Ejector head abnormity detection equipment

Abstract

The invention provides plug anomaly detection equipment. The plug anomaly detection equipment comprises a plug detection system, a cooling system and a data processing system, the cooling system is used for cooling the plug detection system and the plug working environment; the plug detection system comprises a visual unit used for shooting plug images; the visual unit is in communication connection with the data processing system; and the data processing system comprises a data preprocessing unit, a plug falling detection unit, a plug surface flaw detection unit and an alarm unit, and is used for data acquisition, data processing, plug falling and surface flaw detection when the plug works. The method comprises the following steps: preprocessing original point cloud data to obtain preprocessed point cloud data, and segmenting the preprocessed point cloud data to obtain header data; and then plug falling detection is carried out, if the plug does not fall, plug surface flaw detection is carried out, and if the plug falls, the steps of data preprocessing and plug falling detection are repeated.

Description

Technical Field

[0001] The invention relates to the technical field of industrial detection, and in particular to a device for detecting abnormality of a plug. Background Art

[0002] The seamless steel pipe production method is a process for producing seamless steel pipes or other metal pipes and alloy pipes by perforation and other methods. The process generally includes heating, perforation, pipe rolling, leveling, sizing, reducing and finishing, among which perforation is the main process. The perforation plug used in the perforation process is a crucial tool in the production of seamless steel pipes. In the actual production process, the plug may fall off, which will cause problems such as inner surface defects of the steel pipe, inner diameter and wall thickness deviation of the steel pipe, damage to the perforator and rolling mill, and a large amount of heat, dust and smoke will be generated during the hot rolling process, and a lot of water vapor will appear during the rapid cooling process. The harsh environment affects the operating status of the equipment and the accuracy of the detection. When the perforation plug falls off, the production line must be stopped for maintenance, which will cause production interruption and affect the production efficiency and delivery time of the factory. In addition, the falling plug may cause further damage to the equipment, increasing the cost and time of maintenance. At the same time, the falling plug will also lead to the waste of raw materials and semi-finished products, increasing the cost burden of the enterprise. During the perforation process, defects such as melt tip and meat loss may appear on the plug, which will cause defects in the perforated rolled steel pipe, such as guide plate marks, etc., seriously affecting the production quality of the hot-rolled steel pipe.

[0003] For example, application number: CN202210984474.9, a steel plant head detection system, according to its structural design drawing, uses two groups of high-speed industrial cameras and a group of radars. Through deep learning and machine vision, the six images collected by the high-speed camera are processed and predicted to obtain the head drop detection results.

[0004] For example, application number: CN201520420680.2, a punch head detection device, the detection basis comes from a funnel-shaped cavity pressure sensor opened inside the device, and the relevant information of the plug falling is obtained through the sensor.

[0005] For example, application number: CN202310827620.1, a seamless steel pipe perforation plug detection system based on machine vision, the structural design relied on by the detection system is similar to the structure of application number CN202210984474.9, and the 2D camera group collects the plug image through a deep learning neural network to judge the plug drop.

[0006] The above methods mostly use sensor modules or traditional cameras to determine whether the plug has fallen off. The sensor module is limited in its own settings, such as package size, power consumption requirements, etc. Traditional CCD cameras are difficult to resist interference from high-temperature water vapor, fine smoke and dust during the plug piercing process. The above solutions cannot reduce the noise caused by high-temperature water vapor and fine smoke and dust when the camera is shooting, nor can they detect surface defects such as plug melting tip and plug meat loss in the hot rolling piercing process. Summary of the invention

[0007] The technical problem to be solved by the present invention is: how to design a detection device which is less affected by the environment and can detect plug drop and surface defects at the same time.

[0008] The present invention solves the above technical problems through the following technical means:

[0009] A plug abnormality detection device comprises a plug detection system, a cooling system and a data processing system; the cooling system cools down the plug detection system and the plug working environment; the plug detection system comprises a visual unit for photographing a plug image; the visual unit is communicatively connected with the data processing system; the data processing system comprises a data preprocessing unit, a plug drop detection unit, a plug surface defect detection unit and an alarm unit;

[0010] The data preprocessing system receives the point cloud data sent by the visual unit, and segments the point cloud data to obtain vertex data;

[0011] The plug drop detection system detects whether the plug has dropped based on the segmented plug data. The specific detection process is as follows: performing lateral projection on the plug data to reduce the data dimension and obtain a lateral projection image of the plug; performing inference on the lateral projection image of the plug based on the trained deep learning detection model to determine the plug state and obtain drop determination information; and sending a drop alarm signal to the alarm unit based on the drop determination information;

[0012] If the plug has not fallen off, the plug surface defect detection system is started, and the detection process is as follows: ray projection is performed on the plug data, and the plug surface is projected as a depth image with the plug surface as the reference plane to obtain the plug cross-sectional contour projection image; the depth image is binarized according to the depth threshold to generate a binary image; the connected area of ​​the binary image is extracted to determine whether the area meets the conditions. If so, a retention operation is performed and an alarm signal is sent to the alarm unit. If not, a discard operation is performed.

[0013] Furthermore, the plug detection system includes a plug detection support frame (4), including a pillar (41) and a rotating support (42) located at the top of the pillar (41); the top of the rotating support (42) is connected to an I-beam support (44) through a rear roller member (43) and can drive the I-beam support (44) to move; the front end of the I-beam support (44) is connected to an angle control mechanism (46) through a front roller member (45); the angle control mechanism (46) clamps the plug detection system and can drive the plug detection system to adjust in all directions; the cooling system is located on one side of the plug detection support frame (4), and can apply a cold air flow to the plug (9) below the plug detection system through the plug detection system.

[0014] Furthermore, the rear roller member (43) can indirectly push the visual unit (10) to move in the direction of the “X” axis;

[0015] The angle control mechanism (46) includes a "Z" axis rotation component (461) for adjusting the visual unit (10) to rotate about the "Z" axis, an "X" axis rotation component (462) for adjusting the visual unit (10) to rotate about the "X" axis, and a "Y" axis rotation component (463) for adjusting the visual unit (10) to rotate about the "Y" axis.

[0016] Furthermore, the "Z" axis rotating assembly (461) includes a rotating support seat (4611), the top of which is connected to the front roller member (45) via a support column (4613), a rotating member (4612) is provided at the middle position of the rotating support seat (4611), and the bottom of the rotating member (4612) is connected to the "X" axis rotating assembly (462) via a rotating column (4614).

[0017] Furthermore, the "X" axis rotating assembly (462) includes a rotating support seat 2 (4621) and a support seat (4624) located below the rotating support seat 1 (4611), and the middle positions on both sides of the support seat (4624) are rotatably connected with vertical rods (4623), and rotating plates (4622) are installed on both sides of the vertical rods (4623), and arc-shaped track grooves are opened on the rotating plates (4622), and protrusions are arranged at corresponding positions on both sides of the rotating support seat 2 (4621);

[0018] When the vertical rod (4623) drives the rotating plate (4622) to rotate along the "X" axis, the protrusion can move in the corresponding arc track groove.

