A method, apparatus, electronic device and storage medium for detecting intermediate-stage sprue nozzles.

Abstract

This application discloses a method, apparatus, electronic device, and storage medium for detecting a tundish nozzle, belonging to the field of automation technology in iron and steel metallurgy. The method includes: determining the resolution of the target image based on a target image of any target tundish nozzle to be detected and the basic parameter information of the target tundish nozzle; determining the target cross-sectional pixel area of ​​the target tundish nozzle based on the target image and a preset threshold segmentation algorithm; determining the target slag line pixel information and target necking pixel information of the target tundish nozzle based on the target image and a trained tundish nozzle feature recognition model; and determining the target cross-sectional physical area, target slag line physical information, and target necking physical information of the target tundish nozzle based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, respectively. This application can improve the accuracy of parameter measurement at the tundish nozzle, reducing measurement errors while improving measurement efficiency.

Description

Technical Field

[0001] This application relates to the field of automation technology in iron and steel metallurgy, and in particular to a method, apparatus, electronic device and storage medium for detecting the sprue nozzle. Background Technology

[0002] Currently, the tundish nozzle is a protective casting channel for molten steel between the tundish and the crystallizer. During the steelmaking process, the tundish nozzle cross-section is controlled by a stopper rod, thereby controlling the flow rate and flow field of molten steel inside the crystallizer. The stopper rod can effectively prevent secondary oxidation and splashing of molten steel.

[0003] However, during the steel casting process, the molten steel washes over the inner wall of the tundish nozzle, causing inclusions in the molten steel to adhere to and accumulate on the inner wall of the nozzle, forming nodules. At the same time, slag forms on the outer side of the nozzle and near the discharge port. Nodules and slag can easily cause fluctuations in the flow field of the crystallizer, leading to unstable casting, nodule shedding, slag entrapment, and nozzle blockage, which seriously affect the quality of the cast billet. Therefore, after the tundish nozzle is removed from the production line, it is necessary to effectively inspect the condition of the tundish nozzle to provide reliable assurance regarding the material, structure, and casting process of the nozzle.

[0004] Due to the high operating temperature of the sprue nozzle and the irregular shape of the nozzle after slag erosion, quantitative detection of the nozzle is quite difficult. Therefore, the current main methods for assessing the condition of the nozzle are visual inspection, tape measure measurement, and rubbing. However, manual measurement has a large measurement error, low accuracy, and low efficiency. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for detecting the intermediate sprue nozzle. The embodiments provided by this application can improve the accuracy of parameter measurement at the intermediate sprue nozzle, and improve measurement efficiency while reducing measurement errors.

[0006] In a first aspect, this application provides a method for detecting a sprue nozzle, the method comprising:

[0007] Based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet in the target, the resolution of the target image is determined;

[0008] Based on the target image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined;

[0009] Based on the target image and the trained sprue nozzle feature recognition model, the target slag line pixel information and the target necking pixel information at the target sprue nozzle are determined, wherein the trained sprue nozzle feature recognition model is used to characterize the model for recognizing slag line features and necking features.

[0010] Based on the resolution, the target cross-sectional pixel area, the target slag line pixel information, and the target necking pixel information, the target cross-sectional physical area, target slag line physical information, and target necking physical information at the water inlet of the target are determined respectively.

[0011] In one feasible implementation, determining the resolution of the target image based on the target image at the injection port of any target to be detected and the basic parameter information of the injection port in the target includes:

[0012] Based on the target image of the sprue inlet of any target to be detected, the reference scale pixel length of the target image is determined, wherein the reference scale is used to characterize any physical unit size of the sprue inlet of the target in the target image;

[0013] Based on the basic parameter information of the water inlet in the target, the physical length of the reference scale of the water inlet in the target is determined;

[0014] The resolution of the target image is determined based on the pixel length and physical length of the reference ruler.

[0015] In one feasible implementation, the target image at the injection port of any target to be detected is determined by the following method:

[0016] Determine the initial image of the injection port in any target to be detected;

[0017] Based on the initial image and the trained middle-bore nozzle recognition model, the target image at any target middle-bore nozzle to be detected is determined, wherein the trained middle-bore nozzle recognition model is used to characterize the model for recognizing the middle-bore nozzle.

