A method, apparatus, and medium for oil nose detection

Abstract

The application discloses an oil nozzle detection method, device and medium, comprising: collecting three-dimensional point cloud data corresponding to a sintering trolley wheel during operation of the trolley; three dimensions corresponding to the three-dimensional point cloud data are respectively a direction perpendicular to a trolley deck plane, a trolley operation direction and a direction perpendicular to a horizontal ground; projecting the three-dimensional point cloud data to a preset two-dimensional plane, and taking a coordinate value of the direction perpendicular to the trolley deck plane as a pixel value in the preset two-dimensional plane to obtain a target height map corresponding to the trolley wheel; wherein two dimensions of the preset two-dimensional plane are respectively the direction perpendicular to the horizontal ground and the trolley operation direction; segmenting the target height map to obtain a height segmentation map including a single wheel; and detecting an oil nozzle of the trolley wheel based on the height segmentation map. In this way, accurate oil nozzle data can be provided for automatic oiling, and oiling failure can be avoided.

Description

Technical Field

[0001] This application relates to a method for detecting oil nozzles, and particularly to a method, equipment and medium for detecting oil nozzles. Background Technology

[0002] Sintering is a crucial step in the steel production process. The sintering process involves batching, mixing, and granulating iron-containing raw materials, followed by high-temperature calcination under the influence of a main exhaust fan on a sintering machine, causing a series of physicochemical changes in the materials. The trolleys of the sintering machine and annular cooler are vital moving mechanisms in the sintering process, with their wheels playing important roles in bearing weight and reducing friction. During operation, the trolley wheels are repeatedly subjected to harsh environments such as alternating high and low temperatures and varying loads. Prolonged operation and frequent collisions can lead to bearing delusion, even bearing deformation and wheel seizure, thus affecting production. To reduce the failure rate of the sintering machine, regular lubrication and fault detection of the trolley wheels are necessary. The center of the trolley wheel is the axle, which requires grease for lubrication. The grease inlet is called the grease nozzle, and the protruding part around the nozzle is called the grease cap, which protects the nozzle from scraping and impacts.

[0003] Currently, most sintering machine trolleys in steel plants are lubricated manually on a regular basis. This often results in insufficient lubrication of the bearings due to untimely or incomplete lubrication, leading to wheel damage. Some plants use automatic lubrication machines; however, providing accurate data for these machines and preventing lubrication failures is a problem that needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a nozzle detection method, device, and medium that can provide accurate nozzle data for automatic refueling and avoid refueling failures. The specific solution is as follows:

[0005] Firstly, this application discloses a method for detecting fuel injectors, including:

[0006] During the operation of the sintering trolley, three-dimensional point cloud data corresponding to the trolley wheels are collected; the three dimensions of the three-dimensional point cloud data are the direction perpendicular to the plane of the trolley sideboard, the direction of trolley operation, and the direction perpendicular to the horizontal ground.

[0007] The three-dimensional point cloud data is projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard are used as the pixel values ​​in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheels; wherein, the two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley running direction, respectively.

[0008] The target height map is segmented to obtain a height segmentation map including a single wheel;

[0009] The oil nozzles of the trolley wheels are detected based on the height segmentation map.

[0010] Optionally, segmenting the target height map to obtain a height segmentation map including a single wheel includes:

[0011] The target height map is segmented based on the first distance between two adjacent wheels of different sintering trolleys and the second distance between two wheels of the same sintering trolley, resulting in a height segmentation map including a single wheel.

[0012] Optionally, the step of detecting the oil nozzles on the trolley wheels based on the height segmentation map includes:

[0013] Find the point with the largest pixel value from the height segmentation map to obtain the target point;

[0014] Find points in the height segmentation map whose pixel difference with the target point is less than a preset threshold to obtain the end face point set of the oil nozzle protection end cap;

[0015] The average pixel value of the end face point set is determined to obtain the first height value of the oil nozzle protective end cap;

[0016] In the height segmentation diagram, the circular area at the bottom of the nozzle is determined with the center of the wheel as the center.

[0017] The average pixel value of all points within the circular area at the bottom of the nozzle is determined to obtain the first average value;

[0018] Filter out points with pixel values ​​less than the first mean value within the circular area at the bottom of the nozzle to obtain the nozzle bottom point set;

[0019] The average pixel value of the bottom point set of the nozzle is determined to obtain the second height value of the bottom of the nozzle;

[0020] The difference between the first height value and the second height value is determined to obtain the nozzle depth value.

