A sintering state detection method, system, electronic device and storage medium

Abstract

This application discloses a sintering state detection method, comprising: acquiring visible light images and infrared thermal images of the tail section of a sintering machine; wherein the tail section includes multiple red-fired layer connected regions; determining the area of ​​the red-fired layer connected regions using the visible light images; determining the centroid position of the red-fired layer connected regions using the infrared thermal images; and determining the sintering state based on the area and centroid position of the red-fired layer connected regions. If the sintering state is over-sintered or under-sintered, this application calculates the optimal machine speed based on the centroid position of the red-fired layer connected regions and the current machine speed, and then adjusts the sintering machine according to the optimal machine speed. This application can accurately detect over-sintered or under-sintered states and provide corresponding over-sintered / under-sintered control schemes. This application also discloses a sintering state detection system, a storage medium, and an electronic device, which have the above-mentioned beneficial effects.

Description

Technical Field

[0001] This application relates to the field of sintering machine control technology, and in particular to a sintering state detection method, system, electronic device and storage medium. Background Technology

[0002] Accurately controlling the position of the sintering endpoint in the bellows is crucial for fully utilizing the effective area of ​​the sintering machine, ensuring high quality, high output, and efficient cooling. If the sintering endpoint is reached prematurely, the sintering area is not fully utilized, and a large amount of air passes through the rear of the sintering machine, disrupting the ventilation system and reducing sinter output. Although over-burning may improve the mechanical strength of the sinter, it also increases the FeO content, worsening its reducibility and reducing the lifespan of the grate bars, while also wasting energy. If the sintering endpoint is delayed, it inevitably leads to increased raw material, increased return ore, and lower yield. Furthermore, unburned fuel unloaded into the cooler will continue to burn, damaging the equipment and reducing cooling efficiency.

[0003] Therefore, how to accurately detect the sintering state is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a sintering state detection method, system, electronic device, and storage medium that can accurately detect the sintering state.

[0005] To address the aforementioned technical problems, this application provides a method for detecting sintering state, comprising:

[0006] Visible light and infrared thermal images of the tail section of the sintering machine are acquired; wherein the tail section includes multiple connected domains of the red flame layer;

[0007] The area of ​​the connected region of the red fire layer is determined using the visible light image;

[0008] The centroid position of the connected domain of the red fire layer is determined using the infrared thermal image.

[0009] The sintering state is determined based on the area and centroid position of the connected domain of the red-fired layer.

[0010] Optionally, determining the area of ​​the connected region of the red-fire layer using the visible light image includes:

[0011] The visible light image is binarized to obtain a binarized visible light image;

[0012] The contour of each of the red-fire layer connected regions is identified based on the binarized visible light image, and the area of ​​each of the red-fire layer connected regions is calculated.

[0013] Optionally, after identifying the contour of each of the red-fire layer connected regions based on the binarized visible light image, the method further includes:

[0014] Remove the red-fire layer connected components in the binarized visible light image whose number of pixels is less than a preset number.

[0015] Optionally, determining the centroid position of the connected domain of the red-fire layer using the infrared thermal image includes:

[0016] The binarized visible light image and the infrared thermal image are registered and fused to obtain the position information of each connected domain of the red fire layer in the infrared temperature matrix corresponding to the infrared thermal image.

[0017] The centroid position of each of the connected domains of the infrared temperature layer is calculated based on the position information of each connected domain of the infrared temperature layer.

[0018] Optionally, the sintering state is determined based on the area and centroid position of the connected domain of the red-fired layer, including:

[0019] Calculate the degree of overheating (OB) using the first calculation formula. delta ;

[0020] If the degree of overheating is OB delta If the value is greater than the first preset value, the sintering state of the sintering machine is determined to be an over-burning state;

[0021] Wherein, the first calculation formula is OB delta =D(S)*(KB1-Yc) / H; Yc is the centroid ordinate of the connected domain of the red fire layer, KB1 is a preset parameter, KB1∈[H / 5,2H / 5], and H is the thickness of the material layer; S is the total area of ​​all the connected regions of the red fire layer, and PT is the total number of pixels in all the connected regions of the red fire layer in the infrared thermal image.

[0022] Optionally, the sintering state is determined based on the area and centroid position of the connected domain of the red-fired layer, including:

[0023] The area of ​​the upper half of the red flame layer connected region in the visible light image is determined based on the area of ​​the red flame layer connected region.

