A method for automatically identifying the direction of composite honeycomb implantation based on double-ring identification

Abstract

The application relates to the field of cellular visual identification technology, in particular to a honeycomb composite automatic implantation direction identification method based on double-ring identification. The method comprises the following steps: acquiring the image of a honeycomb profile; determining the center point of the honeycomb profile according to the image; and identifying the automatic implantation direction of the honeycomb profile through double-ring identification according to the center point. The honeycomb composite automatic implantation direction identification method based on double-ring identification aims to solve the problems of abnormal shutdown and abnormal line change of a honeycomb composite automatic implantation device during machining.

Description

Technical Field

[0001] This invention relates to the field of cellular visual recognition technology, and more specifically to a method for identifying the automatic implantation direction of composite cellular structures based on dual-ring recognition. Background Technology

[0002] With the development of the civil aviation industry, noise level has become a crucial technical indicator affecting the market competitiveness of aircraft models. Engines are the primary noise source, and the application of nacelle acoustic liner silencing technology can effectively reduce engine noise. Nacelle acoustic liner silencing involves laying an acoustic liner layer inside the engine nacelle ducts to reduce the outward propagation of noise. Sound-absorbing honeycomb composite materials are the core structure of the acoustic liner for commercial aircraft engine nacelles.

[0003] The sound-absorbing honeycomb composite material structure includes honeycomb profiles (such as...) Figure 1 As shown in the diagram, the main processing method for preparing sound-absorbing honeycomb composite materials is manual. First, adhesive is applied to the inner wall of the honeycomb cavity using a cotton swab. Then, the pre-cut embedded sound-absorbing caps are manually inserted into the honeycomb cavity to a specified depth, and the edges are compacted. This manual operation is cumbersome, the manufacturing cycle of the sound-absorbing honeycomb is long, and the insertion accuracy is greatly affected by the operator's skill level, resulting in low production efficiency and uncontrollable sound-absorbing honeycomb quality.

[0004] The automated composite honeycomb implantation equipment is a manufacturing technology based on robotics and visual recognition to automate the processing of sound-absorbing honeycombs, replacing manual labor. This equipment uses a robot to identify the location of the honeycomb cells, guiding the robot's tool tip to apply adhesive to the inner wall of the cell cavity, and then implanting the sound-absorbing caps within the cells. This equipment effectively improves the efficiency and quality of sound-absorbing honeycomb fabrication.

[0005] However, in actual automated implantation work, due to light interference, obstruction by small objects, damage to the edge of the honeycomb cavity, or deformation of the honeycomb body under pressure, the identification of honeycomb holes may fail. Such individual failures in honeycomb hole identification will cause the automated implantation equipment to stop or change lines abnormally, resulting in a large area of ​​honeycomb holes being skipped and not processed after the sound-absorbing honeycomb is automatically prepared.

[0006] Therefore, the inventors have provided a method for identifying the automatic implantation direction of composite honeycomb based on dual-ring recognition. Summary of the Invention

[0007] (1) Technical problems to be solved

[0008] This invention provides a method for identifying the automatic implantation direction of composite honeycomb based on dual-ring recognition, which solves the technical problems of abnormal shutdown and abnormal line change in the automatic implantation equipment of composite honeycomb during processing.

[0009] (2) Technical solution

[0010] This invention provides a method for automatically identifying the implantation direction of composite honeycomb based on dual-ring recognition, comprising the following steps:

[0011] Acquire images of honeycomb profiles;

[0012] Based on the image, determine the center point of the honeycomb profile;

[0013] Based on the center point, the automatic implantation direction of the honeycomb profile is identified by a double ring.

[0014] Furthermore, acquiring the image of the honeycomb profile specifically involves:

[0015] The image information is captured using an industrial RGBD camera fixed to the end of a robotic arm.

