CN118096706B - System and method for detecting appearance of radome preform for spaceflight - Google Patents
System and method for detecting appearance of radome preform for spaceflight Download PDFInfo
- Publication number
- CN118096706B CN118096706B CN202410277355.9A CN202410277355A CN118096706B CN 118096706 B CN118096706 B CN 118096706B CN 202410277355 A CN202410277355 A CN 202410277355A CN 118096706 B CN118096706 B CN 118096706B
- Authority
- CN
- China
- Prior art keywords
- module
- shadow
- detection target
- shadow image
- capturing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 185
- 238000009877 rendering Methods 0.000 claims abstract description 50
- 230000007547 defect Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 31
- 230000011218 segmentation Effects 0.000 claims description 24
- 230000008521 reorganization Effects 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 3
- 238000005215 recombination Methods 0.000 claims description 3
- 230000006798 recombination Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 238000002601 radiography Methods 0.000 abstract description 3
- 238000012797 qualification Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000005192 partition Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000011152 fibreglass Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of radomes, in particular to an appearance detection system and method for a prefabricated body of a radome for spaceflight, wherein the system comprises a capturing layer, a rendering layer and a detection layer; setting detection target capturing logic in a capturing layer, capturing shadow images of detection targets based on the capturing logic, synchronously receiving the detection target shadow images captured by the capturing layer by a rendering layer, and synchronously acquiring capturing logic applied when capturing the detection target shadow images; according to the invention, the appearance detection condition of the prefabricated radome is provided in a radiography mode, the detection process can be adaptively configured based on the specification of the prefabricated radome, the appearance detection effect is comprehensive, and the defect judgment of the prefabricated radome can be greatly replaced by manual work, so that the yield qualification rate of the prefabricated radome is improved, the safety guarantee is further provided for the antenna equipment provided with the prefabricated radome, the stable operation of the antenna is ensured, and the antenna is better protected through the radome.
Description
Technical Field
The invention relates to the technical field of radomes, in particular to a system and a method for detecting the appearance of a prefabricated body of a radome for spaceflight.
Background
Prefabricated radomes are radomes prefabricated in a factory, which can be installed and assembled on site to reduce the time and cost of site construction. Prefabricated radomes are typically made of high strength materials such as fiberglass, carbon fiber, etc. to ensure adequate strength and durability;
the prefabricated radome for the aerospace is a radome applied to an antenna of aerospace equipment.
At present, the appearance detection of the radome is usually focused on the integrity of the material and the function of the radome surface, and the detection effect is poor when the shape of the radome meets the standard of a qualified finished product or not by manual visual detection, so that the service life, the mechanical property and the like of the radome are directly influenced if the shape of the radome does not meet the standard.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a system and a method for detecting the appearance of a prefabricated body of a radome for spaceflight, which solve the technical problems in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
In a first aspect, an appearance detection system for a radome preform for aerospace comprises a capturing layer, a rendering layer and a detection layer;
Setting a detection target capturing logic in a capturing layer, capturing shadow images of the detection target based on the capturing logic, synchronously receiving the shadow images of the detection target captured by the capturing layer by a rendering layer, synchronously acquiring the capturing logic applied when capturing the shadow images of the detection target, completing the segmentation of the shadow images of the detection target based on the capturing logic, further executing rendering on the shadow images in the detection target through a segmentation result, acquiring the shadow images which are completely rendered in the rendering layer by the detection layer, and identifying whether defects exist in the appearance of the detection target based on the shadow images which are completely rendered;
the rendering layer comprises a receiving module, a dividing module and a rendering module, wherein the receiving module is used for receiving a detection target shadow image captured in the capturing layer and capturing logic applied when the detection target shadow image is captured, the dividing module is used for acquiring the detection target shadow image received in the receiving module, determining a division line of the detection target shadow image based on the capturing logic, dividing the detection target shadow image by using the division line, and the rendering module is used for extracting the shadow image in an image block which is divided and contains part of the detection target image and all the detection target shadow image and rendering the shadow image;
When the receiving module receives the target shadow images, the receiving module continuously receives the target shadow images in a group of two groups, and when the rendering module renders the shadow images, the rendering colors of the shadow images from the same group are inconsistent.