[0024] Calculate the degree of underburning (UB) using the second calculation formula. delta ;

[0025] If the underheating level UB delta If the value is greater than the second preset value, the sintering state of the sintering machine is determined to be under-sintering.

[0026] Wherein, the second calculation formula is UB delta=D(Sa)*(Yc-KB1') / H, where Yc is the centroid ordinate of the connected domain of the red fire layer, KB1' is a preset parameter, KB1'∈[H / 5,2H / 5], and H is the thickness of the material layer; Sa is the total area of ​​the connected domain of the upper half of the red fire layer, PT is the total number of pixels in all the connected domains of the red fire layer in the infrared thermal image, and k is a preset constant.

[0027] Optionally, after determining the sintering state based on the area and centroid position of the connected domain of the red-fired layer, the method further includes:

[0028] If the sintering state is over-sintered or under-sintered, the optimal speed of the sintering machine is calculated based on the centroid position of the red-fired layer connected domain and the current machine speed.

[0029] The sintering machine is adjusted according to the optimal speed.

[0030] This application also provides a sintering state detection system, including:

[0031] The image acquisition module is used to acquire visible light images and infrared thermal images of the tail section of the sintering machine; wherein, the tail section includes multiple red-fired layer connected domains;

[0032] An area determination module is used to determine the area of ​​the connected domain of the red fire layer using the visible light image;

[0033] The center of gravity determination module is used to determine the center of gravity position of the connected domain of the red fire layer using the infrared thermal image;

[0034] The sintering state detection module is used to determine the sintering state based on the area and centroid position of the connected domain of the red-fired layer.

[0035] This application also provides a storage medium storing a computer program thereon, which, when executed, implements the steps of the above-described sintering state detection method.

[0036] This application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor, when calling the computer program in the memory, implements the steps of the above-described sintering state detection method.

[0037] This application provides a sintering state detection method, comprising: acquiring a visible light image and an infrared thermal image of the tail section of a sintering machine; wherein the tail section includes multiple red-fired layer connected regions; determining the area of ​​the red-fired layer connected regions using the visible light image; determining the centroid position of the red-fired layer connected regions using the infrared thermal image; and determining the sintering state based on the area and centroid position of the red-fired layer connected regions.

[0038] This application acquires visible light and infrared thermal images of the tail section of a sintering machine. The visible light image is used to determine the area of ​​the connected region of the red-hot layer, and the infrared thermal image is used to determine the centroid position of the connected region. The sintering state is then determined based on the area and centroid position of the connected region. Compared to relying on manual experience to determine the sintering state, this application accurately detects the sintering state by determining the area and centroid position of the connected region. This application also provides a sintering state detection system, an electronic device, and a storage medium, all with the aforementioned advantages, which will not be elaborated upon here. Attached Figure Description

[0039] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a sintering state detection method provided in an embodiment of this application;

[0041] Figure 2 This is a schematic diagram illustrating the working principle of a tail section detection device provided in an embodiment of this application;

[0042] Figure 3 This is a schematic diagram showing the positional relationship between a binocular camera and a sintering machine, provided in an embodiment of this application.

[0043] Figure 4 This is a schematic diagram illustrating the principle of speed adjustment provided in an embodiment of this application;

[0044] Figure 5 This is a schematic diagram of a sintering state detection system provided in an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] Please see below. Figure 1 , Figure 1 This is a flowchart of a sintering state detection method provided in an embodiment of this application.

[0047] Specific steps may include:

[0048] S101: Acquire visible light and infrared thermal images of the tail section of the sintering machine;

[0049] This embodiment can be applied to a tail section detection device based on a binocular camera. Please refer to [link / reference]. Figure 2 , Figure 2 This is a schematic diagram illustrating the working principle of a tail section detection device provided in this application embodiment. Sensors on the sintering machine are used to detect the position of the tail section. A binocular camera acquires visible light and infrared thermal images of the tail section through an observation hole. Compressed air is input to reduce the impact of dust on the imaging, and cooling water is used to ensure the binocular camera operates at its normal operating temperature. The binocular camera transmits the visible light and infrared thermal images to the tail section detection device via a gigabit network cable and a gigabit network card. The sintering process parameter server interacts with the tail section detection device via the network card to exchange information about the sintering machine's speed. Please refer to [link to relevant documentation]. Figure 3 , Figure 3 This is a schematic diagram illustrating the positional relationship between a binocular camera and a sintering machine, provided in an embodiment of this application. The binocular camera can be directly facing the trolley's travel direction. The tail section of the machine includes multiple red-fired layers, which are connected together to form a red-fired layer connected domain.