[0016] Further, determining the center point of the honeycomb profile based on the image specifically includes the following steps:

[0017] The image is flipped and corrected so that it is aligned with the coordinates of the human field of vision;

[0018] The image is converted to grayscale and noise interference is removed to obtain the target grayscale image.

[0019] The target grayscale image is binarized to obtain the shape of the honeycomb profile structure;

[0020] The outline of the honeycomb profile structure is smoothed.

[0021] Based on the smoothed honeycomb profile structure shape, obtain the contour information enclosed by the contour;

[0022] Based on the contour information, the contour morphological center point of each honeycomb cell is calculated.

[0023] Furthermore, the median filtering function is used to eliminate noise interference in the grayscale image.

[0024] Furthermore, before smoothing the contour of the honeycomb profile structure, the process further includes:

[0025] Morphological opening / closing operations are performed on the image of the honeycomb profile structure shape to eliminate noise interference.

[0026] Furthermore, the automatic implantation direction of the honeycomb profile identified by the double ring based on the center position specifically includes the following steps:

[0027] Obtain the center point of the camera's field of view;

[0028] The contour morphological center points of all honeycomb holes within the camera's field of view are counted, and sorted in ascending order according to the distance from each contour morphological center point to the camera's field of view center point.

[0029] The center point of the central honeycomb aperture that is closest to the center point of the camera's field of view within the camera's field of view is determined as point BestC1.

[0030] Filter the inner ring honeycomb holes and outer ring honeycomb holes near the central honeycomb hole;

[0031] The implantation direction of the automatic implantation device is identified based on the current implantation direction of the automatic implantation device and the judgment results of the inner ring honeycomb holes and the outer ring honeycomb holes.

[0032] Furthermore, the screening of the inner and outer ring honeycomb holes near the central honeycomb hole specifically involves:

[0033] The region less than one honeycomb hole diameter away from the central honeycomb hole is defined as the inner ring honeycomb hole; and,

[0034] The area located at a distance greater than one honeycomb hole diameter but less than two honeycomb hole diameters from the central honeycomb hole is defined as the outer ring honeycomb hole.

[0035] Further, the step of identifying the implantation direction of the automatic implantation device based on the current implantation direction of the automatic implantation device and the judgment results of the inner ring honeycomb holes and the outer ring honeycomb holes specifically includes the following steps:

[0036] Record the current implantation direction, denoted as δ0;

[0037] Traverse all successfully identified honeycomb holes in the inner ring honeycomb holes, calculate the angle between the line connecting each honeycomb hole and the center point of the camera's field of view and δ0, and select the point with the smallest angle between the inner ring honeycomb hole and δ0 as BestC2_1, and its angle is denoted as δ1.

[0038] Traverse all successfully identified honeycomb holes in the outer ring, calculate the angle between the line connecting each honeycomb hole and the center point of the camera's field of view and δ0, and select the point with the smallest angle between the outer ring honeycomb hole and δ0, denoted as BestC2_2, and its angle is denoted as δ2.

[0039] Based on the calculation results of δ1 and δ2, analyze and judge the calculation result of BestC2.

[0040] Furthermore, the calculation result of BestC2, which is a comprehensive analysis and judgment result based on the calculation results of δ1 and δ2, specifically includes:

[0041] When the minimum included angle of the inner ring honeycomb pore screening is within ±30° and the outer ring honeycomb pore screening has any included angle, the point BestC2_1 is recorded as BestC2, and the automatic implantation direction δ0 remains unchanged.

[0042] When the minimum included angle of the inner ring honeycomb pore screening is greater than 30° and the minimum included angle of the outer ring honeycomb pore screening is less than 30°, the point BestC2_2 is recorded as BestC2, and the automatic implantation direction δ0 remains unchanged.

[0043] When the minimum included angle of the inner ring honeycomb pore screening is greater than 30° and the minimum included angle of the outer ring honeycomb pore screening is also greater than 30°, the point BestC2_1 is recorded as BestC2, and the automatic implantation direction δ0 takes its supplementary angle, that is, δ0=180°-δ0.