Further, the capturing layer comprises an acquisition module, an uploading module and a logic module, wherein the acquisition module is used for acquiring shadow images of the detection targets, the uploading module is used for uploading outer contour standard specification parameters of the detection targets, the logic module is used for receiving the outer contour standard specification parameters of the detection targets uploaded by the uploading module, and the acquisition logic of the detection targets when the shadow image acquisition is executed is set based on the outer contour standard specification parameters of the detection targets;
The camera is symmetrically arranged on the surface of the support, the two camera end image acquisition visual angles of the cameras are converged at one point, the camera end operation acquired image data of the cameras, namely, detection target shadow images, are overlapped with the camera end image acquisition visual angle convergence points of the two groups of cameras, each group of cameras is provided with a group of light source modules, and the camera end operation stages are used for deploying the camera-configured light source modules in the opposite directions of the cameras to synchronously operate.
Still further, the detection target shadow image acquisition logic set in the logic module includes: adjusting the focal length of a camera in the acquisition module and setting the running times of a circular electric slide rail driving bracket in the acquisition module;
setting of the running times of the annular electric sliding rail driving support in the acquisition module obeys:
Wherein: m is the running times of the annular electric slide rail driving bracket; d L is the length of the detection target; d W is the width of the detection target; d H is the height of the detection target; f c is the tip curvature of the detection target; θ is a normalization factor;
The running times m of the annular electric sliding rail driving support are rounded upwards, and the normalization factor theta is an integer not smaller than 1.
Further, when the camera in the acquisition module adjusts the focal length and acquires the detection target shadow image, the area of the detection target shadow image is smaller than one half of the detection target shadow image, the outline of the detection target shadow image in the detection target shadow image does not coincide with the boundary of the detection target shadow image, and when the annular electric slide rail in the acquisition module drives the bracket to operate, the operation angle of the driving bracket is not smaller than five degrees and not larger than fifteen degrees each time; the camera in the acquisition module sequentially runs once after angle adjustment is completed based on the support each time, the uploading module and the logic module in the capturing layer are refreshed when the detection layer is completed to run each time, and the rendering layer and the detection layer follow the refreshing operation of the uploading module and the logic module and are in linkage operation again.
Furthermore, the operation stage of the segmentation module is to determine a coordinate system based on the length and width of the detection target shadow image adjacent to the detection target during acquisition, determine a group of straight lines passing through the origin on the coordinate system based on the positions of the two groups of cameras in the acquisition module during acquisition of the detection target shadow image, and the segmentation line of the detection target shadow image determined in the segmentation module is a line segment formed by connecting any two points on the contour of the shadow image of the detection target, and is mutually perpendicular to a group of straight lines passing through the origin on the coordinate system determined based on the positions of the two groups of cameras in the acquisition module during acquisition of the detection target shadow image.
Further, the detection layer comprises a reorganization module, a folding module and an identification module, wherein the reorganization module is used for acquiring the shadow images which are completely rendered in the rendering layer, identifying the shadow images which are completely rendered, combining the shadow images which are completely rendered with the same source, the folding module is used for receiving the shadow images which are completely combined in the reorganization module, carrying out folding processing on the shadow images which are completely combined, the identification module is used for traversing the shadow images which are completely combined after the folding processing, and identifying whether defects exist in the shadow images which are completely combined corresponding to the detection target based on the shadow coverage rate of the shadow images which are completely combined after the folding processing.
Furthermore, when the recombination module combines the shadow images which are completely rendered, the parting line is used as a splicing boundary of the two groups of shadow images which are completely rendered, and the two groups of endpoints of the parting line are used as splicing points to complete the combination operation, so that the two groups of shadow images which are completely combined respectively correspond to the endpoints of the parting line, at least one group of endpoints are mutually overlapped and are not overlapped, and the distance is shortest based on the state that one group of endpoints are mutually overlapped;
When the folding module carries out folding processing on the combined shadow image, the folding angle is one hundred and eighty degrees, the folding position is a dividing line, the folding module carries out folding on the combined shadow image, takes the left side of the dividing line as a folding target, rotates and folds towards the right side of the dividing line based on the folding angle, resets after the folding is completed, takes the right side of the dividing line as a folding target, rotates and folds towards the left side of the dividing line based on the folding angle, and resets after the folding is completed;
after the shadow image is folded each time, the identification module operates once before resetting.