[0021] Optionally, the step of detecting the oil nozzles on the trolley wheels based on the height segmentation map further includes:

[0022] Points with pixel values ​​greater than the second height value are selected within the circular area at the bottom of the nozzle to obtain the nozzle point set;

[0023] Fit the nozzle outline circle corresponding to the nozzle point set to determine the center coordinates of each nozzle.

[0024] The nozzle direction and nozzle angle are determined based on the center coordinates of the two nozzles.

[0025] Optionally, the step of detecting the oil nozzles on the trolley wheels based on the height segmentation map includes:

[0026] Determine the average inner and outer diameters of the oil nozzle protective end cap;

[0027] In the height segmentation diagram, a circle is drawn with the center of the wheel as the center and the average of the inner and outer diameters as the radius to obtain the target circle;

[0028] Take points from the target circle at preset intervals and determine whether the point is the data for the nozzle protection end cap.

[0029] If the number of points that are not part of the nozzle protection end cap data exceeds the preset threshold, the nozzle protection end cap is determined to be damaged.

[0030] Optionally, the step of detecting the oil nozzles on the trolley wheels based on the height segmentation map includes:

[0031] The first radius and the second radius are determined based on the dimensions of the wheel nozzle cover; the second radius is larger than the first radius.

[0032] In the height segmentation diagram, the wheel center is used as the center, and an annular region is determined based on the first radius and the second radius;

[0033] Determine the average pixel value of all points within the annular region to obtain the second average value;

[0034] The set of points within the annular region that are greater than the second mean is defined as the screw point set;

[0035] The number of screws is determined based on the set of screw points;

[0036] The number of screws is used to determine whether any screws are missing.

[0037] Optionally, the step of projecting the three-dimensional point cloud data onto a preset two-dimensional plane and using the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard as pixel values ​​in the preset two-dimensional plane to obtain a target height map corresponding to the trolley wheels includes:

[0038] A circular correction coefficient is determined, and the three-dimensional point cloud data is corrected using the correction coefficient. The corrected three-dimensional point cloud data is then projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard are used as the pixel values ​​in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheel.

[0039] Optionally, determining the circle correction coefficient includes:

[0040] The 3D point cloud data before correction is projected onto a preset 2D plane, and a segmented image including a single wheel is segmented.

[0041] Ellipse fitting is performed based on the segmentation map to obtain the contour ellipse corresponding to the trolley wheel.

[0042] The circle correction coefficient is determined based on the ellipse parameters of the outline ellipse.

[0043] Secondly, this application discloses a nozzle detection device, comprising:

[0044] The three-dimensional point cloud data acquisition module is used to acquire three-dimensional point cloud data corresponding to the wheels of the sintering trolley during its operation. The three dimensions of the three-dimensional point cloud data are the direction perpendicular to the plane of the trolley sideboard, the direction of the trolley's operation, and the direction perpendicular to the horizontal ground.

[0045] The target height map acquisition module is used to project the three-dimensional point cloud data onto a preset two-dimensional plane, and use the coordinate value of the direction perpendicular to the plane of the trolley sideboard as the pixel value in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheels; wherein, the two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley running direction, respectively;

[0046] The height map segmentation module is used to segment the target height map to obtain a height segmentation map including a single wheel;

[0047] The nozzle detection module is used to detect the nozzles on the trolley wheels based on the height segmentation map.

[0048] Thirdly, this application discloses an electronic device, including a memory and a processor, wherein:

[0049] The memory is used to store computer programs;

[0050] The processor is used to execute the computer program to implement the aforementioned nozzle detection method.

[0051] Fourthly, this application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned nozzle detection method.

