured using cosine similarity.

[0041] Calculate the product of the element-wise range and coefficient of variation of the skin depth sequence for each edge cell within each neighborhood window. Sum all products obtained for each neighborhood window to obtain the skin effect severity for each neighborhood window, denoted as . .

[0042] The negative correlation mapping result of the heating sufficiency of each neighborhood window is positively fused with the skin effect severity to obtain the induction heating sufficiency of each neighborhood window, denoted as . In this embodiment, the formula for the sufficiency of induction heating is as follows: .

[0043] It should be understood that the sufficiency of induction heating is used to reflect the severity of the skin effect caused by the alternating electromagnetic field of the induction coil within each neighborhood window range of the infrared thermal imaging image of the induction furnace, as well as the degree of sufficient and uniform induction heating of the material; the severity of the skin effect is used to reflect the obviousness of the skin depth of the material within each neighborhood window range of the infrared thermal imaging image of the induction furnace; and the degree of sufficient heating is used to characterize the high temperature level within each neighborhood window range of the infrared thermal imaging image of the induction furnace, as well as the temperature variation differences within different neighborhood window ranges. During the heating process in an induction furnace, the milder the skin effect caused by the alternating electromagnetic field of the induction coil in the infrared thermal imaging image of the material, and the more fully the material is heated, the greater the skin depth of the material in each region of the infrared thermal imaging image, the smaller the pixel grayscale range in the vertical direction of the material edge pixels, and the more uniform the change in pixel grayscale value in the vertical direction of the material edge pixels, i.e., the less severe the skin effect. At the same time, the better the heating condition in each region of the infrared thermal imaging image of the induction furnace, the higher the average grayscale value in the neighborhood window, and the smaller the difference in temperature change trend in different neighborhood areas over time, i.e., the greater the degree of heating.

[0044] Thus, the sufficiency of induction heating in each neighboring window of any frame of infrared thermal imaging image of the induction furnace during the heating process can be obtained through the above method.

[0045] Step 4: Based on the environmental medium interference and the sufficiency of induction heating in each neighborhood window, obtain the heating control factor for each neighborhood window; based on the value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging, control the heating of the induction furnace.

[0046] In the heating control of induction furnace, when the skin effect of the material caused by the alternating electromagnetic field of the induction coil is less pronounced in the local area of ​​the infrared thermal imaging of the induction furnace, the material is more fully heated and the interference from the environmental medium in the induction furnace is less blurred, the material is heated more evenly and fully in the induction furnace. At this time, there is less need to adjust the temperature of the induction coil of the induction furnace, thereby avoiding excessive heating of the material and energy waste.

[0047] Therefore, this application constructs a heating control factor to characterize the degree of temperature control of the induction coil during the heating process of the induction furnace. It can be obtained through the interference of the environmental medium and the sufficiency of induction heating. Specifically, in one processing case of this application, the reciprocal of the product of the interference of the environmental medium and the sufficiency of induction heating in each neighborhood window of the infrared thermal imaging image of the induction furnace is normalized and used as the heating control factor of each neighborhood window. In this embodiment, the normalization function adopts the sigmoid function.

[0048] The flowchart for obtaining the heating control factor is shown below. Figure 2 As shown.

[0049] During the heating control of an induction furnace, when the sufficiency of induction heating within the adjacent window is low and the interference from the environmental medium is also low, it indicates that the quality of the infrared thermal imaging image of the material induction furnace is less affected by the environmental medium, and can accurately characterize the temperature field characteristics of the material. At this time, the material is more unevenly and fully heated in the induction furnace, and the skin effect caused by the alternating electromagnetic field of the induction coil is more severe. Therefore, the temperature of the induction coil of the induction furnace should be increased in a timely manner to ensure that the material is fully and evenly heated and to improve the energy transfer efficiency of the induction furnace.

[0050] Thus, the heating control factor of each neighboring window in any frame of the infrared thermal imaging image of the induction furnace during the heating process can be obtained through the above method.

[0051] This application sets a heating control threshold P. To prevent insufficient accuracy in controlling the temperature of the induction furnace coil due to the short acquisition time of the infrared thermal imaging image of the induction furnace, the cold start control period of the induction furnace coil temperature is set to 2 minutes. That is, the first moment after 2 minutes after the heating control of the induction furnace is taken as the earliest moment for each control of the temperature of the induction furnace coil.

[0052] When the average value of the heating control factor corresponding to all neighboring windows in the infrared thermal imaging image of the induction furnace is less than the heating control threshold, it is considered that the material in the induction furnace is being heated sufficiently and uniformly, and the skin effect caused by the alternating electromagnetic field of the induction coil is slight, so there is no need to adjust the temperature of the induction coil. Conversely, when the average value of the heating control factor corresponding to all neighboring windows in the infrared thermal imaging image of the induction furnace is greater than or equal to the heating control threshold, it is considered that the material in the induction furnace is not being heated evenly and the degree of heating is insufficient, and the skin effect caused by the alternating electromagnetic field of the induction coil is severe. In this case, the temperature of the induction coil should be increased to ensure that the material is heated sufficiently and uniformly. In this application, the heating control threshold P and the induction coil temperature of the induction furnace that are increased each time are 0.6 and 10°C, respectively. In this embodiment, the temperature of the induction coil of the induction furnace can be achieved by adjusting the output power of the induction furnace power supply through a PLC programmable logic controller. Since the PLC adjustment control of the output power of the induction furnace power supply is a known technology, the specific acquisition process will not be described in detail. Implementers can set the heating control threshold P and the induction coil temperature value of the induction furnace according to the actual situation.