[0050] S102: Determine the area of ​​the connected domain of the red fire layer using the visible light image.

[0051] S103: Determine the centroid position of the connected domain of the red fire layer using the infrared thermal image.

[0052] like Figure 3 As shown, in this embodiment, a binocular camera is installed at the tail of the sintering machine. The binocular camera includes an infrared thermal imager and a visible light camera. Due to the high contrast at the tail, the high-temperature portion of the red-fire layer in the visible light image is severely distorted in color. This results in a significant deviation in the extraction of the centroid position of the red-fire layer from the visible light image, affecting the final result of using this feature. Infrared thermal images do not have this problem, as the temperature data acquired by the infrared thermal imager is negligibly affected by natural light. Furthermore, the higher light contrast at the edge of the red-fire layer actually greatly aids in extracting the red-fire layer outline. The visible light image can provide accurate positional information for the connected regions of the red-fire layer. Therefore, this embodiment can extract the centroid position and area of ​​the connected regions of the red-fire layer through binocular information fusion.

[0053] S104: Determine the sintering state based on the area and centroid position of the connected domain of the red-fired layer.

[0054] The sintering state includes normal state, over-burned state, and under-burned state. Different sintering states correspond to different areas and centroid positions of the red-fired layer connected domains. In this embodiment, the sintering state is determined based on the area and centroid position of the red-fired layer connected domains so as to adjust the speed of the sintering machine according to the sintering state.

[0055] This embodiment acquires visible light and infrared thermal images of the tail section of the sintering machine. The visible light image is used to determine the area of ​​the connected region of the red-fired layer, and the infrared thermal image is used to determine the centroid position of this connected region. The sintering state is then determined based on the area and centroid position of the connected region. Compared to relying on manual experience to determine the sintering state, this embodiment accurately detects the sintering state by determining the area and centroid position of the connected region of the red-fired layer.

[0056] The following is a scheme for intelligent identification and control of sintering overheating based on tail section analysis. In this embodiment, the degree of overheating is OB. delta The identification is performed using two features: the area S of the connected regions of the red-fired layer and the centroid position Yc of the connected regions of the red-fired layer. These features are related to the degree of over-firing. Under normal sintering conditions, the position and size of the red-fired layer fall within a relatively fixed effective range, rather than a specific value. Let the thickness of the material layer in the sintering machine be H, the area of ​​each connected region of the red-fired zone in the tail section image be Sn∈[Sl, Sh] (n is the number of connected regions of the red-fired layer), and the ordinate of the centroid of the connected regions of the red-fired layer be Yn∈[Yl, Yh]. The specific process includes the following steps:

[0057] Step A1: Obtain the best binocular image at the same moment and perform binarization processing on the visible light image.

[0058] Among them, the best binocular image refers to a visible light image and an infrared thermal image captured at an angle perpendicular to the tail section (also known as the sintered cake section) and free from dust interference. Specifically, the visible light image is binarized (the pixel grayscale value of the red fire layer is 1, and the grayscale value of the other pixels is 0) to obtain the binarized visible light image.

[0059] Step A2: Extract the contours of the connected regions of the red fire layer in the visible light image and obtain the position information of each connected region of the red fire layer.

[0060] In this step, the contour of each red-fire layer connected region can be identified using a binarized visible light image, and then the position information and area of ​​each red-fire layer connected region can be determined based on the contour. Furthermore, after identifying the contour of each red-fire layer connected region based on the binarized visible light image, red-fire layer connected regions with a pixel count less than a preset number can be removed from the binarized visible light image to obtain the position information of the remaining red-fire layer connected regions. Specifically, in this embodiment, red-fire layer connected regions with a pixel count less than 1 / k of the total number of pixels in the image (k∈[2800,3200]) can be discarded.

[0061] Step A3: Retrieve the position of the red fire layer connected domain in the infrared temperature matrix through the registered relationship.