[0019] Furthermore, the "Y" axis rotation assembly (463) includes connecting plates (4631) installed on both sides of the support seat (4624), wherein the inner sides of the two connecting plates (4631) are provided with a rotating support seat three (4632), and the two rotating support seats three (4632) clamp the visual unit (10).

[0020] Furthermore, the front roller member (45) includes a bottom plate (451), side plates (454) are provided on both sides of the top of the bottom plate (451), an I-beam front roller (455) for driving the I-beam bracket (44) is installed on the inner side of the side plate (454), and a guide wheel (453) for contacting the lower part of the I-beam bracket (44) is provided between the two side plates (454) and below the I-beam front roller (455).

[0021] Furthermore, the rear roller member (43) includes a bracket base (431) installed on the top of the rotating bracket (42), support plates (432) are installed on both sides of the top of the bracket base (431), and I-beam rear rollers (433) for driving the I-beam bracket (44) are installed on the inner sides of the two support plates (432). Guide light axes (437) are also provided on both sides of the top of the bracket base (431) and on the front sides of the two support plates (432).

[0022] Furthermore, the data processing system processes the original point cloud data as follows:

[0023] S11, collecting and obtaining original point cloud data;

[0024] S12, downsampling the original point cloud data through voxel filtering to obtain a downsampled point cloud;

[0025] S13, density-based point cloud segmentation, based on the density of points within the domain, points with accessible density are classified into the same cluster, points with unreachable density are divided into new clusters, and all points are traversed until all points have corresponding clusters, thus obtaining segmented point clouds and segmented clusters;

[0026] S14, introduce preset conditions for the segmented point cloud, screen the segmented clusters according to the preset conditions, and obtain the target cluster, wherein for each cluster C i , calculate the coordinates of the center point (x c ,y c ,z c );

[0027] S15. Determine cluster C i Whether the preset point condition and the preset center condition are met; i The coordinates of the center point (x c ,y c ,zc ), compared with the preset coordinate range;

[0028] S16. If yes, then for the current cluster C i Execute the retention operation;

[0029] S17: If not, a discard operation is performed on the current cluster.

[0030] 10. The plug abnormality detection device according to any one of claims 1 to 9, characterized in that the specific method of lateral projection in the plug drop detection system is:

[0031] S211, input point cloud data;

[0032] S212, calculating the projection point cloud coordinate range according to the point cloud data, wherein the boundaries of the y coordinate and the z coordinate in the point cloud data are calculated, the physical boundaries of the two-dimensional image are defined, and the size of the two-dimensional projection image is determined:

[0033] y min =min(y i ),y max =max(y i ),z min =min(z i ),z max =max(z i );

[0035] S213, calculating the image resolution in the y direction and the z direction according to the boundary value of the physical boundary of the two-dimensional image and the size of the two-dimensional projection image:

[0036]

[0037] S214, calculating coordinate projection;

[0038] S215, acquiring a lateral projection image, and obtaining the image pixel position through a coordinate conversion operation.

[0039] Furthermore, in S215, the y coordinate and z coordinate of each point in the point cloud data are converted to the image pixel position (i, j) using the following mapping logic:

[0040]

[0041] Furthermore, the specific method of ray projection of the plug surface defect detection system is as follows: using the least squares method to perform ellipse fitting on each contour of the processed plug data to obtain the center (x0, y0) of the ellipse, the major axis a, the minor axis b, and the rotation angle ω; using a ray projection-based method to perform plane projection on the plug point cloud data, the point cloud data is projected as a depth image with its surface as the reference plane, and the ray projection step includes:

[0042] S311, send ray l1 from the center of the circle to the starting phase angle θ1 as the starting direction, and send ray l1 from the center of the circle to the ending phase angle θ n Emit ray l n As the termination direction, θ1 and θ n Multiple rays l are emitted with a fixed step length i , satisfying θ i+1 -θ i =step;

[0043] S312, calculate the phase and Euclidean distance of each point to the center of the ellipse. Specifically, for each point (x s ,y s ), the phase and Euclidean distance are calculated as

[0044] S313, calculating the contour point with the closest phase distance on each ray within a given boundary threshold range as the representative point of the ray. Specifically, for ray l i Its nearest contour point (x k ,y k )satisfy like Then the contour point is ray l i The representative point of the ray l i There is no representative point;

[0045] S314, calculate the distance from the representative point to the ellipse surface, and calculate the distance from the representative point to the ellipse surface according to the ellipse parameters and the phase of the representative point. By The radius of the ellipse in the direction of the representative point can be calculated, so the distance from the representative point to the ellipse surface can be obtained by Calculate, if d s >0 means the point is above the boundary. s <0 means the point is below the boundary;

[0046] S315, depth map grayscale value calculation, grayscale value can be expressed by Calculate, where RES zis the resolution in the z direction, pixelMid is the grayscale median; the width of the final generated depth image is the number of rays n, and the height is the number of contours in the point cloud data; due to the inconsistent radius of each contour in the top data, the resolution of each row of data in the depth image in the width direction is different, so it is calculated separately, and the calculation formula is

[0047] Furthermore, the binary image generation method is: based on a given depth threshold depth th , through the formula Calculate the corresponding grayscale threshold and compare the grayscale value of the depth map with the grayscale value of the depth map. th By comparison, the formula Generate a binary image B(x,y), where G(x,y) represents the grayscale value of (x,y).

[0048] Furthermore, the method for calculating the connected region of a binary image is as follows: for any connected region R k , whose area is RES x is the x-direction resolution, RES y is the resolution in the y direction; if S k Satisfy the condition S k ≥S min , then the connected region is considered to be a defect.

[0049] The advantages of the present invention are:

[0050] 1. The present invention arranges a rotating bracket, a rear roller, a front roller and an angle control mechanism on the plug detection support frame. Through the cooperation of the above structures, the plug detection system can be used to perform lateral, longitudinal and all-round rotation adjustment, and the detection angle of the plug detection system is continuously adjusted, which can improve the detection accuracy and better fit the existing production line without changing the installation position; the present application is flexible and light in installation, which is convenient for combination with the manufacturer's production line and does not affect the normal operation of the production line;

[0051] 2. The existing hot rolling production lines are already in production and operation, and the installation space for new equipment is very limited. Therefore, this application requires very high flexibility in equipment installation. The advantage of the angle control mechanism is that it can easily adjust the position in the three directions of X, Y, and Z, thereby indirectly driving the full-scale adjustment of the plug detection part, which is more flexible;

[0052] 3. The present invention sets a cooling system. Under the high temperature conditions of the hot rolling production line, if there is no perfect cooling system, it is difficult to ensure long-term stable operation of the detection. The cold airflow of the present invention can remove the smoke and water vapor below the viewing angle of the detection box, providing a good external environment for the detection;

[0053] 4. The heat insulation board frame outside the head detection part of the present invention adopts high temperature resistant heat insulation material, which can cope with the high temperature and corrosive environment of the hot rolling zone. The design of the internal detection device is different from the traditional camera. Traditional cameras are mostly highly integrated with lasers and cameras, and the depth of field of the camera is too small to adapt to the hot rolling environment. In order to meet the detection requirements, the present application separates the camera and the laser to achieve free combination, which can better meet the depth of field range of thermal inspection and ensure that the camera has the best viewing angle. A cooling device is added to the laser to ensure the normal operation of the laser. In summary, the equipment of the present application itself has the advantages of high temperature resistance, corrosion resistance, anti-interference, and easy installation.