[0018] In one feasible implementation, determining the target cross-sectional pixel area at the sprue inlet in the target based on the target image and a preset threshold segmentation algorithm includes:

[0019] Perform grayscale processing on the target image to determine the coordinates of the target points in the target image;

[0020] Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined from the target image.

[0021] In one feasible implementation, based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the sprue inlet in the target is determined from the target image, including:

[0022] Based on the target point coordinates and preset point division rules, candidate region images of the middle-water inlet are determined from the target image;

[0023] Based on the candidate region image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined.

[0024] In one feasible implementation, after determining the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target spout based on the resolution, the target cross-sectional pixel area, the target slag line pixel information, and the target necking pixel information, the spout spout detection method further includes:

[0025] Based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle, a tundish nozzle database is constructed for operators to query.

[0026] In one feasible implementation, after constructing a tundish nozzle database based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle for query by operators, the tundish nozzle detection method further includes:

[0027] Based on the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target inlet, it is determined whether the structure and casting process of the target inlet need to be optimized.

[0028] In a second aspect, this application provides a device for detecting a sprue nozzle, the device comprising:

[0029] The first determining module is used to determine the resolution of the target image based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet of the target;

[0030] The second determining module is used to determine the target cross-sectional pixel area at the water inlet in the target based on the target image and a preset threshold segmentation algorithm;

[0031] The third determining module is used to determine the target slag line pixel information and the target necking pixel information at the target slag inlet based on the target image and the trained slag inlet feature recognition model, wherein the trained slag inlet feature recognition model is used to characterize the model for recognizing slag line features and necking features.

[0032] The fourth determining module is used to determine the physical area of ​​the target cross section, the physical information of the target slag line, and the physical information of the target necking at the water inlet of the target, based on the resolution, the pixel area of ​​the target cross section, the pixel information of the target slag line, and the pixel information of the target necking.

[0033] In a third aspect of this application, an electronic device is provided, including a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the above-described method for detecting the water inlet.

[0034] In a fourth aspect, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described method for detecting the sprue outlet.

[0035] Compared with the prior art, the method, apparatus, and electronic equipment for detecting the sprue nozzle provided in this application determine the resolution of the target image based on the target image and basic parameter information of the sprue nozzle of any target to be detected, and determine the target cross-sectional pixel area of ​​the target sprue nozzle based on the target image and a preset threshold segmentation algorithm. Then, based on the target image and a trained sprue nozzle feature recognition model, determine the target slag line pixel information and target necking pixel information of the target sprue nozzle. Based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, determine the target cross-sectional physical area, target slag line physical information, and target necking physical information of the target sprue nozzle, respectively. This can improve the accuracy of parameter measurement at the sprue nozzle and improve measurement efficiency while reducing measurement errors. Attached Figure Description

[0036] Figure 1 This paper shows one of the flowcharts of a method for detecting a sprue nozzle provided in an embodiment of this application;

[0037] Figure 2 This is a second flowchart illustrating a method for detecting a sprue nozzle provided in an embodiment of this application;

[0038] Figure 3 This paper shows a structural block diagram of a detection device for a sprue nozzle provided in an embodiment of this application;

[0039] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0040] Figure 3 and Figure 4 The correspondence between the figure labels and figure titles in the accompanying drawings is as follows:

[0041] 300 Detection device for the middle water inlet; 310 First determination module; 320 Second determination module; 330 Third determination module; 340 Fourth determination module; 350 Construction module; 360 Fifth determination module; 400 Electronic device; 410 Processor; 420 Memory; 430 Bus. Detailed Implementation

[0042] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0043] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying 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 limitation, 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. The term "two or more" includes two or more cases.

[0044] First, the applicable application scenarios of this application will be introduced. The embodiments provided in this application are applicable to the field of automation technology in iron and steel metallurgy.

[0045] Currently, due to the high operating temperature of the sprue nozzle and the irregular shape caused by slag erosion at the nozzle outlet, quantitative detection of the nozzle is quite difficult. Therefore, the current assessment of the nozzle's condition mainly relies on manual visual inspection, tape measure measurement, and rubbing. However, manual measurement has a large measurement error, low accuracy, and low efficiency.