Furthermore, the shadow coverage rate after the combined shadow image folding processing in the recognition module is obtained by the following formula:
Wherein: k is shadow coverage rate after the folding processing of the combined shadow image is completed; m, N is the number of regions in the lateral and longitudinal directions in the shadow image of the completed combination equally divided into m×n regions; sim (R m,n,Rm,n ') is the gray value similarity of region R m,n to region R m,n'; s turn1 is the area ratio of the shielding area of the folding side covered on the other side to the area of the other side in the first shadow image; s turn2 is the area ratio of the shielding area of the folding side covered on the other side to the area of the other side in the second shadow image; k Heald is the comprehensive shadow coverage rate after all the combined shadow images are folded; u is the set of shadow images that complete the combination; k v is the shadow coverage rate of the v-th group after the folding processing of the combined shadow image; u 0 is the total amount of shadow images in u that are combined;
Wherein, the region R m,n and the region R m,n' are symmetrical to each other in the shadow image relative to the dividing line of the shadow image, S turn1≤1,0＜Sturn2 is more than 0 and less than or equal to 1, For representing the symmetry of the shadow image that completes the combination,The closer its value is to 1, the more symmetrical the shadow image that completes the combination; and in the operation stage of the identification module, the defect judgment threshold is manually set by a user at the system end, and whether the appearance of the detection target of the source of K Heald has defects is judged based on the comparison of the defect judgment threshold and K Heald .
Furthermore, the receiving module is interactively connected with the dividing module and the rendering module through a local area network, the receiving module is interactively connected with the logic module through the local area network, the logic module is interactively connected with the uploading module and the collecting module through a wireless network, the rendering module is interactively connected with the reorganizing module through the wireless network, and the reorganizing module is interactively connected with the folding module and the identifying module through the wireless network.
In a second aspect, a method for detecting the appearance of a prefabricated body of a radome for spaceflight includes the following steps:
s1: setting a capturing logic, and capturing monitoring target shadow image data based on the capturing logic;
s2: receiving detection target shadow image data, performing segmentation processing on the detection target shadow image data, and extracting a shadow image based on a segmentation processing result;
s3: rendering the shadow image;
S4: acquiring a shadow image which is rendered, identifying a shadow image source, and reorganizing the shadow image;
S41: a setting stage of shadow image reorganization logic;
s5: folding the recombined shadow image, and analyzing shadow coverage rate based on a folding result;
s6: and identifying whether the detection target has defects according to the analyzed shadow coverage rate.
Compared with the prior art, the technical proposal provided by the invention has the following advantages that
The beneficial effects are that:
The invention provides an appearance detection system and method for a prefabricated body of a radome for spaceflight, wherein the appearance detection condition of the prefabricated radome is provided in a radiography mode, the detection process can be adaptively configured based on the specification of the prefabricated radome, the appearance detection effect is comprehensive, the defect judgment of the prefabricated radome can be greatly replaced by manpower, the yield of the prefabricated radome is improved, the safety guarantee is further provided for antenna equipment provided with the prefabricated radome, the stable operation of an antenna is ensured, and the antenna is better protected through the radome.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a structure of an appearance detection system of a prefabricated body of a radome for spaceflight;
FIG. 2 is a schematic flow chart of a method for detecting the appearance of a prefabricated body of an antenna housing for spaceflight;
FIG. 3 is a schematic diagram of a capturing module structure of a capturing layer in the system according to the present invention;
FIG. 4 is a schematic view of the acquisition view angle of the acquisition module of the capturing layer in the system according to the present invention;
FIG. 5 is a diagram of an exemplary acquisition-module-based imaging of a detection target in accordance with the present invention;
FIG. 6 is a schematic diagram of a shadow image reorganization logic in accordance with the present invention;
Reference numerals in the drawings represent respectively: 1. detecting a target; 2. annular electric slide rail; 3. a bracket; 4. a camera; 5. a light source module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described below with reference to examples.