[0044] Furthermore, after identifying the implantation direction of the automated implantation device, the method further includes:

[0045] Output the coordinates and direction of the cellular holes to be implanted in the implantation direction, and modify the current implantation direction of the automatic implantation device.

[0046] (3) Beneficial effects

[0047] In summary, this invention captures honeycomb images using a visual sensor; identifies the morphological centers of the honeycomb cells based on the captured images; and analyzes various working conditions during the honeycomb processing using a dual-ring recognition criterion. Finally, it outputs the coordinates of the honeycomb cells to be processed in the current state, as well as the coordinates and orientation of the next honeycomb cell to be processed. It is simple to operate, provides precise visual positioning, is insensitive to changes in ambient light, exhibits strong computational positioning robustness, high speed, low cost, and high security, significantly improving the efficiency of continuous automatic implantation of honeycomb profiles. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a structural diagram of a honeycomb profile;

[0050] Figure 2 This is a flowchart illustrating a method for identifying the automatic implantation direction of composite honeycomb based on dual-ring recognition, provided in an embodiment of the present invention.

[0051] Figure 3This is a flowchart illustrating the process of identifying the center point of a honeycomb profile in a method for automatically implanting direction of composite honeycomb based on double-ring recognition, as provided in an embodiment of the present invention.

[0052] Figure 4 This is a flowchart illustrating the automatic implantation direction identification method for composite honeycomb based on dual-ring recognition, provided in an embodiment of the present invention.

[0053] Figure 5 This is a schematic diagram showing the positions of the inner and outer ring honeycomb holes provided in an embodiment of the present invention.

[0054] In the picture:

[0055] 10 - Inner ring honeycomb holes; 20 - Outer ring honeycomb holes. Detailed Implementation

[0056] The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and examples. The following detailed description of the embodiments and the accompanying drawings are used to illustrate the principles of the present invention by way of example, but should not be used to limit the scope of the present invention, that is, the present invention is not limited to the described embodiments.

[0057] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0058] Figure 2 This is a flowchart illustrating a method for identifying the automatic implantation direction of composite honeycomb based on dual-ring recognition, as provided in an embodiment of the present invention. Figure 2 As shown, the method may include the following steps:

[0059] S100: Obtain an image of the honeycomb profile.

[0060] Specifically, an industrial RGBD camera fixed to the end of the robotic arm is used to capture image information. The industrial RGBD camera is mounted at the end of the robotic arm and takes pictures of the honeycomb profile before each processing.

[0061] S200. Determine the center point of the honeycomb profile based on the image.

[0062] like Figure 3 As shown, step S200 specifically includes the following steps:

[0063] S201. Perform flipping correction on the image to align the coordinates of the image with the coordinates of the human field of view.

[0064] Image correction is performed on the images captured by the camera. This mainly involves automatically calculating parameters such as the captured image size, center point, rotation matrix, and redundant borders using a computer. Then, the image is rotated according to the feeding direction and the image orientation to align the image coordinates, robot coordinates, and physical coordinates. To ensure real-time computation and reduce the amount of image calculation, a 60*60mm window is automatically selected as the effective area for image calculation.

[0065] S202. Perform grayscale conversion on the image to convert it into a grayscale image and remove noise interference to obtain the target grayscale image.

[0066] Specifically, the image grayscale operation converts the three-channel color image captured by the RGBD camera into a single-channel grayscale image using the COLOR_RGB2GRAY grayscale algorithm. The principle of grayscale is: GRAY = B*0.114 + G*0.587 + R*0.299. The image median filtering operation reduces noise in the image, minimizing the impact of noise during camera shooting.

[0067] S203. Perform binarization on the target grayscale image to obtain the shape of the honeycomb profile structure.