[0046] Furthermore, traditional manual measurement methods cannot obtain accurate steel passage area at the sprue, affecting subsequent evaluation of sprue usage. Manual measurement of slag lines at the sprue also carries certain risks associated with high-temperature operation, and the measurement results are easily influenced by the operator. In addition, manually measured sprue passage data cannot record the offline sprue usage in real time, as well as the continuous casting process equipment data during sprue operation, thus affecting the subsequent use and optimization of the sprue.

[0047] Based on this, the embodiments of this application provide a method, apparatus, electronic device and storage medium for detecting the intermediate sprue nozzle. The embodiments provided by this application can improve the accuracy of parameter measurement at the intermediate sprue nozzle, and improve measurement efficiency while reducing measurement errors.

[0048] Please see Figure 1 , Figure 1 This is one of the flowcharts of a method for detecting a sprue nozzle provided in an embodiment of this application, such as... Figure 1 As shown in the figure, the detection method for the intermediate sprue nozzle provided in this application embodiment includes the following steps:

[0049] S101. Based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet of the target, determine the resolution of the target image.

[0050] In this step, the embodiments provided in this application, under the premise of evaluating the usage of the water inlet in the target to be detected, first need to collect the target image at the water inlet in the target and the basic parameter information corresponding to the water inlet in the target. Then, based on the pixel information of the collected target image and the basic parameter information of the water inlet in the target, the resolution of the target image is determined. In the embodiments provided in this application, the resolution is characterized by θ.

[0051] The basic parameter information corresponding to the water inlet in the target includes, but is not limited to, the actual length of the water inlet in the target.

[0052] It is understood that the target image in the embodiments provided in this application may be captured by a manual camera, an industrial camera image acquisition device, or an industrial video system, etc., and is used to complete the storage of the target image at the sprue inlet of the target. It is assumed that the target image in the embodiments provided in this application is represented by image(w1,h1).

[0053] S102. Based on the target image and the preset threshold segmentation algorithm, determine the target cross-sectional pixel area at the water inlet in the target.

[0054] In this step, after acquiring the target image at the molten steel inlet of the target, it is necessary to determine the steel flow area that affects the flow rate of molten steel at the molten steel inlet of the target. In the embodiment provided in this application, the steel flow area is determined based on the pixel area of ​​the target cross section at the molten steel inlet of the target.

[0055] Assuming that the embodiments provided in this application are specifically, but not limited to, determining the target cross-sectional pixel area at the water inlet in the target based on a preset threshold segmentation algorithm or semantic segmentation method and the corresponding target image, and assuming that the target cross-sectional pixel area in the embodiments provided in this application can be specifically represented by Sp.

[0056] The embodiments provided in this application are specific but not limited to the use of preset threshold segmentation algorithms, semantic segmentation, or manual annotation.

[0057] S103. Based on the target image and the trained slurry nozzle feature recognition model, determine the target slag line pixel information and the target necking pixel information at the target slurry nozzle, wherein the trained slurry nozzle feature recognition model is used to characterize the model for recognizing slag line features and necking features.

[0058] In this step, the main factors affecting the molten steel flow rate at the target ladle nozzle in the embodiments provided in this application, in addition to the steel passage area determined based on the pixel area of ​​the target cross-section, also include the width and height of the target ladle nozzle. The embodiments provided in this application determine the height and width of the target ladle nozzle based on the determined target slag line pixel information and target necking pixel information at the target ladle nozzle. In addition to automatically and / or manually determining the target slag line pixel information and target necking pixel information in the target image, the embodiments provided in this application can also identify the target slag line pixel information and target necking pixel information at the target ladle nozzle in the target image through a trained ladle nozzle feature recognition model.

[0059] In the above-described embodiments, the present application uses a trained mid-bottle nozzle feature recognition model to determine the target slag line pixel information and the target necking pixel information at the target mid-bottle nozzle. However, in practical application scenarios, manual selection can also be used to determine the target slag line pixel information and the target necking pixel information at the target mid-bottle nozzle.

[0060] It is understood that the target slag line pixel information in the embodiments provided in this application can specifically be the target slag line pixel height, specifically denoted by h. p To represent; the target necking pixel information in the embodiments provided in this application can specifically be the target necking pixel width, specifically w p To express.