[0054] 5. The present invention projects the processed point cloud data into a 2D image by lateral projection, and detects the 2D projection image based on the deep learning pattern recognition method to determine the state of the plug. This method not only improves the reliability and convenience of plug detection, but also provides new ideas for subsequent tasks such as plug melt tip detection and plug meat loss detection, and has a reference role in the research of related fields.

[0055] Since the plug has obvious longitudinal (y direction) and height (z direction) features, the yOz plane can well show these features and clearly display the outline and size of the plug. However, the data in the x direction is relatively redundant and contributes less to the judgment of the plug state. Selecting the yOz plane not only retains the main shape features of the plug, but also makes the features after data projection more intuitive, providing a basis for subsequent morphological recognition.

[0056] 6. The present invention uses ray projection to convert the preprocessed point cloud into a depth image, and then applies image binarization and connected region analysis technology to screen out defect areas that meet the depth threshold and area requirements. This method not only improves the accuracy and efficiency of plug defect detection, but also provides a reference for further research in related fields.

[0057] In the point cloud filtering and point cloud segmentation operations of the present invention, the main purpose of filtering is to downsample the original point cloud, remove redundant data while ensuring data semantics and detail information, and reduce the amount of calculation of the entire processing flow. Point cloud segmentation is to distinguish the top data from the noise data caused by external factors such as water vapor and borax, so as to improve data quality.

[0058] The density-based point cloud segmentation of the present invention can segment the point cloud into different clusters according to the connectivity between the point clouds, thereby improving the segmentation effect of block noise points and reducing false detection or missed detection caused by a large amount of noise data. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic diagram of a device for detecting plug drop and surface defects according to an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of another viewing angle of the device for detecting plug drop and surface defects according to an embodiment of the present invention;

[0061] Figure 3 This is a schematic structural diagram of a plug detection support frame according to an embodiment of the present invention;

[0062] Figure 4 It is a schematic structural diagram of a rotating bracket according to an embodiment of the present invention;

[0063] Figure 5 It is a schematic structural diagram of a rear roller member and an I-beam support according to an embodiment of the present invention;

[0064] Figure 6 It is a schematic structural diagram of a rear roller member according to an embodiment of the present invention;

[0065] Figure 7 It is a schematic structural diagram of a front roller member according to an embodiment of the present invention;

[0066] Figure 8 It is a structural schematic diagram of the angle control mechanism according to an embodiment of the present invention;

[0067] Fig. 9 This is a schematic diagram of the structure of a plug detection member according to an embodiment of the present invention;

[0068] Fig.10 This is a schematic diagram of the structure of an electric control cabinet according to an embodiment of the present invention;

[0069] Fig.11 A cold air trend diagram of the cooling system according to an embodiment of the present invention;

[0070] Fig.12 The figure is a flowchart of the overall process of detecting abnormal plug in an embodiment of the present invention.

[0071] Fig.13 Schematic diagram of basic steps of a method for detecting a plug drop based on lateral projection in an embodiment of the present invention;

[0072] Fig.14 Schematic diagram of specific steps of preprocessing the original point cloud in an embodiment of the present invention;

[0073] Fig.15 Schematic diagram of specific steps of performing lateral projection in an embodiment of the present invention;

[0074] Fig.16 A schematic diagram of basic steps of a plug surface defect detection method based on ray projection in an embodiment of the present invention;

[0075] Fig.17 It is a schematic diagram of ray projection in an embodiment of the present invention;

[0076] Fig.18 , Fig.19 This is a test diagram for the detection of plug drop in an embodiment of the present invention.

[0077] Description of reference numerals:

[0078] 1. Air cooler; 2. Air duct; 3. Fan;

[0079] 4. Head detection support frame; 41. Pillar;

[0080] 42. Rotating bracket; 421. Positioning support; 422. Adjusting friction top screw; 423. Adjusting frame; 424. Rotating rod; 425. Bearing;

[0081] 43, rear roller member; 431, bracket base; 432, support plate; 433, I-beam rear roller; 434, support; 435, friction adjustment screw; 436, locking screw; 437, guide light axis;

[0082] 44, I-beam support; 441, reinforcing rib; 442, longitudinal beam; 443, diagonal beam;

[0083] 45, front roller; 451, bottom plate; 452, limit plate; 453, guide wheel; 454, side plate; 455, I-beam front roller;

[0084] 46, angle control mechanism; 461, "Z" axis rotation assembly; 4611, rotation support seat 1; 4612, rotation member; 4613, support column; 4614, rotation column; 462, "X" axis rotation assembly; 4621, rotation support seat 2; 4622, rotation plate; 4623, vertical rod; 4624, support seat; 463, "Y" axis rotation assembly; 4631, connecting plate; 4632, rotation support seat 3;

[0085] 5. Insulation board frame;

[0086] 6. Electric control cabinet; 601. Touch screen; 602. Cabinet air conditioner; 603. Condensate evaporator;

[0087] 7. Steel pipe; 8. Three-claw pipe clamping machine; 9. Head;

[0088] 10. Head detection component; 101. Laser sensor; 102. Refrigeration sheet; 103. Camera. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0090] This embodiment provides a plug abnormality detection device, including a plug detection system, a cooling system, and a data processing system; the cooling system cools down the plug detection system and the plug working environment; the plug detection system includes a visual unit for photographing a plug image; the visual unit is communicatively connected with the data processing system; the data processing system includes a data preprocessing unit, a plug drop detection unit, a plug surface defect detection unit, and an alarm unit;

[0091] The data preprocessing system receives the point cloud data sent by the visual unit, and segments the point cloud data to obtain vertex data;

[0092] The plug drop detection system detects whether the plug has dropped based on the segmented plug data. The specific detection process is as follows: performing lateral projection on the plug data to reduce the data dimension and obtain a lateral projection image of the plug; performing inference on the lateral projection image of the plug based on the trained deep learning detection model to determine the plug state and obtain drop determination information; and sending a drop alarm signal to the alarm unit based on the drop determination information;

[0093] If the plug has not fallen off, the plug surface defect detection system is started, and the detection process is as follows: ray projection is performed on the plug data, and the plug surface is projected as a depth image with the plug surface as the reference plane to obtain the plug cross-sectional contour projection image; the depth image is binarized according to the depth threshold to generate a binary image; the connected area of ​​the binary image is extracted to determine whether the area meets the conditions. If so, a retention operation is performed and an alarm signal is sent to the alarm unit. If not, a discard operation is performed.