[0062] In this embodiment, the binarized visible light image and the infrared thermal image are registered and fused to obtain the position information of each connected region of the red-fire layer in the infrared temperature matrix corresponding to the infrared thermal image; the centroid position of each connected region of the red-fire layer is calculated based on the position information of each connected region of the red-fire layer in the infrared temperature matrix. The registration and fusion process is as follows: the infrared thermal image and the binarized visible light image are calibrated; the scaling factor of the infrared thermal image relative to the binarized visible light image is determined; the offset distance of the infrared thermal image relative to the binarized visible light image is obtained; the two images are superimposed to obtain the finally registered and fused image; and the position information of each connected red-fire region in the infrared temperature matrix is ​​obtained by reverse calculation.

[0063] Step A4: Calculate the area and centroid position of the connected domain of the red-hot layer to determine if it is overburned; if yes, proceed to step A5; if no, proceed to step A1.

[0064] The process of calculating the area of ​​the connected region of the red fire layer from the binarized visible light image is as follows:

[0065] S i =∑g(x, y) (i = 1...n);

[0066] S i Let g(x,y) represent the area of ​​the connected region of the i-th red fire layer, and g(x,y) represent the gray value of the pixel after binarization.

[0067] The process of calculating the centroid ordinate Yc of the connected domain of the red-hot layer using the infrared temperature matrix is ​​as follows:

[0068]

[0069] y ij Let t represent the ordinate of the j-th pixel in the connected domain of the i-th red fire layer. ij This represents the temperature value of the j-th pixel in the i-th connected red-hot region.

[0070] Step A5: Calculate the degree of overheating.

[0071] The size and center of gravity of the red-fired layer's connected region are closely related to the degree of overburning, with the location of the connected region being the primary factor. Therefore, the connected region of the red-fired layer is used as a standard to measure the degree of overburning. Based on experience, under normal sintering conditions, the center of gravity of the red-fired layer in the tail section is generally located within the range of [H / 5, 2H / 5] (with the grate plate as a reference, and H being the thickness of the material layer).

[0072] Specifically, in this embodiment, the degree of overheating (OB) can be calculated using the first calculation formula. delta If the degree of overheating is OB delta If the value is greater than the first preset value, the sintering state of the sintering machine is determined to be an over-burning state;

[0073] The first calculation formula above is OB delta =D(S)*(KB1-Yc) / H; Yc is the centroid ordinate of the connected domain of the red fire layer, KB1 is a preset parameter, KB1∈[H / 5,2H / 5], Yc∈[0,H / 5], H is the thickness of the material layer; S is the total area of ​​all the connected regions of the red fire layer, and PT is the total number of pixels in all the connected regions of the red fire layer in the infrared thermal image.

[0074] Step A6: Adjust the speed of the sintering machine based on the overheating adjustment strategy to restore the sintering state to normal.

[0075] If the sintering state is an over-burning state, the optimal speed of the sintering machine is calculated based on the centroid position of the red-fired layer connected domain and the current machine speed, so that the sintering machine can be adjusted according to the optimal speed.

[0076] Optimal speed SP need The calculation formula for SP is as follows: need =KB2*(1-Yc / H)*SP now +KB3;

[0077] Where KB2∈[5 / 4,5 / 3], KB3<0.1m / min, both are constants; Yc∈[0,H / 5], SP now This is the current machine speed. This embodiment can be based on the optimal machine speed SP. need Intelligent speed adjustment: Specifically, the speed of the sintering machine can be adjusted using an intelligent control model based on the degree of over-burning. Please refer to Table 1:

[0078] Table 1 Overheating Control Strategy

[0079] Overheating Adjustment Adjusting interval 0.1 > abs(OBdelta) >= 0.01 Sp = sp + 0.1 5 minutes 0.2 > abs(OBdelta) >= 0.1 Sp = sp + 0.2 5 minutes 0.4 > abs(OBdelta) >= 0.2 Sp = sp + 0.3 5 minutes abs(OBdelta)<0.01 No adjustment

[0080] The above embodiments rely on adjusting the sintering endpoint to a suitable position by controlling the sintering machine speed SP_speed during the sintering process, and establishing an intelligent identification system OB based on the image features of the tail section to recognize the degree of over-burning of the current sintering mixture. delta This embodiment is based on the degree of overheating and the current machine speed SP. now Calculate the optimal speed SP of the current sintering machine. need ;

[0081] This embodiment establishes an intelligent recognition algorithm based on the image features of the sintering machine tail section to determine whether over-sintering occurs during the current sintering process, and also establishes an intelligent control model. When the permeability of the mixture does not change significantly, the sintering endpoint is correctly controlled by increasing the machine speed; when the permeability changes significantly, the material layer thickness should be adjusted, and attention should be paid to adapting the machine speed to correctly control the endpoint.