Example 1:
The system for detecting the appearance of a prefabricated body of a radome for spaceflight in this embodiment, as shown in fig. 1, includes: the device comprises a capturing layer, a rendering layer and a detection layer;
Setting a detection target capturing logic in a capturing layer, capturing shadow images of the detection target based on the capturing logic, synchronously receiving the shadow images of the detection target captured by the capturing layer by a rendering layer, synchronously acquiring the capturing logic applied when capturing the shadow images of the detection target, completing the segmentation of the shadow images of the detection target based on the capturing logic, further executing rendering on the shadow images in the detection target through a segmentation result, acquiring the shadow images which are completely rendered in the rendering layer by the detection layer, and identifying whether defects exist in the appearance of the detection target based on the shadow images which are completely rendered;
The capturing layer comprises an acquisition module, an uploading module and a logic module, wherein the acquisition module is used for acquiring shadow images of the detection targets, the uploading module is used for uploading outer contour standard specification parameters of the detection targets, the logic module is used for receiving the outer contour standard specification parameters of the detection targets uploaded by the uploading module, and the acquisition logic of the detection targets when the shadow image acquisition is executed is set based on the outer contour standard specification parameters of the detection targets;
The camera is symmetrically arranged on the surface of the support, the image acquisition view angles of the camera ends of the two groups of cameras are converged at one point, the image data acquired by the camera ends of the cameras are the detection target shadow images, when the detection target shadow images are acquired, the center point of the bottom surface of the detection target coincides with the convergence point of the image acquisition view angles of the camera ends of the two groups of cameras, each group of cameras is provided with one group of light source modules, and the camera operation stage is that the light source modules configured by the cameras are deployed in opposite directions;
the rendering layer comprises a receiving module, a dividing module and a rendering module, wherein the receiving module is used for receiving a detection target shadow image captured in the capturing layer and capturing logic applied when the detection target shadow image is captured, the dividing module is used for acquiring the detection target shadow image received in the receiving module, determining a division line of the detection target shadow image based on the capturing logic, dividing the detection target shadow image by using the division line, and the rendering module is used for extracting the shadow image in an image block which is divided and contains part of the detection target image and all the detection target shadow image and rendering the shadow image;
When the receiving module receives the target shadow images, the receiving module continuously receives the target shadow images in a group of two groups, and when the rendering module renders the shadow images, the rendering colors of the shadow images from the same group are inconsistent;
The detection layer comprises a reorganization module, a folding module and an identification module, wherein the reorganization module is used for acquiring shadow images which are completely rendered in the rendering layer, identifying shadow image sources which are completely rendered to detect target shadow images, combining the shadow images which are completely rendered with the same source group, the folding module is used for receiving the shadow images which are completely combined in the reorganization module, carrying out folding processing on the shadow images which are completely combined, and the identification module is used for traversing the shadow images which are completely combined after the folding processing, and identifying whether defects exist in the shadow images which are completely combined corresponding to the detection target based on the shadow coverage rate of the shadow images which are completely combined after the folding processing;
The receiving module is interactively connected with the segmentation module and the rendering module through a local area network, the receiving module is interactively connected with the logic module through the local area network, the logic module is interactively connected with the uploading module and the collecting module through a wireless network, the rendering module is interactively connected with the reorganization module through the wireless network, and the reorganization module is interactively connected with the folding module and the identification module through the wireless network.
In this embodiment, the uploading module operates to upload the external outline standard specification parameters of the detection target, the logic module synchronously receives the external outline standard specification parameters of the detection target uploaded by the uploading module, sets the acquisition logic of the detection target when the shadow image acquisition is performed based on the external outline standard specification parameters of the detection target, the acquisition module further operates to acquire the shadow image of the detection target, the receiving module receives the shadow image of the detection target captured in the capturing layer in real time, and the capturing logic applied when the shadow image of the detection target is captured, the dividing module operates to acquire the shadow image of the detection target received in the receiving module at a later stage, determines the dividing line of the shadow image of the detection target based on the capturing logic, divides the shadow image of the detection target by applying the dividing line, and then the rendering module extracts the segmented shadow images in the image blocks containing part of the detection target images and all the detection target shadow images, the shadow images are subjected to rendering processing, the reorganization module further acquires the shadow images which are completely rendered in the rendering layer, identifies the source detection target shadow images of the shadow images which are completely rendered, combines the shadow images which are completely rendered with the source as the same group, the folding module receives the shadow images which are completely combined in the reorganization module, carries out folding processing on the shadow images which are completely combined, and finally traverses the shadow images which are completely combined after folding processing through the identification module, and identifies whether defects exist in the shadow images which are completely combined corresponding to the detection targets based on the shadow coverage rate of the shadow images which are completely combined after folding processing.
Referring to fig. 3, the structure distribution of the acquisition module in the capturing layer of the system is further shown, so that a user implementing the technical scheme can configure hardware conveniently, necessary conditions are provided for implementing the system, and fig. 4 further shows and defines an acquisition view angle when the camera 4 in the acquisition module acquires the shadow image of the detection target;
the shadow generated by the light source module 5 irradiating the detection target 1 in the acquisition module is further shown by the shadow part in fig. 5, the shadow image combined by the operation of the recombination module in the system is further shown by fig. 6, and the broken line in the figure shows the dividing line used for dividing the shadow image of the detection target.
Example 2:
On the aspect of implementation, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, an aerospace radome preform appearance detection system in embodiment 1:
The detection target shadow image acquisition logic set in the logic module comprises: adjusting the focal length of a camera in the acquisition module and setting the running times of a circular electric slide rail driving bracket in the acquisition module;
setting of the running times of the annular electric slide rail driving support in the acquisition module obeys:
Wherein: m is the running times of the annular electric slide rail driving bracket; d L is the length of the detection target; d W is the width of the detection target; d H is the height of the detection target; f c is the tip curvature of the detection target; θ is a normalization factor;
The running times m of the annular electric sliding rail driving support are rounded upwards, and the normalization factor theta is an integer not smaller than 1.