[0094] Each system is described in detail below.

[0095] 1. Plug detection system and cooling system

[0096] The plug detection system and cooling system constitute the hardware part of the plug detection, so they are described as a whole. Figure 1 and Figure 2The hardware part of the head abnormality detection device includes a cooling fan 1, a duct 2, a fan 3, a head detection support frame 4, a heat insulation board frame 5, an electric control cabinet 6 and a visual unit 10 installed on the same operating platform or the ground. In this embodiment, the visual unit adopts a 3D profiler. The cooling fan 1, the duct 2 and the fan 3 are installed on one side of the head detection support frame 4, and the electric control cabinet 6 is located on the other side, which is used to control the cooling fan 1, the fan 3, the head detection support frame 4 and the visual unit 10 intelligently.

[0097] Reference Figure 1 , Figure 2 and Fig.11 The air cooler 1 is connected to the fan 3 through the air duct 2, and the fan 3 is connected to the insulation board frame 5 and the visual unit 10 through the air duct 2, and then acts from the bottom of the insulation board frame 5 to the top head 9 below and the working area of ​​the steel pipe 7. It should be noted that the bottom of the steel pipe 7 is supported by the three-claw pipe clamping machine 8, and the top head 9 is on the same horizontal plane as the steel pipe 7 and is located on the rear side of the steel pipe 7.

[0098] Reference Figure 1 and Figure 2 The top detection support frame 4 includes a pillar 41, a rotating bracket 42, a rear roller member 43, an I-beam bracket 44, a front roller member 45 and an angle control mechanism 46, wherein the pillar 41 is vertically fixed, a rotating bracket 42 is installed on the top of the pillar 41, a rear roller member 43 is installed on the top of the rotating bracket 42, the rear roller member 43 is installed at the rear end of the I-beam bracket 44, and a front roller member 45 is also installed at the front end of the I-beam bracket 44, and the bottom of the front roller member 45 is connected to the visual unit 10 through the angle control mechanism 46, An insulation board frame 5 is provided on the outer side of the visual unit 10; in summary, the rotating bracket 42 can drive the I-beam bracket 44 and the visual unit 10 to rotate along the central axis of the rotating bracket 42 in a large trajectory; the rear roller member 43 and the front roller member 45 can drive the I-beam bracket 44 and the visual unit 10 to move laterally in the "X" axis direction along the direction of the I-beam; the angle control mechanism 46 can drive the visual unit 10 to rotate in all directions, and the visual unit 10 can be adjusted according to the specific working area of ​​the head 9.

[0099] Reference Figure 3 The support 41 is a cylindrical structure as a whole, and a threaded hole is set at the bottom to be fixed on the operating platform or the ground. The top of the support 41 is fixed with a rotating bracket 42 by bolts and screws. The height and diameter of the support 41 depend on the actual operating environment and are not limited in this application.

[0100] Reference Figure 4The rotating bracket 42 includes a positioning support 421 fixedly connected to the top of the support 41 by bolts, screws, etc., a rotating rod 424 is rotatably connected to the middle position of the inner side of the positioning support 421, and a fan-shaped adjustment frame 423 that can be fixed to the positioning support 421 by a pin or a screw, and an adjustment friction top screw 422 that contacts the positioning support 421 are arranged on the outer side of the rotating rod 424. The top of the rotating rod 424 is connected to a positioning plate fixed to the rear roller member 43 through a bearing 425; therefore, when the rotating rod 42 is controlled, When rotating in the positioning pillar 421, the fan-shaped adjustment frame 423 and the friction adjustment screw 422 can rotate on the positioning pillar 421 along with the rotating rod 424, thereby indirectly driving the I-beam support 44 and the visual unit 10 to rotate around the positioning pillar 421. When the fan-shaped adjustment frame 423 and the positioning pillar 421 are rotated to the desired position, the fan-shaped adjustment frame 423 and the positioning pillar 421 can be locked and fixed by a pin or a screw. In this process, the rear roller 43 will not affect the normal rotation of the rotating rod 424.

[0101] Reference Figure 5 and Figure 6 The rear roller member 43 includes a bracket base 431 installed on the top of the rotating bracket 42, and support plates 432 are installed on both sides of the top of the bracket base 431. The inner sides of the two support plates 432 are installed with I-beam rear rollers 433 for driving the I-beam bracket 44 to move horizontally along the "X" axis. Two guide light axes 437 for positioning the I-beam bracket 44 for horizontal movement are symmetrically arranged on both sides of the top of the bracket base 431 and located in front of the two support plates 432. An adjustment frame 434 is also provided on the top of the bracket base 431 and located on the rear sides of the two support plates 432. A locking screw 436 and a friction adjustment screw 435 are installed on the top of the adjustment frame 434. The top of the adjustment frame 434 can contact the bottom surface of the I-beam bracket 44. By adjusting the vertical position of the friction adjustment screw 435 up and down, the distance between it and the bottom surface of the I-beam bracket 44 can be adjusted, thereby adjusting the friction between it and the I-beam bracket 44; and the locking screw 436 can fix the adjustment frame 434 and the I-beam bracket 44. When the I-beam bracket 44 needs to be positioned, the locking screw 436 can be used to lock the adjustment frame 434 and the I-beam bracket 44.

[0102] It should be noted that the rear roller 433 of the I-beam of the present application can be driven by an external motor or manually driven.

[0103] Reference Figure 5The I-beam bracket 44 is arranged horizontally as a whole, and a longitudinal beam 442 is provided at its top near the rear end, that is, near the end of the rear roller member 43. The longitudinal beam 442 is arranged perpendicular to the I-beam bracket 44, and the rear side of the longitudinal beam 442 is fixed to the top of the I-beam bracket 44 through an inclined beam 443, and the front side of the longitudinal beam 442 is fixed to the top of the I-beam bracket 44 through a reinforcing rib 441.

[0104] Reference Figure 3 and Figure 7 The front roller member 45 is installed at the bottom of the front end of the I-beam bracket 44, and can cooperate with the rear roller member 43 to drive the lateral movement of the I-beam bracket 44; the front roller member 45 includes a bottom plate 451, and side plates 454 are provided on both sides of the top of the bottom plate 451. The inner side of the side plate 454 is provided with an I-beam front roller 455 for driving the I-beam bracket 44, and a guide wheel 453 for contacting the lower part of the I-beam bracket 44 is provided between the two side plates 454 and below the I-beam front roller 455. Two groups of symmetrical limiting plates 452 are provided at the top of the bottom plate 451 and on the front side of the two groups of side plates 454. A gap is left between the two groups of limiting plates 452 to pass through the middle vertical plate of the I-beam bracket 44, which can play a certain limiting role in the lateral movement of the I-beam bracket 44.

[0105] It should be noted that the front roller 455 of the I-beam of the present application can be driven by an external motor or manually driven.