[0082] The following provides a sintering under-firing intelligent identification and control scheme based on tail section analysis. In this embodiment, the degree of under-firing is UB. delta The identification is performed using two features: the area S of the connected regions of the red-fired layer and the centroid position Yc of the connected regions of the red-fired layer. Under normal sintering conditions, the position and size of the red-fired layer fall within a relatively fixed effective range, rather than a specific value. Let the thickness of the material layer in the sintering machine be H, the area of ​​each connected region of the red-fired layer in the tail section image be Sn∈[Sl, Sh] (n is the number of connected regions of the red-fired layer), and the ordinate of the centroid of the red-fired zone be Yn∈[Yl, Yh]. The specific process includes the following steps:

[0083] Step B1: Obtain the best binocular image at the same moment and perform binarization processing on the visible light image.

[0084] The optimal binocular image refers to a visible light image and an infrared thermal image captured simultaneously from a shooting angle perpendicular to the tail section (also known as the sintered cake section), without dust interference. Specifically, the visible light image is binarized (the pixels of the red fire layer have a grayscale value of 1, and the grayscale value of the remaining pixels is 0) to obtain the binarized visible light image.

[0085] Step B2: Extract the contours of the connected regions of the red fire layer in the visible light image and obtain the positional information of each connected region of the red fire layer;

[0086] In this step, the contour of each red-fire layer connected region can be identified using a binarized visible light image, and then the position information and area of ​​each red-fire layer connected region can be determined based on the contour. Furthermore, after identifying the contour of each red-fire layer connected region based on the binarized visible light image, red-fire layer connected regions with a pixel count less than a preset number can be removed from the binarized visible light image to obtain the position information of the remaining red-fire layer connected regions. Specifically, in this embodiment, red-fire layer connected regions with a pixel count less than 1 / k of the total number of pixels in the image (k∈[2800,3200]) can be discarded.

[0087] Step B3: Retrieve the position of the red fire layer connected domain in the infrared temperature matrix through the registered relationship.

[0088] In this embodiment, the binarized visible light image and the infrared thermal image are registered and fused to obtain the position information of each connected region of the red-fire layer in the infrared temperature matrix corresponding to the infrared thermal image; the centroid position of each connected region of the red-fire layer is calculated based on the position information of each connected region of the red-fire layer in the infrared temperature matrix. The registration and fusion process is as follows: the infrared thermal image and the binarized visible light image are calibrated; the scaling factor of the infrared thermal image relative to the binarized visible light image is determined; the offset distance of the infrared thermal image relative to the binarized visible light image is obtained; the two images are superimposed to obtain the finally registered and fused image; and the position information of each connected red-fire region in the infrared temperature matrix is ​​obtained by reverse calculation.

[0089] Step B4: Calculate the area of ​​the connected domain of the upper half of the red flame layer and the centroid position of the connected domain of the red flame layer to determine whether it is underburned; if yes, proceed to step B5; if no, proceed to step B1.

[0090] Specifically, the area of ​​the upper half of the red-fire layer connected region in the visible light image can be determined by the area of ​​the red-fire layer connected region on the cross-section of the computer tail.

[0091] S i =∑g(x, y) (i = 1...n);

[0092]

[0093] S i Let g(x,y) represent the area of ​​the i-th red-fire layer connected region, g(x,y) represent the gray value of the pixel after binarization, Yci represent the centroid position of the i-th red-fire layer connected region, Sa represent the total area of ​​the upper half of the red-fire layer connected region, PT represent the total number of pixels in all the red-fire layer connected regions in the infrared thermal image, and n represent the number of red-fire layer connected regions.

[0094] The centroid ordinate of the red-hot region is calculated using the infrared temperature matrix as follows:

[0095]

[0096] y ij Let t represent the ordinate of the j-th pixel in the connected domain of the i-th red fire layer. ij This represents the temperature value of the j-th pixel in the i-th connected red-hot region.

[0097] Step B5: Calculate the degree of underheating.