Through the formula calculation, the quantity of the shadow images of the detection targets acquired by the acquisition module is further limited, the shadow image data of the detection targets acquired by the acquisition module is ensured, the detection precision of the system can be met, and a reliable precision constraint condition is provided for the detection result of the detection targets.
As shown in fig. 1, when a camera in the acquisition module adjusts a focal length and acquires a detection target shadow image, an area where a monitoring target image in the detection target shadow image is located is smaller than one half of that of the detection target shadow image, and the outline of the monitoring target image in the detection target shadow image is not overlapped with the boundary of the detection target shadow image, when an annular electric sliding rail in the acquisition module drives a bracket to operate, the operation angle of the driving bracket is not smaller than five degrees and not larger than fifteen degrees each time;
The camera in the acquisition module sequentially runs once after angle adjustment is completed based on the support each time, the uploading module and the logic module in the capturing layer are refreshed when the detection layer is completed to run each time, and the rendering layer and the detection layer follow the refreshing operation of the uploading module and the logic module and are in linkage operation again.
Through the arrangement, the operation logic of the acquisition module is further limited.
As shown in fig. 1, in the operation stage of the segmentation module, a coordinate system is determined based on the length and width of the detection target shadow image adjacent to the detection target during acquisition, a group of straight lines passing through the origin on the coordinate system is determined based on the positions of the two groups of cameras in the acquisition module during acquisition of the detection target shadow image, the segmentation line of the detection target shadow image determined in the segmentation module is a line segment formed by connecting any two points on the contour of the shadow image of the detection target, and the segmentation line is mutually perpendicular to a group of straight lines passing through the origin on the coordinate system determined based on the positions of the two groups of cameras in the acquisition module during acquisition of the detection target shadow image.
Through the arrangement, limitation is further brought to the dividing line applied in the running stage of the dividing module.
As shown in fig. 1, when the reorganization module combines the shadow images which are completely rendered, the partition line is used as a splicing boundary of the two groups of shadow images which are completely rendered, and two groups of endpoints of the partition line are used as splicing points to complete the combination operation, so that the two groups of shadow images which are completely combined respectively correspond to the endpoints of the partition line, at least one group of endpoints are mutually overlapped and not overlapped, and the distance is shortest based on the state that one group of endpoints are mutually overlapped;
When the folding module carries out folding processing on the combined shadow image, the folding angle is one hundred eighty degrees, the folding position is a dividing line, the folding module carries out folding on the combined shadow image, takes the left side of the dividing line as a folding target, rotates and folds towards the right side of the dividing line based on the folding angle, resets after the folding is completed, takes the right side of the dividing line as a folding target, rotates and folds towards the left side of the dividing line based on the folding angle, and resets after the folding is completed;
after the shadow image is folded each time, the identification module operates once before resetting.
Through the arrangement, the system operation logic is further perfected, and the system can be ensured to continuously and stably operate.
As shown in fig. 1, the shadow coverage after the combined shadow image folding processing in the recognition module is obtained by the following formula:
Wherein: k is shadow coverage rate after the folding processing of the combined shadow image is completed; m, N is the number of regions in the lateral and longitudinal directions in the shadow image of the completed combination equally divided into m×n regions; sim (R m,n,Rm,n ') is the gray value similarity of region R m,n to region R m,n'; s turn1 is the area ratio of the shielding area of the folding side covered on the other side to the area of the other side in the first shadow image; s turn2 is the area ratio of the shielding area of the folding side covered on the other side to the area of the other side in the second shadow image; k Heald is the comprehensive shadow coverage rate after all the combined shadow images are folded; u is the set of shadow images that complete the combination; k v is the shadow coverage rate of the v-th group after the folding processing of the combined shadow image; u 0 is the total amount of shadow images in u that are combined;
Wherein, the region R m,n and the region R m,n' are symmetrical to each other in the shadow image relative to the dividing line of the shadow image, S turn1≤1,0＜Sturn2 is more than 0 and less than or equal to 1, For representing the symmetry of the shadow image that completes the combination,The closer its value is to 1, the more symmetrical the shadow image that completes the combination; and in the operation stage of the identification module, the defect judgment threshold is manually set by a user at the system end, and whether the appearance of the detection target of the source of K Heald has defects is judged based on the comparison of the defect judgment threshold and K Heald .