[0106] Reference Figure 8 The angle control mechanism 46 includes a "Z" axis rotation component 461 for adjusting the visual unit 10 to rotate along the "Z" axis, an "X" axis rotation component 462 for adjusting the visual unit 10 to rotate along the "X" axis, and a "Y" axis rotation component 463 for adjusting the visual unit 10 to rotate along the "Y" axis.

[0107] Furthermore, the "Z" axis rotating assembly 461 includes a rotating support seat 4611 located directly below the base plate 451, and the top of the rotating support seat 4611 is connected to the base plate 451 of the front roller member 45 via a support column 4613, and a rotating member 4612 is arranged at the middle position of the rotating support seat 4611, and the bottom of the rotating member 4612 is connected to the "X" axis rotating assembly 462 via a rotating column 4614. It should be noted that the rotating member 4612 can be driven to rotate by an external motor, wherein the rotating member 4612 and the rotating column 4614 are provided with through holes leading to the bottom, and when cooling is subsequently performed, the air duct 2 can be inserted from here to apply cold air to the visual unit 10, and when air cooling is not performed, the air duct 2 can be taken out to prevent affecting the normal rotation of the rotating member 4612 and the rotating column 4614.

[0108] Furthermore, the "X" axis rotating assembly 462 includes a rotating support seat 4621 located directly below the rotating support seat 4611, and a support seat 4624 is also provided below the rotating support seat 4621. The middle positions on both sides of the support seat 4624 are rotatably connected with vertical rods 4623, and rotating plates 4622 are installed on both sides of the bottom of the vertical rods 4623. An arc-shaped trajectory groove is opened on the rotating plate 4622, and protrusions are provided at corresponding positions on both sides of the rotating support seat 4621; when the vertical rod 4623 drives the rotating plate 4622 to rotate along the "X" axis, the protrusion can move in the corresponding arc-shaped trajectory groove, and the contact position between the vertical rod 4623 and the rotating support seat 4621 is the rotating part, and the rotating part here can be driven by an external motor.

[0109] Furthermore, the "Y" axis rotation assembly 463 includes connecting plates 4631 installed on the other two sides of the support seat 4624, wherein the inner sides of the two connecting plates 4631 are provided with rotating support seats 4632, and the two rotating support seats 4632 clamp the visual unit 10, and the two rotating support seats 4632 can be driven by an external motor or manually driven by an externally connected handle.

[0110] Reference Fig. 9 The heat insulation board frame 5 is a rectangular frame with an upper opening as a whole, and a visual unit 10 is installed inside it, wherein a laser sensor 101 and a camera 103 are arranged inside the visual unit 10, wherein the laser sensor 101 and the camera 103 can both act on the lower head 9 operating position through the visual unit 10 and the external heat insulation board frame 5; a cooling plate 102 is arranged above the laser sensor 101; after the equipment runs normally, the detection module camera 103 and the laser sensor 101 are calibrated first, the temperature of the pipe is very high during the hot rolling process, and it is necessary to ensure that the detection laser and camera are about 1.5m away from the head pipe, and the laser line falls in the vertical direction with the pipe, and then adjust the angle of the camera to ensure that the brightest laser line can be seen in the field of view of the camera, and then start the fan 3 to test the strength of the airflow and the cooling effect.

[0111] Reference Fig.10 A touch screen 601 is provided at the front end of the electric control cabinet 6, and a cabinet air conditioner 602 and a condensate evaporator 603 are also provided on one side of the electric control cabinet 6. The electric control cabinet 6 is used to intelligently control the components of each component of the present application, such as the cold air fan 1, the fan 3, the visual unit 10, the rear roller member 43, the front roller member 45, the "Z" axis rotation component 461, the "X" axis rotation component 462 and the "Y" axis rotation component 463.

[0112] The specific operating principles of this application are as follows:

[0113] Equipment Installation Overview( Figure 1), it mainly includes a rotating bracket 42, an I-beam bracket 44, a rear roller member 43, a front roller member 45, an angle control mechanism 46, a heat insulation board frame 5, a visual unit 10, a cold air circuit, an electric control box 6 and the like. Select a suitable installation position and fix the support 41. After the assembly is completed, the angle control mechanism 46 is used to adjust the X, Y, and Z axis directions of the visual unit 10 so that the viewing angles of the laser and camera in the visual unit 10 box are in the best position. Finally, the I-beam bracket 44 is fixed, and the rear roller member 43 and the front roller member 45 are locked. Then, start assembling the cold air circuit. After completion, power on to verify whether the functions of each module are normal;

[0114] After the equipment is powered on, the air cooler 1 will continuously output high-pressure airflow. After the high-power airflow passes through the high-power fan 3, the airflow continues to increase. After the strong airflow passes through the air duct, it reaches the visual unit 10 box. The airflow will quickly take away the heat in the box, playing a role in cooling the equipment. The airflow that takes away the heat continues to blow out from the air outlet to remove the water vapor and smoke under the detection box to ensure a good environment within the detection viewing angle. The camera 103 and laser sensor 101 in the detection box will be linked with the PLC of the production line. Before the top head passes through, the laser and camera will be turned on to start collecting data.

[0115] 2. Head abnormality detection

[0116] Based on the first point above, the visual unit takes the image of the plug station and sends it to the data processing system. After denoising, the plug image data is obtained, and then it is tested by the plug drop detection system and the plug surface abnormality detection system. Fig.12 The method shown in the figure comprises the following steps:

[0117] Step S1, preprocessing the original point cloud data to obtain preprocessed point cloud data, and segmenting it to obtain vertex data;

[0118] Step S2, plug drop detection, if the plug does not drop, execute step S3, if the plug drops, repeat steps S1 and S2; the plug drop detection includes the following steps:

[0119] S21, performing lateral projection on the plug data to reduce the data dimension and obtain a lateral projection image of the plug;

[0120] S22, annotating data of the lateral projection image of the top head and building a deep learning detection model;

[0121] S23, reasoning the lateral projection image of the mandrel based on the deep learning detection model, determining the mandrel status, and obtaining drop determination information;

[0122] S24, performing a drop alarm according to the drop determination information;

[0123] Step S3, plug surface defect detection, includes the following steps:

[0124] S31, performing ray projection on the plug data, projecting the plug surface as a depth image with the plug surface as a reference plane, and obtaining a projection image of the plug cross-section contour;

[0125] S32, binarizing the depth image according to the depth threshold to generate a binary image;

[0126] S33, extract the connected area of ​​the binary image, and determine whether the area meets the conditions. If so, perform a retain operation and alarm. If not, perform a discard operation.

[0127] The following describes data preprocessing, plug drop detection, and plug surface defect detection in detail.

[0128] 1) Data preprocessing

[0129] like Figure 2 As shown, in this embodiment, the point cloud data is collected by the 3D profiler arranged at the top working position. In the working environment, a cooling device has been arranged to cool the top working position environment to reduce the influence of water vapor on the collected data, but there is still a small amount of water vapor and other influencing factors in the environment, resulting in large noise in the point cloud data.