[0061] The trained sprue feature recognition model in the embodiments provided in this application is obtained by training an initial neural network model based on a large number of sample images and sample feature labels in the sample images.

[0062] S104. Based on the resolution, the target cross-sectional pixel area, the target slag line pixel information, and the target necking pixel information, determine the target cross-sectional physical area, target slag line physical information, and target necking physical information at the water inlet of the target, respectively.

[0063] In this step, the embodiments provided in this application respectively consider the resolution θ and the target cross-sectional pixel area S. p Determine the physical area of ​​the target cross-section at the water inlet of the target, where the physical area of ​​the target cross-section is denoted by S. k Characterization, and S k =Spθ 2 Based on the resolution θ and the target slag line pixel information h p Determine the physical information of the target slag line at the water inlet of the target, where the physical information of the target slag line is represented by h. k Characterization, and h k =h p θ; based on resolution θ and target necking pixel information w p Determine the physical information of the target necking at the water inlet of the target, where the physical information of the target necking is represented by w. k Characterization, and w k =w p θ.

[0064] Compared with the prior art, the method for detecting the slurry nozzle provided in this application determines the resolution of the target image based on the target image and basic parameter information of the slurry nozzle of any target to be detected, and determines the target cross-sectional pixel area of ​​the target slurry nozzle based on the target image and a preset threshold segmentation algorithm. Then, based on the target image and a trained slurry nozzle feature recognition model, it determines the target slag line pixel information and target necking pixel information of the target slurry nozzle. Based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, it determines the target cross-sectional physical area, target slag line physical information, and target necking physical information of the target slurry nozzle, respectively. This method can improve the accuracy of parameter measurement at the slurry nozzle and improve measurement efficiency while reducing measurement errors.

[0065] In one embodiment, step S101 includes the following sub-steps:

[0066] Sub-step 1011: Based on the target image of the slurry outlet of any target to be detected, determine the reference scale pixel length of the target image, wherein the reference scale is used to characterize any physical unit size of the slurry outlet of the target in the target image.

[0067] In this step, to determine the resolution of the target image, the embodiments provided in this application first determine the size of any physical unit at the sprue in the target image, that is, the reference scale pixel length, which can be specifically represented by wa mm.

[0068] Sub-step 1012: Based on the basic parameter information of the water inlet in the target, determine the physical length of the reference scale of the water inlet in the target.

[0069] In this step, the embodiment provided in this application determines the physical length of the reference scale of the water inlet in the target based on the reference scale pixel length of the water inlet in the target and the basic parameter information of the water inlet in the target, which can be specifically represented by La mm.

[0070] Sub-step 1013: Determine the resolution of the target image based on the pixel length of the reference ruler and the physical length of the reference ruler.

[0071] In this step, the resolution of the target image can be specifically θ = La / wa.

[0072] In one embodiment, the target image at the injection port of any target to be detected is determined by the following sub-steps, specifically including:

[0073] Sub-step 1: Determine the initial image of the water inlet in any target to be detected.

[0074] In this step, an initial image of the sprue inlet of the target to be detected is acquired using a target image acquisition device. The initial image must contain at least a panoramic image of the sprue inlet of the target.

[0075] Sub-step 2: Based on the initial image and the trained middle package nozzle recognition model, determine the target image at any target middle package nozzle to be detected, wherein the trained middle package nozzle recognition model is used to characterize the model for recognizing the middle package nozzle.

[0076] In this step, the embodiments provided in this application require inputting the initial image into the trained middle-bag nozzle recognition model to determine the target image at the target middle-bag nozzle and remove relatively obvious and large background images.

[0077] The trained sprue identification model in the embodiments provided in this application is trained based on the initial sample image and the initial image label.

[0078] Here, it is assumed that the target image in the embodiments provided in this application can be specifically represented by image(w1,h1), and the initial image can be specifically represented by image(w,h).

[0079] In one embodiment, step S103 includes the following sub-steps:

[0080] Sub-step 1031: Perform grayscale processing on the target image to determine the coordinates of the target points in the target image.