Through the calculation of the formula, the operation of each layer in the system generates data, and final reliable and accurate decision is made for the defect judgment of the detection target.
Example 3:
On the aspect of implementation, on the basis of embodiment 1, this embodiment further specifically describes an aerospace radome preform appearance detection system in embodiment 1 with reference to fig. 2:
the method for detecting the appearance of the antenna housing preform for spaceflight comprises the following steps:
s1: setting a capturing logic, and capturing monitoring target shadow image data based on the capturing logic;
s2: receiving detection target shadow image data, performing segmentation processing on the detection target shadow image data, and extracting a shadow image based on a segmentation processing result;
s3: rendering the shadow image;
S4: acquiring a shadow image which is rendered, identifying a shadow image source, and reorganizing the shadow image;
S41: a setting stage of shadow image reorganization logic;
s5: folding the recombined shadow image, and analyzing shadow coverage rate based on a folding result;
s6: and identifying whether the detection target has defects according to the analyzed shadow coverage rate.
In summary, the system and the method in the above embodiments provide the condition for detecting the appearance of the prefabricated radome in a radiography manner, and the monitoring process can adaptively configure based on the specification of the prefabricated radome, so that the appearance detection effect is relatively comprehensive, and the defect judgment can be performed on the prefabricated radome by replacing manual work to a large extent, thereby improving the yield qualification rate of the prefabricated radome, further providing safety guarantee for the antenna equipment provided with the prefabricated radome, ensuring the stable operation of the antenna, and obtaining better protection through the radome.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. An exterior inspection system for a radome preform for aerospace, comprising: the device comprises a capturing layer, a rendering layer and a detection layer;
Setting a detection target capturing logic in a capturing layer, capturing shadow images of the detection target based on the capturing logic, synchronously receiving the shadow images of the detection target captured by the capturing layer by a rendering layer, synchronously acquiring the capturing logic applied when capturing the shadow images of the detection target, completing the segmentation of the shadow images of the detection target based on the capturing logic, further executing rendering on the shadow images in the detection target through a segmentation result, acquiring the shadow images which are completely rendered in the rendering layer by the detection layer, and identifying whether defects exist in the appearance of the detection target based on the shadow images which are completely rendered;
the rendering layer comprises a receiving module, a dividing module and a rendering module, wherein the receiving module is used for receiving a detection target shadow image captured in the capturing layer and capturing logic applied when the detection target shadow image is captured, the dividing module is used for acquiring the detection target shadow image received in the receiving module, determining a division line of the detection target shadow image based on the capturing logic, dividing the detection target shadow image by using the division line, and the rendering module is used for extracting the shadow image in an image block which is divided and contains part of the detection target image and all the detection target shadow image and rendering the shadow image;
When the receiving module receives the target shadow images, the receiving module continuously receives the target shadow images in a group of two groups, and when the rendering module renders the shadow images, the rendering colors of the shadow images from the same group are inconsistent;
The detection layer comprises a reorganization module, a folding module and an identification module, wherein the reorganization module is used for acquiring shadow images which are completely rendered in the rendering layer, identifying shadow image sources which are completely rendered to detect target shadow images, combining the shadow images which are completely rendered with the same source group, the folding module is used for receiving the shadow images which are completely combined in the reorganization module, carrying out folding processing on the shadow images which are completely combined, and the identification module is used for traversing the shadow images which are completely combined after the folding processing, and identifying whether defects exist in the shadow images which are completely combined corresponding to the detection target based on the shadow coverage rate of the shadow images which are completely combined after the folding processing;
When the recombination module combines the shadow images which are completely rendered, the division line is used as a splicing boundary of the two groups of shadow images which are completely rendered, and the two groups of endpoints of the division line are used as splicing points to complete the combination operation, so that the two groups of shadow images which are completely combined respectively correspond to the endpoints of the division line, at least one group of endpoints are mutually overlapped and are not overlapped, and the distance is shortest based on the state that one group of endpoints are mutually overlapped;
When the folding module carries out folding processing on the combined shadow image, the folding angle is one hundred and eighty degrees, the folding position is a dividing line, the folding module carries out folding on the combined shadow image, takes the left side of the dividing line as a folding target, rotates and folds towards the right side of the dividing line based on the folding angle, resets after the folding is completed, takes the right side of the dividing line as a folding target, rotates and folds towards the left side of the dividing line based on the folding angle, and resets after the folding is completed;
after the shadow image is folded each time, the identification module operates once before resetting;
The shadow coverage rate after the combined shadow image folding processing in the identification module is obtained by the following formula:
；
wherein: the shadow coverage rate after the folding processing of the combined shadow image is completed; Is equally divided into The number of regions in the transverse and longitudinal directions in the shadow image of the completed combination of the regions; Is a region And region ofGray value similarity of (2); the ratio of the shielding area of the folding side covered on the other side to the area of the other side in the first shadow image; A ratio of the area of the shielding covered on the other side to the area of the other side for the folded side in the second shadow image; k Heald is the comprehensive shadow coverage rate after all the combined shadow images are folded; u is the set of shadow images that complete the combination; The shadow coverage rate after the folding processing of the combined shadow image is completed for the v group; the total amount of shadow images that complete the combination in u;
Wherein the area And region ofIn the shadow image, the dividing lines relative to the shadow image are symmetrical with each other, 0 < >≤1，0＜≤1，Symmetry 0 <, for representing the shadow image of the completed combinationLess than or equal to 1, the closer the value is to 1, the more symmetrical the shadow image is; and in the operation stage of the identification module, the defect judgment threshold is manually set by a user at the system end, and whether the appearance of the detection target of the source of K Heald has defects is judged based on the comparison of the defect judgment threshold and K Heald .