[0053] Based on the same concept as the method embodiments of this application, an induction furnace heating control device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0054] Based on the same concept as the method embodiments of this application, an induction furnace heating control system is provided, wherein the system stores a computer program, and when the computer program is executed by a processor, it implements any of the methods described above.

[0055] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of the systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0056] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A heating control method for an induction furnace, characterized in that, The method includes the following steps: Acquire infrared thermal imaging images of all frames during the heating process of the induction furnace; A neighborhood window of the preset infrared thermal image is used. The gray values ​​of the pixels in each neighborhood window are segmented to obtain dark spot pixels. The difference in gray value distribution between all dark spot pixels and the remaining pixels in each neighborhood window is analyzed. Combined with the positional distribution of all dark spot pixels, the shot noise status of each neighborhood window is obtained. The distribution of gray value gradient and the distribution of gray value gradient direction angle of edge pixels in each neighborhood window are analyzed to obtain the edge gradient blur status of each neighborhood window. The shot noise status and the edge gradient blur status of each neighborhood window are positively fused to obtain the environmental medium interference of each neighborhood window. The distribution characteristics of gray values ​​of pixels in the vertical direction of each edge pixel in each neighborhood window are analyzed to obtain the skin effect severity of each neighborhood window; the degree of heating sufficiency of each neighborhood window is obtained based on the similarity of gray value distribution between each neighborhood window and other neighborhood windows in the current frame and all previous frames of infrared thermal imaging images; the negative correlation mapping result of the heating sufficiency of each neighborhood window is positively fused with the skin effect severity to obtain the inductive heating sufficiency of each neighborhood window. Based on the environmental medium interference and the sufficiency of induction heating in each neighborhood window, the heating control factor of each neighborhood window is obtained; based on the value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging, the heating of the induction furnace is controlled.

2. The induction furnace heating control method as described in claim 1, characterized in that, The obtained dark spot pixels are specifically as follows: The grayscale values ​​of all pixels in each neighborhood window are used for segmentation to obtain a grayscale segmentation threshold. Pixels with grayscale values ​​greater than the grayscale segmentation threshold are designated as dark spot pixels.

3. The induction furnace heating control method as described in claim 1, characterized in that, The process of obtaining the shot noise status for each neighborhood window includes: The difference between the mean gray value of all non-dark spot pixels and the mean gray value of all dark spot pixels in each neighborhood window is recorded as the gray value difference; the disorder level of the two-dimensional coordinates of all dark spot pixels in each neighborhood window is obtained; the result of forward fusion of the gray value difference and the disorder level is used as the shot noise status of each neighborhood window.

4. The induction furnace heating control method as described in claim 1, characterized in that, The edge gradient blurring status of each neighborhood window is obtained specifically as follows: Calculate the mean gray-level gradient of all edge pixels in each neighborhood window, and obtain the degree of dispersion of the gray-level gradient direction angle of all edge pixels in each neighborhood window; the result of positively fusing the mean gray-level gradient of each neighborhood window with the degree of dispersion is used as the edge gradient blur status of each neighborhood window.

5. The induction furnace heating control method as described in claim 1, characterized in that, The skin effect severity of each neighborhood window is obtained as follows: Starting from each edge cell within the neighborhood window, obtain any edge cell within the neighborhood window and all cells whose vertical coordinates are less than the vertical coordinates of each edge cell. The sequence of gray values ​​of all cells obtained from any edge cell is recorded as the skin depth sequence of any edge cell. Calculate the product of the element range and the coefficient of variation of the skin depth sequence corresponding to each edge cell within each neighborhood window. Sum all the products obtained for each neighborhood window to obtain the skin effect severity of each neighborhood window.

6. The induction furnace heating control method as described in claim 1, characterized in that, The specific process for obtaining the degree of heating sufficiency of each neighboring window is as follows: Calculate the average gray value of all pixels in each neighborhood window in each frame of infrared thermal imaging image. Record the sequence of average gray values ​​of each neighborhood window in the current frame and all previous frames of infrared thermal imaging images of the corresponding induction furnace as the gray value average sequence of each neighborhood window in the current frame. The similarity between each neighboring window and the grayscale mean sequence of the other neighboring windows in the current frame is obtained. All similarity values ​​obtained for each neighboring window are accumulated and multiplied with the grayscale mean of all pixels in each neighboring window to obtain the degree of heating of each neighboring window.

7. The induction furnace heating control method as described in claim 1, characterized in that, The heating control factor for each neighborhood window is obtained by normalizing the product of the environmental medium interference and the sufficiency of induction heating.

8. The induction furnace heating control method as described in claim 1, characterized in that, The process of controlling the heating of the induction furnace includes: Calculate the mean value of the heating control factor of all neighboring windows in the infrared thermal imaging image. If the mean value is less than the preset heating control threshold, it is determined that the temperature of the induction furnace does not need to be adjusted; otherwise, the temperature of the induction furnace is increased by the preset temperature range.

9. An induction furnace heating control device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-8.

10. An induction furnace heating control system, wherein the system stores a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-8.

Images