[0052] As can be seen, this application collects three-dimensional point cloud data corresponding to the wheels of the sintering trolley during its operation. The three dimensions of the three-dimensional point cloud data are the direction perpendicular to the trolley's sidewall plane, the trolley's running direction, and the direction perpendicular to the horizontal ground. The three-dimensional point cloud data is projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the trolley's sidewall plane are used as pixel values ​​in the preset two-dimensional plane to obtain a target height map corresponding to the trolley wheels. The two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley's running direction. The target height map is segmented to obtain a height segmentation map including a single wheel. Based on the height segmentation map, the trolley wheels are used for nozzle detection. That is, this application first obtains the three-dimensional point cloud data of the wheels, then projects it onto a two-dimensional plane to obtain a height map of the wheels. The pixel values ​​in this height map are coordinate values ​​of the direction perpendicular to the trolley's sidewall plane. Then, nozzle detection is performed based on the height map. This provides accurate nozzle data for automatic refueling and avoids refueling failures. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0054] Figure 1 This is a flowchart of a nozzle detection method disclosed in an embodiment of this application;

[0055] Figure 2 This is a cross-sectional schematic diagram of the installation position of a line structured light imaging device disclosed in an embodiment of this application;

[0056] Figure 3 This is a schematic diagram of wheel segmentation disclosed in an embodiment of this application;

[0057] Figure 4 This is a schematic diagram of a specific main wheel component disclosed in an embodiment of this application;

[0058] Figure 5 This is a schematic diagram of the bottom area of ​​a specific end cap and nozzle disclosed in an embodiment of this application;

[0059] Figure 6 This is a schematic diagram of a specific nozzle orientation disclosed in an embodiment of this application;

[0060] Figure 7 This is a schematic diagram of a specific screw limiting area disclosed in an embodiment of this application;

[0061] Figure 8This is a schematic diagram of the structure of a nozzle detection device disclosed in an embodiment of this application;

[0062] Figure 9 This is a schematic diagram of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0063] 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, and 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.

[0064] Currently, most sintering machine trolleys in steel plants are lubricated manually on a regular basis. This often results in insufficient lubrication of the bearings due to untimely or incomplete lubrication, leading to wheel damage. Some plants use automatic lubrication machines, but providing accurate data for these machines and preventing lubrication failures is a problem that needs to be solved. Therefore, this application provides a nozzle detection solution that can provide accurate nozzle data for automatic lubrication, thus preventing lubrication failures.

[0065] See Figure 1 As shown in the figure, this application discloses a method for detecting fuel nozzles, including:

[0066] Step S11: During the operation of the sintering trolley, collect three-dimensional point cloud data corresponding to the trolley wheels; the three dimensions corresponding to the three-dimensional point cloud data are the direction perpendicular to the plane of the trolley sideboard, the trolley running direction, and the direction perpendicular to the horizontal ground.

[0067] This application embodiment uses a line structured light imaging device to acquire 3D point cloud data corresponding to the wheels of a trolley. The line structured light imaging device employs active structured light projection imaging technology, projecting a single line. It consists of two parts: a camera and a line laser light source. After the structured light is projected onto the surface of the object under test, it is height-modulated by the object. The modulated structured light is acquired by the camera system and transmitted to a computer for analysis and calculation to obtain the 3D surface shape data of the object. See also... Figure 2 As shown, Figure 2This is a cross-sectional schematic diagram of the installation position of a line structured light imaging device disclosed in this application embodiment. The following description uses the left side as an example; the other side is symmetrically installed with the same treatment. The device is installed near the center of the wheel, 0.8m-2m from the outer edge of the wheel. The field of view covers the longitudinal area of ​​the trolley wheel. The specific installation position needs to be determined based on the site environment and sintering process requirements. The line structured light imaging device consists of a line laser and a camera, which are connected together by a bracket. After special calibration, 3D scanning is performed. Typically, the line laser is perpendicular to the trolley sideboard, and the line plane is vertical. The camera is on the same horizontal plane as the line laser, at an angle of approximately 40° to the line laser, capturing the light stripes projected onto the sideboard.

[0068] In a specific implementation, the line structured light device measures the contour data of the cross-section of a single laser line in a single measurement, measuring n points at a time, denoted as p1, p2, p3, ..., p1, ..., pn. The result is two-dimensional data within the laser plane. To establish complete trolley wheel data, a world coordinate system needs to be defined first, with the trolley's motion direction as the Z-axis, and the X and Y axes remaining unchanged (corresponding to the two axes of the laser plane). Point p1 in the two-dimensional coordinate system is then transformed into point Pi in the world coordinate system. Pi is a three-column data set containing three-dimensional coordinates, with each row representing the X, Y, and Z coordinate values ​​from top to bottom. Therefore, point Pi is:

[0069]

[0070] The cross-sectional data of the kth detection is denoted as Pc(k):