[0130] Voxel filtering downsampling;

[0131] In this embodiment, there are a large number of dense points in the original three-dimensional point cloud data, which contains redundant information. Downsampling the point cloud on the basis of meeting the task accuracy requirements is a prerequisite for ensuring the real-time performance of the algorithm. Voxel filtering is a commonly used downsampling method. Its core idea is to divide the point cloud into three-dimensional grids (i.e., voxels) and replace all points in the voxel with representative points in each voxel, thereby reducing the amount of point cloud data. For the input point cloud, its boundary range is [X min ,X max ],[Y min ,Y max ],[Z min ,Z max ]. The side length of the voxel grid is defined as (l x ,l y ,l z ), then every point (x i ,y i ,z i ), the index of the voxel is calculated as:

[0132]

[0133] For each voxel grid, the geometric center of all the points it contains is used as the representative point of the voxel, which is calculated as follows:

[0134]

[0135] Obtain the main cluster based on density segmentation;

[0136] In this embodiment, density-based point cloud segmentation can segment the point cloud into different clusters according to the connectivity state between point clouds, thereby improving the segmentation effect for成片的块状噪点 (成片的块状噪点 can be translated as continuous blocky noise), reducing false detections or missed detections caused by a large amount of noise data. First, set the status of all points to unvisited, and then for each point p, if the point is not visited, mark the point as visited. And calculate the number of points n ε (p), which can be expressed as:

[0137] N ε (p) = {q ∈ D|dist(p, q) ≤ ε}

[0138] where D is the point cloud data set, and dist(p, q) represents the distance between p and q. For the preset point number threshold minPts, if N ε (p) < minPts, mark the point as a noise point, if N ε (p) ≥ minPts, mark the point as a core point, and create a new cluster, add p and all points within its neighborhood to the cluster. Then expand the cluster. For each point q in the cluster, calculate the ε-neighborhood N ε (q) of q. If N ε (q) > minPts, add all unvisited points within the neighborhood of q to the current cluster. In this way, gradually traverse each density-reachable point until no new core points can be found. Repeat the above steps until all points are visited. For the segmented point cloud, there may be some small clusters that do not meet the target requirements or noise clusters that deviate from the specified area. To further extract the target clusters that meet the requirements, the following conditions are introduced to screen the segmented clusters to ensure that the retained clusters meet specific spatial range and density requirements. For each cluster C i , calculate the coordinates (x c , y c , z c ) of its center point, and compare it with the set coordinate range. If the cluster center is not within the predefined range, discard the cluster. The specific calculation is as follows:

[0139]

[0140] In this embodiment, set the xyz range of the cluster center to [x min , x max , [x min , x max , [xmin ,x max ]. If x min ≤x c ≤x max And y min ≤y c ≤y max And z min ≤z c ≤z max , then the cluster center meets the conditions and proceeds to the next step. Otherwise, the cluster is discarded. To exclude small clusters caused by noise or sparse point cloud areas, clusters with points greater than a certain value are retained. Set a minimum point threshold N min , if cluster C i The points satisfy:

[0141] |C i |≥N min

[0142] If the cluster is not found, the cluster is retained; otherwise, the cluster is discarded.

[0143] 2) Head drop detection

[0144] Performing lateral projection on the plug data segmented in the aforementioned step S1 to reduce the data dimension and obtain a lateral projection image of the plug;

[0145] like Figure 4 As shown, in this embodiment, the step S2 of performing the lateral projection further includes the following specific steps:

[0146] S21, input point cloud data;

[0147] In this embodiment, due to the large amount of 3D point cloud data and high dimensionality, direct processing often requires a lot of computing resources and time. Projection is an effective means to simplify calculations. Projecting point cloud data onto a two-dimensional plane can significantly reduce the amount of data, making it easier to complete subsequent analysis operations quickly and at low cost. Although some spatial information is discarded through projection, this processing method can significantly shorten the calculation time while ensuring key features.

[0148] S22, calculating the coordinate range of the projected point cloud;

[0149] In this embodiment, the boundaries of the y coordinates and z coordinates in the point cloud data are calculated. The boundary values ​​define the physical boundaries of the two-dimensional image so as to determine the size and resolution of the image. The specific calculation formula is as follows:

[0150] y min =min(y i ),y max =max(y i ),z min =min(z i),z max =max(z i );

[0152] S23, calculating image resolution;

[0153] In this embodiment, the resolutions in the y and z directions are calculated according to the boundary value and the sizes W and H of the two-dimensional projection image:

[0154]

[0155] S24, calculating coordinate projection;

[0156] S25, acquiring a lateral projection image;

[0157] In this embodiment, the y and z coordinates of each point in the point cloud are converted to the pixel position (i, j) in the image. The mapping formula is as follows:

[0158]

[0159] S26, annotating the projected image data and building a deep learning detection model;

[0160] S27, reasoning the projection image based on the deep learning detection model, judging the state of the head, and determining whether the head falls;

[0161] S28. Activate a drop alarm.

[0162] In this embodiment, the head feature recognition model of the present invention is implemented based on a convolutional neural network. The equipment continuously collects and enriches intact and dropped images of the head under different working conditions, and gradually expands the training data set, thereby steadily improving the system's recognition accuracy and detection accuracy of the head features. The system adopts an online detection method, which effectively combines deep learning with machine vision functions: specifically, the machine vision module is responsible for image capture and processing, and obtains image information in the production process in real time; the deep learning module uses the GPU of the same host to analyze and classify image features and distinguish the head status. While ensuring the detection effect, this design greatly improves the overall computing efficiency and real-time response speed of the system, further ensuring the rapidity and reliability of production detection.

[0163] In summary, the present invention is based on the point cloud data collected by a 3D camera, and realizes data downsampling and segmentation of top data and water vapor noise data through point cloud filtering and a density-based clustering algorithm, which makes full use of the spatial three-dimensional information of the point cloud and improves the denoising effect.

[0164] In the point cloud filtering and point cloud segmentation operations of the present invention, the main purpose of filtering is to downsample the original point cloud, remove redundant data while ensuring data semantics and detail information, and reduce the amount of calculation of the entire processing flow. Point cloud segmentation is to distinguish the top data from the noise data caused by external factors such as water vapor and borax, so as to improve data quality.

[0165] The density-based point cloud segmentation of the present invention can segment the point cloud into different clusters according to the connectivity between the point clouds, thereby improving the segmentation effect of block noise points and reducing false detection or missed detection caused by a large amount of noise data.

[0166] The present invention projects the processed point cloud data into a 2D image by lateral projection, and detects the 2D projection image based on the deep learning pattern recognition method to determine the state of the plug. This method not only improves the reliability and convenience of plug detection, but also provides new ideas for subsequent tasks such as plug melt tip detection and plug meat loss detection, and has a reference role in research in related fields.

[0167] Since the plug has obvious longitudinal (y direction, i.e., plug length direction) and height (z direction) features, the yOz plane can well represent these features and clearly show the profile and size of the plug. However, the data in the x direction is relatively redundant and contributes less to the judgment of the plug state. Selecting the yOz plane not only retains the main shape features of the plug, but also makes the features after data projection more intuitive, providing a basis for subsequent morphological recognition.

[0168] like Figure 7 Figure 8 As shown, Figure 7 Figure 8 For the test image, Figure 7 The upper left picture in the middle is the image taken by the 3D camera, and the lower left picture is the image after lateral projection. From the lower left picture, it can be seen that there is a top head, which means that the top head has not fallen off. Figure 8 The display shows the detection results at different time points. Since the 3D camera shoots the top from top to bottom, the data of the lower half of the top is missing, so the image of the top after lateral projection is in a downward state. It should be noted here that Figure 7 , Figure 8 The time in the figure is the testing time, not the technology disclosure time.

[0169] 3) Plug surface defect detection

[0170] When the detection head does not fall off, continue to detect whether there are defects on the surface of the head, which specifically includes the following steps:

[0171] (1) Calculate the ray projection depth image;

[0172] In this embodiment, for the processed point cloud data, the least squares method is used to perform ellipse fitting on each contour of the plug data to obtain the center (x0, y0) of the ellipse, the major axis a, the minor axis b and the rotation angle ω. In order to ensure that the relative position of the point cloud before and after the projection between the contours remains unchanged, a ray projection-based method is used to perform plane projection on the plug point cloud data. The point cloud data is projected as a depth image with its surface as the reference plane to facilitate defect detection. For a schematic diagram of the projection of a single contour, see Figure 6 .

[0173] In the projection operation of this embodiment, a ray l1 is emitted from the center of the circle to the starting phase angle θ1 as the starting direction, and a ray l2 is emitted from the center of the circle to the ending phase angle θ n Emit ray l n As the termination direction, θ1 and θ n Multiple rays l are emitted with a fixed step length i , satisfying θ i+1 -θ i =step;

[0174] like Figure 5 As shown, the phase and Euclidean distance of each point to the ellipse center are calculated. Specifically, for each point (x s ,y s ), the phase and Euclidean distance are calculated as

[0175] The contour point with the closest phase distance on each ray is calculated within a given boundary threshold range as the representative point of the ray. Specifically, for ray l i Its nearest contour point (x k ,y k )satisfy like Then the contour point is ray l i The representative point of the ray l i There is no representative point;

[0176] Calculate the distance from the representative point to the ellipse surface, based on the ellipse parameters and the phase of the representative point By The radius of the ellipse in the direction of the representative point can be calculated, so the distance from the representative point to the ellipse surface can be obtained by Calculate, if d s >0 means the point is above the boundary. s <0 means the point is below the boundary;

[0177] Depth map grayscale value calculation: The grayscale value in the depth map reflects the fluctuation of the contour surface compared to the reference surface. The grayscale value can be calculated by the formula Calculate, where RES z is the resolution in the z direction, and pixelMid is the grayscale median. The width of the resulting depth image is the number of rays n, and the height is the number of contours in the point cloud data. Since the radii of the contours in the top data are inconsistent, the resolution of each row of data in the depth image in the width direction is different, and must be calculated separately. The calculation formula is

[0178] (2) Perform image binarization based on the depth threshold;

[0179] In this embodiment, based on a given depth threshold depth th , through the formula Calculate the corresponding grayscale threshold and compare the grayscale value of the depth map with the grayscale value of the depth map. th By comparison, the formula Generate a binary image B(x,y), where G(x,y) represents the grayscale value of (x,y).

[0180] (3) Extracting connected regions;

[0181] (4) Determine whether the area meets the conditions;

[0182] (5) If yes, execute the retention operation and issue an alarm;

[0183] (6) If not, execute the discard operation.

[0184] In this embodiment, the foreground pixels are analyzed for connected regions. Specifically, if there are foreground pixels in the eight neighborhoods of the upper, lower, left, right, and four diagonal pixels of each foreground pixel, these foreground pixels belong to a group of connected regions. All foreground pixels are traversed until all connected regions are found. For any connected region R k , whose area is RES x is the x-direction resolution, RES y is the resolution in the y direction. k Satisfy the condition S k ≥S min , then the connected region is considered to be a defect.

[0185] In summary, this method is based on the point cloud data collected by the 3D camera, combined with point cloud filtering and density-based clustering algorithm, to achieve data downsampling and effective segmentation of the head data and water vapor noise data. By utilizing the three-dimensional spatial information of the point cloud, the effect of noise removal is significantly improved. On this basis, ray projection is used to convert the preprocessed point cloud into a depth image, and then image binarization and connected region analysis technology are applied to screen out defect areas that meet the depth threshold and area requirements. This method not only improves the accuracy and efficiency of head defect detection, but also provides a reference for further research in related fields.

[0186] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A plug abnormality detection device, characterized in that: It includes a plug detection system, a cooling system, and a data processing system; the cooling system cools down the plug detection system and the plug working environment; the plug detection system includes a visual unit for photographing a plug image; the visual unit is in communication connection with the data processing system; the data processing system includes a data preprocessing unit, a plug drop detection unit, a plug surface defect detection unit, and an alarm unit; The data preprocessing system receives the point cloud data sent by the visual unit, and segments the point cloud data to obtain vertex data; The plug drop detection system detects whether the plug has dropped based on the segmented plug data. The specific detection process is as follows: performing lateral projection on the plug data to reduce the data dimension and obtain a lateral projection image of the plug; performing inference on the lateral projection image of the plug based on the trained deep learning detection model to determine the plug state and obtain drop determination information; and sending a drop alarm signal to the alarm unit based on the drop determination information; If the plug has not fallen off, the plug surface defect detection system is started, and the detection process is as follows: ray projection is performed on the plug data, and the plug surface is projected as a depth image with the plug surface as the reference plane to obtain the plug cross-sectional contour projection image; the depth image is binarized according to the depth threshold to generate a binary image; the connected area of ​​the binary image is extracted to determine whether the area meets the conditions. If so, a retention operation is performed and an alarm signal is sent to the alarm unit. If not, a discard operation is performed.

2. The plug abnormality detection device according to claim 1, characterized in that: The plug detection system comprises a plug detection support frame (4), comprising a pillar (41) and a rotating support (42) located at the top of the pillar (41); the top of the rotating support (42) is connected to an I-beam support (44) via a rear roller member (43) and can drive the I-beam support (44) to move; the front end of the I-beam support (44) is connected to an angle control mechanism (46) via a front roller member (45); the angle control mechanism (46) clamps the plug detection system and can drive the plug detection system to adjust in all directions; the cooling system is located on one side of the plug detection support frame (4), and can transmit a cold air flow to the plug (9) below the plug detection system through the plug detection system.

3. The plug abnormality detection device according to claim 2, characterized in that: The rear roller member (43) can indirectly push the visual unit (10) to move in the "X" axis direction; The angle control mechanism (46) comprises a "Z" axis rotation component (461) for adjusting the visual unit (10) to rotate about the "Z" axis, an "X" axis rotation component (462) for adjusting the visual unit (10) to rotate about the "X" axis, and a "Y" axis rotation component (463) for adjusting the visual unit (10) to rotate about the "Y" axis.

4. The plug abnormality detection device according to claim 3, characterized in that: The "Z" axis rotating assembly (461) includes a rotating support seat (4611), the top of which is connected to the front roller member (45) via a support column (4613), a rotating member (4612) is provided at the middle position of the rotating support seat (4611), and the bottom of the rotating member (4612) is connected to the "X" axis rotating assembly (462) via a rotating column (4614).

5. The plug abnormality detection device according to claim 3, characterized in that: The "X" axis rotating assembly (462) includes a rotating support seat (4621) and a support seat (4624) located below the rotating support seat (4611), and the middle positions on both sides of the support seat (4624) are rotatably connected with vertical rods (4623), and rotating plates (4622) are installed on both sides of the vertical rods (4623), and arc-shaped track grooves are opened on the rotating plates (4622), and protrusions are arranged at corresponding positions on both sides of the rotating support seat (4621); When the vertical rod (4623) drives the rotating plate (4622) to rotate along the "X" axis, the protrusion can move in the corresponding arc track groove.

6. The plug abnormality detection device according to claim 3, characterized in that: The "Y" axis rotating assembly (463) includes connecting plates (4631) installed on both sides of the support seat (4624), wherein the inner sides of the two connecting plates (4631) are provided with rotating support seats three (4632), and the two rotating support seats three (4632) clamp the visual unit (10).

7. The plug abnormality detection device according to claim 2, characterized in that: The front roller member (45) comprises a bottom plate (451), side plates (454) are arranged on both sides of the top of the bottom plate (451), an I-beam front roller (455) for driving the I-beam bracket (44) is installed on the inner side of the side plate (454), and a guide wheel (453) for contacting the lower part of the I-beam bracket (44) is arranged between the two side plates (454) and below the I-beam front roller (455).

8. The plug abnormality detection device according to claim 2, characterized in that: The rear roller member (43) comprises a support base (431) mounted on the top of the rotating support (42), support plates (432) are mounted on both sides of the top of the support base (431), and I-beam rear rollers (433) for driving the I-beam support (44) are mounted on the inner sides of the two support plates (432). Guide light axes (437) are also arranged on both sides of the top of the support base (431) and on the front sides of the two support plates (432).

9. The plug abnormality detection device according to claim 1, characterized in that: The processing process of the data processing system on the original point cloud data is as follows: S11, collecting and obtaining original point cloud data; S12, downsampling the original point cloud data through voxel filtering to obtain a downsampled point cloud; S13, density-based point cloud segmentation, based on the density of points within the domain, points with accessible density are classified into the same cluster, points with unreachable density are divided into new clusters, and all points are traversed until all points have corresponding clusters, thus obtaining segmented point clouds and segmented clusters; S14, introduce preset conditions for the segmented point cloud, screen the segmented clusters according to the preset conditions, and obtain the target cluster, wherein for each cluster C i , calculate the coordinates of the center point (x c ,y c ,z c ); S15. Determine cluster C i Whether the preset point condition and the preset center condition are met; i The coordinates of the center point (x c ,y c ,z c ), compared with the preset coordinate range; S16. If yes, then for the current cluster C i Execute the retention operation; S17: If not, a discard operation is performed on the current cluster.

10. The plug abnormality detection device according to any one of claims 1 to 9, characterized in that: The specific method of lateral projection in the head drop detection system is: S211, input point cloud data; S212, calculating the projection point cloud coordinate range according to the point cloud data, wherein the boundaries of the y coordinate and the z coordinate in the point cloud data are calculated, the physical boundaries of the two-dimensional image are defined, and the size of the two-dimensional projection image is determined: y min =min(y i ),y max =max(y i ),z min =min(z i ),z max =max(z i ); S213, calculating the image resolution in the y direction and the z direction according to the boundary value of the physical boundary of the two-dimensional image and the size of the two-dimensional projection image: S214, calculating coordinate projection; S215, acquiring a lateral projection image, and obtaining the image pixel position through a coordinate conversion operation.

11. The plug abnormality detection device according to claim 10, characterized in that: In S215, the y coordinate and z coordinate of each point in the point cloud data are converted to the image pixel position (i, j) using the following mapping logic:

12. The plug abnormality detection device according to claim 1, characterized in that: The specific method of ray projection of the plug surface defect detection system is as follows: using the least square method to perform ellipse fitting on each contour of the processed plug data to obtain the center (x0, y0) of the ellipse, the major axis a, the minor axis b, and the rotation angle ω; using a ray projection-based method to perform plane projection on the plug point cloud data, the point cloud data is projected as a depth image with its surface as the reference plane, and the ray projection step includes: S311, send ray l1 from the center of the circle to the starting phase angle θ1 as the starting direction, and send ray l1 from the center of the circle to the ending phase angle θ n Emit ray l n As the termination direction, θ1 and θ n Multiple rays l are emitted with a fixed step length i , satisfying θ i+l -θ i =step; S312, calculate the phase and Euclidean distance of each point to the center of the ellipse. Specifically, for each point (x s ,y s ), the phase and Euclidean distance are calculated as S313, calculating the contour point with the closest phase distance on each ray within a given boundary threshold range as the representative point of the ray. Specifically, for ray l i Its nearest contour point (x k ,y k )satisfy like Then the contour point is ray l i The representative point of the ray l i There is no representative point; S314, calculate the distance from the representative point to the ellipse surface, and calculate the distance from the representative point to the ellipse surface according to the ellipse parameters and the phase of the representative point. By The radius of the ellipse in the direction of the representative point can be calculated, so the distance from the representative point to the ellipse surface can be obtained by Calculate, if d s >0 means the point is above the boundary. s <0 means the point is below the boundary; S315, depth map grayscale value calculation, grayscale value can be expressed by Calculate, where RES z is the resolution in the z direction, pixelMid is the grayscale median; the width of the final generated depth image is the number of rays n, and the height is the number of contours in the point cloud data; due to the inconsistent radius of each contour in the top data, the resolution of each row of data in the depth image in the width direction is different, so it is calculated separately, and the calculation formula is 13. The plug abnormality detection device according to any one of claims 1 to 12, characterized in that: The binary image generation method is: based on a given depth threshold depth th , through the formula Calculate the corresponding grayscale threshold and compare the grayscale value of the depth map with the grayscale value of the depth map. th By comparison, the formula Generate a binary image B(x,y), where G(x,y) represents the grayscale value of (x,y).

14. The plug abnormality detection device according to claim 13, characterized in that: The calculation method of the connected area of ​​a binary image is as follows: k , whose area is RES x is the x-direction resolution, RES y is the resolution in the y direction; if S k Satisfy the condition S k ≥S min , then the connected region is considered to be a defect.

Images