[0068] Specifically, the image binarization operation uses an appropriate grayscale value as a threshold to capture an image of a honeycomb cavity that is approximately hexagonal.

[0069] S204. Smooth the outline of the honeycomb profile structure.

[0070] Specifically, the morphological opening / closing operation of the image adjusts the appropriate kernel size, eliminates white and black noise in the image, and makes the image of the honeycomb cavity smoother.

[0071] S205. Based on the smoothed honeycomb profile structure shape, obtain the contour information enclosed by the contour.

[0072] Specifically, contour finding operations are performed to further capture the contour information of the cellular contour envelope based on the adjusted and corrected image.

[0073] S206. Based on the contour information, calculate the contour morphological center point of each honeycomb cell.

[0074] Specifically, the calculation of the morphological center point of the honeycomb hole contour involves calculating and saving the coordinates of the morphological center point of the honeycomb profile hole contour based on the contour information. The morphological center is calculated using the moments of the image, and the formula is as follows:

[0075]

[0076] In the formula, p and q represent the order of the matrix;

[0077] Centered on the corner point m 00

[0078]

[0079] First moment m 01

[0080]

[0081] First moment m 10

[0082]

[0083] That is, the coordinates of the morphological center point x = m 10 / m 00 y = m 01 / m 00 .

[0084] S300: Based on the center point, the automatic implantation direction of the honeycomb profile is identified through a double ring.

[0085] Specifically, based on the information identified by the center point of the honeycomb aperture, the coordinates of the currently implanted honeycomb aperture and the coordinates and orientation of the honeycomb aperture to be implanted by the automatic implantation device are comprehensively selected, and the position information is sent to the robot in a specific format for interpolation movement, such as... Figure 4 As shown, the specific steps include the following:

[0086] S301, Obtain the center point of the camera's field of view.

[0087] Specifically, the center point of the field of view is fixed and denoted as roi(roi.x+roi.width / 2,roi.y+roi.height / 2). This point serves as the fixed interpolation point between the industrial RGBD camera and the robot, and as the origin of the interpolation operation.

[0088] S302. Count the contour morphological center points of all honeycomb holes within the camera's field of view, and sort them from smallest to largest according to the distance of each contour morphological center point to the center point of the camera's field of view.

[0089] Specifically, the above steps ultimately calculate the contour morphological center point, calculate the distance *diss* from each point to the ROI point, and bind and record the center point, distance *diss*, and contour index *i* one by one. The formula for calculating the distance *diss* from the contour center point to the ROI point is:

[0090]

[0091] After traversing all the cell center points and calculating, sort them in ascending order according to the distance (diss) from each point to the ROI point.

[0092] S303. Determine the center point of the central honeycomb aperture that is closest to the center point of the camera's field of view within the camera's field of view as point BestC1.

[0093] Specifically, the cell grid point closest to the center of the camera's field of view, selected from the above sorting, is denoted as BestC1. Logically, this point is the point that the automatic implantation device should implant.

[0094] S304, inner ring honeycomb holes and outer ring honeycomb holes near the screening center honeycomb holes.

[0095] Specifically, such as Figure 5 As shown, the double-ring cell arrays arranged above are selected such that the cells located in the 2nd to 7th order and whose diss is less than 13mm are used as the inner ring of the double-ring cell array, with a maximum of 6 cells 10 in the inner ring; the cells located in the 8th to 19th order and whose diss is greater than 14mm and less than 22mm are used as the outer ring of the double-ring cell array, with a maximum of 12 cells 20 in the outer ring.

[0096] S305. Based on the current implantation direction of the automatic implantation device and the judgment results of the inner and outer ring honeycomb holes, identify the implantation direction of the automatic implantation device.

[0097] As an optional implementation, in step S304, the inner ring honeycomb holes and outer ring honeycomb holes near the central honeycomb hole are screened, specifically as follows:

[0098] The region less than one cell diameter from the center cell is defined as the inner ring cell; and,

[0099] The area located at a distance greater than one cell diameter but less than two cell diameters from the center cell is defined as the outer ring cell.

[0100] As an optional implementation, in step S305, the implantation direction of the automatic implantation device is identified based on the current implantation direction of the automatic implantation device and the judgment results of the inner ring honeycomb holes and the outer ring honeycomb holes. This specifically includes the following steps:

[0101] S3051. Record the current implantation direction, denoted as δ0;

[0102] S3052. Traverse all successfully identified honeycomb holes in the inner ring. Calculate the angle between the line connecting each honeycomb hole and the center point of the camera's field of view and δ0, and select the point with the smallest angle between the inner ring honeycomb hole and δ0, denoted as BestC2_1, and its angle is denoted as δ1.

[0103] S3053. Traverse all successfully identified honeycomb holes in the outer ring. Calculate the angle between the line connecting each honeycomb hole and the center point of the camera's field of view and δ0. Select the point with the smallest angle between the outer ring honeycomb hole and δ0 and denot it as BestC2_2. The angle is denoted as δ2.

[0104] S3054. Based on the calculation results of δ1 and δ2, analyze and judge the calculation result of BestC2.

[0105] As an optional implementation, in step S3044, the calculation result of BestC2 is comprehensively analyzed and judged based on the calculation results of δ1 and δ2, specifically including the following three cases:

[0106] a) When the minimum included angle of the inner ring honeycomb cell screening is within ±30° and the outer ring honeycomb cell screening has any included angle, i.e. Mark the point BestC2_1 as BestC2, and keep the automatic implantation direction δ0 unchanged;

[0107] b) When the minimum included angle of the inner ring honeycomb cell screening is greater than 30° and the minimum included angle of the outer ring honeycomb cell screening is less than 30°, i.e. Mark the point BestC2_2 as BestC2, and keep the automatic implantation direction δ0 unchanged;

[0108] c) When the minimum included angle of the inner ring honeycomb cell screening is greater than 30° and the minimum included angle of the outer ring honeycomb cell screening is also greater than 30°, i.e. Let point BestC2_1 be denoted as BestC2, and take its supplementary angle δ0 for the automatic implantation direction, i.e., δ0 = 180° - δ0.

[0109] As an optional implementation, after identifying the implantation direction of the automated implantation device, the method further includes: outputting the coordinates and direction of the honeycomb holes to be implanted, and modifying the current implantation direction of the automated implantation device. Specifically, the BestC1 and BestC2 points and the implantation direction δ0 of the automated implantation device are finally converted into a unified format and transmitted to the automated implantation device. Using this method, the overall efficiency of composite honeycomb implantation is significantly improved.

[0110] This recognition method provides accurate coordinate information for automated honeycomb profile implantation equipment. It can identify the outline of each irregularly shaped and not completely consistent hexagonal honeycomb cell, calculate the morphological center of the honeycomb cell, and use a dual-ring recognition algorithm to select the best implantation honeycomb cell and the best implantation direction. Finally, the coordinate information is sent to the robot for interpolation motion.

[0111] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. The present invention is not limited to the specific steps and structures described above and shown in the figures. Furthermore, for the sake of brevity, detailed descriptions of known methods and techniques are omitted here.

[0112] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art without departing from the scope of the invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for identifying the direction of automatic implantation of a composite honeycomb based on double-ring identification, characterized in that, The method comprises the following steps: acquiring an image of the honeycomb profile; determining a center point of the honeycomb profile according to the image; identifying an automatic implantation direction of the honeycomb profile by double ring according to the center point; the step of identifying the automatic implantation direction of the honeycomb profile by double ring according to the center point specifically comprises the following steps: acquiring a camera field of view center point; counting all honeycomb hole contour morphological center points within the camera field of view range, and sorting the contour morphological center points according to the distance from the camera field of view center point in ascending order; determining the center point of the center honeycomb hole closest to the camera field of view center point as the BestC1 point; screening inner ring honeycomb holes and outer ring honeycomb holes near the center honeycomb hole; identifying the implantation direction of the automatic implantation equipment according to the current implantation direction of the automatic implantation equipment and the judgment result of the inner ring honeycomb hole and the outer ring honeycomb hole.

2. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The step of acquiring the image of the honeycomb profile specifically comprises: capturing the image information by using an industrial RGBD camera fixed at the end of a mechanical arm.

3. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The step of determining the center point of the honeycomb profile according to the image specifically comprises the following steps: performing flip correction according to the image, so that the image is aligned with the coordinates of the artificial field of view; performing a grayscale operation on the image to convert it into a grayscale image and eliminate noise interference, so as to obtain a target grayscale image; performing a binarization operation on the target grayscale image to obtain a honeycomb profile structure shape; performing smoothing processing on the contour of the honeycomb profile structure shape; acquiring contour information enveloped by the contour according to the smoothed honeycomb profile structure shape; calculating the contour morphological center point of each honeycomb hole according to the contour information.

4. The method of claim 3, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The noise interference in the grayscale image is eliminated by using a median filter function.

5. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, Before the step of performing smoothing processing on the contour of the honeycomb profile structure shape, the method further comprises the following steps: performing morphological opening / closing operation on the image of the honeycomb profile structure shape to eliminate noise interference.

6. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The step of screening the inner ring honeycomb holes and the outer ring honeycomb holes near the center honeycomb hole specifically comprises the following steps: determining an area within 1 honeycomb hole diameter from the center honeycomb hole as the inner ring honeycomb hole; and determining an area within 2 honeycomb hole diameters from the center honeycomb hole as the outer ring honeycomb hole.

7. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The step of identifying the implantation direction of the automatic implantation equipment according to the current implantation direction of the automatic implantation equipment and the judgment result of the inner ring honeycomb hole and the outer ring honeycomb hole specifically comprises the following steps: recording the current implantation direction, denoted as ; Iterate through all successfully identified honeycomb holes in the inner ring, and calculate the line connecting each honeycomb hole to the center point of the camera's field of view. The included angle, and screen out the inner ring honeycomb holes and The point with the smallest included angle is denoted as BestC2_1, and its included angle is denoted as... ; Iterate through all successfully identified honeycomb holes in the outer ring, and calculate the line connecting each honeycomb hole to the center point of the camera's field of view. The included angle, and screen out the outer ring honeycomb holes and The point with the smallest included angle is denoted as BestC2_2, and its included angle is denoted as... ; According to , The calculation result of the analysis and determination result BestC2.

8. The method of claim 7, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, The according to , The calculation result of the comprehensive analysis and judgment result BestC2 includes: When the minimum included angle of the inner ring honeycomb hole screening is within ± 30° and the outer ring honeycomb hole screening exists an included angle of any angle, the BestC2_1 point is recorded as BestC2, and the automatic implantation direction unchanged; When the minimum included angle of the inner ring honeycomb hole screening is greater than 30° and the minimum included angle of the outer ring honeycomb hole screening is less than 30°, the BestC2_2 point is recorded as BestC2, and the automatic implantation direction is determined unchanged; When the minimum included angle of the inner ring honeycomb hole screen is greater than 30° and the minimum included angle of the outer ring honeycomb hole screen is also greater than 30°, the BestC2_1 point is recorded as BestC2, and the automatic implantation direction is determined Take its supplementary angle, that is, .

9. The method of claim 1, wherein the method is a method of identifying the direction of automatic implantation of a double-ring-based composite honeycomb, characterized by, After the step of identifying the implantation direction of the automatic implantation equipment, the method further comprises the following steps: outputting the honeycomb hole coordinates and direction that need to be implanted in the implantation direction, and modifying the current implantation direction of the automatic implantation equipment.

Images