[0071]

[0072] The trolley runs at a speed of v, and data is collected every time interval t. After the k-th detection, all the data is denoted as Pa(k):

[0073] Pa(1)=Pc(1);

[0074]

[0075] Through the above transformation, the side cross-sectional data of the trolley wheels can be unified into the world coordinate system. As the trolley continues to move, a complete dataset of the trolley wheel contours can be constructed. Based on the overall data model, the state of each wheel on the side of the sintering machine trolley can be intuitively reflected. That is, the three dimensions corresponding to the world coordinate system are the direction perpendicular to the plane of the trolley side panel, the direction of trolley travel, and the direction perpendicular to the horizontal ground.

[0076] Step S12: Project the three-dimensional point cloud data onto a preset two-dimensional plane, and use the coordinate value of the direction perpendicular to the plane of the trolley as the pixel value in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheel; wherein, the two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley running direction, respectively.

[0077] In one implementation, a circular correction coefficient can be determined, the three-dimensional point cloud data can be corrected using the correction coefficient, and the corrected three-dimensional point cloud data can be projected onto a preset two-dimensional plane. The coordinate value of the direction perpendicular to the plane of the trolley sideboard is used as the pixel value in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheel.

[0078] The step of determining the circularity correction coefficient specifically includes: projecting the uncorrected 3D point cloud data onto a preset 2D plane and segmenting it to obtain a segmented image including a single wheel; performing ellipse fitting based on the segmented image to obtain the contour ellipse corresponding to the trolley wheel; and determining the circularity correction coefficient based on the ellipse parameters of the contour ellipse. Specifically, the ratio of the lengths between the vertical axis and the horizontal axis of the ellipse can be determined as the circularity correction coefficient. Furthermore, the height map obtained by projecting the uncorrected 3D point cloud data onto the preset 2D plane can be segmented based on the first distance between two adjacent wheels of different sintering trolleys and the second distance between two wheels of the same sintering trolley to obtain a segmented image including a single wheel.

[0079] It should be noted that due to the inherent speed error of the sintering machine, the wheel may be compressed or stretched along its direction of travel, resulting in the scanned wheel not necessarily being a perfect circle. When the sintering machine speed remains constant for a short period, the scanned wheel profile can be considered an ellipse. The individual wheel height maps can be segmented, and the profile data can be found by first performing a profile lookup. Then, an ellipse can be fitted onto the profile data, specifically, the center Cr, the length l of the horizontal axis, and the length h of the vertical axis. In other words, using the profile points, the following equation can be fitted:

[0080]

[0081] Where Cr.x is the x-coordinate of the center Cr; Cr.y is the y-coordinate of the center Cr. It should be noted that x and y here are coordinates in the image coordinate system, that is, the horizontal axis is the x-axis and the vertical axis is the y-axis.

[0082] The horizontal length of the ellipse is corrected to match the vertical length; that is, the horizontal coordinate values ​​need to be multiplied by a coefficient k: k = h / l. When the Z coordinates of all points are multiplied by k and then projected onto the image, the projected wheel is a perfect circle.

[0083] In another implementation, if the wheel is already perfectly round, no correction is required.

[0084] Step S13: Segment the target height map to obtain a height segmentation map including a single wheel.

[0085] In a specific implementation, the target height map can be segmented based on the first distance between two adjacent wheels of different sintering trolleys and the second distance between two wheels of the same sintering trolley, to obtain a height segmentation map including a single wheel.

[0086] Furthermore, it can identify the trolley's number and match the trolley's number with the detection results corresponding to the height segmentation map of a single wheel.

[0087] That is, the point cloud data is projected onto the XZ plane, where the X direction represents the height direction of the image, the Z direction represents the width direction of the image, each pixel represents 1*1mm, and the corresponding y-direction value is the pixel value of the image. This generates a height map, which is then used for image segmentation. Figure 3 As shown, Figure 3 This is a schematic diagram of wheel segmentation disclosed in an embodiment of this application. L1 is the second distance, L2 is the first distance, and L3 is the trolley length. Based on the positional limits in the X and Y directions, the wheel positions are determined, allowing the sideboard to be segmented and its numbering information recorded. The trolley numbers can be matched one-to-one with the segmented trolleys. For example... Figure 4 As shown, Figure 4 This is a schematic diagram of the main components of a specific wheel disclosed in an embodiment of this application, wherein the oil nozzle cover is fixed to the wheel by screws, and the oil nozzle and bearing are located at the center of the wheel.