2. The system for detecting the appearance of a prefabricated body of a radome for spaceflight according to claim 1, wherein the capturing layer comprises an acquisition module, an uploading module and a logic module, the acquisition module is used for acquiring a shadow image of a detection target, the uploading module is used for uploading an outer contour standard specification parameter of the detection target, the logic module is used for receiving the outer contour standard specification parameter of the detection target uploaded by the uploading module, and the acquisition logic of the detection target when the shadow image acquisition is executed is set based on the outer contour standard specification parameter of the detection target;
The camera is symmetrically arranged on the surface of the support, the two camera end image acquisition visual angles of the cameras are converged at one point, the camera end operation acquired image data of the cameras, namely, detection target shadow images, are overlapped with the camera end image acquisition visual angle convergence points of the two groups of cameras, each group of cameras is provided with a group of light source modules, and the camera end operation stages are used for deploying the camera-configured light source modules in the opposite directions of the cameras to synchronously operate.
3. The system of claim 2, wherein the logic module is configured to set the detection target shadow image acquisition logic to include: adjusting the focal length of a camera in the acquisition module and setting the running times of a circular electric slide rail driving bracket in the acquisition module;
setting of the running times of the annular electric sliding rail driving support in the acquisition module obeys:
；
wherein: driving the support to run for the annular electric slide rail; for detecting the length of the target; For detecting the width of the target; High as detection target; tip curvature for detection target; Is a normalization factor;
Wherein, annular electronic slide rail drive support number of times of operation The value is rounded up, and the normalization factorIs an integer not less than 1.
4. The system for detecting the appearance of a prefabricated space radome according to claim 2, wherein when a camera in the acquisition module is used for adjusting a focal length and acquiring a detection target shadow image, the area of the detection target shadow image is smaller than one half of the detection target shadow image, the outline of the detection target shadow image does not coincide with the boundary of the detection target shadow image, and when the annular electric slide rail driving bracket in the acquisition module is operated, the operation angle of the driving bracket is not smaller than five degrees and not larger than fifteen degrees each time;
The camera in the acquisition module sequentially runs once after angle adjustment is completed based on the support each time, the uploading module and the logic module in the capturing layer are refreshed when the detection layer is completed to run each time, and the rendering layer and the detection layer follow the refreshing operation of the uploading module and the logic module and are in linkage operation again.
5. The system for detecting the appearance of a prefabricated space radome according to claim 1, wherein the operation stage of the segmentation module is characterized in that a coordinate system is determined based on the adjacent length and width of a detection target when the shadow image of the detection target is acquired, a group of straight lines passing through an origin on the coordinate system is determined based on the positions of two groups of cameras in the acquisition module when the shadow image of the detection target is acquired, the segmentation line of the shadow image of the detection target determined in the segmentation module is a line segment formed by connecting any two points on the contour of the shadow image of the detection target, and the segmentation line is mutually perpendicular to a group of straight lines passing through the origin on the coordinate system determined based on the positions of the two groups of cameras in the acquisition module when the shadow image of the detection target is acquired.
6. The system for detecting the appearance of a prefabricated space radome according to claim 1, wherein the receiving module is interactively connected with the dividing module and the rendering module through a local area network, the receiving module is interactively connected with the logic module through the local area network, the logic module is interactively connected with the uploading module and the collecting module through a wireless network, the rendering module is interactively connected with the reorganizing module through the wireless network, and the reorganizing module is interactively connected with the folding module and the identifying module through the wireless network.