[0098] The size of the connected area of ​​the red-fired layer and the position of its center of gravity are closely related to the degree of underfiring. The main factor is the position of the connected area of ​​the red-fired layer. Therefore, the position of the connected area of ​​the red-fired layer is used as a standard to measure the degree of underfiring. Based on experience, under normal sintering conditions, the position range of the center of gravity of the red-fired layer in the tail section is generally [H / 5, 2H / 5] (with the grate plate as the reference, and H as the thickness of the material layer).

[0099] Specifically, in this embodiment, the degree of underburning UB can be calculated using the second calculation formula. delta If the degree of underburning is UB delta If the value is greater than the second preset value, the sintering state of the sintering machine is determined to be under-sintering.

[0100] Wherein, the second calculation formula is UB delta =D(Sa)*(Yc-KB1') / H, where Yc is the centroid ordinate of the connected domain of the red fire layer, KB1' is a preset parameter, KB1'∈[H / 5,2H / 5], Yc∈[H / 2,H], and H is the thickness of the material layer; Sa is the total area of ​​the upper half of the red-fire layer connected domain (the total area of ​​the upper half of the red-fire area on the cross-section of the sintered cake), PT is the total number of pixels of all the red-fire layer connected domains in the infrared thermal image (i.e., the total number of pixels of the tail sintered cake cross-section in the infrared image), and k is a preset constant, k∈[2800,3200].

[0101] Step B6: Adjust the speed of the sintering machine based on the under-sintering adjustment strategy to restore the sintering state to normal.

[0102] If the sintering state is under-sintering, the optimal speed of the sintering machine is calculated based on the centroid position of the red-fired layer's connected domain and the current machine speed, so that the sintering machine can be adjusted according to the optimal speed.

[0103] Optimal speed SP need The calculation formula for SP is as follows: need =KB2*(1-Yc / H)*SP now +KB3;

[0104] Where KB2∈[5 / 4,5 / 3], KB3<0.1m / min, both are constants; Yc∈[H / 2,H], SP now This is the current machine speed.

[0105] Specifically, this embodiment can be based on the optimal speed SP. need Intelligent speed adjustment: Specifically, the speed of the sintering machine can be adjusted using an intelligent control model based on the degree of over-burning. Please refer to Table 2:

[0106] Table 2 Underheating Control Strategies

[0107] under-burning Adjustment Adjusting interval 0.3 > abs(UBdelta) >= 0.1 Sp = sp - 0.1 5 minutes 0.6 > abs(UBdelta) >= 0.3 Sp = sp - 0.2 5 minutes 0.8 > abs(UBdelta) >= 0.6 Sp = sp - 0.3 5 minutes abs(UBdelta)<0.1 No adjustment

[0108] The above embodiments rely on adjusting the sintering endpoint to a suitable position by controlling the sintering machine speed SP_speed during the sintering process, and establishing an intelligent identification system UB based on the image features of the tail section to determine the under-sintering degree of the current sintering mixture. delta This embodiment is based on the degree of underburning and the current machine speed SP. now Calculate the optimal speed SP of the current sintering machine. need This embodiment is based on the degree of underburning and the current machine speed SP. now Calculate the optimal speed SP of the current sintering machine. need ;

[0109] This embodiment establishes an intelligent recognition algorithm based on the image features of the sintering machine tail section to determine whether there is under-sintering during the current sintering process, and establishes an intelligent control model. When the permeability of the mixture does not change significantly, the sintering endpoint is correctly controlled by slowing down the machine speed; when the permeability changes significantly, the material layer thickness should be adjusted, and attention should be paid to adapting the machine speed to correctly control the endpoint.

[0110] Please see Figure 4 , Figure 4 This is a schematic diagram of a speed adjustment principle provided in an embodiment of this application. After the tail section graphic is input into the tail section detection device, the degree of over-burning or under-burning is determined by the intelligent identification method and model of sintering process parameters. Based on the current speed and the degree of over-burning or under-burning, the optimal speed of the sintering process is determined by tail-based analysis. The actual speed SP_speed of the sintering machine is adjusted according to the optimal speed by the intelligent control model.