[0081] In this step, the embodiments provided in this application perform grayscale processing on the target image image(w1,h1) to obtain the point with the highest brightness in the target image, i.e., the target point P. h The target point P h Brightness value T h And the target point P h Target point coordinates (x h ,y h ).

[0082] Sub-step 1032: Based on the target point coordinates and the preset threshold segmentation algorithm, determine the target cross-sectional pixel area at the water inlet in the target from the target image.

[0083] In this step, the embodiments provided in this application first determine the candidate region image of the middle bag nozzle from the target image based on the target point coordinates and preset point division rules, and then determine the target cross-sectional pixel area at the target middle bag nozzle based on the candidate region image and preset threshold segmentation algorithm.

[0084] In this application, it is assumed that the embodiments provided first use the target point coordinates (x... h ,y h Centered on x, the candidate region image is cropped with a side length of w1 / 2 pixels. h -w1 / 4,y h -w1 / 4,w1 / 2,w1 / 2), and based on a preset threshold segmentation algorithm, extract the brightness of the above candidate region image into the region with a value of [T]. h -10,T h The region contour of +10] is calculated, and after filtering out the contour, the sum of the pixel areas of the remaining contour is obtained, which is the pixel area S of the target cross section at the water inlet in the target. p .

[0085] In the above, the preset point division rule is specifically based on the target point coordinates (x, y, y). h ,y h Centered on x, the candidate region image is cropped with a side length of w1 / 2 pixels. h -w1 / 4,y h-w1 / 4,w1 / 2,w1 / 2).

[0086] Compared with the prior art, the method for detecting the sprue nozzle provided in this application determines the resolution of the target image based on the target image and basic parameter information of any target sprue nozzle to be detected, and determines the target cross-sectional pixel area of ​​the target sprue nozzle based on the target image and a preset threshold segmentation algorithm. Then, based on the target image and a trained sprue nozzle feature recognition model, it determines the target slag line pixel information and target necking pixel information of the target sprue nozzle. Based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, it determines the target cross-sectional physical area, target slag line physical information, and target necking physical information of the target sprue nozzle, respectively. This method can improve the accuracy of parameter measurement at the sprue nozzle, reduce measurement errors, and improve measurement efficiency. Furthermore, this application introduces image recognition technology to achieve non-contact quantitative detection of the steel discharge area, target slag line physical height, and target necking physical width of the target sprue nozzle, providing effective support for the optimization of the target sprue nozzle material, structure, and casting process.

[0087] Please see Figure 2 , Figure 2 This is a second flowchart of a method for detecting a sprue nozzle provided in an embodiment of this application, as shown below. Figure 2 As shown in the figure, the detection method for the intermediate sprue nozzle provided in this application embodiment includes the following steps:

[0088] S201. Based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet of the target, determine the resolution of the target image.

[0089] S202. Based on the target image and the preset threshold segmentation algorithm, determine the target cross-sectional pixel area at the water inlet in the target.

[0090] S203. Based on the target image and the trained slurry nozzle feature recognition model, determine the target slag line pixel information and the target necking pixel information at the target slurry nozzle, wherein the trained slurry nozzle feature recognition model is used to characterize the model for recognizing slag line features and necking features.

[0091] S204. Based on the resolution, the target cross-sectional pixel area, the target slag line pixel information, and the target necking pixel information, determine the target cross-sectional physical area, target slag line physical information, and target necking physical information at the water inlet of the target, respectively.

[0092] S205. Based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle, construct a tundish nozzle database for operators to query.

[0093] In this step, the embodiment provided in this application collects core continuous casting process equipment data (including steel grade, temperature, composition, casting speed, width, taper, and crystallizer vibration parameters, etc.) from the external casting machine L2 system, and stores the target cross-sectional physical area, target slag line physical information, target necking physical information, and the above-mentioned continuous casting process equipment data in a corresponding database, so that subsequent operators can trace and track the source of problems.

[0094] S206. Based on the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target inlet, determine whether it is necessary to optimize the structure and casting process of the target inlet.

[0095] In this step, if any of the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target inlet exceed the corresponding preset standard threshold data, then the structure and casting process of the target inlet need to be optimized, or one or more parameter data need to be adjusted.

[0096] The following specific example illustrates the application process of the detection method for the water inlet of the middle casing:

[0097] First, the embodiment provided in this application uses a manual photography method to acquire an initial image imageo(4000,3000) of the target's water inlet. A rectangular bounding box is manually selected to determine the target image image(674,1824) in the initial image. The reference scale pixel length is obtained as 381. Based on the physical length of the reference scale of 125mm, the resolution of the target image is calculated as θ=0.3281mm / pixel.

[0098] Then, the target image image(674,1824) at the water inlet of the target is processed in grayscale to obtain the brightness value 249 and the target point coordinates (355,1492) corresponding to the maximum brightness point (target point) Ph in the image. The candidate region image imaget(187,1305,337,337) is then cropped with the target point coordinates (355,1492) as the center and a side length of 337 pixels. The threshold segmentation method is used to extract the contour of the region with brightness [239,255] in the candidate region image imaget. After filtering out the contour, the area of ​​the remaining contour is calculated to be 6198, and the pixel area of ​​the target cross section is calculated to be 667.21 mm2.

[0099] Next, the target slag line pixel height of 745 and the target necking image pixel width of 274 were obtained by manual selection. The physical height of the target slag line was calculated to be 244.43 mm and the physical width of the target necking image was calculated to be 89.90 mm.

[0100] Data on core continuous casting process equipment, such as steel grade S, temperature T, composition C, casting speed V, width H, taper R, and crystallizer vibration parameters K, are collected from the external casting machine system. The target cross-sectional pixel area is recorded as 667.21 mm2, the target slag line physical height is recorded as 244.43 mm, the target necking physical width is recorded as 89.90 mm, and other core continuous casting process equipment data are recorded.

[0101] Compared with the prior art, the method for detecting the inlet nozzle provided in this application determines the resolution of the target image based on the target image and basic parameter information of the inlet nozzle of any target to be detected, and determines the target cross-sectional pixel area of ​​the inlet nozzle based on the target image and a preset threshold segmentation algorithm. Then, based on the target image and a trained inlet nozzle feature recognition model, it determines the target slag line pixel information and the target necking pixel information of the inlet nozzle. Based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, it determines the target inlet nozzle's inlet nozzle size. The physical area of ​​the target cross-section, the physical information of the target slag line, and the physical information of the target necking at the nozzle can improve the accuracy of parameter measurement at the ladle nozzle, reduce measurement errors, and improve measurement efficiency. Furthermore, this application introduces image recognition technology to achieve non-contact quantitative detection of the steel passage area at the steel discharge port, the physical height of the target slag line, and the physical width of the target necking at the target ladle nozzle. This provides effective support for the optimization of the material, structure, and casting process of the target ladle nozzle. Moreover, this application automatically records the above parameters at the target ladle nozzle, providing detection and data support for the subsequent optimization of the material, structure, and casting process of the target ladle nozzle.

[0102] Please see Figure 3 , Figure 3 This paper shows a structural block diagram of a detection device for a sprue nozzle provided in an embodiment of this application. Figure 3 As shown, the detection device 300 for the intermediate water inlet includes:

[0103] The first determining module 310 is used to determine the resolution of the target image based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet of the target.

[0104] The second determining module 320 is used to determine the target cross-sectional pixel area at the water inlet of the target based on the target image and a preset threshold segmentation algorithm.

[0105] The third determining module 330 is used to determine the target slag line pixel information and the target necking pixel information at the target slag inlet based on the target image and the trained slag inlet feature recognition model, wherein the trained slag inlet feature recognition model is used to characterize the model for recognizing slag line features and necking features.

[0106] The fourth determining module 340 is used to determine the physical area of ​​the target cross section, the physical information of the target slag line, and the physical information of the target necking at the water inlet of the target, based on the resolution, the pixel area of ​​the target cross section, the pixel information of the target slag line, and the pixel information of the target necking.

[0107] The construction module 350 is used to construct a tundish nozzle database based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle, so that operators can query it.

[0108] The fifth determining module 360 ​​is used to determine whether the structure and casting process of the target inlet need to be optimized based on the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target inlet.

[0109] Optionally, the first determining module 310 is specifically used for:

[0110] Based on the target image of the sprue inlet of any target to be detected, the reference scale pixel length of the target image is determined, wherein the reference scale is used to characterize any physical unit size of the sprue inlet of the target in the target image.

[0111] Based on the basic parameter information of the water inlet in the target, the physical length of the reference scale of the water inlet in the target is determined.

[0112] The resolution of the target image is determined based on the pixel length and physical length of the reference ruler.

[0113] Optionally, the target image at the sprue nozzle of any target to be detected is determined by the following method:

[0114] Determine the initial image of the water inlet in any target to be detected.

[0115] Based on the initial image and the trained middle-bore nozzle recognition model, the target image at any target middle-bore nozzle to be detected is determined, wherein the trained middle-bore nozzle recognition model is used to characterize the model for recognizing the middle-bore nozzle.

[0116] Optionally, the second determining module 320 is specifically used for:

[0117] The target image is processed in grayscale to determine the coordinates of the target points in the target image.

[0118] Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined from the target image.

[0119] Optionally, based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the sprue inlet in the target is determined from the target image, including:

[0120] Based on the target point coordinates and preset point division rules, candidate region images of the middle water inlet are determined from the target image.

[0121] Based on the candidate region image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined.

[0122] The detection device 300 for the middle-bowl nozzle provided in this application embodiment, compared with the prior art, determines the resolution of the target image based on the target image and basic parameter information of any target middle-bowl nozzle to be detected, and determines the target cross-sectional pixel area of ​​the target middle-bowl nozzle based on the target image and a preset threshold segmentation algorithm. Then, based on the target image and a trained middle-bowl nozzle feature recognition model, it determines the target slag line pixel information and target necking pixel information of the target middle-bowl nozzle. Based on the resolution, target cross-sectional pixel area, target slag line pixel information, and target necking pixel information, it respectively determines the target middle-bowl nozzle. The physical area of ​​the target cross-section, the physical information of the target slag line, and the physical information of the target necking at the tundish nozzle can improve the accuracy of parameter measurement at the tundish nozzle, reduce measurement errors, and improve measurement efficiency. Furthermore, this application introduces image recognition technology to achieve non-contact quantitative detection of the steel discharge area, the physical height of the target slag line, and the physical width of the target necking at the target tundish nozzle. This provides effective support for the optimization of the material, structure, and casting process of the target tundish nozzle. Moreover, this application automatically records the above parameters at the target tundish nozzle, providing detection and data support for the subsequent optimization of the material, structure, and casting process of the target tundish nozzle.

[0123] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0124] Memory 420 stores machine-readable instructions executable by processor 410. When electronic device 400 is running, processor 410 and memory 420 communicate via bus 430. When the machine-readable instructions are executed by processor 410, they can perform the operations described above. Figures 1 to 2 The steps of the detection method for the middle water inlet in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0125] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figures 1 to 2 The steps of the detection method for the middle sprue nozzle in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0126] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0127] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0128] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0129] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0130] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0131] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0132] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute a process for detecting the inlet of a solid-state drive controller.

[0133] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0139] 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 spirit and scope of the technical solutions of the embodiments of this application.

[0140] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0141] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A method for detecting the sprue nozzle, characterized in that, The detection method for the intermediate water inlet includes: Based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet in the target, the resolution of the target image is determined; The step of determining the resolution of the target image based on the target image at the inlet of any target to be detected and the basic parameter information of the inlet of the target includes: Based on the target image of the sprue inlet of any target to be detected, the reference scale pixel length of the target image is determined, wherein the reference scale is used to characterize any physical unit size of the sprue inlet of the target in the target image; Based on the basic parameter information of the water inlet in the target, the physical length of the reference scale of the water inlet in the target is determined; The resolution of the target image is determined based on the pixel length of the reference ruler and the physical length of the reference ruler; The target image at the sprue nozzle of any target to be detected is determined by the following method: Determine the initial image of the injection port in any target to be detected; Based on the initial image and the trained middle-bag nozzle recognition model, the target image at any target middle-bag nozzle to be detected is determined, wherein the trained middle-bag nozzle recognition model is used to characterize the model for recognizing the middle-bag nozzle. Based on the target image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined; Based on the target image and the trained sprue nozzle feature recognition model, the target slag line pixel information and the target necking pixel information at the target sprue nozzle are determined. The trained sprue nozzle feature recognition model is used to characterize the model for recognizing slag line features and necking features. The trained sprue nozzle feature recognition model is obtained by training an initial neural network model based on a large number of sample images and sample feature labels in the sample images. Based on the resolution, the target cross-sectional pixel area, the target slag line pixel information, and the target necking pixel information, the target cross-sectional physical area, target slag line physical information, and target necking physical information at the water inlet of the target are determined respectively. Based on the target image and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined, including: Perform grayscale processing on the target image to determine the coordinates of the target points in the target image; Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined from the target image; Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the sprue inlet in the target image is determined, including: Based on the target point coordinates and preset point division rules, candidate region images of the middle-water inlet are determined from the target image; Based on the candidate region image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined.

2. The method for detecting the intermediate water inlet according to claim 1, characterized in that, After determining the physical area of ​​the target cross-section, the physical information of the target slag line, and the physical information of the target necking at the target spout based on the resolution, the pixel area of ​​the target cross-section, the pixel information of the target slag line, and the pixel information of the target necking, the spouting detection method further includes: Based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle, a tundish nozzle database is constructed for operators to query.

3. The method for detecting the intermediate sprue nozzle according to claim 2, characterized in that, After constructing a tundish nozzle database based on the target cross-sectional physical area, target slag line physical information, target necking physical information, and continuous casting process equipment data of the target tundish nozzle for query by operators, the tundish nozzle detection method further includes: Based on the target cross-sectional physical area, target slag line physical information, and target necking physical information at the target inlet, it is determined whether the structure and casting process of the target inlet need to be optimized.

4. A detection device for a sprue nozzle, characterized in that, The detection device for the intermediate water inlet includes: The first determining module is used to determine the resolution of the target image based on the target image at the water inlet of any target to be detected and the basic parameter information of the water inlet of the target; The step of determining the resolution of the target image based on the target image at the inlet of any target to be detected and the basic parameter information of the inlet of the target includes: Based on the target image of the sprue inlet of any target to be detected, the reference scale pixel length of the target image is determined, wherein the reference scale is used to characterize any physical unit size of the sprue inlet of the target in the target image; Based on the basic parameter information of the water inlet in the target, the physical length of the reference scale of the water inlet in the target is determined; The resolution of the target image is determined based on the pixel length of the reference ruler and the physical length of the reference ruler; The target image at the sprue nozzle of any target to be detected is determined by the following method: Determine the initial image of the injection port in any target to be detected; Based on the initial image and the trained middle-bag nozzle recognition model, the target image at any target middle-bag nozzle to be detected is determined, wherein the trained middle-bag nozzle recognition model is used to characterize the model for recognizing the middle-bag nozzle. The second determining module is used to determine the target cross-sectional pixel area at the water inlet in the target based on the target image and a preset threshold segmentation algorithm; The third determining module is used to determine the target slag line pixel information and the target necking pixel information at the target slag inlet based on the target image and the trained slag inlet feature recognition model. The trained slag inlet feature recognition model is used to characterize the model for recognizing slag line features and necking features. The trained slag inlet feature recognition model is obtained by training an initial neural network model based on a large number of sample images and sample feature labels in the sample images. The fourth determining module is used to determine the physical area of ​​the target cross section, the physical information of the target slag line, and the physical information of the target necking at the water inlet of the target, respectively, based on the resolution, the pixel area of ​​the target cross section, the pixel information of the target slag line, and the pixel information of the target necking. Based on the target image and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined, including: Perform grayscale processing on the target image to determine the coordinates of the target points in the target image; Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined from the target image; Based on the target point coordinates and a preset threshold segmentation algorithm, the target cross-sectional pixel area at the sprue inlet in the target image is determined, including: Based on the target point coordinates and preset point division rules, candidate region images of the middle-water inlet are determined from the target image; Based on the candidate region image and the preset threshold segmentation algorithm, the target cross-sectional pixel area at the water inlet in the target is determined.

5. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the detection method for the middle-fill nozzle as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the detection method for the middle-bottle nozzle as described in any one of claims 1-3.

Images