[0088] Step S14: Detect the oil nozzles on the trolley wheels based on the height segmentation map.

[0089] In a specific implementation, the point with the largest pixel value can be found in the height segmentation map to obtain the target point; points with a pixel difference less than a preset threshold between the target point and the height segmentation map can be found to obtain the end face point set of the nozzle protective end cap; the pixel mean of the end face point set is determined to obtain the first height value of the nozzle protective end cap; a circular area at the bottom of the nozzle is determined in the height segmentation map with the wheel center as the center; the pixel mean of all points in the circular area at the bottom of the nozzle is determined to obtain the first mean; points with pixel values ​​less than the first mean are selected in the circular area at the bottom of the nozzle to obtain the bottom point set of the nozzle; the pixel mean of the bottom point set of the nozzle is determined to obtain the second height value of the bottom of the nozzle; the difference between the first height value and the second height value is determined to obtain the nozzle depth value. Ellipse fitting can be performed on the height segmentation map to obtain the wheel center of the trolley wheel.

[0090] It should be noted that the depth of the oil nozzle refers to the distance from the end face of the protective end cap of the oil nozzle to the bottom of the wheel oil nozzle. During oil filling, the oil gun of the fuel dispenser needs to abut against the bottom of the wheel oil nozzle to complete normal oil filling without oil leakage. For example, refer to Figure 5 as shown in, Figure 5 which is a schematic diagram of a specific end cap and oil nozzle bottom area disclosed in the embodiments of the present application. The protective end cap of the oil nozzle is the most prominent part on the side surface of the wheel, that is, the Y-axis value is the largest. First, find the point with the largest pixel value in the projection height of the wheel, that is, the maximum value fmax in the Y-axis direction, then select all the following points:

[0091]

[0092] that is, all points that do not differ much from the maximum value are selected as the end face points of the protective end cap of the oil nozzle. The average value of the point set P is calculated, which is the height value h1 of the end cap face:

[0093]

[0094] The bottom area of the oil nozzle is the area near the center point of the wheel, with the center Cr of the wheel as the center of a circle, as the radius, a circle is drawn in the corrected height map to form an area

[0095] The height average value h2 of all points in this area is calculated. Since the oil nozzle is contained in the bottom area of the oil nozzle, the calculated average value h2 is relatively large. Therefore, within the circular area, all points P3 with pixel values less than h2 are selected: P3={p|p∈P2&p.y<h2};

[0096] Calculate the average value h3 of all the selected points P3, and this height is the height of the bottom of the oil nozzle. The depth of the oil nozzle is hy: hy=h1-h3. In this way, the depth of the oil nozzle measured by the line structured light method can provide data support for the advancing depth of the oil gun of the fuel dispenser, which facilitates the automatic control of the fuel dispenser.

[0097] Further, the embodiments of the present application may also filter out points with pixel values greater than the second height value in the circular area at the bottom of the oil nozzle to obtain an oil nozzle point set; fit the oil nozzle contour circle corresponding to the oil nozzle point set to determine the center coordinates of each oil nozzle; determine the oil nozzle direction and the oil nozzle angle based on the center coordinates of the two oil nozzles.

[0098] It should be noted that some sintering machines have a single oil nozzle on their wheel, in which case the nozzle is located at the center of the wheel, and there is no need to determine its orientation. Other sintering machines have a double oil nozzle on their wheel, with neither nozzle located at the center of the wheel, but rather symmetrically distributed. The orientation of each oil nozzle varies depending on the assembly, requiring determination of the nozzle's direction and angle. First, select the nozzle dimensions. Typically, the nozzle extends about 10mm from the bottom surface; this is the location of the oil filling hole. Based on the wheel's center radius (Cr), and the designed radius of the oil nozzle... Draw a circle to form region P2, and calculate the average value h2 of all points within the circle. Since the nozzle is higher than the bottom area, select all points P4 with height values ​​greater than h2 within the circle as the target points of the nozzle: P4 = {p | p ∈ P2 & p.y > h2}.

[0099] Further, the nozzle direction is calculated, a marking area is established, the nozzle data P4 area is set to 255, and other areas are set to 0, the contour is found, the contour circle is fitted, and the center coordinates of each nozzle are calculated: Cr1, Cr2.

[0100]

[0101]

[0102] Where R1 is the radius of one nozzle; R2 is the radius of the other nozzle.

[0103] The nozzle direction vector is the difference between the coordinates of the two center points, n = Cr2 - Cr1. Figure 6 This is a schematic diagram illustrating the direction of a specific oil nozzle according to an embodiment of this application. The oil nozzle angle θ is: θ = cos -1 (ny / |n|).

[0104] In this way, the direction and angle of the nozzle can be measured by line structured light. This data provides data support for the alignment of the fuel dispenser's nozzle and the fuel nozzle, which facilitates the automatic control of the fuel dispenser.

[0105] Furthermore, the average inner and outer diameters of the nozzle protective end cap can be determined. A target circle is obtained by drawing a circle with the wheel center as the center and the average inner and outer diameters as the radius in the height segmentation diagram. Points are taken from the target circle at preset intervals to determine whether each point represents nozzle protective end cap data. If the number of points that are not nozzle protective end cap data exceeds a preset threshold, the nozzle protective end cap is determined to be damaged. Specifically, if the Euclidean distance between a point and the wheel center is less than a preset threshold, it is considered nozzle protective end cap data.

[0106] It should be noted that the fuel injector protective end cap serves both to protect the fuel injector and to assist in refueling and positioning it. Damage to the fuel injector protective end cap can lead to injector damage, prevent the fuel dispenser from positioning the injector, and may even damage the fuel dispenser's grippers. Therefore, detecting damage to the fuel injector protective end cap is crucial. The fuel injector protective end cap has fixed inner diameter rl and outer diameter ro in its design dimensions. Using the wheel's center Cr as the center, and the average value of the inner and outer diameters r = (r1 + ro) / 2 as the radius, draw a circle, and at intervals of... For each interval angle, determine whether a point on the circle corresponding to each interval angle contains oil cap data P, i.e.:

[0107]

[0108] Where i is 0, 1, 2, ..., n, and it is guaranteed that... Right now

[0109] For each coordinate (x, y) corresponding to i, determine whether it belongs to the data of the nozzle protection end cap. Count the number k of all non-native nozzle protection end cap data. When k is greater than a certain preset threshold, the cover is considered damaged. The angle of damage is: In this way, the damage to the nozzle protective end cap is detected using line structured light. If damage is found, refueling of that wheel is skipped, and an alarm is triggered. This data serves as the theoretical basis for the fuel dispenser to determine whether to refuel that nozzle, facilitating the automatic control of the fuel dispenser.

[0110] Furthermore, in this embodiment, a first radius and a second radius can be determined based on the size of the wheel nozzle cover; the second radius is larger than the first radius; an annular region is determined in the height segmentation map with the wheel center as the center and based on the first radius and the second radius; the pixel mean of all points in the annular region is determined to obtain a second mean; the set of points in the annular region that are greater than the second mean is determined as a screw point set; the number of screws is determined based on the screw point set; and the number of screws is used to determine whether a screw is missing.

[0111] It should be noted that the nozzle cover screw is used to secure the nozzle cover. If this screw comes loose, there is a risk that the cover will detach, potentially damaging the nozzle. Therefore, to better ensure the normal operation of the wheel, it is necessary to inspect the cover screw. If it is found to be loose, it should be promptly alerted for manual handling. First, select the screw dimensions. Using the wheel's center Cr as the center and rt as the radius, determine the actual size of the nozzle cover, slightly smaller than the actual size. Draw a circle to form a reference circle. Using rq as the radius, slightly larger than the outer diameter of the nozzle protective end cap, establish a region circle. The screw should be outside this region circle but within the reference circle. Figure 7This is a schematic diagram of a specific screw limiting area disclosed in an embodiment of this application. Specifically, point P5 within this area is:

[0112] P5={P|rq 2 ≤(px-Cr.x) 2 +(py-Cr.y) 2 ≤rt 2}

[0113] Calculate the average height ht of all points within the region. Identify all points within the region whose height is greater than the average ht; these are the screw data points P6: P6 = {p | p ∈ P5 & p.y > ht}. Further, count the number of screw data points, establish a marker region, set the screw data points to 255, and other regions to 0, find the contour, fit the contour circle Cs, and calculate the center coordinates of each screw data point. The screw data point is considered complete when the absolute value of the difference between the distance ds between the center point and the wheel center point and the set value D is less than a very small threshold. When that point is identified as a screw, that is:

[0114]

[0115] Count the number of screw center points; if the number is less than the actual number, it indicates that a screw has fallen off the wheel. Combine this with the trolley number alarm procedure.

[0116] In this way, by employing a line structured light imaging device, a cross-sectional profile of the side of the trolley wheel can be acquired in real time. As the trolley moves, the entire wheel profile data is scanned to generate a wheel profile point cloud model. Key wheel parameters are analyzed, including nozzle depth, the extent of damage to the nozzle protective end cap, and nozzle positioning parameters. This provides data support for real-time refueling of the fuel dispenser, enabling automatic control of the fuel dispenser. If the nozzle protective end cap or nozzle cover plate screws are found to be loose, an alarm is promptly triggered based on the trolley's location information, providing feedback on the fault type and corresponding trolley number. This reduces the time the trolley operates with faults and facilitates automatic refueling of the sintering machine wheels. This equipment is relatively simple to install, has low maintenance costs, requires few supporting devices, and is stable and reliable.

[0117] See Figure 8 As shown in the figure, this application discloses a nozzle detection device, including:

[0118] The three-dimensional point cloud data acquisition module 11 is used to acquire three-dimensional point cloud data corresponding to the wheels of the sintering trolley during its operation; the three dimensions corresponding to the three-dimensional point cloud data are the direction perpendicular to the plane of the trolley sideboard, the direction of the trolley's operation, and the direction perpendicular to the horizontal ground.

[0119] The target height map acquisition module 12 is used to project the three-dimensional point cloud data onto a preset two-dimensional plane, and use the coordinate value of the direction perpendicular to the plane of the trolley sideboard as the pixel value in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheel; wherein, the two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley running direction, respectively.

[0120] The height map segmentation module 13 is used to segment the target height map to obtain a height segmentation map including a single wheel;

[0121] The nozzle detection module 14 is used to detect the nozzles on the trolley wheels based on the height segmentation map.

[0122] As can be seen, this application collects three-dimensional point cloud data corresponding to the wheels of the sintering trolley during its operation. The three dimensions of the three-dimensional point cloud data are the direction perpendicular to the trolley's sidewall plane, the trolley's running direction, and the direction perpendicular to the horizontal ground. The three-dimensional point cloud data is projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the trolley's sidewall plane are used as pixel values ​​in the preset two-dimensional plane to obtain a target height map corresponding to the trolley wheels. The two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley's running direction. The target height map is segmented to obtain a height segmentation map including a single wheel. Based on the height segmentation map, the trolley wheels are used for nozzle detection. That is, this application first obtains the three-dimensional point cloud data of the wheels, then projects it onto a two-dimensional plane to obtain a height map of the wheels. The pixel values ​​in this height map are coordinate values ​​of the direction perpendicular to the trolley's sidewall plane. Then, nozzle detection is performed based on the height map. This provides accurate nozzle data for automatic refueling and avoids refueling failures.

[0123] See Figure 9 As shown in the figure, this application discloses an electronic device 20, including a processor 21 and a memory 22; wherein, the memory 22 is used to store a computer program; the processor 21 is used to execute the computer program, the nozzle detection method disclosed in the foregoing embodiment.

[0124] The specific process of the above-mentioned nozzle detection method can be found in the relevant content disclosed in the foregoing embodiments, and will not be repeated here.

[0125] Furthermore, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, and the storage method can be temporary storage or permanent storage.

[0126] In addition, the electronic device 20 also includes a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26; wherein, the power supply 23 is used to provide operating voltage for the various hardware devices on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0127] Furthermore, embodiments of this application also disclose a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the nozzle detection method disclosed in the foregoing embodiments.

[0128] The specific process of the above-mentioned nozzle detection method can be found in the relevant content disclosed in the foregoing embodiments, and will not be repeated here.

[0129] 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 apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0130] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0131] The above provides a detailed description of the nozzle detection method, equipment, and medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for detecting fuel nozzles, characterized in that, include: During the operation of the sintering trolley, three-dimensional point cloud data corresponding to the trolley wheels are collected; The three dimensions corresponding to the three-dimensional point cloud data are the direction perpendicular to the plane of the trolley sideboard, the direction of trolley movement, and the direction perpendicular to the horizontal ground. The three-dimensional point cloud data is projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard are used as the pixel values ​​in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheels; wherein, the two dimensions of the preset two-dimensional plane are the direction perpendicular to the horizontal ground and the trolley running direction, respectively. The target height map is segmented to obtain a height segmentation map including a single wheel; The oil nozzles of the trolley wheels are detected based on the height segmentation map. The step of detecting the nozzle on the trolley wheel based on the height segmentation map includes: finding the point with the largest pixel value in the height segmentation map to obtain a target point; finding points in the height segmentation map whose pixel difference with the target point is less than a preset threshold to obtain a set of end face points for the nozzle protective end cap; determining the pixel mean of the end face point set to obtain a first height value of the nozzle protective end cap; determining a circular area at the bottom of the nozzle with the wheel center as the center in the height segmentation map; determining the pixel mean of all points in the circular area at the bottom of the nozzle to obtain a first mean; filtering out points with pixel values ​​less than the first mean in the circular area at the bottom of the nozzle to obtain a set of bottom points for the nozzle; determining the pixel mean of the bottom points for the nozzle to obtain a second height value at the bottom of the nozzle; determining the difference between the first height value and the second height value to obtain a nozzle depth value; filtering out points with pixel values ​​greater than the second height value in the circular area at the bottom of the nozzle to obtain a set of nozzle points; fitting the nozzle outline circle corresponding to the nozzle point set to determine the center coordinates of each nozzle; and determining the nozzle direction and nozzle angle based on the center coordinates of the two nozzles.

2. The nozzle detection method according to claim 1, characterized in that, The segmentation of the target height map to obtain a height segmentation map including a single wheel includes: The target height map is segmented based on the first distance between two adjacent wheels of different sintering trolleys and the second distance between two wheels of the same sintering trolley, resulting in a height segmentation map including a single wheel.

3. The nozzle detection method according to claim 1, characterized in that, The method of detecting oil nozzles on the trolley wheels based on the height segmentation map also includes: Determine the average inner and outer diameters of the oil nozzle protective end cap; In the height segmentation diagram, a circle is drawn with the center of the wheel as the center and the average of the inner and outer diameters as the radius to obtain the target circle; Take points from the target circle at preset intervals and determine whether the point is the data for the nozzle protection end cap. If the number of points that are not part of the nozzle protection end cap data exceeds the preset threshold, the nozzle protection end cap is determined to be damaged.

4. The nozzle detection method according to claim 1, characterized in that, The method of detecting oil nozzles on the trolley wheels based on the height segmentation map also includes: The first radius and the second radius are determined based on the dimensions of the wheel nozzle cover; the second radius is larger than the first radius. In the height segmentation diagram, the wheel center is used as the center, and an annular region is determined based on the first radius and the second radius; Determine the average pixel value of all points within the annular region to obtain the second average value; The set of points within the annular region that are greater than the second mean is defined as the screw point set; The number of screws is determined based on the set of screw points; The number of screws is used to determine whether any screws are missing.

5. The nozzle detection method according to any one of claims 1 to 4, characterized in that, The step of projecting the three-dimensional point cloud data onto a preset two-dimensional plane and using the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard as pixel values ​​in the preset two-dimensional plane to obtain a target height map corresponding to the trolley wheels includes: A circular correction coefficient is determined, and the three-dimensional point cloud data is corrected using the correction coefficient. The corrected three-dimensional point cloud data is then projected onto a preset two-dimensional plane, and the coordinate values ​​of the direction perpendicular to the plane of the trolley sideboard are used as the pixel values ​​in the preset two-dimensional plane to obtain the target height map corresponding to the trolley wheel.

6. The nozzle detection method according to claim 5, characterized in that, The determination of the circle correction coefficient includes: The 3D point cloud data before correction is projected onto a preset 2D plane, and a segmented image including a single wheel is segmented. Ellipse fitting is performed based on the segmentation map to obtain the contour ellipse corresponding to the trolley wheel. The circle correction coefficient is determined based on the ellipse parameters of the outline ellipse.

7. An electronic device, characterized in that, Includes memory and processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program to implement the nozzle detection method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the nozzle detection method as described in any one of claims 1 to 6.

Images