[0111] Please see Figure 5 , Figure 5 This is a schematic diagram of a sintering state detection system provided in an embodiment of this application;

[0112] The system may include:

[0113] Image acquisition module 501 is used to acquire visible light images and infrared thermal images of the tail section of the sintering machine; wherein, the tail section includes multiple red-fired layer connected domains;

[0114] Area determination module 502 is used to determine the area of ​​the connected domain of the red fire layer using the visible light image;

[0115] The center of gravity determination module 503 is used to determine the center of gravity position of the connected domain of the red fire layer using the infrared thermal image;

[0116] The sintering state detection module 504 is used to determine the sintering state based on the area and centroid position of the connected domain of the red-fired layer.

[0117] This embodiment acquires visible light and infrared thermal images of the tail section of the sintering machine. The visible light image is used to determine the area of ​​the connected region of the red-fired layer, and the infrared thermal image is used to determine the centroid position of this connected region. The sintering state is then determined based on the area and centroid position of the connected region. Compared to relying on manual experience to determine the sintering state, this embodiment accurately detects the sintering state by determining the area and centroid position of the connected region of the red-fired layer.

[0118] Furthermore, the area determination module 502 is used to perform binarization processing on the visible light image to obtain a binarized visible light image; it is also used to identify the contour of each of the red fire layer connected regions based on the binarized visible light image, and calculate the area of ​​each of the red fire layer connected regions.

[0119] Furthermore, it also includes:

[0120] The filtering module is used to remove red-fire layer connected regions in the binarized visible light image whose number of pixels is less than a preset number after identifying the contour of each red-fire layer connected region based on the binarized visible light image.

[0121] Furthermore, the centroid determination module 503 is used to register and fuse the binarized visible light image with the infrared thermal image to obtain the position information of each of the red-fire layer connected regions in the infrared temperature matrix corresponding to the infrared thermal image; it is also used to calculate the centroid position of each of the red-fire layer connected regions based on the position information of each of the red-fire layer connected regions in the infrared temperature matrix.

[0122] Furthermore, the sintering state detection module 504 is used for:

[0123] Calculate the degree of overheating (OB) using the first calculation formula. delta ;

[0124] If the degree of overheating is OB delta If the value is greater than the first preset value, the sintering state of the sintering machine is determined to be an over-burning state;

[0125] Wherein, the first calculation formula is OB delta =D(S)*(KB1-Yc) / H; Yc is the centroid ordinate of the connected domain of the red fire layer, KB1 is a preset parameter, KB1∈[H / 5,2H / 5], and H is the thickness of the material layer; S is the total area of ​​all the connected regions of the red fire layer, and PT is the total number of pixels in all the connected regions of the red fire layer in the infrared thermal image.

[0126] Furthermore, the sintering state detection module 504 is used for:

[0127] The area of ​​the upper half of the red flame layer connected region in the visible light image is determined based on the area of ​​the red flame layer connected region.

[0128] Calculate the degree of underburning (UB) using the second calculation formula. delta ;

[0129] If the underheating level UB delta If the value is greater than the second preset value, the sintering state of the sintering machine is determined to be under-sintering.

[0130] Wherein, the second calculation formula is UB delta =D(Sa)*(Yc-KB1') / H, where Yc is the centroid ordinate of the connected domain of the red fire layer, KB1' is a preset parameter, KB1'∈[H / 5,2H / 5], and H is the thickness of the material layer; Sa is the total area of ​​the connected domain of the upper half of the red fire layer, PT is the total number of pixels in all the connected domains of the red fire layer in the infrared thermal image, and k is a preset constant.

[0131] Furthermore, it also includes:

[0132] The speed adjustment module is used to calculate the optimal speed of the sintering machine based on the center of gravity position of the connected domain of the red-fired layer and the current speed if the sintering state is an over-fired state or an under-fired state after determining the sintering state based on the area and center of gravity position of the connected domain of the red-fired layer; it is also used to adjust the sintering machine according to the optimal speed.

[0133] Since the embodiments of the system part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the system part, and they will not be repeated here.

[0134] This application also provides a storage medium on which a computer program is stored, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0135] This application also provides an electronic device that may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the electronic device may also include various network interfaces, power supplies, and other components.

[0136] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0137] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only 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 a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. 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.

Claims

1. A method for detecting sintering state, characterized in that, include: Visible light and infrared thermal images of the tail section of the sintering machine are acquired; wherein the tail section includes multiple red-fired layer connected domains; The area of ​​the connected region of the red fire layer is determined using the visible light image; The centroid position of the connected domain of the red fire layer is determined using the infrared thermal image. The sintering state is determined based on the area and centroid position of the connected domain of the red-fired layer; The determination of the sintering state based on the area and centroid position of the connected domain of the red-fired layer includes: The area of ​​the upper half of the red flame layer connected region in the visible light image is determined based on the area of ​​the red flame layer connected region. Calculate the degree of underburning using the second calculation formula. ; If the degree of underheating If the value is greater than the second preset value, the sintering state of the sintering machine is determined to be under-sintering. Wherein, the second calculation formula is Yc is the ordinate of the centroid of the connected domain of the red fire layer. These are preset parameters. H is the thickness of the material layer; Sa is the total area of ​​the connected domain of the upper half of the red fire layer, PT is the total number of pixels in all the connected domains of the red fire layer in the infrared thermal image, and k is a preset constant.

2. The sintering state detection method according to claim 1, characterized in that, Determining the area of ​​the connected region of the red-fire layer using the visible light image includes: The visible light image is binarized to obtain a binarized visible light image; The contour of each of the red-fire layer connected regions is identified based on the binarized visible light image, and the area of ​​each of the red-fire layer connected regions is calculated.

3. The sintering state detection method according to claim 2, characterized in that, After identifying the contour of each of the red-fire layer connected regions based on the binarized visible light image, the method further includes: Remove the red-fire layer connected components in the binarized visible light image whose number of pixels is less than a preset number.

4. The sintering state detection method according to claim 2, characterized in that, Determining the centroid position of the connected domain of the red-fire layer using the infrared thermal image includes: The binarized visible light image and the infrared thermal image are registered and fused to obtain the position information of each connected domain of the red fire layer in the infrared temperature matrix corresponding to the infrared thermal image. The centroid position of each of the connected domains of the infrared temperature layer is calculated based on the position information of each connected domain of the infrared temperature layer.

5. The sintering state detection method according to claim 4, characterized in that, The sintering state is determined based on the area and centroid position of the connected domain of the red-fired layer, including: Calculate the degree of overheating using the first calculation formula. ; If the degree of overheating If the value is greater than the first preset value, the sintering state of the sintering machine is determined to be an over-burning state; Wherein, the first calculation formula is Yc is the centroid ordinate of the connected domain of the red fire layer, and KB1 is a preset parameter. H is the thickness of the material layer; S is the total area of ​​all the connected regions of the red fire layer, and PT is the total number of pixels in all the connected regions of the red fire layer in the infrared thermal image.

6. The sintering state detection method according to any one of claims 1 to 5, characterized in that, After determining the sintering state based on the area and centroid position of the connected domain of the red-fired layer, the process further includes: If the sintering state is over-sintered or under-sintered, the optimal speed of the sintering machine is calculated based on the centroid position of the red-fired layer connected domain and the current machine speed. The sintering machine is adjusted according to the optimal machine speed.

7. A sintering state detection system, characterized in that, include: The image acquisition module is used to acquire visible light images and infrared thermal images of the tail section of the sintering machine; wherein, the tail section includes multiple red-fired layer connected domains; An area determination module is used to determine the area of ​​the connected domain of the red fire layer using the visible light image; The center of gravity determination module is used to determine the center of gravity position of the connected domain of the red fire layer using the infrared thermal image; The sintering state detection module is used to determine the sintering state based on the area and centroid position of the connected domain of the red-fired layer. The process by which the sintering state detection module determines the sintering state based on the area and centroid position of the connected domain of the red-fired layer includes: The area of ​​the upper half of the red flame layer connected region in the visible light image is determined based on the area of ​​the red flame layer connected region. Calculate the degree of underburning using the second calculation formula. ; If the degree of underheating If the value is greater than the second preset value, the sintering state of the sintering machine is determined to be under-sintering. Wherein, the second calculation formula is Yc is the ordinate of the centroid of the connected domain of the red fire layer. These are preset parameters. H is the thickness of the material layer; Sa is the total area of ​​the connected domain of the upper half of the red fire layer, PT is the total number of pixels in all the connected domains of the red fire layer in the infrared thermal image, and k is a preset constant.

8. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor, when calling the computer program in the memory, implements the steps of the sintering state detection method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores computer-executable instructions, which, when loaded and executed by a processor, implement the steps of the sintering state detection method as described in any one of claims 1 to 6.

Images