7. A method for detecting the appearance of a prefabricated space radome, which is an implementation method for a prefabricated space radome appearance detection system according to any one of claims 1 to 6, and is characterized by comprising the following steps:
s1: setting a capturing logic, and capturing monitoring target shadow image data based on the capturing logic;
s2: receiving detection target shadow image data, performing segmentation processing on the detection target shadow image data, and extracting a shadow image based on a segmentation processing result;
s3: rendering the shadow image;
S4: acquiring a shadow image which is rendered, identifying a shadow image source, and reorganizing the shadow image;
S41: a setting stage of shadow image reorganization logic;
s5: folding the recombined shadow image, and analyzing shadow coverage rate based on a folding result;
s6: and identifying whether the detection target has defects according to the analyzed shadow coverage rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410277355.9A CN118096706B (en) | 2024-03-12 | 2024-03-12 | System and method for detecting appearance of radome preform for spaceflight |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410277355.9A CN118096706B (en) | 2024-03-12 | 2024-03-12 | System and method for detecting appearance of radome preform for spaceflight |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118096706A CN118096706A (en) | 2024-05-28 |
| CN118096706B true CN118096706B (en) | 2024-07-23 |
Family
ID=91151307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410277355.9A Active CN118096706B (en) | 2024-03-12 | 2024-03-12 | System and method for detecting appearance of radome preform for spaceflight |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118096706B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205568A (en) * | 2021-04-30 | 2021-08-03 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN115908432A (en) * | 2023-03-13 | 2023-04-04 | 单县龙宇生物科技有限公司 | Material output quality detection system and prediction method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10402671B2 (en) * | 2016-03-28 | 2019-09-03 | General Dynamics Mission Systems, Inc. | System and methods for automatic solar panel recognition and defect detection using infrared imaging |
| CN117237344B (en) * | 2023-11-13 | 2024-01-19 | 深圳市帝一通讯有限公司 | Machine vision-based method for detecting appearance quality of electronic atomizer chip |
-
2024
- 2024-03-12 CN CN202410277355.9A patent/CN118096706B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205568A (en) * | 2021-04-30 | 2021-08-03 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN115908432A (en) * | 2023-03-13 | 2023-04-04 | 单县龙宇生物科技有限公司 | Material output quality detection system and prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118096706A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107154040B (en) | Tunnel lining surface image crack detection method | |
| CN105957007B (en) | Image split-joint method based on characteristic point plane similarity | |
| CN110703800A (en) | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities | |
| CN109961399B (en) | Optimal suture line searching method based on image distance transformation | |
| CN104483326A (en) | High-voltage wire insulator defect detection method and high-voltage wire insulator defect detection system based on deep belief network | |
| CN112417926A (en) | Parking space identification method and device, computer equipment and readable storage medium | |
| CN111127412A (en) | Pathological image recognition device based on generation countermeasure network | |
| CN109858527B (en) | Image fusion method | |
| CN110838112A (en) | Insulator defect detection method based on Hough transform and YOLOv3 network | |
| JPWO2019111976A1 (en) | Object detection device, prediction model creation device, object detection method and program | |
| CN110288571B (en) | High-speed rail contact net insulator abnormity detection method based on image processing | |
| CN112730454A (en) | Intelligent damage detection method for composite material based on fusion of optics, infrared thermal waves and ultrasonic waves | |
| CN111667470A (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| CN111126381A (en) | Insulator inclined positioning and identifying method based on R-DFPN algorithm | |
| CN111444916A (en) | License plate positioning and identifying method and system under unconstrained condition | |
| CN113610846A (en) | Tubular part inner side abnormality detection method and system based on artificial intelligence | |
| CN118096706B (en) | System and method for detecting appearance of radome preform for spaceflight | |
| CN109684914A (en) | Based on unmanned plane image intelligent identification Method | |
| CN115546716A (en) | Binocular vision-based method for positioning fire source around power transmission line | |
| CN117876308A (en) | Photovoltaic panel detection method based on image analysis | |
| CN116307300B (en) | Production process optimization method and system for plastic pipeline | |
| CN115375762A (en) | Three-dimensional reconstruction method for power line based on trinocular vision | |
| CN115239667A (en) | Tire qualification detection method based on multi-view camera | |
| CN115880221A (en) | Power grid line defect analysis method integrating visible light and infrared image processing | |
| CN116342693A (en) | Bridge cable surface damage rapid positioning method based on point cloud and convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |